Details | Last modification | View Log | RSS feed
Rev | Author | Line No. | Line |
---|---|---|---|
2 | daniel-mar | 1 | <?xml version="1.0"?> |
2 | <user-agents> |
||
3 | <user-agent> |
||
4 | <ID>id_a_f_3</ID> |
||
5 | <String>!Susie (http://www.sync2it.com/susie)</String> |
||
6 | <Description>Sync2It bookmark management & clustering engine</Description> |
||
7 | <Type>C R</Type> |
||
8 | <Comment></Comment> |
||
9 | <Link1>http://www.sync2it.com</Link1> |
||
10 | <Link2></Link2> |
||
11 | </user-agent> |
||
12 | <user-agent> |
||
13 | <ID>id_a_f_6</ID> |
||
14 | <String><a href='http://www.unchaos.com/'> UnChaos </a> From Chaos To Order Hybrid Web Search Engine.(vadim_gonchar@unchaos.com)</String> |
||
15 | <Description>UnCHAOS search robot</Description> |
||
16 | <Type>R</Type> |
||
17 | <Comment>Site is dead</Comment> |
||
18 | <Link1>http://www.unchaos.com/</Link1> |
||
19 | <Link2></Link2> |
||
20 | </user-agent> |
||
21 | <user-agent> |
||
22 | <ID>id_a_f_7</ID> |
||
23 | <String><a href='http://www.unchaos.com/'> UnChaos Bot Hybrid Web Search Engine. </a> (vadim_gonchar@unchaos.com)</String> |
||
24 | <Description>UnCHAOS search robot</Description> |
||
25 | <Type>R</Type> |
||
26 | <Comment>Site is dead</Comment> |
||
27 | <Link1>http://www.unchaos.com/</Link1> |
||
28 | <Link2></Link2> |
||
29 | </user-agent> |
||
30 | <user-agent> |
||
31 | <ID>id_a_f_8</ID> |
||
32 | <String><b> UnChaosBot From Chaos To Order UnChaos Hybrid Web Search Engine at www.unchaos.com </b> (info@unchaos.com)</String> |
||
33 | <Description>UnCHAOS search robot</Description> |
||
34 | <Type>R</Type> |
||
35 | <Comment>Site is dead</Comment> |
||
36 | <Link1>http://www.unchaos.com/</Link1> |
||
37 | <Link2></Link2> |
||
38 | </user-agent> |
||
39 | <user-agent> |
||
40 | <ID>id_a_f_9</ID> |
||
41 | <String><http://www.sygol.com/> http://www.sygol.com</String> |
||
42 | <Description>Sygol Search (Italy) robot</Description> |
||
43 | <Type>R</Type> |
||
44 | <Comment>s.also SygolBot</Comment> |
||
45 | <Link1>http://www.sygol.com/</Link1> |
||
46 | <Link2></Link2> |
||
47 | </user-agent> |
||
48 | <user-agent> |
||
49 | <ID>id_a_f_4</ID> |
||
50 | <String>( Robots.txt Validator http://www.searchengineworld.com/cgi-bin/robotcheck.cgi )</String> |
||
51 | <Description>SearchEngineWorld's robots.txt validator</Description> |
||
52 | <Type>C</Type> |
||
53 | <Comment>Services is no more available</Comment> |
||
54 | <Link1>http://www.searchengineworld.com/cgi-bin/robotcheck.cgi</Link1> |
||
55 | <Link2></Link2> |
||
56 | </user-agent> |
||
57 | <user-agent> |
||
58 | <ID>id_a_f_171105_1</ID> |
||
59 | <String>(DreamPassport/3.0; isao/MyDiGiRabi)</String> |
||
60 | <Description>DreamCast DreamPassport browser</Description> |
||
61 | <Type>B</Type> |
||
62 | <Comment></Comment> |
||
63 | <Link1>http://www.dricas.com/dp/</Link1> |
||
64 | <Link2></Link2> |
||
65 | </user-agent> |
||
66 | <user-agent> |
||
67 | <ID>id_a_f_290606_1</ID> |
||
68 | <String>(Privoxy/1.0)</String> |
||
69 | <Description>Privoxy web proxy</Description> |
||
70 | <Type>P</Type> |
||
71 | <Comment>s.also Privoxy/3.0 (Anonymous)</Comment> |
||
72 | <Link1>http://www.privoxy.org/</Link1> |
||
73 | <Link2></Link2> |
||
74 | </user-agent> |
||
75 | <user-agent> |
||
76 | <ID>id_a_f_230507_1</ID> |
||
77 | <String>*/Nutch-0.9-dev</String> |
||
78 | <Description>Unknown Yahoo robot</Description> |
||
79 | <Type>R</Type> |
||
80 | <Comment>123.113.184.2xx</Comment> |
||
81 | <Link1>http://www.yahoo.com</Link1> |
||
82 | <Link2></Link2> |
||
83 | </user-agent> |
||
84 | <user-agent> |
||
85 | <ID>id_a_f_5</ID> |
||
86 | <String>+SitiDi.net/SitiDiBot/1.0 (+Have Good Day)</String> |
||
87 | <Description>SitiDi.net search (Germany) robot</Description> |
||
88 | <Type>R</Type> |
||
89 | <Comment></Comment> |
||
90 | <Link1>http://www.sitidi.net/</Link1> |
||
91 | <Link2></Link2> |
||
92 | </user-agent> |
||
93 | <user-agent> |
||
94 | <ID>id_a_f_1</ID> |
||
95 | <String>-DIE-KRAEHE- META-SEARCH-ENGINE/1.1 http://www.die-kraehe.de</String> |
||
96 | <Description>Die Kraehe Meta-Search-Engine (Germany) link checking</Description> |
||
97 | <Type>R</Type> |
||
98 | <Comment></Comment> |
||
99 | <Link1>http://www.die-kraehe.de</Link1> |
||
100 | <Link2></Link2> |
||
101 | </user-agent> |
||
102 | <user-agent> |
||
103 | <ID>id_a_f_060206_1</ID> |
||
104 | <String>123spider-Bot (Version: 1.02, powered by www.123spider.de</String> |
||
105 | <Description>123spider.de (Germany) web directory link checking</Description> |
||
106 | <Type>C</Type> |
||
107 | <Comment></Comment> |
||
108 | <Link1>http://www.123spider.de/</Link1> |
||
109 | <Link2></Link2> |
||
110 | </user-agent> |
||
111 | <user-agent> |
||
112 | <ID>id_a_f_180806_1</ID> |
||
113 | <String>192.comAgent</String> |
||
114 | <Description>192.com - UK web directory</Description> |
||
115 | <Type>R</Type> |
||
116 | <Comment>217.160.75.2xx</Comment> |
||
117 | <Link1>http://www.192.com/</Link1> |
||
118 | <Link2></Link2> |
||
119 | </user-agent> |
||
120 | <user-agent> |
||
121 | <ID>id_a_f_060606_1</ID> |
||
122 | <String>1st ZipCommander (Net) - http://www.zipcommander.com/</String> |
||
123 | <Description>1st ZipCommander Net - IE based browser</Description> |
||
124 | <Type>B</Type> |
||
125 | <Comment></Comment> |
||
126 | <Link1>http://www.zipcommander.com/</Link1> |
||
127 | <Link2></Link2> |
||
128 | </user-agent> |
||
129 | <user-agent> |
||
130 | <ID>id_a_f_10</ID> |
||
131 | <String>2Bone_LinkChecker/1.0 libwww-perl/5.64</String> |
||
132 | <Description>2Bone online link checker</Description> |
||
133 | <Type>C</Type> |
||
134 | <Comment></Comment> |
||
135 | <Link1>http://www.2bone.com/links/linkchecker.shtml</Link1> |
||
136 | <Link2></Link2> |
||
137 | </user-agent> |
||
138 | <user-agent> |
||
139 | <ID>id_a_f_11</ID> |
||
140 | <String>4anything.com LinkChecker v2.0</String> |
||
141 | <Description>4Anything robot</Description> |
||
142 | <Type>R</Type> |
||
143 | <Comment></Comment> |
||
144 | <Link1>http://www.4anything.com</Link1> |
||
145 | <Link2></Link2> |
||
146 | </user-agent> |
||
147 | <user-agent> |
||
148 | <ID>id_a_f_110207_1</ID> |
||
149 | <String>8484 Boston Project v 1.0</String> |
||
150 | <Description>Unknown guestbook spamming or harvesting tool from diff. IPs</Description> |
||
151 | <Type>S</Type> |
||
152 | <Comment>s. various honey pot sites</Comment> |
||
153 | <Link1>http://www.projecthoneypot.org/bsh_X19tb2RlPWdsb2JhbCZfX2J5PWMmY3RyeT11cyZ1YWc9ODQ4NCtCb3N0b24rUHJvamVjdCt2KzEuMA..</Link1> |
||
154 | <Link2></Link2> |
||
155 | </user-agent> |
||
156 | <user-agent> |
||
157 | <ID>id_a_f_2</ID> |
||
158 | <String>:robot/1.0 (linux) ( admin e-mail: undefined http://www.neofonie.de/loesungen/search/robot.html )</String> |
||
159 | <Description>neofonie search robot Germany</Description> |
||
160 | <Type>R</Type> |
||
161 | <Comment></Comment> |
||
162 | <Link1>http://www.neofonie.de/loesungen/search/</Link1> |
||
163 | <Link2></Link2> |
||
164 | </user-agent> |
||
165 | <user-agent> |
||
166 | <ID>id_a_f_12</ID> |
||
167 | <String>A-Online Search</String> |
||
168 | <Description>A-Online.at robot - now Jet2Web Search</Description> |
||
169 | <Type>R</Type> |
||
170 | <Comment></Comment> |
||
171 | <Link1>http://www.jet2web.net/portal</Link1> |
||
172 | <Link2></Link2> |
||
173 | </user-agent> |
||
174 | <user-agent> |
||
175 | <ID>id_a_f_090707_1</ID> |
||
176 | <String>A1 Keyword Research/1.0.2 (+http://www.micro-sys.dk/products/keyword-research/) miggibot/2007.03.27</String> |
||
177 | <Description>A1 Keyword Research - search engine and keyword optimization software</Description> |
||
178 | <Type>C</Type> |
||
179 | <Comment></Comment> |
||
180 | <Link1>http://www.micro-sys.dk/products/keyword-research/</Link1> |
||
181 | <Link2></Link2> |
||
182 | </user-agent> |
||
183 | <user-agent> |
||
184 | <ID>id_a_f_100906_1</ID> |
||
185 | <String>A1 Sitemap Generator/1.0 (+http://www.micro-sys.dk/products/sitemap-generator/) miggibot/2006.01.24</String> |
||
186 | <Description>MiggiBot website crawler engine - A1 Sitemap Generator</Description> |
||
187 | <Type>R</Type> |
||
188 | <Comment></Comment> |
||
189 | <Link1>http://www.micro-sys.dk/products/sitemap-generator/</Link1> |
||
190 | <Link2>http://www.micro-sys.dk/developer/miggibot/</Link2> |
||
191 | </user-agent> |
||
192 | <user-agent> |
||
193 | <ID>id_a_f_250408_2</ID> |
||
194 | <String>aardvark-crawler</String> |
||
195 | <Description>Aardvark web crawler for Sun's Blog recommendations</Description> |
||
196 | <Type>R</Type> |
||
197 | <Comment>192.9.71.7x</Comment> |
||
198 | <Link1>http://blogs.sun.com/plamere/</Link1> |
||
199 | <Link2></Link2> |
||
200 | </user-agent> |
||
201 | <user-agent> |
||
202 | <ID>id_a_f_13</ID> |
||
203 | <String>AbachoBOT</String> |
||
204 | <Description>Abacho / Crawler.de robot</Description> |
||
205 | <Type>R</Type> |
||
206 | <Comment></Comment> |
||
207 | <Link1>http://www.abacho.com</Link1> |
||
208 | <Link2></Link2> |
||
209 | </user-agent> |
||
210 | <user-agent> |
||
211 | <ID>id_a_f_14</ID> |
||
212 | <String>AbachoBOT (Mozilla compatible)</String> |
||
213 | <Description>Abacho / Crawler.de robot</Description> |
||
214 | <Type>R</Type> |
||
215 | <Comment></Comment> |
||
216 | <Link1>http://www.abacho.com</Link1> |
||
217 | <Link2></Link2> |
||
218 | </user-agent> |
||
219 | <user-agent> |
||
220 | <ID>id_a_f_15</ID> |
||
221 | <String>ABCdatos BotLink/5.xx.xxx#BBL</String> |
||
222 | <Description>ABCdatos - Castilian program & tutorial directory</Description> |
||
223 | <Type>R</Type> |
||
224 | <Comment></Comment> |
||
225 | <Link1>http://www.abcdatos.com</Link1> |
||
226 | <Link2></Link2> |
||
227 | </user-agent> |
||
228 | <user-agent> |
||
229 | <ID>id_a_f_16</ID> |
||
230 | <String>Aberja Checkomat</String> |
||
231 | <Description>Aberja Hybridsuchmaschine (Germany) link checking</Description> |
||
232 | <Type>R</Type> |
||
233 | <Comment></Comment> |
||
234 | <Link1>http://www.aberja.de</Link1> |
||
235 | <Link2></Link2> |
||
236 | </user-agent> |
||
237 | <user-agent> |
||
238 | <ID>id_a_f_17</ID> |
||
239 | <String>abot/0.1 (abot; http://www.abot.com; abot@abot.com)</String> |
||
240 | <Description>Nameprotect copyright search robot (24.177.134.x)</Description> |
||
241 | <Type>R</Type> |
||
242 | <Comment>s. also - np/0.1_(np;_http://www.nameprotect.com... - aipbot/1.0 (aipbot; http://www.aipbot.com...</Comment> |
||
243 | <Link1>http://www.nameprotect.com/</Link1> |
||
244 | <Link2></Link2> |
||
245 | </user-agent> |
||
246 | <user-agent> |
||
247 | <ID>id_a_f_18</ID> |
||
248 | <String>About/0.1libwww-perl/5.47</String> |
||
249 | <Description>About robot</Description> |
||
250 | <Type>R</Type> |
||
251 | <Comment></Comment> |
||
252 | <Link1>http://www.about.com</Link1> |
||
253 | <Link2></Link2> |
||
254 | </user-agent> |
||
255 | <user-agent> |
||
256 | <ID>id_a_f_051206_3</ID> |
||
257 | <String>Accelatech RSSCrawler/0.4</String> |
||
258 | <Description>Accela Technology RSS feed crawler</Description> |
||
259 | <Type>R</Type> |
||
260 | <Comment>125.100.242.2xx</Comment> |
||
261 | <Link1>http://www.accelatech.com/</Link1> |
||
262 | <Link2></Link2> |
||
263 | </user-agent> |
||
264 | <user-agent> |
||
265 | <ID>id_a_f_19</ID> |
||
266 | <String>accoona</String> |
||
267 | <Description>Accoona Search robot</Description> |
||
268 | <Type>R</Type> |
||
269 | <Comment>65.17.255.xx</Comment> |
||
270 | <Link1>http://www.accoona.com</Link1> |
||
271 | <Link2></Link2> |
||
272 | </user-agent> |
||
273 | <user-agent> |
||
274 | <ID>id_a_f_20</ID> |
||
275 | <String>Accoona-AI-Agent/1.1.1 (crawler at accoona dot com)</String> |
||
276 | <Description>Accoona Search robot</Description> |
||
277 | <Type>R</Type> |
||
278 | <Comment>65.17.255.xx</Comment> |
||
279 | <Link1>http://www.accoona.com</Link1> |
||
280 | <Link2></Link2> |
||
281 | </user-agent> |
||
282 | <user-agent> |
||
283 | <ID>id_a_f_140906_3</ID> |
||
284 | <String>Accoona-AI-Agent/1.1.2 (aicrawler at accoonabot dot com)</String> |
||
285 | <Description>Accoona Search robot</Description> |
||
286 | <Type>R</Type> |
||
287 | <Comment>65.17.255.xx</Comment> |
||
288 | <Link1>http://www.accoona.com</Link1> |
||
289 | <Link2></Link2> |
||
290 | </user-agent> |
||
291 | <user-agent> |
||
292 | <ID>id_a_f_21</ID> |
||
293 | <String>Ace Explorer</String> |
||
294 | <Description>Ace Explorer - IE based browser</Description> |
||
295 | <Type>B</Type> |
||
296 | <Comment></Comment> |
||
297 | <Link1>http://www.aceexplorer.com</Link1> |
||
298 | <Link2></Link2> |
||
299 | </user-agent> |
||
300 | <user-agent> |
||
301 | <ID>id_a_f_280806_1</ID> |
||
302 | <String>Ack (http://www.ackerm.com/)</String> |
||
303 | <Description>Ackerm search robot</Description> |
||
304 | <Type>R</Type> |
||
305 | <Comment>64.74.153.xx</Comment> |
||
306 | <Link1>http://www.ackerm.com/</Link1> |
||
307 | <Link2></Link2> |
||
308 | </user-agent> |
||
309 | <user-agent> |
||
310 | <ID>id_a_f_22</ID> |
||
311 | <String>AcoiRobot</String> |
||
312 | <Description>Acoi picture finder robot</Description> |
||
313 | <Type>R</Type> |
||
314 | <Comment></Comment> |
||
315 | <Link1>http://monetdb.cwi.nl/acoi/projects.html</Link1> |
||
316 | <Link2></Link2> |
||
317 | </user-agent> |
||
318 | <user-agent> |
||
319 | <ID>id_a_f_23</ID> |
||
320 | <String>Acoon Robot v1.50.001</String> |
||
321 | <Description>Acoon.de search (Germany) robot</Description> |
||
322 | <Type>R</Type> |
||
323 | <Comment>80.237.153.10x</Comment> |
||
324 | <Link1>http://www.acoon.de</Link1> |
||
325 | <Link2></Link2> |
||
326 | </user-agent> |
||
327 | <user-agent> |
||
328 | <ID>id_a_f_24</ID> |
||
329 | <String>Acoon Robot v1.52 (http://www.acoon.de)</String> |
||
330 | <Description>Acoon.de search (Germany) robot</Description> |
||
331 | <Type>R</Type> |
||
332 | <Comment>80.237.153.10x</Comment> |
||
333 | <Link1>http://www.acoon.de</Link1> |
||
334 | <Link2></Link2> |
||
335 | </user-agent> |
||
336 | <user-agent> |
||
337 | <ID>id_a_f_100508_1</ID> |
||
338 | <String>Acoon-Robot 4.0.x.[xx] (http://www.acoon.de)</String> |
||
339 | <Description>Acoon.de search (Germany) robot</Description> |
||
340 | <Type>R</Type> |
||
341 | <Comment>80.237.209.xx</Comment> |
||
342 | <Link1>http://www.acoon.de</Link1> |
||
343 | <Link2></Link2> |
||
344 | </user-agent> |
||
345 | <user-agent> |
||
346 | <ID>id_a_f_010108_1</ID> |
||
347 | <String>Acoon-Robot v3.xx (http://www.acoon.de and http://www.acoon.com)</String> |
||
348 | <Description>Acoon.de search (Germany) robot</Description> |
||
349 | <Type>R</Type> |
||
350 | <Comment>80.237.153.10x</Comment> |
||
351 | <Link1>http://www.acoon.de</Link1> |
||
352 | <Link2></Link2> |
||
353 | </user-agent> |
||
354 | <user-agent> |
||
355 | <ID>id_a_f_110507_1</ID> |
||
356 | <String>Acorn/Nutch-0.9 (Non-Profit Search Engine; acorn.isara.org; acorn at isara dot org)</String> |
||
357 | <Description>Acorn Search Project</Description> |
||
358 | <Type>R</Type> |
||
359 | <Comment>124.157.145.1xx</Comment> |
||
360 | <Link1>http://acorn.no-ip.org/</Link1> |
||
361 | <Link2></Link2> |
||
362 | </user-agent> |
||
363 | <user-agent> |
||
364 | <ID>id_a_f_25</ID> |
||
365 | <String>ActiveBookmark 1.x</String> |
||
366 | <Description>LibMaster.com Active Bookmark HTML page creator</Description> |
||
367 | <Type>C B</Type> |
||
368 | <Comment></Comment> |
||
369 | <Link1>http://www.libmaster.com/software.php</Link1> |
||
370 | <Link2></Link2> |
||
371 | </user-agent> |
||
372 | <user-agent> |
||
373 | <ID>id_a_f_060806_2</ID> |
||
374 | <String>Activeworlds</String> |
||
375 | <Description>Activeworlds 3D homepage browser</Description> |
||
376 | <Type>B</Type> |
||
377 | <Comment></Comment> |
||
378 | <Link1>http://www.activeworlds.com</Link1> |
||
379 | <Link2></Link2> |
||
380 | </user-agent> |
||
381 | <user-agent> |
||
382 | <ID>id_a_f_26</ID> |
||
383 | <String>ActiveWorlds/3.xx (xxx)</String> |
||
384 | <Description>Activeworlds 3D homepage browser</Description> |
||
385 | <Type>B</Type> |
||
386 | <Comment></Comment> |
||
387 | <Link1>http://www.activeworlds.com</Link1> |
||
388 | <Link2></Link2> |
||
389 | </user-agent> |
||
390 | <user-agent> |
||
391 | <ID>id_a_f_27</ID> |
||
392 | <String>Ad Muncher v4.xx.x</String> |
||
393 | <Description>Ad Muncher - banner killer</Description> |
||
394 | <Type>P</Type> |
||
395 | <Comment></Comment> |
||
396 | <Link1>http://www.admuncher.com/</Link1> |
||
397 | <Link2></Link2> |
||
398 | </user-agent> |
||
399 | <user-agent> |
||
400 | <ID>id_a_f_28</ID> |
||
401 | <String>Ad Muncher v4x Build xxxxx</String> |
||
402 | <Description>Ad Muncher - banner killer</Description> |
||
403 | <Type>P</Type> |
||
404 | <Comment></Comment> |
||
405 | <Link1>http://www.admuncher.com/</Link1> |
||
406 | <Link2></Link2> |
||
407 | </user-agent> |
||
408 | <user-agent> |
||
409 | <ID>id_a_f_061006_1</ID> |
||
410 | <String>Adaxas Spider (http://www.adaxas.net/)</String> |
||
411 | <Description>website directory adaxas link checking</Description> |
||
412 | <Type>C</Type> |
||
413 | <Comment>85.10.199.xx</Comment> |
||
414 | <Link1>http://www.adaxas.net/</Link1> |
||
415 | <Link2></Link2> |
||
416 | </user-agent> |
||
417 | <user-agent> |
||
418 | <ID>id_a_f_29</ID> |
||
419 | <String>Advanced Browser (http://www.avantbrowser.com)</String> |
||
420 | <Description>Avant Browser - IE based browser</Description> |
||
421 | <Type>B</Type> |
||
422 | <Comment></Comment> |
||
423 | <Link1>http://www.avantbrowser.com</Link1> |
||
424 | <Link2></Link2> |
||
425 | </user-agent> |
||
426 | <user-agent> |
||
427 | <ID>id_a_f_30</ID> |
||
428 | <String>AESOP_com_SpiderMan</String> |
||
429 | <Description>Aesop robot</Description> |
||
430 | <Type>R</Type> |
||
431 | <Comment></Comment> |
||
432 | <Link1>http://www.aesop.com</Link1> |
||
433 | <Link2></Link2> |
||
434 | </user-agent> |
||
435 | <user-agent> |
||
436 | <ID>id_a_f_31</ID> |
||
437 | <String>agadine/1.x.x (+http://www.agada.de)</String> |
||
438 | <Description>Agada search (Germany) robot</Description> |
||
439 | <Type>R</Type> |
||
440 | <Comment>s. also Mozilla/4.0 (agadine3.0)</Comment> |
||
441 | <Link1>http://www.agada.de</Link1> |
||
442 | <Link2></Link2> |
||
443 | </user-agent> |
||
444 | <user-agent> |
||
445 | <ID>id_a_f_32</ID> |
||
446 | <String>Agent-SharewarePlazaFileCheckBot/2.0+(+http://www.SharewarePlaza.com)</String> |
||
447 | <Description>SharewarePlaza link checking</Description> |
||
448 | <Type>R</Type> |
||
449 | <Comment></Comment> |
||
450 | <Link1>http://www.sharewareplaza.com</Link1> |
||
451 | <Link2></Link2> |
||
452 | </user-agent> |
||
453 | <user-agent> |
||
454 | <ID>id_a_f_33</ID> |
||
455 | <String>AgentName/0.1 libwww-perl/5.48</String> |
||
456 | <Description>Linkomatic submission verifier</Description> |
||
457 | <Type>R</Type> |
||
458 | <Comment></Comment> |
||
459 | <Link1>http://www.linkomatic.com/</Link1> |
||
460 | <Link2></Link2> |
||
461 | </user-agent> |
||
462 | <user-agent> |
||
463 | <ID>id_a_f_34</ID> |
||
464 | <String>AIBOT/2.1 By +(www.21seek.com A Real artificial intelligence search engine China)</String> |
||
465 | <Description>21seek.com (China) robot (218.17.90.xxx)</Description> |
||
466 | <Type>R</Type> |
||
467 | <Comment></Comment> |
||
468 | <Link1>http://www.21seek.com</Link1> |
||
469 | <Link2></Link2> |
||
470 | </user-agent> |
||
471 | <user-agent> |
||
472 | <ID>id_a_f_130807_1</ID> |
||
473 | <String>AideRSS/1.0 (aiderss.com)</String> |
||
474 | <Description>AideRss - Postrank RSS and Blog filtering</Description> |
||
475 | <Type>C</Type> |
||
476 | <Comment>72.44.35.2xx</Comment> |
||
477 | <Link1>http://www.aiderss.com/</Link1> |
||
478 | <Link2></Link2> |
||
479 | </user-agent> |
||
480 | <user-agent> |
||
481 | <ID>id_a_f_35</ID> |
||
482 | <String>aipbot/1.0 (aipbot; http://www.aipbot.com; aipbot@aipbot.com)</String> |
||
483 | <Description>Nameprotect copyright search robot (24.177.134.x)</Description> |
||
484 | <Type>R</Type> |
||
485 | <Comment>s. also - np/0.1_(np;_http://www.nameprotect.com... - abot/0.1 (abot; http://www.abot.com...</Comment> |
||
486 | <Link1>http://www.nameprotect.com/</Link1> |
||
487 | <Link2></Link2> |
||
488 | </user-agent> |
||
489 | <user-agent> |
||
490 | <ID>id_a_f_36</ID> |
||
491 | <String>aipbot/2-beta (aipbot dev; http://aipbot.com; aipbot@aipbot.com)</String> |
||
492 | <Description>Nameprotect copyright search robot (24.177.134.x)</Description> |
||
493 | <Type>R</Type> |
||
494 | <Comment>s. also - np/0.1_(np;_http://www.nameprotect.com... - abot/0.1 (abot; http://www.abot.com...</Comment> |
||
495 | <Link1>http://www.nameprotect.com/</Link1> |
||
496 | <Link2></Link2> |
||
497 | </user-agent> |
||
498 | <user-agent> |
||
499 | <ID>id_a_f_291108_1</ID> |
||
500 | <String>Akregator/1.2.9; librss/remnants</String> |
||
501 | <Description>Akregator news feed reader for KDE</Description> |
||
502 | <Type>B</Type> |
||
503 | <Comment></Comment> |
||
504 | <Link1>http://akregator.kde.org/</Link1> |
||
505 | <Link2></Link2> |
||
506 | </user-agent> |
||
507 | <user-agent> |
||
508 | <ID>id_a_f_37</ID> |
||
509 | <String>Aladin/3.324</String> |
||
510 | <Description>Aladin robot</Description> |
||
511 | <Type>R</Type> |
||
512 | <Comment></Comment> |
||
513 | <Link1>http://www.aladin.de</Link1> |
||
514 | <Link2></Link2> |
||
515 | </user-agent> |
||
516 | <user-agent> |
||
517 | <ID>id_a_f_180408_1</ID> |
||
518 | <String>Alcatel-BG3/1.0 UP.Browser/5.0.3.1.2</String> |
||
519 | <Description>Phone.com UP.Browser for mobiles on Alcatel cellphone</Description> |
||
520 | <Type>B</Type> |
||
521 | <Comment></Comment> |
||
522 | <Link1>http://www.openwave.com</Link1> |
||
523 | <Link2></Link2> |
||
524 | </user-agent> |
||
525 | <user-agent> |
||
526 | <ID>id_a_f_38</ID> |
||
527 | <String>Aleksika Spider/1.0 (+http://www.aleksika.com/)</String> |
||
528 | <Description>Aleksika Danmark - Search engine optimization spider</Description> |
||
529 | <Type>R</Type> |
||
530 | <Comment></Comment> |
||
531 | <Link1>http://www.aleksika.com</Link1> |
||
532 | <Link2></Link2> |
||
533 | </user-agent> |
||
534 | <user-agent> |
||
535 | <ID>id_a_f_291108_2</ID> |
||
536 | <String>AlertInfo 2.0 (Powered by Newsbrain)</String> |
||
537 | <Description>Alertinfo - French version of Feedreader 3.xx </Description> |
||
538 | <Type>B</Type> |
||
539 | <Comment></Comment> |
||
540 | <Link1>http://www.feedreader.com/</Link1> |
||
541 | <Link2>http://www.geste.fr/alertinfo/home.html</Link2> |
||
542 | </user-agent> |
||
543 | <user-agent> |
||
544 | <ID>id_a_f_39</ID> |
||
545 | <String>AlkalineBOT/1.3</String> |
||
546 | <Description>Vestris robot</Description> |
||
547 | <Type>R</Type> |
||
548 | <Comment></Comment> |
||
549 | <Link1>http://alkaline.vestris.com/</Link1> |
||
550 | <Link2></Link2> |
||
551 | </user-agent> |
||
552 | <user-agent> |
||
553 | <ID>id_a_f_40</ID> |
||
554 | <String>AlkalineBOT/1.4 (1.4.0326.0 RTM)</String> |
||
555 | <Description>Vestris robot</Description> |
||
556 | <Type>R</Type> |
||
557 | <Comment></Comment> |
||
558 | <Link1>http://alkaline.vestris.com/</Link1> |
||
559 | <Link2></Link2> |
||
560 | </user-agent> |
||
561 | <user-agent> |
||
562 | <ID>id_a_f_41</ID> |
||
563 | <String>Allesklar/0.1 libwww-perl/5.46</String> |
||
564 | <Description>Allesklar.de robot</Description> |
||
565 | <Type>R</Type> |
||
566 | <Comment></Comment> |
||
567 | <Link1>http://www.allesklar.de</Link1> |
||
568 | <Link2></Link2> |
||
569 | </user-agent> |
||
570 | <user-agent> |
||
571 | <ID>id_a_f_42</ID> |
||
572 | <String>Alligator 1.31 (www.nearsoftware.com)</String> |
||
573 | <Description>Alligator download manager</Description> |
||
574 | <Type>D</Type> |
||
575 | <Comment></Comment> |
||
576 | <Link1>http://www.nearsoftware.com</Link1> |
||
577 | <Link2></Link2> |
||
578 | </user-agent> |
||
579 | <user-agent> |
||
580 | <ID>id_a_f_011108_1</ID> |
||
581 | <String>Allrati/1.1 (+)</String> |
||
582 | <Description>Unknown robot from Allrati.com</Description> |
||
583 | <Type>R</Type> |
||
584 | <Comment>67.205.96.xxx/67.205.104.xx</Comment> |
||
585 | <Link1>http://www.allrati.com/</Link1> |
||
586 | <Link2></Link2> |
||
587 | </user-agent> |
||
588 | <user-agent> |
||
589 | <ID>id_a_f_43</ID> |
||
590 | <String>AltaVista Intranet V2.0 AVS EVAL search@freeit.com</String> |
||
591 | <Description>Altavista robot</Description> |
||
592 | <Type>R</Type> |
||
593 | <Comment></Comment> |
||
594 | <Link1>http://www.altavista.com</Link1> |
||
595 | <Link2></Link2> |
||
596 | </user-agent> |
||
597 | <user-agent> |
||
598 | <ID>id_a_f_44</ID> |
||
599 | <String>AltaVista Intranet V2.0 Compaq Altavista Eval sveand@altavista.net</String> |
||
600 | <Description>Altavista robot</Description> |
||
601 | <Type>R</Type> |
||
602 | <Comment></Comment> |
||
603 | <Link1>http://www.altavista.com</Link1> |
||
604 | <Link2></Link2> |
||
605 | </user-agent> |
||
606 | <user-agent> |
||
607 | <ID>id_a_f_45</ID> |
||
608 | <String>AltaVista Intranet V2.0 evreka.com crawler@evreka.com</String> |
||
609 | <Description>Altavista robot</Description> |
||
610 | <Type>R</Type> |
||
611 | <Comment></Comment> |
||
612 | <Link1>http://www.altavista.com</Link1> |
||
613 | <Link2></Link2> |
||
614 | </user-agent> |
||
615 | <user-agent> |
||
616 | <ID>id_a_f_46</ID> |
||
617 | <String>AltaVista V2.0B crawler@evreka.com</String> |
||
618 | <Description>Altavista robot</Description> |
||
619 | <Type>R</Type> |
||
620 | <Comment></Comment> |
||
621 | <Link1>http://www.altavista.com</Link1> |
||
622 | <Link2></Link2> |
||
623 | </user-agent> |
||
624 | <user-agent> |
||
625 | <ID>id_a_f_280209_1</ID> |
||
626 | <String>amaya/x.xx libwww/x.x.x</String> |
||
627 | <Description>Amaya - W3C's Editor/Browser</Description> |
||
628 | <Type>B</Type> |
||
629 | <Comment></Comment> |
||
630 | <Link1>http://www.w3.org/Amaya/</Link1> |
||
631 | <Link2></Link2> |
||
632 | </user-agent> |
||
633 | <user-agent> |
||
634 | <ID>id_a_f_47</ID> |
||
635 | <String>AmfibiBOT</String> |
||
636 | <Description>Amfibi Search robot</Description> |
||
637 | <Type>R</Type> |
||
638 | <Comment>64.111.217.9x</Comment> |
||
639 | <Link1>http://www.amfibi.com/</Link1> |
||
640 | <Link2></Link2> |
||
641 | </user-agent> |
||
642 | <user-agent> |
||
643 | <ID>id_a_f_48</ID> |
||
644 | <String>Amfibibot/0.06 (Amfibi Web Search; http://www.amfibi.com; agent@amfibi.com)</String> |
||
645 | <Description>Amfibi Search robot</Description> |
||
646 | <Type>R</Type> |
||
647 | <Comment>64.111.217.9x</Comment> |
||
648 | <Link1>http://www.amfibi.com/</Link1> |
||
649 | <Link2></Link2> |
||
650 | </user-agent> |
||
651 | <user-agent> |
||
652 | <ID>id_a_f_141105_2</ID> |
||
653 | <String>Amfibibot/0.07 (Amfibi Robot; http://www.amfibi.com; agent@amfibi.com)</String> |
||
654 | <Description>Amfibi Search robot</Description> |
||
655 | <Type>R</Type> |
||
656 | <Comment>64.111.217.9x</Comment> |
||
657 | <Link1>http://www.amfibi.com/</Link1> |
||
658 | <Link2></Link2> |
||
659 | </user-agent> |
||
660 | <user-agent> |
||
661 | <ID>id_a_f_49</ID> |
||
662 | <String>amibot</String> |
||
663 | <Description>amibot - Amidalla search engine robot (62.241.33.xx)</Description> |
||
664 | <Type>R</Type> |
||
665 | <Comment>s. also libwww-perl/5.65</Comment> |
||
666 | <Link1>http://www.amidalla.com/</Link1> |
||
667 | <Link2></Link2> |
||
668 | </user-agent> |
||
669 | <user-agent> |
||
670 | <ID>id_a_f_50</ID> |
||
671 | <String>Amiga-AWeb/3.4.167SE</String> |
||
672 | <Description>AWeb Amiga browser</Description> |
||
673 | <Type>B</Type> |
||
674 | <Comment></Comment> |
||
675 | <Link1>http://www.amitrix.com/aweb.html</Link1> |
||
676 | <Link2></Link2> |
||
677 | </user-agent> |
||
678 | <user-agent> |
||
679 | <ID>id_a_f_51</ID> |
||
680 | <String>AmigaVoyager/3.4.4 (MorphOS/PPC native)</String> |
||
681 | <Description>Voyager - Amiga browser</Description> |
||
682 | <Type>B</Type> |
||
683 | <Comment></Comment> |
||
684 | <Link1>http://www.vapor.com/voyager/</Link1> |
||
685 | <Link2></Link2> |
||
686 | </user-agent> |
||
687 | <user-agent> |
||
688 | <ID>id_a_f_091205_1</ID> |
||
689 | <String>AmiTCP Miami (AmigaOS 2.04)</String> |
||
690 | <Description>Amiga Miami TCP Stack</Description> |
||
691 | <Type></Type> |
||
692 | <Comment></Comment> |
||
693 | <Link1>http://home.ptd.net/~strdustr/amirc/Netware.html</Link1> |
||
694 | <Link2></Link2> |
||
695 | </user-agent> |
||
696 | <user-agent> |
||
697 | <ID>id_a_f_210608_1</ID> |
||
698 | <String>Amoi 8512/R21.0 NF-Browser/3.3</String> |
||
699 | <Description>NF embedded browser on Amois Skypephone</Description> |
||
700 | <Type>B</Type> |
||
701 | <Comment></Comment> |
||
702 | <Link1>http://3skypephone.com/</Link1> |
||
703 | <Link2></Link2> |
||
704 | </user-agent> |
||
705 | <user-agent> |
||
706 | <ID>id_a_f_190206_3</ID> |
||
707 | <String>amzn_assoc</String> |
||
708 | <Description>Amazon.com robot for checking their affiliate sites</Description> |
||
709 | <Type>C</Type> |
||
710 | <Comment>s. also aranhabot</Comment> |
||
711 | <Link1></Link1> |
||
712 | <Link2></Link2> |
||
713 | </user-agent> |
||
714 | <user-agent> |
||
715 | <ID>id_a_f_52</ID> |
||
716 | <String>AnnoMille spider 0.1 alpha - http://www.annomille.it</String> |
||
717 | <Description>Annomille Italian historical oriented robot</Description> |
||
718 | <Type>R</Type> |
||
719 | <Comment></Comment> |
||
720 | <Link1>http://www.annomille.it</Link1> |
||
721 | <Link2></Link2> |
||
722 | </user-agent> |
||
723 | <user-agent> |
||
724 | <ID>id_a_f_53</ID> |
||
725 | <String>annotate_google; http://ponderer.org/download/annotate_google.user.js</String> |
||
726 | <Description>annotate Google - Firefox extension for annotating Google search results</Description> |
||
727 | <Type>B</Type> |
||
728 | <Comment></Comment> |
||
729 | <Link1>http://ponderer.org/annotate_google</Link1> |
||
730 | <Link2></Link2> |
||
731 | </user-agent> |
||
732 | <user-agent> |
||
733 | <ID>id_a_f_54</ID> |
||
734 | <String>Anonymized by ProxyOS: http://www.megaproxy.com</String> |
||
735 | <Description>Megaproxy user</Description> |
||
736 | <Type>P</Type> |
||
737 | <Comment></Comment> |
||
738 | <Link1>http://www.megaproxy.com</Link1> |
||
739 | <Link2></Link2> |
||
740 | </user-agent> |
||
741 | <user-agent> |
||
742 | <ID>id_a_f_55</ID> |
||
743 | <String>Anonymizer/1.1</String> |
||
744 | <Description>faked user agent</Description> |
||
745 | <Type></Type> |
||
746 | <Comment></Comment> |
||
747 | <Link1></Link1> |
||
748 | <Link2></Link2> |
||
749 | </user-agent> |
||
750 | <user-agent> |
||
751 | <ID>id_a_f_56</ID> |
||
752 | <String>AnswerBus (http://www.answerbus.com/)</String> |
||
753 | <Description>AnswerBus natural language search using COLLATE technology</Description> |
||
754 | <Type>R</Type> |
||
755 | <Comment></Comment> |
||
756 | <Link1>http://www.answerbus.com</Link1> |
||
757 | <Link2>http://collate.dfki.de/kurzdarstellung.html</Link2> |
||
758 | </user-agent> |
||
759 | <user-agent> |
||
760 | <ID>id_a_f_57</ID> |
||
761 | <String>AnswerChase PROve x.0</String> |
||
762 | <Description>AnswerChase search tool</Description> |
||
763 | <Type></Type> |
||
764 | <Comment></Comment> |
||
765 | <Link1>http://www.answerchase.com</Link1> |
||
766 | <Link2></Link2> |
||
767 | </user-agent> |
||
768 | <user-agent> |
||
769 | <ID>id_a_f_58</ID> |
||
770 | <String>AnswerChase x.0</String> |
||
771 | <Description>AnswerChase search tool</Description> |
||
772 | <Type></Type> |
||
773 | <Comment></Comment> |
||
774 | <Link1>http://www.answerchase.com</Link1> |
||
775 | <Link2></Link2> |
||
776 | </user-agent> |
||
777 | <user-agent> |
||
778 | <ID>id_a_f_59</ID> |
||
779 | <String>ANTFresco/x.xx</String> |
||
780 | <Description>ANT Fresco Browser</Description> |
||
781 | <Type>B</Type> |
||
782 | <Comment>s. also Mozilla/x.xx (compatible; ANTFresco....)</Comment> |
||
783 | <Link1>http://www.antlimited.com/products/fresco.htm</Link1> |
||
784 | <Link2></Link2> |
||
785 | </user-agent> |
||
786 | <user-agent> |
||
787 | <ID>id_a_f_60</ID> |
||
788 | <String>antibot-V1.1.5/i586-linux-2.2</String> |
||
789 | <Description>Antibot (discontinued) robot</Description> |
||
790 | <Type>R</Type> |
||
791 | <Comment></Comment> |
||
792 | <Link1>http://www.antidot.net</Link1> |
||
793 | <Link2></Link2> |
||
794 | </user-agent> |
||
795 | <user-agent> |
||
796 | <ID>id_a_f_61</ID> |
||
797 | <String>AnzwersCrawl/2.0 (anzwerscrawl@anzwers.com.au;Engine)</String> |
||
798 | <Description>Anzwers (Yahoo) Australia robot</Description> |
||
799 | <Type>R</Type> |
||
800 | <Comment></Comment> |
||
801 | <Link1>http://au.anzwers.yahoo.com/</Link1> |
||
802 | <Link2></Link2> |
||
803 | </user-agent> |
||
804 | <user-agent> |
||
805 | <ID>id_a_f_030206_1</ID> |
||
806 | <String>Apexoo Spider 1.x</String> |
||
807 | <Description>Apexoo Search spider</Description> |
||
808 | <Type>R</Type> |
||
809 | <Comment>216.240.143.xx</Comment> |
||
810 | <Link1>http://www.apexoo.com/</Link1> |
||
811 | <Link2></Link2> |
||
812 | </user-agent> |
||
813 | <user-agent> |
||
814 | <ID>id_a_f_62</ID> |
||
815 | <String>Aplix HTTP/1.0.1</String> |
||
816 | <Description>JavaOS app. for SEGA Saturn Internet and Sanyo Internet-TV</Description> |
||
817 | <Type>B</Type> |
||
818 | <Comment></Comment> |
||
819 | <Link1></Link1> |
||
820 | <Link2></Link2> |
||
821 | </user-agent> |
||
822 | <user-agent> |
||
823 | <ID>id_a_f_63</ID> |
||
824 | <String>Aplix_SANYO_browser/1.x (Japanese)</String> |
||
825 | <Description>JavaOS app. for Sanyo Internet-TV</Description> |
||
826 | <Type>B</Type> |
||
827 | <Comment></Comment> |
||
828 | <Link1></Link1> |
||
829 | <Link2></Link2> |
||
830 | </user-agent> |
||
831 | <user-agent> |
||
832 | <ID>id_a_f_64</ID> |
||
833 | <String>Aplix_SEGASATURN_browser/1.x (Japanese)</String> |
||
834 | <Description>JavaOS app. for SEGA Saturn Internet</Description> |
||
835 | <Type>B</Type> |
||
836 | <Comment></Comment> |
||
837 | <Link1></Link1> |
||
838 | <Link2></Link2> |
||
839 | </user-agent> |
||
840 | <user-agent> |
||
841 | <ID>id_a_f_65</ID> |
||
842 | <String>Aport</String> |
||
843 | <Description>Aport robot</Description> |
||
844 | <Type>R</Type> |
||
845 | <Comment></Comment> |
||
846 | <Link1>http://www.aport.ru</Link1> |
||
847 | <Link2></Link2> |
||
848 | </user-agent> |
||
849 | <user-agent> |
||
850 | <ID>id_a_f_66</ID> |
||
851 | <String>appie 1.1 (www.walhello.com)</String> |
||
852 | <Description>Walhello Internet Search robot</Description> |
||
853 | <Type>R</Type> |
||
854 | <Comment></Comment> |
||
855 | <Link1>http://www.walhello.com</Link1> |
||
856 | <Link2></Link2> |
||
857 | </user-agent> |
||
858 | <user-agent> |
||
859 | <ID>id_a_f_140608_1</ID> |
||
860 | <String>Apple iPhone v1.1.4 CoreMedia v1.0.0.4A102</String> |
||
861 | <Description>CoreMedia player on Apple iPhone</Description> |
||
862 | <Type>B</Type> |
||
863 | <Comment></Comment> |
||
864 | <Link1>http://www.apple.com/iphone/</Link1> |
||
865 | <Link2></Link2> |
||
866 | </user-agent> |
||
867 | <user-agent> |
||
868 | <ID>id_a_f_070209_1</ID> |
||
869 | <String>Apple-PubSub/65.1.1</String> |
||
870 | <Description>PubSub - Mac OS X utility for managing RSS/Atom subscriptions via the PubSub framework</Description> |
||
871 | <Type>B</Type> |
||
872 | <Comment></Comment> |
||
873 | <Link1>http://developer.apple.com/documentation/Darwin/Reference/ManPages/man1/pubsub.1.html</Link1> |
||
874 | <Link2></Link2> |
||
875 | </user-agent> |
||
876 | <user-agent> |
||
877 | <ID>id_a_f_120707_1</ID> |
||
878 | <String>ArabyBot (compatible; Mozilla/5.0; GoogleBot; FAST Crawler 6.4; http://www.araby.com;)</String> |
||
879 | <Description>Araby search - Arabia</Description> |
||
880 | <Type>R</Type> |
||
881 | <Comment>209.85.31.2xx</Comment> |
||
882 | <Link1>http://www.araby.com/</Link1> |
||
883 | <Link2></Link2> |
||
884 | </user-agent> |
||
885 | <user-agent> |
||
886 | <ID>id_a_f_260608_1</ID> |
||
887 | <String>ArachBot</String> |
||
888 | <Description>Covac Arachnid Web Crawler</Description> |
||
889 | <Type>R</Type> |
||
890 | <Comment>s.also Covac TexAs Arachbot</Comment> |
||
891 | <Link1>http://www.covac-software.com/</Link1> |
||
892 | <Link2></Link2> |
||
893 | </user-agent> |
||
894 | <user-agent> |
||
895 | <ID>id_a_f_67</ID> |
||
896 | <String>Arachnoidea (arachnoidea@euroseek.com)</String> |
||
897 | <Description>Euroseek spider</Description> |
||
898 | <Type>R</Type> |
||
899 | <Comment></Comment> |
||
900 | <Link1>http://www.euroseek.com</Link1> |
||
901 | <Link2></Link2> |
||
902 | </user-agent> |
||
903 | <user-agent> |
||
904 | <ID>id_a_f_190206_2</ID> |
||
905 | <String>aranhabot</String> |
||
906 | <Description>Amazon.com robot for checking their affiliate sites</Description> |
||
907 | <Type>C</Type> |
||
908 | <Comment>s. also amzn_assoc</Comment> |
||
909 | <Link1></Link1> |
||
910 | <Link2></Link2> |
||
911 | </user-agent> |
||
912 | <user-agent> |
||
913 | <ID>id_a_f_68</ID> |
||
914 | <String>ArchitextSpider</String> |
||
915 | <Description>Excite spider</Description> |
||
916 | <Type>R</Type> |
||
917 | <Comment></Comment> |
||
918 | <Link1>http://www.excite.com</Link1> |
||
919 | <Link2></Link2> |
||
920 | </user-agent> |
||
921 | <user-agent> |
||
922 | <ID>id_a_f_69</ID> |
||
923 | <String>archive.org_bot</String> |
||
924 | <Description>Heritrix - The Internet Archive's open-source crawler (207.241.225.2xx)</Description> |
||
925 | <Type>R</Type> |
||
926 | <Comment>s.also - InternetArchive/0.8-dev - Mozilla/5.0 (compatible;archive.org_bot/...</Comment> |
||
927 | <Link1>http://www.archive.org/</Link1> |
||
928 | <Link2></Link2> |
||
929 | </user-agent> |
||
930 | <user-agent> |
||
931 | <ID>id_a_f_70</ID> |
||
932 | <String>Argus/1.1 (Nutch; http://www.simpy.com/bot.html; feedback at simpy dot com)</String> |
||
933 | <Description>Simpy Bookmarklet crawler (69.55.233.xx)</Description> |
||
934 | <Type>C</Type> |
||
935 | <Comment>s. also Simpy</Comment> |
||
936 | <Link1>http://www.simpy.com/</Link1> |
||
937 | <Link2></Link2> |
||
938 | </user-agent> |
||
939 | <user-agent> |
||
940 | <ID>id_a_f_031205_1</ID> |
||
941 | <String>Arikus_Spider</String> |
||
942 | <Description>Arikus inContext search engine software</Description> |
||
943 | <Type>R</Type> |
||
944 | <Comment></Comment> |
||
945 | <Link1>http://www.arikus.com/inContext-enterprise.html</Link1> |
||
946 | <Link2></Link2> |
||
947 | </user-agent> |
||
948 | <user-agent> |
||
949 | <ID>id_a_f_210208_1</ID> |
||
950 | <String>Arquivo-web-crawler (compatible; heritrix/1.12.1 +http://arquivo-web.fccn.pt)</String> |
||
951 | <Description>Tomba project: the Portuguese web archive</Description> |
||
952 | <Type>R</Type> |
||
953 | <Comment>193.136.192.xx</Comment> |
||
954 | <Link1>http://arquivo-web.fccn.pt/</Link1> |
||
955 | <Link2>http://arquivo-web.fccn.pt/crawler?set_language=en</Link2> |
||
956 | </user-agent> |
||
957 | <user-agent> |
||
958 | <ID>id_a_f_251007_1</ID> |
||
959 | <String>ASAHA Search Engine Turkey V.001 (http://www.asaha.com/)</String> |
||
960 | <Description>Asaha search robot (Turkey)</Description> |
||
961 | <Type>R</Type> |
||
962 | <Comment>62.68.194.2xx</Comment> |
||
963 | <Link1>http://www.asaha.com/</Link1> |
||
964 | <Link2></Link2> |
||
965 | </user-agent> |
||
966 | <user-agent> |
||
967 | <ID>id_a_f_71</ID> |
||
968 | <String>Asahina-Antenna/1.x</String> |
||
969 | <Description>ASAHINA Antenna information detecting agent</Description> |
||
970 | <Type>R</Type> |
||
971 | <Comment></Comment> |
||
972 | <Link1>http://masshy.fastwave.gr.jp/hina/release/</Link1> |
||
973 | <Link2></Link2> |
||
974 | </user-agent> |
||
975 | <user-agent> |
||
976 | <ID>id_a_f_72</ID> |
||
977 | <String>Asahina-Antenna/1.x (libhina.pl/x.x ; libtime.pl/x.x)</String> |
||
978 | <Description>ASAHINA Antenna information detecting agent</Description> |
||
979 | <Type>R</Type> |
||
980 | <Comment></Comment> |
||
981 | <Link1>http://masshy.fastwave.gr.jp/hina/release/</Link1> |
||
982 | <Link2></Link2> |
||
983 | </user-agent> |
||
984 | <user-agent> |
||
985 | <ID>id_a_f_73</ID> |
||
986 | <String>ask.24x.info</String> |
||
987 | <Description>Ask 24x Info robot</Description> |
||
988 | <Type>R</Type> |
||
989 | <Comment></Comment> |
||
990 | <Link1>http://ask.24x.info/</Link1> |
||
991 | <Link2></Link2> |
||
992 | </user-agent> |
||
993 | <user-agent> |
||
994 | <ID>id_a_f_74</ID> |
||
995 | <String>AskAboutOil/0.06-rcp (Nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@askaboutoil.com)</String> |
||
996 | <Description>Ask About Oil - Petroleum related search (24.227.212.xxx) using Nutch</Description> |
||
997 | <Type>R</Type> |
||
998 | <Comment></Comment> |
||
999 | <Link1>http://askaboutoil.com/search.jsp</Link1> |
||
1000 | <Link2>http://www.nutch.org</Link2> |
||
1001 | </user-agent> |
||
1002 | <user-agent> |
||
1003 | <ID>id_a_f_120806_1</ID> |
||
1004 | <String>asked/Nutch-0.8 (web crawler; http://asked.jp; epicurus at gmail dot com)</String> |
||
1005 | <Description>askEd! / Inferret search (Japan) robot using Nutch</Description> |
||
1006 | <Type>R</Type> |
||
1007 | <Comment>131.112.125.1xx</Comment> |
||
1008 | <Link1>http://asked.jp/</Link1> |
||
1009 | <Link2></Link2> |
||
1010 | </user-agent> |
||
1011 | <user-agent> |
||
1012 | <ID>id_a_f_75</ID> |
||
1013 | <String>ASPSeek/1.2.5</String> |
||
1014 | <Description>ASPSeek search engine software -Yahoo-Inc. / Telecom Canada robot </Description> |
||
1015 | <Type>R</Type> |
||
1016 | <Comment></Comment> |
||
1017 | <Link1>http://www.aspseek.org</Link1> |
||
1018 | <Link2></Link2> |
||
1019 | </user-agent> |
||
1020 | <user-agent> |
||
1021 | <ID>id_a_f_76</ID> |
||
1022 | <String>ASPseek/1.2.9d</String> |
||
1023 | <Description>Swsoft.net robot using Aspseek</Description> |
||
1024 | <Type>R</Type> |
||
1025 | <Comment></Comment> |
||
1026 | <Link1>http://www.aspseek.com</Link1> |
||
1027 | <Link2></Link2> |
||
1028 | </user-agent> |
||
1029 | <user-agent> |
||
1030 | <ID>id_a_f_77</ID> |
||
1031 | <String>ASPSeek/1.2.x</String> |
||
1032 | <Description>ASPSeek search engine software</Description> |
||
1033 | <Type>R</Type> |
||
1034 | <Comment></Comment> |
||
1035 | <Link1>http://www.aspseek.org</Link1> |
||
1036 | <Link2></Link2> |
||
1037 | </user-agent> |
||
1038 | <user-agent> |
||
1039 | <ID>id_a_f_78</ID> |
||
1040 | <String>ASPSeek/1.2.xa</String> |
||
1041 | <Description>ASPSeek search engine software</Description> |
||
1042 | <Type>R</Type> |
||
1043 | <Comment></Comment> |
||
1044 | <Link1>http://www.aspseek.org</Link1> |
||
1045 | <Link2></Link2> |
||
1046 | </user-agent> |
||
1047 | <user-agent> |
||
1048 | <ID>id_a_f_79</ID> |
||
1049 | <String>ASPseek/1.2.xx</String> |
||
1050 | <Description>ASPSeek search engine software</Description> |
||
1051 | <Type>R</Type> |
||
1052 | <Comment></Comment> |
||
1053 | <Link1>http://www.aspseek.org</Link1> |
||
1054 | <Link2></Link2> |
||
1055 | </user-agent> |
||
1056 | <user-agent> |
||
1057 | <ID>id_a_f_80</ID> |
||
1058 | <String>ASPSeek/1.2.xxpre</String> |
||
1059 | <Description>ASPSeek search engine software</Description> |
||
1060 | <Type>R</Type> |
||
1061 | <Comment></Comment> |
||
1062 | <Link1>http://www.aspseek.org</Link1> |
||
1063 | <Link2></Link2> |
||
1064 | </user-agent> |
||
1065 | <user-agent> |
||
1066 | <ID>id_a_f_81</ID> |
||
1067 | <String>ASSORT/0.10</String> |
||
1068 | <Description>Associative Sort robot</Description> |
||
1069 | <Type>R</Type> |
||
1070 | <Comment>site is down</Comment> |
||
1071 | <Link1>http://pcmath126.unice.fr/assort-robot.html</Link1> |
||
1072 | <Link2></Link2> |
||
1073 | </user-agent> |
||
1074 | <user-agent> |
||
1075 | <ID>id_a_f_82</ID> |
||
1076 | <String>asterias/2.0</String> |
||
1077 | <Description>Singingfish media spider (64.12.186.2xx) via AOL search</Description> |
||
1078 | <Type>R</Type> |
||
1079 | <Comment>s. also Mozilla/4.0 (compatible; MSIE 6.0 compatible; Asterias Crawler ...</Comment> |
||
1080 | <Link1>http://search.singingfish.com/sfw/home.jsp</Link1> |
||
1081 | <Link2></Link2> |
||
1082 | </user-agent> |
||
1083 | <user-agent> |
||
1084 | <ID>id_a_f_83</ID> |
||
1085 | <String>AtlocalBot/1.1 +(http://www.atlocal.com/local-web-site-owner.html)</String> |
||
1086 | <Description>Atlocal local business search robot</Description> |
||
1087 | <Type>R</Type> |
||
1088 | <Comment></Comment> |
||
1089 | <Link1>http://www.atlocal.com/</Link1> |
||
1090 | <Link2></Link2> |
||
1091 | </user-agent> |
||
1092 | <user-agent> |
||
1093 | <ID>id_a_f_041207_2</ID> |
||
1094 | <String>Atomic_Email_Hunter/4.0</String> |
||
1095 | <Description>Atomic Email Hunter email extracing and harvesting</Description> |
||
1096 | <Type>S</Type> |
||
1097 | <Comment></Comment> |
||
1098 | <Link1></Link1> |
||
1099 | <Link2></Link2> |
||
1100 | </user-agent> |
||
1101 | <user-agent> |
||
1102 | <ID>id_a_f_84</ID> |
||
1103 | <String>Atomz/1.0</String> |
||
1104 | <Description>Atomz robot</Description> |
||
1105 | <Type>R</Type> |
||
1106 | <Comment></Comment> |
||
1107 | <Link1>http://www.atomz.com</Link1> |
||
1108 | <Link2></Link2> |
||
1109 | </user-agent> |
||
1110 | <user-agent> |
||
1111 | <ID>id_a_f_85</ID> |
||
1112 | <String>atSpider/1.0</String> |
||
1113 | <Description>atSpider (ceased) email harvester / spambot</Description> |
||
1114 | <Type>S</Type> |
||
1115 | <Comment></Comment> |
||
1116 | <Link1></Link1> |
||
1117 | <Link2></Link2> |
||
1118 | </user-agent> |
||
1119 | <user-agent> |
||
1120 | <ID>id_a_f_060707_1</ID> |
||
1121 | <String>Attentio/Nutch-0.9-dev (Attentio's beta blog crawler; www.attentio.com; info@attentio.com)</String> |
||
1122 | <Description>Attentio social media monitoring and analysing </Description> |
||
1123 | <Type>R</Type> |
||
1124 | <Comment>85.88.35.xx</Comment> |
||
1125 | <Link1>http://www.attentio.com/</Link1> |
||
1126 | <Link2></Link2> |
||
1127 | </user-agent> |
||
1128 | <user-agent> |
||
1129 | <ID>id_a_f_231105_2</ID> |
||
1130 | <String>AU-MIC/2.0 MMP/2.0</String> |
||
1131 | <Description>Samsung SPH-A660 phone with Sprint software</Description> |
||
1132 | <Type>B</Type> |
||
1133 | <Comment></Comment> |
||
1134 | <Link1>http://www1.sprintpcs.com/explore/showcase/Showcase.jsp?scTopic=pcsVision</Link1> |
||
1135 | <Link2></Link2> |
||
1136 | </user-agent> |
||
1137 | <user-agent> |
||
1138 | <ID>id_a_f_240208_1</ID> |
||
1139 | <String>AUDIOVOX-SMT5600</String> |
||
1140 | <Description>Audiovox SMT5600 (AT&T) Smartphone mobile phone browser</Description> |
||
1141 | <Type>B</Type> |
||
1142 | <Comment></Comment> |
||
1143 | <Link1>http://www.audiovox.com/</Link1> |
||
1144 | <Link2>http://www.audiovox.com/manuals/owners/SMT%205600%20QSG%209-7%20FINAL.pdf</Link2> |
||
1145 | </user-agent> |
||
1146 | <user-agent> |
||
1147 | <ID>id_a_f_86</ID> |
||
1148 | <String>augurfind</String> |
||
1149 | <Description>Augurnet Swiss (was www.augurnet.ch) search robot</Description> |
||
1150 | <Type>R</Type> |
||
1151 | <Comment></Comment> |
||
1152 | <Link1></Link1> |
||
1153 | <Link2></Link2> |
||
1154 | </user-agent> |
||
1155 | <user-agent> |
||
1156 | <ID>id_a_f_87</ID> |
||
1157 | <String>augurnfind V-1.x</String> |
||
1158 | <Description>Augurnet Swiss (was www.augurnet.ch) search robot</Description> |
||
1159 | <Type>R</Type> |
||
1160 | <Comment></Comment> |
||
1161 | <Link1></Link1> |
||
1162 | <Link2></Link2> |
||
1163 | </user-agent> |
||
1164 | <user-agent> |
||
1165 | <ID>id_a_f_88</ID> |
||
1166 | <String>autoemailspider</String> |
||
1167 | <Description>Auto Email Pro Email harvester</Description> |
||
1168 | <Type>S</Type> |
||
1169 | <Comment>was http://autoemailspider.com - site is dead</Comment> |
||
1170 | <Link1></Link1> |
||
1171 | <Link2></Link2> |
||
1172 | </user-agent> |
||
1173 | <user-agent> |
||
1174 | <ID>id_a_f_89</ID> |
||
1175 | <String>autohttp</String> |
||
1176 | <Description>Linkscan tool from Elsop</Description> |
||
1177 | <Type>C</Type> |
||
1178 | <Comment>s. Linkscan/x ?</Comment> |
||
1179 | <Link1>http://www.elsop.com/linkscan/</Link1> |
||
1180 | <Link2></Link2> |
||
1181 | </user-agent> |
||
1182 | <user-agent> |
||
1183 | <ID>id_a_f_050208_1</ID> |
||
1184 | <String>autowebdir 1.1 (www.autowebdir.com)</String> |
||
1185 | <Description>Autowebdir - The Automatically Generated Web Directory</Description> |
||
1186 | <Type>R</Type> |
||
1187 | <Comment>84.104.43.x</Comment> |
||
1188 | <Link1>http://www.autowebdir.com/</Link1> |
||
1189 | <Link2></Link2> |
||
1190 | </user-agent> |
||
1191 | <user-agent> |
||
1192 | <ID>id_a_f_90</ID> |
||
1193 | <String>AV Fetch 1.0</String> |
||
1194 | <Description>Altavista robot ??</Description> |
||
1195 | <Type>R</Type> |
||
1196 | <Comment></Comment> |
||
1197 | <Link1>http://www.altavista.com/</Link1> |
||
1198 | <Link2></Link2> |
||
1199 | </user-agent> |
||
1200 | <user-agent> |
||
1201 | <ID>id_a_f_91</ID> |
||
1202 | <String>Avant Browser (http://www.avantbrowser.com)</String> |
||
1203 | <Description>Avant Browser - IE based browser</Description> |
||
1204 | <Type>B</Type> |
||
1205 | <Comment></Comment> |
||
1206 | <Link1>http://www.avantbrowser.com</Link1> |
||
1207 | <Link2></Link2> |
||
1208 | </user-agent> |
||
1209 | <user-agent> |
||
1210 | <ID>id_a_f_92</ID> |
||
1211 | <String>AVSearch-1.0(peter.turney@nrc.ca)</String> |
||
1212 | <Description>National Research Council Canada robot</Description> |
||
1213 | <Type>R</Type> |
||
1214 | <Comment></Comment> |
||
1215 | <Link1>http://www.nrc-cnrc.gc.ca/main_e.html</Link1> |
||
1216 | <Link2></Link2> |
||
1217 | </user-agent> |
||
1218 | <user-agent> |
||
1219 | <ID>id_a_f_93</ID> |
||
1220 | <String>AVSearch-2.0-fusionIdx-14-CompetitorWebSites</String> |
||
1221 | <Description>Unknown robot from 205.203.108.xx (telerate.com)</Description> |
||
1222 | <Type></Type> |
||
1223 | <Comment></Comment> |
||
1224 | <Link1></Link1> |
||
1225 | <Link2></Link2> |
||
1226 | </user-agent> |
||
1227 | <user-agent> |
||
1228 | <ID>id_a_f_94</ID> |
||
1229 | <String>AVSearch-3.0(AltaVista/AVC)</String> |
||
1230 | <Description>Altavista robot</Description> |
||
1231 | <Type>R</Type> |
||
1232 | <Comment></Comment> |
||
1233 | <Link1>http://www.altavista.com/</Link1> |
||
1234 | <Link2></Link2> |
||
1235 | </user-agent> |
||
1236 | <user-agent> |
||
1237 | <ID>id_a_f_95</ID> |
||
1238 | <String>AWeb</String> |
||
1239 | <Description>AWeb Amiga browser</Description> |
||
1240 | <Type>B</Type> |
||
1241 | <Comment></Comment> |
||
1242 | <Link1>http://aweb.sunsite.dk/</Link1> |
||
1243 | <Link2></Link2> |
||
1244 | </user-agent> |
||
1245 | <user-agent> |
||
1246 | <ID>id_a_f_96</ID> |
||
1247 | <String>axadine/ (Axadine Crawler; http://www.axada.de/; )</String> |
||
1248 | <Description>Axada search Germany robot</Description> |
||
1249 | <Type>R</Type> |
||
1250 | <Comment></Comment> |
||
1251 | <Link1>http://www.axada.de</Link1> |
||
1252 | <Link2></Link2> |
||
1253 | </user-agent> |
||
1254 | <user-agent> |
||
1255 | <ID>id_a_f_97</ID> |
||
1256 | <String>AxmoRobot - Crawling your site for better indexing on www.axmo.com search engine.</String> |
||
1257 | <Description>Axmo search robot</Description> |
||
1258 | <Type>R</Type> |
||
1259 | <Comment></Comment> |
||
1260 | <Link1>http://www.axmo.com</Link1> |
||
1261 | <Link2></Link2> |
||
1262 | </user-agent> |
||
1263 | <user-agent> |
||
1264 | <ID>id_a_f_250306_1</ID> |
||
1265 | <String>Azureus 2.x.x.x</String> |
||
1266 | <Description>Azureus Java BitTorrent Client</Description> |
||
1267 | <Type>D</Type> |
||
1268 | <Comment></Comment> |
||
1269 | <Link1>http://azureus.sourceforge.net/</Link1> |
||
1270 | <Link2></Link2> |
||
1271 | </user-agent> |
||
1272 | <user-agent> |
||
1273 | <ID>id_a_f_131208_1</ID> |
||
1274 | <String>BabalooSpider/1.3 (BabalooSpider; http://www.babaloo.si; spider@babaloo.si)</String> |
||
1275 | <Description>Babaloo search robot (Slovenia)</Description> |
||
1276 | <Type>R</Type> |
||
1277 | <Comment>84.255.237.2xx</Comment> |
||
1278 | <Link1>http://www.babaloo.si/</Link1> |
||
1279 | <Link2></Link2> |
||
1280 | </user-agent> |
||
1281 | <user-agent> |
||
1282 | <ID>id_a_f_98</ID> |
||
1283 | <String>BaboomBot/1.x.x (+http://www.baboom.us)</String> |
||
1284 | <Description>BaBoom Web Portal (ODP) robot (66.98.254.xx)</Description> |
||
1285 | <Type>R</Type> |
||
1286 | <Comment></Comment> |
||
1287 | <Link1>http://www.baboom.us</Link1> |
||
1288 | <Link2></Link2> |
||
1289 | </user-agent> |
||
1290 | <user-agent> |
||
1291 | <ID>id_a_f_050406_1</ID> |
||
1292 | <String>BackStreet Browser 3.x</String> |
||
1293 | <Description>BackStreet Browser - Offline browser / website downloader</Description> |
||
1294 | <Type>D</Type> |
||
1295 | <Comment></Comment> |
||
1296 | <Link1>http://www.spadixbd.com/backstreet/</Link1> |
||
1297 | <Link2></Link2> |
||
1298 | </user-agent> |
||
1299 | <user-agent> |
||
1300 | <ID>id_a_f_140508_1</ID> |
||
1301 | <String>BaiduImagespider+(+http://www.baidu.jp/search/s308.html)</String> |
||
1302 | <Description>Baidu search (Japan) image crawler</Description> |
||
1303 | <Type>R</Type> |
||
1304 | <Comment>119.63.193.94.[x]xx</Comment> |
||
1305 | <Link1>http://www.baidu.jp/</Link1> |
||
1306 | <Link2></Link2> |
||
1307 | </user-agent> |
||
1308 | <user-agent> |
||
1309 | <ID>id_a_f_99</ID> |
||
1310 | <String>BaiDuSpider</String> |
||
1311 | <Description>Baidu spidering engine - used by diff. IPs</Description> |
||
1312 | <Type>R</Type> |
||
1313 | <Comment></Comment> |
||
1314 | <Link1>http://www.baidu.com</Link1> |
||
1315 | <Link2></Link2> |
||
1316 | </user-agent> |
||
1317 | <user-agent> |
||
1318 | <ID>id_a_f_080608_1</ID> |
||
1319 | <String>Baiduspider+(+http://help.baidu.jp/system/05.html)</String> |
||
1320 | <Description>Baidu spidering engine - used by diff. IPs</Description> |
||
1321 | <Type>R</Type> |
||
1322 | <Comment></Comment> |
||
1323 | <Link1>http://www.baidu.com</Link1> |
||
1324 | <Link2></Link2> |
||
1325 | </user-agent> |
||
1326 | <user-agent> |
||
1327 | <ID>id_a_f_100</ID> |
||
1328 | <String>Baiduspider+(+http://www.baidu.com/search/spider.htm)</String> |
||
1329 | <Description>Baidu spidering engine - used by diff. IPs</Description> |
||
1330 | <Type>R</Type> |
||
1331 | <Comment></Comment> |
||
1332 | <Link1>http://www.baidu.com</Link1> |
||
1333 | <Link2></Link2> |
||
1334 | </user-agent> |
||
1335 | <user-agent> |
||
1336 | <ID>id_a_f_080407_1</ID> |
||
1337 | <String>Baiduspider+(+http://www.baidu.com/search/spider_jp.html)</String> |
||
1338 | <Description>Baidu search (Japan) crawler</Description> |
||
1339 | <Type>R</Type> |
||
1340 | <Comment>119.63.193.[x]xx</Comment> |
||
1341 | <Link1>http://www.baidu.jp</Link1> |
||
1342 | <Link2></Link2> |
||
1343 | </user-agent> |
||
1344 | <user-agent> |
||
1345 | <ID>id_a_f_031107_1</ID> |
||
1346 | <String>Balihoo/Nutch-1.0-dev (Crawler for Balihoo.com search engine - obeys robots.txt and robots meta tags ; http://balihoo.com/index.aspx; robot at balihoo dot com)</String> |
||
1347 | <Description>Balihoo - Vertical search engine crawler (beta)</Description> |
||
1348 | <Type>R</Type> |
||
1349 | <Comment></Comment> |
||
1350 | <Link1>http://www.balihoo.com/</Link1> |
||
1351 | <Link2>http://www.balihoo.com/pdfs/BalihooFactSheet.pdf</Link2> |
||
1352 | </user-agent> |
||
1353 | <user-agent> |
||
1354 | <ID>id_a_f_101</ID> |
||
1355 | <String>BanBots/1.2 (spider@banbots.com)</String> |
||
1356 | <Description>Project BanBots Perl script robot</Description> |
||
1357 | <Type>C</Type> |
||
1358 | <Comment>s. also Mozilla/5.0 (compatible; BanBots/2.0b..</Comment> |
||
1359 | <Link1>http://www.banbots.com/</Link1> |
||
1360 | <Link2></Link2> |
||
1361 | </user-agent> |
||
1362 | <user-agent> |
||
1363 | <ID>id_a_f_140506_3</ID> |
||
1364 | <String>Barca/2.0.xxxx</String> |
||
1365 | <Description>Barca Pro email & PIM software</Description> |
||
1366 | <Type>B</Type> |
||
1367 | <Comment></Comment> |
||
1368 | <Link1>http://www.pocosystems.com/home/index.php?option=com_content&task=view&id=105&Itemid=54</Link1> |
||
1369 | <Link2></Link2> |
||
1370 | </user-agent> |
||
1371 | <user-agent> |
||
1372 | <ID>id_a_f_120206_2</ID> |
||
1373 | <String>BarcaPro/1.4.xxxx</String> |
||
1374 | <Description>Barca Pro email & PIM software</Description> |
||
1375 | <Type>B</Type> |
||
1376 | <Comment></Comment> |
||
1377 | <Link1>http://www.pocosystems.com/home/index.php?option=com_content&task=view&id=105&Itemid=54</Link1> |
||
1378 | <Link2></Link2> |
||
1379 | </user-agent> |
||
1380 | <user-agent> |
||
1381 | <ID>id_a_f_102</ID> |
||
1382 | <String>BarraHomeCrawler (albertof@barrahome.org)</String> |
||
1383 | <Description>Barrahome crawler</Description> |
||
1384 | <Type>R</Type> |
||
1385 | <Comment>64.246.56.xx</Comment> |
||
1386 | <Link1>http://www.barrahome.org</Link1> |
||
1387 | <Link2></Link2> |
||
1388 | </user-agent> |
||
1389 | <user-agent> |
||
1390 | <ID>id_a_f_011006_1</ID> |
||
1391 | <String>bCentral Billing Post-Process</String> |
||
1392 | <Description>Unknown user agent from Microsoft</Description> |
||
1393 | <Type></Type> |
||
1394 | <Comment>204.71.191.1xx</Comment> |
||
1395 | <Link1></Link1> |
||
1396 | <Link2></Link2> |
||
1397 | </user-agent> |
||
1398 | <user-agent> |
||
1399 | <ID>id_a_f_103</ID> |
||
1400 | <String>bdcindexer_2.6.2 (research@bdc)</String> |
||
1401 | <Description>Business.com robot</Description> |
||
1402 | <Type>R</Type> |
||
1403 | <Comment>208.144.233.xxx</Comment> |
||
1404 | <Link1>http://www.business.com</Link1> |
||
1405 | <Link2></Link2> |
||
1406 | </user-agent> |
||
1407 | <user-agent> |
||
1408 | <ID>id_a_f_104</ID> |
||
1409 | <String>BDFetch</String> |
||
1410 | <Description>Brandimensions Brand Protection robot</Description> |
||
1411 | <Type>R</Type> |
||
1412 | <Comment></Comment> |
||
1413 | <Link1>http://www.brandimensions.com/</Link1> |
||
1414 | <Link2></Link2> |
||
1415 | </user-agent> |
||
1416 | <user-agent> |
||
1417 | <ID>id_a_f_105</ID> |
||
1418 | <String>BDNcentral Crawler v2.3 [en] (http://www.bdncentral.com/robot.html) (X11; I; Linux 2.0.44 i686)</String> |
||
1419 | <Description>Bdncentral Sitesearch robot</Description> |
||
1420 | <Type>R</Type> |
||
1421 | <Comment></Comment> |
||
1422 | <Link1>http://www.bdncentral.com</Link1> |
||
1423 | <Link2></Link2> |
||
1424 | </user-agent> |
||
1425 | <user-agent> |
||
1426 | <ID>id_a_f_111205_3</ID> |
||
1427 | <String>BeamMachine/0.5 (dead link remover of www.beammachine.net)</String> |
||
1428 | <Description>beammachine web directory (Germany) link checking</Description> |
||
1429 | <Type>R C</Type> |
||
1430 | <Comment></Comment> |
||
1431 | <Link1>http://www.beammachine.net/de/</Link1> |
||
1432 | <Link2></Link2> |
||
1433 | </user-agent> |
||
1434 | <user-agent> |
||
1435 | <ID>id_a_f_106</ID> |
||
1436 | <String>beautybot/1.0 (+http://www.uchoose.de/crawler/beautybot/)</String> |
||
1437 | <Description>Beauty robot for Cosmoty - German beauty and wellness search</Description> |
||
1438 | <Type>R</Type> |
||
1439 | <Comment></Comment> |
||
1440 | <Link1>http://www.cosmoty.de</Link1> |
||
1441 | <Link2>http://www.uchoose.de/Projekte/Lifestyle/beauty/</Link2> |
||
1442 | </user-agent> |
||
1443 | <user-agent> |
||
1444 | <ID>id_a_f_230406_1</ID> |
||
1445 | <String>BebopBot/2.5.1 ( crawler http://www.apassion4jazz.net/bebopbot.html )</String> |
||
1446 | <Description>A Passion for Jazz music related search robot</Description> |
||
1447 | <Type>R</Type> |
||
1448 | <Comment>68.6.204.2xx</Comment> |
||
1449 | <Link1>http://www.apassion4jazz.net/</Link1> |
||
1450 | <Link2></Link2> |
||
1451 | </user-agent> |
||
1452 | <user-agent> |
||
1453 | <ID>id_a_f_107</ID> |
||
1454 | <String>BeebwareDirectory/v0.01</String> |
||
1455 | <Description>LinkcheckerBeepware (site is down) web directory link checking</Description> |
||
1456 | <Type>C</Type> |
||
1457 | <Comment></Comment> |
||
1458 | <Link1>http://directory.beebware.co.uk</Link1> |
||
1459 | <Link2></Link2> |
||
1460 | </user-agent> |
||
1461 | <user-agent> |
||
1462 | <ID>id_a_f_108</ID> |
||
1463 | <String>Big Brother (http://pauillac.inria.fr/~fpottier/)</String> |
||
1464 | <Description>Big Brother link checking tool</Description> |
||
1465 | <Type>C</Type> |
||
1466 | <Comment></Comment> |
||
1467 | <Link1>http://pauillac.inria.fr</Link1> |
||
1468 | <Link2></Link2> |
||
1469 | </user-agent> |
||
1470 | <user-agent> |
||
1471 | <ID>id_a_f_130606_1</ID> |
||
1472 | <String>Big Fish v1.0</String> |
||
1473 | <Description>GoonGee.com link popularity checking</Description> |
||
1474 | <Type>C</Type> |
||
1475 | <Comment>216.89.111.x</Comment> |
||
1476 | <Link1>http://www.goongee.com/big-fish/</Link1> |
||
1477 | <Link2></Link2> |
||
1478 | </user-agent> |
||
1479 | <user-agent> |
||
1480 | <ID>id_a_f_109</ID> |
||
1481 | <String>BigBrother/1.6e</String> |
||
1482 | <Description>BB4 network monitoring</Description> |
||
1483 | <Type>C</Type> |
||
1484 | <Comment></Comment> |
||
1485 | <Link1>http://www.bb4.com</Link1> |
||
1486 | <Link2></Link2> |
||
1487 | </user-agent> |
||
1488 | <user-agent> |
||
1489 | <ID>id_a_f_110</ID> |
||
1490 | <String>BigCliqueBOT/1.03-dev (bigclicbot; http://www.bigclique.com; bot@bigclique.com)</String> |
||
1491 | <Description>BigClique Search robot</Description> |
||
1492 | <Type>R</Type> |
||
1493 | <Comment></Comment> |
||
1494 | <Link1>http://www.bigclique.com</Link1> |
||
1495 | <Link2></Link2> |
||
1496 | </user-agent> |
||
1497 | <user-agent> |
||
1498 | <ID>id_a_f_080206_4</ID> |
||
1499 | <String>BIGLOTRON (Beta 2;GNU/Linux)</String> |
||
1500 | <Description>Biglotron search (France) robot</Description> |
||
1501 | <Type>R</Type> |
||
1502 | <Comment></Comment> |
||
1503 | <Link1>http://www.biglotron.com/</Link1> |
||
1504 | <Link2></Link2> |
||
1505 | </user-agent> |
||
1506 | <user-agent> |
||
1507 | <ID>id_a_f_171106_2</ID> |
||
1508 | <String>Bigsearch.ca/Nutch-x.x-dev (Bigsearch.ca Internet Spider; http://www.bigsearch.ca/; info@enhancededge.com)</String> |
||
1509 | <Description>Bigsearch.ca search robot</Description> |
||
1510 | <Type>R</Type> |
||
1511 | <Comment>72.0.207.1xx</Comment> |
||
1512 | <Link1>http://www.bigsearch.ca/</Link1> |
||
1513 | <Link2></Link2> |
||
1514 | </user-agent> |
||
1515 | <user-agent> |
||
1516 | <ID>id_a_f_111</ID> |
||
1517 | <String>Bilbo/2.3b-UNIX</String> |
||
1518 | <Description>Bilbo - web frontend for the Nessus Security Scanner</Description> |
||
1519 | <Type>C</Type> |
||
1520 | <Comment></Comment> |
||
1521 | <Link1>http://home.broadpark.no/%7Etnilsen-1/Linux/Bilbo_-_Nessus_WEB/bilbo_-_nessus_web.html</Link1> |
||
1522 | <Link2></Link2> |
||
1523 | </user-agent> |
||
1524 | <user-agent> |
||
1525 | <ID>id_a_f_170806_1</ID> |
||
1526 | <String>BilgiBetaBot/0.8-dev (bilgi.com (Beta) ; http://lucene.apache.org/nutch/bot.html; nutch-agent@lucene.apache.org)</String> |
||
1527 | <Description>Bilgi.com (Beta) search robot - Turkey</Description> |
||
1528 | <Type>R</Type> |
||
1529 | <Comment>212.156.230.2xx</Comment> |
||
1530 | <Link1>http://www.bilgi.com/</Link1> |
||
1531 | <Link2></Link2> |
||
1532 | </user-agent> |
||
1533 | <user-agent> |
||
1534 | <ID>id_a_f_080607_1</ID> |
||
1535 | <String>BilgiBot/1.0(beta) (http://www.bilgi.com/; bilgi at bilgi dot com)</String> |
||
1536 | <Description>Bilgi.com (Beta) search robot - Turkey</Description> |
||
1537 | <Type>R</Type> |
||
1538 | <Comment>212.156.230.2xx</Comment> |
||
1539 | <Link1>http://www.bilgi.com/</Link1> |
||
1540 | <Link2></Link2> |
||
1541 | </user-agent> |
||
1542 | <user-agent> |
||
1543 | <ID>id_a_f_112</ID> |
||
1544 | <String>billbot wjj@cs.cmu.edu</String> |
||
1545 | <Description>Carnegie Mellon School robot/link checking ?</Description> |
||
1546 | <Type>C</Type> |
||
1547 | <Comment></Comment> |
||
1548 | <Link1>http://www.cs.cmu.edu</Link1> |
||
1549 | <Link2></Link2> |
||
1550 | </user-agent> |
||
1551 | <user-agent> |
||
1552 | <ID>id_a_f_050206_3</ID> |
||
1553 | <String>Bitacle bot/1.1</String> |
||
1554 | <Description>Bitacle Blog Search Archive robot</Description> |
||
1555 | <Type>R</Type> |
||
1556 | <Comment></Comment> |
||
1557 | <Link1>http://bitacle.org/</Link1> |
||
1558 | <Link2></Link2> |
||
1559 | </user-agent> |
||
1560 | <user-agent> |
||
1561 | <ID>id_a_f_050206_2</ID> |
||
1562 | <String>Bitacle Robot (V:1.0;) (http://www.bitacle.com)</String> |
||
1563 | <Description>Bitacle Blog Search Archive robot</Description> |
||
1564 | <Type>R</Type> |
||
1565 | <Comment></Comment> |
||
1566 | <Link1>http://bitacle.org/</Link1> |
||
1567 | <Link2></Link2> |
||
1568 | </user-agent> |
||
1569 | <user-agent> |
||
1570 | <ID>id_a_f_113</ID> |
||
1571 | <String>Biyubi/x.x (Sistema Fenix; G11; Familia Toledo; es-mx)</String> |
||
1572 | <Description>Biyubi Navigator - Mexican browser for Fenix OS</Description> |
||
1573 | <Type>B</Type> |
||
1574 | <Comment></Comment> |
||
1575 | <Link1>http://www.biyubi.com</Link1> |
||
1576 | <Link2></Link2> |
||
1577 | </user-agent> |
||
1578 | <user-agent> |
||
1579 | <ID>id_a_f_114</ID> |
||
1580 | <String>BlackBerry7520/4.0.0 Profile/MIDP-2.0 Configuration/CLDC-1.1 UP.Browser/5.0.3.3 UP.Link/5.1.2.12 (Google WAP Proxy/1.0)</String> |
||
1581 | <Description>Blackberry Wireless Internet browser via Google WAP Proxy</Description> |
||
1582 | <Type>B P</Type> |
||
1583 | <Comment></Comment> |
||
1584 | <Link1>http://www.blackberry.com/products/service/web.shtml</Link1> |
||
1585 | <Link2>http://www.openwave.com</Link2> |
||
1586 | </user-agent> |
||
1587 | <user-agent> |
||
1588 | <ID>id_a_f_115</ID> |
||
1589 | <String>BlackWidow</String> |
||
1590 | <Description>FS Consulting (was www.fsconsult.net) Black Widow web crawler</Description> |
||
1591 | <Type>R</Type> |
||
1592 | <Comment></Comment> |
||
1593 | <Link1></Link1> |
||
1594 | <Link2></Link2> |
||
1595 | </user-agent> |
||
1596 | <user-agent> |
||
1597 | <ID>id_a_f_010306_1</ID> |
||
1598 | <String>BlackWidow</String> |
||
1599 | <Description>BlackWidow web site scanner / downloading tool</Description> |
||
1600 | <Type>D</Type> |
||
1601 | <Comment></Comment> |
||
1602 | <Link1>http://www.softbytelabs.com/BlackWidow</Link1> |
||
1603 | <Link2></Link2> |
||
1604 | </user-agent> |
||
1605 | <user-agent> |
||
1606 | <ID>id_a_f_116</ID> |
||
1607 | <String>Blaiz-Bee/1.0 (+http://www.blaiz.net)</String> |
||
1608 | <Description>Blaiz Enterprises RawGrunt search</Description> |
||
1609 | <Type>R</Type> |
||
1610 | <Comment>203.87.123.1xx</Comment> |
||
1611 | <Link1>http://www.rawgrunt.com/</Link1> |
||
1612 | <Link2>http://www.blaiz.net</Link2> |
||
1613 | </user-agent> |
||
1614 | <user-agent> |
||
1615 | <ID>id_a_f_160307_1</ID> |
||
1616 | <String>Blaiz-Bee/2.00.8222 (BE Internet Search Engine http://www.rawgrunt.com)</String> |
||
1617 | <Description>Blaiz Enterprises RawGrunt search</Description> |
||
1618 | <Type>R</Type> |
||
1619 | <Comment>203.87.123.1xx</Comment> |
||
1620 | <Link1>http://www.rawgrunt.com/</Link1> |
||
1621 | <Link2>http://www.blaiz.net</Link2> |
||
1622 | </user-agent> |
||
1623 | <user-agent> |
||
1624 | <ID>id_a_f_240706_1</ID> |
||
1625 | <String>Blaiz-Bee/2.00.xxxx (+http://www.blaiz.net)</String> |
||
1626 | <Description>Blaiz Enterprises RawGrunt search</Description> |
||
1627 | <Type>R</Type> |
||
1628 | <Comment>203.87.123.1xx</Comment> |
||
1629 | <Link1>http://www.rawgrunt.com/</Link1> |
||
1630 | <Link2>http://www.blaiz.net</Link2> |
||
1631 | </user-agent> |
||
1632 | <user-agent> |
||
1633 | <ID>id_a_f_117</ID> |
||
1634 | <String>BlitzBOT@tricus.net</String> |
||
1635 | <Description>Blitzsuche Germany robot</Description> |
||
1636 | <Type>R</Type> |
||
1637 | <Comment></Comment> |
||
1638 | <Link1>http://blitzsuche.rp-online.de/</Link1> |
||
1639 | <Link2></Link2> |
||
1640 | </user-agent> |
||
1641 | <user-agent> |
||
1642 | <ID>id_a_f_118</ID> |
||
1643 | <String>BlitzBOT@tricus.net (Mozilla compatible)</String> |
||
1644 | <Description>Blitzsuche Germany robot</Description> |
||
1645 | <Type>R</Type> |
||
1646 | <Comment></Comment> |
||
1647 | <Link1>http://blitzsuche.rp-online.de/</Link1> |
||
1648 | <Link2></Link2> |
||
1649 | </user-agent> |
||
1650 | <user-agent> |
||
1651 | <ID>id_a_f_090307_1</ID> |
||
1652 | <String>BlockNote.Net</String> |
||
1653 | <Description>BlockNote web page editor</Description> |
||
1654 | <Type>B</Type> |
||
1655 | <Comment></Comment> |
||
1656 | <Link1>http://blocknote.net/</Link1> |
||
1657 | <Link2></Link2> |
||
1658 | </user-agent> |
||
1659 | <user-agent> |
||
1660 | <ID>id_a_f_119</ID> |
||
1661 | <String>BlogBot/1.x</String> |
||
1662 | <Description>blogdex robot from MIT.edu</Description> |
||
1663 | <Type>R</Type> |
||
1664 | <Comment></Comment> |
||
1665 | <Link1>http://blogdex.media.mit.edu/</Link1> |
||
1666 | <Link2></Link2> |
||
1667 | </user-agent> |
||
1668 | <user-agent> |
||
1669 | <ID>id_a_f_071206_1</ID> |
||
1670 | <String>BlogBridge 2.13 (http://www.blogbridge.com/)</String> |
||
1671 | <Description>BlogBridge RSS reader</Description> |
||
1672 | <Type>B</Type> |
||
1673 | <Comment></Comment> |
||
1674 | <Link1>http://www.blogbridge.com/</Link1> |
||
1675 | <Link2></Link2> |
||
1676 | </user-agent> |
||
1677 | <user-agent> |
||
1678 | <ID>id_a_f_120</ID> |
||
1679 | <String>Bloglines Title Fetch/1.0 (http://www.bloglines.com)</String> |
||
1680 | <Description>Bloglines article search</Description> |
||
1681 | <Type>R</Type> |
||
1682 | <Comment>65.214.44.xx</Comment> |
||
1683 | <Link1>http://www.bloglines.com</Link1> |
||
1684 | <Link2></Link2> |
||
1685 | </user-agent> |
||
1686 | <user-agent> |
||
1687 | <ID>id_a_f_250907_1</ID> |
||
1688 | <String>Bloglines-Images/0.1 (http://www.bloglines.com)</String> |
||
1689 | <Description>Bloglines graphics crawler</Description> |
||
1690 | <Type>R</Type> |
||
1691 | <Comment>65.214.44.xx</Comment> |
||
1692 | <Link1>http://www.bloglines.com</Link1> |
||
1693 | <Link2></Link2> |
||
1694 | </user-agent> |
||
1695 | <user-agent> |
||
1696 | <ID>id_a_f_011108_2</ID> |
||
1697 | <String>Bloglines/3.1 (http://www.bloglines.com)</String> |
||
1698 | <Description>Bloglines news crawler</Description> |
||
1699 | <Type>R</Type> |
||
1700 | <Comment>65.214.44.xx</Comment> |
||
1701 | <Link1>http://www.bloglines.com</Link1> |
||
1702 | <Link2></Link2> |
||
1703 | </user-agent> |
||
1704 | <user-agent> |
||
1705 | <ID>id_a_f_071206_2</ID> |
||
1706 | <String>BlogMap (http://www.feedmap.net)</String> |
||
1707 | <Description>FeedMap / BlogMap geo coding service</Description> |
||
1708 | <Type>C</Type> |
||
1709 | <Comment></Comment> |
||
1710 | <Link1>http://www.feedmap.net/BlogMap/</Link1> |
||
1711 | <Link2></Link2> |
||
1712 | </user-agent> |
||
1713 | <user-agent> |
||
1714 | <ID>id_a_f_121</ID> |
||
1715 | <String>Blogpulse (info@blogpulse.com)</String> |
||
1716 | <Description>Intelliseek's BlogPulse blog search</Description> |
||
1717 | <Type>R</Type> |
||
1718 | <Comment>64.158.138.xx</Comment> |
||
1719 | <Link1>http://www.blogpulse.com</Link1> |
||
1720 | <Link2></Link2> |
||
1721 | </user-agent> |
||
1722 | <user-agent> |
||
1723 | <ID>id_a_f_050208_2</ID> |
||
1724 | <String>BlogPulseLive (support@blogpulse.com)</String> |
||
1725 | <Description>Intelliseek's BlogPulse blog search</Description> |
||
1726 | <Type>R</Type> |
||
1727 | <Comment>64.158.138.xx</Comment> |
||
1728 | <Link1>http://www.blogpulse.com</Link1> |
||
1729 | <Link2></Link2> |
||
1730 | </user-agent> |
||
1731 | <user-agent> |
||
1732 | <ID>id_a_f_161206_2</ID> |
||
1733 | <String>BlogSearch/1.x +http://www.icerocket.com/</String> |
||
1734 | <Description>IceRocket Web search robot</Description> |
||
1735 | <Type>R</Type> |
||
1736 | <Comment>s. also BlogzIce ...</Comment> |
||
1737 | <Link1>http://www.icerocket.com</Link1> |
||
1738 | <Link2></Link2> |
||
1739 | </user-agent> |
||
1740 | <user-agent> |
||
1741 | <ID>id_a_f_020707_1</ID> |
||
1742 | <String>blogsearchbot-pumpkin-3</String> |
||
1743 | <Description>Art of Computing blog search project</Description> |
||
1744 | <Type>R</Type> |
||
1745 | <Comment>88.198.44.2xx</Comment> |
||
1746 | <Link1>http://artofcomputing.net/blog/?p=4</Link1> |
||
1747 | <Link2></Link2> |
||
1748 | </user-agent> |
||
1749 | <user-agent> |
||
1750 | <ID>id_a_f_241205_1</ID> |
||
1751 | <String>BlogsNowBot, V 2.01 (+http://www.blogsnow.com/)</String> |
||
1752 | <Description>BlogsNow realtime link tracker robot</Description> |
||
1753 | <Type>R</Type> |
||
1754 | <Comment></Comment> |
||
1755 | <Link1>http://www.blogsnow.com/</Link1> |
||
1756 | <Link2></Link2> |
||
1757 | </user-agent> |
||
1758 | <user-agent> |
||
1759 | <ID>id_a_f_261107_1</ID> |
||
1760 | <String>BlogVibeBot-v1.1 (spider@blogvibe.nl)</String> |
||
1761 | <Description>BlogVipe news and Blog crawler (Netherlands)</Description> |
||
1762 | <Type>R</Type> |
||
1763 | <Comment>212.61.21.xx</Comment> |
||
1764 | <Link1>http://www.blogvibe.nl</Link1> |
||
1765 | <Link2></Link2> |
||
1766 | </user-agent> |
||
1767 | <user-agent> |
||
1768 | <ID>id_a_f_122</ID> |
||
1769 | <String>blogWatcher_Spider/0.1 (http://www.lr.pi.titech.ac.jp/blogWatcher/)</String> |
||
1770 | <Description>blogWatcher robot from Okumura Group Tokyo (131.112.182.xxx)</Description> |
||
1771 | <Type>R</Type> |
||
1772 | <Comment></Comment> |
||
1773 | <Link1>http://www.lr.pi.titech.ac.jp</Link1> |
||
1774 | <Link2></Link2> |
||
1775 | </user-agent> |
||
1776 | <user-agent> |
||
1777 | <ID>id_a_f_123</ID> |
||
1778 | <String>BlogzIce/1.0 (+http://icerocket.com; rhodes@icerocket.com)</String> |
||
1779 | <Description>IceRocket Web search robot</Description> |
||
1780 | <Type>R</Type> |
||
1781 | <Comment>s. also BlogSearch ...</Comment> |
||
1782 | <Link1>http://www.icerocket.com</Link1> |
||
1783 | <Link2></Link2> |
||
1784 | </user-agent> |
||
1785 | <user-agent> |
||
1786 | <ID>id_a_f_124</ID> |
||
1787 | <String>BlogzIce/1.0 +http://www.icerocket.com/</String> |
||
1788 | <Description>IceRocket Web search robot</Description> |
||
1789 | <Type>R</Type> |
||
1790 | <Comment>s. also BlogSearch ...</Comment> |
||
1791 | <Link1>http://www.icerocket.com</Link1> |
||
1792 | <Link2></Link2> |
||
1793 | </user-agent> |
||
1794 | <user-agent> |
||
1795 | <ID>id_a_f_310108_1</ID> |
||
1796 | <String>BloobyBot</String> |
||
1797 | <Description>Blooby search (beta) robot</Description> |
||
1798 | <Type>R</Type> |
||
1799 | <Comment>206.166.206.18x</Comment> |
||
1800 | <Link1>http://www.blooby.com/</Link1> |
||
1801 | <Link2></Link2> |
||
1802 | </user-agent> |
||
1803 | <user-agent> |
||
1804 | <ID>id_a_f_270507_1</ID> |
||
1805 | <String>Bloodhound/Nutch-0.9 (Testing Crawler for Research - obeys robots.txt and robots meta tags ; http://balihoo.com/index.aspx; robot at balihoo dot com)</String> |
||
1806 | <Description>Balihoo - Search Engine for Advertising Media</Description> |
||
1807 | <Type>R</Type> |
||
1808 | <Comment>204.228.230.xx</Comment> |
||
1809 | <Link1>http://balihoo.com/</Link1> |
||
1810 | <Link2></Link2> |
||
1811 | </user-agent> |
||
1812 | <user-agent> |
||
1813 | <ID>id_a_f_125</ID> |
||
1814 | <String>bluefish 0.6 HTML editor</String> |
||
1815 | <Description>Bluefish HTML-editor for Linux</Description> |
||
1816 | <Type>B</Type> |
||
1817 | <Comment></Comment> |
||
1818 | <Link1>http://bluefish.openoffice.nl/</Link1> |
||
1819 | <Link2></Link2> |
||
1820 | </user-agent> |
||
1821 | <user-agent> |
||
1822 | <ID>id_a_f_126</ID> |
||
1823 | <String>BMCLIENT</String> |
||
1824 | <Description>Part of ButtMan remote access tool</Description> |
||
1825 | <Type></Type> |
||
1826 | <Comment>seems to be a Trojan - see link</Comment> |
||
1827 | <Link1>http://www.glocksoft.com/trojan_list/ButtMan.htm</Link1> |
||
1828 | <Link2></Link2> |
||
1829 | </user-agent> |
||
1830 | <user-agent> |
||
1831 | <ID>id_a_f_120506_1</ID> |
||
1832 | <String>BMLAUNCHER</String> |
||
1833 | <Description>Bookmark Express bookmark manager</Description> |
||
1834 | <Type>C</Type> |
||
1835 | <Comment>Website is dead - was:</Comment> |
||
1836 | <Link1>http://www.bookmarkexpress.com/</Link1> |
||
1837 | <Link2></Link2> |
||
1838 | </user-agent> |
||
1839 | <user-agent> |
||
1840 | <ID>id_a_f_127</ID> |
||
1841 | <String>Bobby/4.0.x RPT-HTTPClient/0.3-3E</String> |
||
1842 | <Description>Bobby web accessibility desktop testing tool</Description> |
||
1843 | <Type>C</Type> |
||
1844 | <Comment></Comment> |
||
1845 | <Link1>http://bobby.watchfire.com/bobby/html/en/index.jsp</Link1> |
||
1846 | <Link2></Link2> |
||
1847 | </user-agent> |
||
1848 | <user-agent> |
||
1849 | <ID>id_a_f_128</ID> |
||
1850 | <String>boitho.com-dc/0.xx (http://www.boitho.com/dcbot.html)</String> |
||
1851 | <Description>Boitho search (Norway) robot via 80.202.212.xx / 80.80.111.xx</Description> |
||
1852 | <Type>R</Type> |
||
1853 | <Comment></Comment> |
||
1854 | <Link1>http://www.boitho.com</Link1> |
||
1855 | <Link2></Link2> |
||
1856 | </user-agent> |
||
1857 | <user-agent> |
||
1858 | <ID>id_a_f_129</ID> |
||
1859 | <String>boitho.com-robot/1.x</String> |
||
1860 | <Description>Boitho search (Norway) robot via 80.202.212.xx / 80.80.111.xx</Description> |
||
1861 | <Type>R</Type> |
||
1862 | <Comment></Comment> |
||
1863 | <Link1>http://www.boitho.com</Link1> |
||
1864 | <Link2></Link2> |
||
1865 | </user-agent> |
||
1866 | <user-agent> |
||
1867 | <ID>id_a_f_130</ID> |
||
1868 | <String>boitho.com-robot/1.x (http://www.boitho.com/bot.html)</String> |
||
1869 | <Description>Boitho search (Norway) robot via 80.202.212.xx / 80.80.111.xx</Description> |
||
1870 | <Type>R</Type> |
||
1871 | <Comment></Comment> |
||
1872 | <Link1>http://www.boitho.com</Link1> |
||
1873 | <Link2></Link2> |
||
1874 | </user-agent> |
||
1875 | <user-agent> |
||
1876 | <ID>id_a_f_060806_1</ID> |
||
1877 | <String>Bookdog/x.x</String> |
||
1878 | <Description>Bookdog - Mac bookmark manager</Description> |
||
1879 | <Type>C</Type> |
||
1880 | <Comment></Comment> |
||
1881 | <Link1>http://www.sheepsystems.com/bookdog/</Link1> |
||
1882 | <Link2></Link2> |
||
1883 | </user-agent> |
||
1884 | <user-agent> |
||
1885 | <ID>id_a_f_131</ID> |
||
1886 | <String>Bookmark Buddy bookmark checker (http://www.bookmarkbuddy.net/)</String> |
||
1887 | <Description>Bookmark Buddy - favorite bookmark manager </Description> |
||
1888 | <Type>C</Type> |
||
1889 | <Comment></Comment> |
||
1890 | <Link1>http://www.bookmarkbuddy.net</Link1> |
||
1891 | <Link2></Link2> |
||
1892 | </user-agent> |
||
1893 | <user-agent> |
||
1894 | <ID>id_a_f_132</ID> |
||
1895 | <String>Bookmark Renewal Check Agent [http://www.bookmark.ne.jp/]</String> |
||
1896 | <Description>Favourites managing program</Description> |
||
1897 | <Type>C</Type> |
||
1898 | <Comment></Comment> |
||
1899 | <Link1>http://www.bookmark.ne.jp</Link1> |
||
1900 | <Link2></Link2> |
||
1901 | </user-agent> |
||
1902 | <user-agent> |
||
1903 | <ID>id_a_f_230807_1</ID> |
||
1904 | <String>Bookmark Renewal Check Agent [http://www.bookmark.ne.jp/] (Version 2.0beta)</String> |
||
1905 | <Description>Favourites managing program</Description> |
||
1906 | <Type>C</Type> |
||
1907 | <Comment></Comment> |
||
1908 | <Link1>http://www.bookmark.ne.jp</Link1> |
||
1909 | <Link2></Link2> |
||
1910 | </user-agent> |
||
1911 | <user-agent> |
||
1912 | <ID>id_a_f_300408_1</ID> |
||
1913 | <String>BookmarkBase(2/;http://bookmarkbase.com)</String> |
||
1914 | <Description>Bookmark Base bookmark manager</Description> |
||
1915 | <Type>C</Type> |
||
1916 | <Comment></Comment> |
||
1917 | <Link1>http://www.bookmarkbase.com/</Link1> |
||
1918 | <Link2></Link2> |
||
1919 | </user-agent> |
||
1920 | <user-agent> |
||
1921 | <ID>id_a_f_133</ID> |
||
1922 | <String>Bot mailto:craftbot@yahoo.com</String> |
||
1923 | <Description>cybercity.fr user robot / faked user agent ?</Description> |
||
1924 | <Type></Type> |
||
1925 | <Comment></Comment> |
||
1926 | <Link1></Link1> |
||
1927 | <Link2></Link2> |
||
1928 | </user-agent> |
||
1929 | <user-agent> |
||
1930 | <ID>id_a_f_160308_1</ID> |
||
1931 | <String>BPImageWalker/2.0 (www.bdbrandprotect.com)</String> |
||
1932 | <Description>BD-Brandprotect copyright infringement crawler</Description> |
||
1933 | <Type>R</Type> |
||
1934 | <Comment>72.14.164.1xx</Comment> |
||
1935 | <Link1>http://www.bdbrandprotect.com/</Link1> |
||
1936 | <Link2>http://www.bdbrandprotect.com/solutions_5.html</Link2> |
||
1937 | </user-agent> |
||
1938 | <user-agent> |
||
1939 | <ID>id_a_f_134</ID> |
||
1940 | <String>BravoBrian bstop.bravobrian.it</String> |
||
1941 | <Description>BravoBrian bSTOP parental control</Description> |
||
1942 | <Type>P R</Type> |
||
1943 | <Comment> s. also BStop</Comment> |
||
1944 | <Link1>http://bstop.bravobrian.it/</Link1> |
||
1945 | <Link2></Link2> |
||
1946 | </user-agent> |
||
1947 | <user-agent> |
||
1948 | <ID>id_a_f_135</ID> |
||
1949 | <String>BravoBrian SpiderEngine MarcoPolo</String> |
||
1950 | <Description>Robot for BravoBrian bSTOP</Description> |
||
1951 | <Type>R</Type> |
||
1952 | <Comment> s. also BStop</Comment> |
||
1953 | <Link1>http://bstop.bravobrian.it/</Link1> |
||
1954 | <Link2></Link2> |
||
1955 | </user-agent> |
||
1956 | <user-agent> |
||
1957 | <ID>id_a_f_220508_1</ID> |
||
1958 | <String>BrightCrawler (http://www.brightcloud.com/brightcrawler.asp)</String> |
||
1959 | <Description>BrightCloud web filtering for classifying websites</Description> |
||
1960 | <Type>P R</Type> |
||
1961 | <Comment></Comment> |
||
1962 | <Link1>http://www.brightcloud.com/brightcrawler.asp</Link1> |
||
1963 | <Link2></Link2> |
||
1964 | </user-agent> |
||
1965 | <user-agent> |
||
1966 | <ID>id_a_f_136</ID> |
||
1967 | <String>BruinBot (+http://webarchive.cs.ucla.edu/bruinbot.html) </String> |
||
1968 | <Description>Webarchive Project Bruinbot crawler</Description> |
||
1969 | <Type>R</Type> |
||
1970 | <Comment></Comment> |
||
1971 | <Link1>http://webarchive.cs.ucla.edu</Link1> |
||
1972 | <Link2></Link2> |
||
1973 | </user-agent> |
||
1974 | <user-agent> |
||
1975 | <ID>id_a_f_137</ID> |
||
1976 | <String>BSDSeek/1.0</String> |
||
1977 | <Description>Inktomi (Hotbot-Lycos NBCi) robot</Description> |
||
1978 | <Type>R</Type> |
||
1979 | <Comment></Comment> |
||
1980 | <Link1>http://www.inktomi.com/</Link1> |
||
1981 | <Link2></Link2> |
||
1982 | </user-agent> |
||
1983 | <user-agent> |
||
1984 | <ID>id_a_f_138</ID> |
||
1985 | <String>BStop.BravoBrian.it Agent Detector</String> |
||
1986 | <Description>BravoBrian bSTOP parental control</Description> |
||
1987 | <Type>P R</Type> |
||
1988 | <Comment>s. also BravoBrian ..</Comment> |
||
1989 | <Link1>http://bstop.bravobrian.it/</Link1> |
||
1990 | <Link2></Link2> |
||
1991 | </user-agent> |
||
1992 | <user-agent> |
||
1993 | <ID>id_a_f_139</ID> |
||
1994 | <String>BTbot/0.x (+http://www.btbot.com/btbot.html)</String> |
||
1995 | <Description>BitTorrent Search Engine btbot robot</Description> |
||
1996 | <Type>R</Type> |
||
1997 | <Comment></Comment> |
||
1998 | <Link1>http://www.btbot.com</Link1> |
||
1999 | <Link2></Link2> |
||
2000 | </user-agent> |
||
2001 | <user-agent> |
||
2002 | <ID>id_a_f_300408_2</ID> |
||
2003 | <String>BTWebClient/180B(9704)</String> |
||
2004 | <Description>µTorrent BitTorrent Client</Description> |
||
2005 | <Type>D</Type> |
||
2006 | <Comment></Comment> |
||
2007 | <Link1>http://www.utorrent.com/</Link1> |
||
2008 | <Link2></Link2> |
||
2009 | </user-agent> |
||
2010 | <user-agent> |
||
2011 | <ID>id_a_f_080407_2</ID> |
||
2012 | <String>BuildCMS crawler (http://www.buildcms.com/crawler)</String> |
||
2013 | <Description>BuildCMS crawler - market monitoring project of BuildCMS</Description> |
||
2014 | <Type>R</Type> |
||
2015 | <Comment>194.24.253.xx</Comment> |
||
2016 | <Link1>http://www.buildcms.com/index.php</Link1> |
||
2017 | <Link2>http://www.buildcms.com/about_us/crawler</Link2> |
||
2018 | </user-agent> |
||
2019 | <user-agent> |
||
2020 | <ID>id_a_f_051206_4</ID> |
||
2021 | <String>Bulkfeeds/r1752 (http://bulkfeeds.net/)</String> |
||
2022 | <Description>Bulkfeeds: RSS directory link checking</Description> |
||
2023 | <Type>C</Type> |
||
2024 | <Comment>202.181.96.2xx</Comment> |
||
2025 | <Link1>http://bulkfeeds.net/</Link1> |
||
2026 | <Link2></Link2> |
||
2027 | </user-agent> |
||
2028 | <user-agent> |
||
2029 | <ID>id_a_f_140</ID> |
||
2030 | <String>BullsEye</String> |
||
2031 | <Description>BullsEye/Intelliseek robot</Description> |
||
2032 | <Type>R</Type> |
||
2033 | <Comment></Comment> |
||
2034 | <Link1>http://www.intelliseek.com/be/bullseye.htm</Link1> |
||
2035 | <Link2></Link2> |
||
2036 | </user-agent> |
||
2037 | <user-agent> |
||
2038 | <ID>id_a_f_141</ID> |
||
2039 | <String>bumblebee@relevare.com</String> |
||
2040 | <Description>Relevare Portal software robot</Description> |
||
2041 | <Type>R</Type> |
||
2042 | <Comment></Comment> |
||
2043 | <Link1>http://www.relevare.com</Link1> |
||
2044 | <Link2></Link2> |
||
2045 | </user-agent> |
||
2046 | <user-agent> |
||
2047 | <ID>id_a_f_142</ID> |
||
2048 | <String>BunnySlippers</String> |
||
2049 | <Description>Microsoft server information robot (see link)</Description> |
||
2050 | <Type>C</Type> |
||
2051 | <Comment></Comment> |
||
2052 | <Link1>http://www.webmasterworld.com/forum11/841.htm</Link1> |
||
2053 | <Link2></Link2> |
||
2054 | </user-agent> |
||
2055 | <user-agent> |
||
2056 | <ID>id_a_f_070606_1</ID> |
||
2057 | <String>BurstFindCrawler/1.1 (crawler.burstfind.com; http://crawler.burstfind.com; crawler@burstfind.com)</String> |
||
2058 | <Description>BurstFind search crawler (64.34.172.xx)</Description> |
||
2059 | <Type>R</Type> |
||
2060 | <Comment></Comment> |
||
2061 | <Link1>http://www.burstfind.com/</Link1> |
||
2062 | <Link2></Link2> |
||
2063 | </user-agent> |
||
2064 | <user-agent> |
||
2065 | <ID>id_a_f_143</ID> |
||
2066 | <String>Buscaplus Robi/1.0 (http://www.buscaplus.com/robi/)</String> |
||
2067 | <Description>Buscaplus (Spain) robot</Description> |
||
2068 | <Type>R</Type> |
||
2069 | <Comment></Comment> |
||
2070 | <Link1>http://www.buscaplus.com</Link1> |
||
2071 | <Link2></Link2> |
||
2072 | </user-agent> |
||
2073 | <user-agent> |
||
2074 | <ID>id_a_f_050807_2</ID> |
||
2075 | <String>BW-C-2.0</String> |
||
2076 | <Description>Logitech Desktop Managers (LDM) Backweb (BW) update check</Description> |
||
2077 | <Type>D</Type> |
||
2078 | <Comment></Comment> |
||
2079 | <Link1>http://www.logitech.com/index.cfm/494/3041&cl=de,de</Link1> |
||
2080 | <Link2></Link2> |
||
2081 | </user-agent> |
||
2082 | <user-agent> |
||
2083 | <ID>id_a_f_140508_2</ID> |
||
2084 | <String>bwh3_user_agent</String> |
||
2085 | <Description>Basic Web Hacking 3 fake user-agent from Hellbound Hackers challenges</Description> |
||
2086 | <Type>S</Type> |
||
2087 | <Comment></Comment> |
||
2088 | <Link1>http://www.hellboundhackers.org/forum/_basic_web_hacking_3-7-6960_0.html</Link1> |
||
2089 | <Link2>http://vuau.wordpress.com/2008/03/12/hbh-basic-web-3-switch-user-agent/</Link2> |
||
2090 | </user-agent> |
||
2091 | <user-agent> |
||
2092 | <ID>id_a_f_140508_3</ID> |
||
2093 | <String>Cabot/Nutch-0.9 (Amfibi's web-crawling robot; http://www.amfibi.com/cabot/; agent@amfibi.com)</String> |
||
2094 | <Description>Amfibi Search robot</Description> |
||
2095 | <Type>R</Type> |
||
2096 | <Comment>64.111.217.9x</Comment> |
||
2097 | <Link1>http://www.amfibi.com/</Link1> |
||
2098 | <Link2></Link2> |
||
2099 | </user-agent> |
||
2100 | <user-agent> |
||
2101 | <ID>id_a_f_280508_1</ID> |
||
2102 | <String>Cabot/Nutch-1.0-dev (Amfibi's web-crawling robot; http://www.amfibi.com/cabot/; agent@amfibi.com)</String> |
||
2103 | <Description>Amfibi Search robot</Description> |
||
2104 | <Type>R</Type> |
||
2105 | <Comment>64.111.217.9x</Comment> |
||
2106 | <Link1>http://www.amfibi.com/</Link1> |
||
2107 | <Link2></Link2> |
||
2108 | </user-agent> |
||
2109 | <user-agent> |
||
2110 | <ID>id_a_f_140506_4</ID> |
||
2111 | <String>CamelHttpStream/1.0</String> |
||
2112 | <Description>Evolution integrated mail solution Camel TCP stream class</Description> |
||
2113 | <Type></Type> |
||
2114 | <Comment></Comment> |
||
2115 | <Link1>http://www.gnome.org/projects/evolution/</Link1> |
||
2116 | <Link2>http://go-evolution.org/Camel.Stream</Link2> |
||
2117 | </user-agent> |
||
2118 | <user-agent> |
||
2119 | <ID>id_a_f_144</ID> |
||
2120 | <String>Cancer Information and Support International;</String> |
||
2121 | <Description>Some user agent</Description> |
||
2122 | <Type></Type> |
||
2123 | <Comment></Comment> |
||
2124 | <Link1></Link1> |
||
2125 | <Link2></Link2> |
||
2126 | </user-agent> |
||
2127 | <user-agent> |
||
2128 | <ID>id_a_f_110206_1</ID> |
||
2129 | <String>carleson/1.0</String> |
||
2130 | <Description>Cosmix project crawler (204.14.48.x / 38.113.234.xxx)</Description> |
||
2131 | <Type>R</Type> |
||
2132 | <Comment>s. also - voyager/1.x - cfetch/1.</Comment> |
||
2133 | <Link1>http://www.cosmixcorp.com/</Link1> |
||
2134 | <Link2></Link2> |
||
2135 | </user-agent> |
||
2136 | <user-agent> |
||
2137 | <ID>id_a_f_145</ID> |
||
2138 | <String>Carnegie_Mellon_University_Research_WebBOT-->PLEASE READ-->http://www.andrew.cmu.edu/~brgordon/webbot/index.html http://www.andrew.cmu.edu/~brgordon/webbot/index.html</String> |
||
2139 | <Description>Carnegie Mellon University WebBOT</Description> |
||
2140 | <Type>R</Type> |
||
2141 | <Comment></Comment> |
||
2142 | <Link1>http://www.andrew.cmu.edu</Link1> |
||
2143 | <Link2></Link2> |
||
2144 | </user-agent> |
||
2145 | <user-agent> |
||
2146 | <ID>id_a_f_146</ID> |
||
2147 | <String>Carnegie_Mellon_University_WebCrawler http://www.andrew.cmu.edu/~brgordon/webbot/index.html</String> |
||
2148 | <Description>Carnegie Mellon University WebBOT</Description> |
||
2149 | <Type>R</Type> |
||
2150 | <Comment></Comment> |
||
2151 | <Link1>http://www.andrew.cmu.edu</Link1> |
||
2152 | <Link2></Link2> |
||
2153 | </user-agent> |
||
2154 | <user-agent> |
||
2155 | <ID>id_a_f_170206_1</ID> |
||
2156 | <String>Catall Spider</String> |
||
2157 | <Description>Catall.de search & web directory (Germany)</Description> |
||
2158 | <Type>R</Type> |
||
2159 | <Comment></Comment> |
||
2160 | <Link1>http://www.catall.de/</Link1> |
||
2161 | <Link2></Link2> |
||
2162 | </user-agent> |
||
2163 | <user-agent> |
||
2164 | <ID>id_a_f_130807_3</ID> |
||
2165 | <String>CazoodleBot/CazoodleBot-0.1 (CazoodleBot Crawler; http://www.cazoodle.com/cazoodlebot; cazoodlebot@cazoodle.com)</String> |
||
2166 | <Description>UIUCs Cazoodle search based on MetaQuerier</Description> |
||
2167 | <Type>R</Type> |
||
2168 | <Comment>72.36.94.1xx</Comment> |
||
2169 | <Link1>http://www.cazoodle.com/</Link1> |
||
2170 | <Link2>http://metaquerier.cs.uiuc.edu/</Link2> |
||
2171 | </user-agent> |
||
2172 | <user-agent> |
||
2173 | <ID>id_a_f_290308_1</ID> |
||
2174 | <String>CCBot/1.0 (+http://www.commoncrawl.org/bot.html)</String> |
||
2175 | <Description>CommonCrawl Foundation search crawler</Description> |
||
2176 | <Type>R</Type> |
||
2177 | <Comment>38.103.63.1[6-8]</Comment> |
||
2178 | <Link1>http://www.commoncrawl.org/faq.htm</Link1> |
||
2179 | <Link2></Link2> |
||
2180 | </user-agent> |
||
2181 | <user-agent> |
||
2182 | <ID>id_a_f_147</ID> |
||
2183 | <String>ccubee/x.x</String> |
||
2184 | <Description>Empyreum Ccubee (Czech) search engine solution</Description> |
||
2185 | <Type>R</Type> |
||
2186 | <Comment></Comment> |
||
2187 | <Link1>http://empyreum.com/technologies/ccubee</Link1> |
||
2188 | <Link2></Link2> |
||
2189 | </user-agent> |
||
2190 | <user-agent> |
||
2191 | <ID>id_a_f_010108_2</ID> |
||
2192 | <String>CDR/1.7.1 Simulator/0.7(+http://timewe.net) Profile/MIDP-1.0 Configuration/CLDC-1.0</String> |
||
2193 | <Description>Timewe mobile browser (WAP) simulator (Japan)</Description> |
||
2194 | <Type>B</Type> |
||
2195 | <Comment>61.142.xx.x[xx]</Comment> |
||
2196 | <Link1>http://timewe.net/</Link1> |
||
2197 | <Link2></Link2> |
||
2198 | </user-agent> |
||
2199 | <user-agent> |
||
2200 | <ID>id_a_f_291105_6</ID> |
||
2201 | <String>CE-Preload</String> |
||
2202 | <Description>Cisco Content Engine</Description> |
||
2203 | <Type>P</Type> |
||
2204 | <Comment></Comment> |
||
2205 | <Link1>http://www.cisco.com/en/US/products/hw/contnetw/index.html</Link1> |
||
2206 | <Link2></Link2> |
||
2207 | </user-agent> |
||
2208 | <user-agent> |
||
2209 | <ID>id_a_f_100408_4</ID> |
||
2210 | <String>CentiverseBot</String> |
||
2211 | <Description>Nordic semantic search engine</Description> |
||
2212 | <Type>C</Type> |
||
2213 | <Comment>87.72.214.9x</Comment> |
||
2214 | <Link1>http://www.centiverse-project.net/post/Educating-the-bots.aspx</Link1> |
||
2215 | <Link2></Link2> |
||
2216 | </user-agent> |
||
2217 | <user-agent> |
||
2218 | <ID>id_a_f_180408_2</ID> |
||
2219 | <String>CentiverseBot - investigator</String> |
||
2220 | <Description>Nordic semantic search engine</Description> |
||
2221 | <Type>C</Type> |
||
2222 | <Comment>87.72.214.9x</Comment> |
||
2223 | <Link1>http://www.centiverse-project.net/post/Educating-the-bots.aspx</Link1> |
||
2224 | <Link2></Link2> |
||
2225 | </user-agent> |
||
2226 | <user-agent> |
||
2227 | <ID>id_a_f_180408_3</ID> |
||
2228 | <String>CentiverseBot/3.0 (http://www.centiverse-project.net)</String> |
||
2229 | <Description>Nordic semantic search engine</Description> |
||
2230 | <Type>C</Type> |
||
2231 | <Comment>87.72.214.9x</Comment> |
||
2232 | <Link1>http://www.centiverse-project.net/post/Educating-the-bots.aspx</Link1> |
||
2233 | <Link2></Link2> |
||
2234 | </user-agent> |
||
2235 | <user-agent> |
||
2236 | <ID>id_a_f_148</ID> |
||
2237 | <String>Ceramic Tile Installation Guide (http://www.floorstransformed.com)</String> |
||
2238 | <Description>Floortransformed.com robot (link ckecking ??)</Description> |
||
2239 | <Type>R</Type> |
||
2240 | <Comment></Comment> |
||
2241 | <Link1>http://www.floorstransformed.com</Link1> |
||
2242 | <Link2></Link2> |
||
2243 | </user-agent> |
||
2244 | <user-agent> |
||
2245 | <ID>id_a_f_131208_2</ID> |
||
2246 | <String>CERN-LineMode/2.15</String> |
||
2247 | <Description>CERN Line Mode Browser</Description> |
||
2248 | <Type>B</Type> |
||
2249 | <Comment></Comment> |
||
2250 | <Link1>http://www.w3.org/LineMode/</Link1> |
||
2251 | <Link2></Link2> |
||
2252 | </user-agent> |
||
2253 | <user-agent> |
||
2254 | <ID>id_a_f_149</ID> |
||
2255 | <String>cfetch/1.0</String> |
||
2256 | <Description>Cosmix project crawler (204.14.48.x / 38.113.234.xxx)</Description> |
||
2257 | <Type>R</Type> |
||
2258 | <Comment>s. also - voyager/1.x - carleson/1.x</Comment> |
||
2259 | <Link1>http://www.cosmixcorp.com</Link1> |
||
2260 | <Link2></Link2> |
||
2261 | </user-agent> |
||
2262 | <user-agent> |
||
2263 | <ID>id_a_f_150</ID> |
||
2264 | <String>CFNetwork/x.x</String> |
||
2265 | <Description>MaxOS X CoreFoundation CFNetwork API</Description> |
||
2266 | <Type></Type> |
||
2267 | <Comment></Comment> |
||
2268 | <Link1>http://www.cocoadev.com/index.pl?CFNetwork</Link1> |
||
2269 | <Link2></Link2> |
||
2270 | </user-agent> |
||
2271 | <user-agent> |
||
2272 | <ID>id_a_f_151</ID> |
||
2273 | <String>cg-eye interactive</String> |
||
2274 | <Description>cg-eye CGI checker</Description> |
||
2275 | <Type>C</Type> |
||
2276 | <Comment></Comment> |
||
2277 | <Link1>http://www.htmlhelp.com</Link1> |
||
2278 | <Link2></Link2> |
||
2279 | </user-agent> |
||
2280 | <user-agent> |
||
2281 | <ID>id_a_f_152</ID> |
||
2282 | <String>Charon/1.x (Amiga)</String> |
||
2283 | <Description>Charon Amiga download manager</Description> |
||
2284 | <Type>D</Type> |
||
2285 | <Comment></Comment> |
||
2286 | <Link1>http://tesla.rcub.bg.ac.yu/%7Eantony/Charon/</Link1> |
||
2287 | <Link2></Link2> |
||
2288 | </user-agent> |
||
2289 | <user-agent> |
||
2290 | <ID>id_a_f_131208_3</ID> |
||
2291 | <String>Chat Catcher/1.0</String> |
||
2292 | <Description>Chat Catcher blog monitoring robot</Description> |
||
2293 | <Type>C</Type> |
||
2294 | <Comment>69.80.208.2xx</Comment> |
||
2295 | <Link1>http://chatcatcher.com/cc/</Link1> |
||
2296 | <Link2></Link2> |
||
2297 | </user-agent> |
||
2298 | <user-agent> |
||
2299 | <ID>id_a_f_153</ID> |
||
2300 | <String>Checkbot/1.xx LWP/5.xx</String> |
||
2301 | <Description>Checkbot link validation</Description> |
||
2302 | <Type>C</Type> |
||
2303 | <Comment></Comment> |
||
2304 | <Link1>http://degraaff.org/checkbot/</Link1> |
||
2305 | <Link2></Link2> |
||
2306 | </user-agent> |
||
2307 | <user-agent> |
||
2308 | <ID>id_a_f_154</ID> |
||
2309 | <String>CheckLinks/1.x.x</String> |
||
2310 | <Description>Checklinks - Perl link checker</Description> |
||
2311 | <Type>C</Type> |
||
2312 | <Comment></Comment> |
||
2313 | <Link1>http://www.jmarshall.com</Link1> |
||
2314 | <Link2></Link2> |
||
2315 | </user-agent> |
||
2316 | <user-agent> |
||
2317 | <ID>id_a_f_155</ID> |
||
2318 | <String>CheckUrl</String> |
||
2319 | <Description>NTL user agent</Description> |
||
2320 | <Type></Type> |
||
2321 | <Comment></Comment> |
||
2322 | <Link1>http://www.ntl.com</Link1> |
||
2323 | <Link2></Link2> |
||
2324 | </user-agent> |
||
2325 | <user-agent> |
||
2326 | <ID>id_a_f_156</ID> |
||
2327 | <String>CheckWeb</String> |
||
2328 | <Description>CheckWeb link validation</Description> |
||
2329 | <Type>C</Type> |
||
2330 | <Comment></Comment> |
||
2331 | <Link1>http://p.duby.free.fr/chkweb.htm</Link1> |
||
2332 | <Link2></Link2> |
||
2333 | </user-agent> |
||
2334 | <user-agent> |
||
2335 | <ID>id_a_f_030206_2</ID> |
||
2336 | <String>Chilkat/1.0.0 (+http://www.chilkatsoft.com/ChilkatHttpUA.asp)</String> |
||
2337 | <Description>Chilkat HTTP component user-agent</Description> |
||
2338 | <Type></Type> |
||
2339 | <Comment></Comment> |
||
2340 | <Link1>http://www.chilkatsoft.com/HttpDotNet.asp</Link1> |
||
2341 | <Link2></Link2> |
||
2342 | </user-agent> |
||
2343 | <user-agent> |
||
2344 | <ID>id_a_f_230506_1</ID> |
||
2345 | <String>China Local Browse 2.6</String> |
||
2346 | <Description>Unknown spam bot from telekom.com.my (218.111.83.xxx)</Description> |
||
2347 | <Type>S</Type> |
||
2348 | <Comment>see link:</Comment> |
||
2349 | <Link1>http://linuxreviews.org/webdesign/602_Apache_Webalizer/</Link1> |
||
2350 | <Link2></Link2> |
||
2351 | </user-agent> |
||
2352 | <user-agent> |
||
2353 | <ID>id_a_f_170408_2</ID> |
||
2354 | <String>Chitika ContentHit 1.0</String> |
||
2355 | <Description>Chitika Inc. Blog advertising</Description> |
||
2356 | <Type>C</Type> |
||
2357 | <Comment>67.15.219.[x]x</Comment> |
||
2358 | <Link1>http://chitika.com/</Link1> |
||
2359 | <Link2></Link2> |
||
2360 | </user-agent> |
||
2361 | <user-agent> |
||
2362 | <ID>id_a_f_157</ID> |
||
2363 | <String>ChristCRAWLER 2.0</String> |
||
2364 | <Description>Christcentral.com Christcrawler (was www.christcrawler.com)</Description> |
||
2365 | <Type>R</Type> |
||
2366 | <Comment>- s. also Mozilla/4.0 (compatible; ChristCrawler..)</Comment> |
||
2367 | <Link1></Link1> |
||
2368 | <Link2></Link2> |
||
2369 | </user-agent> |
||
2370 | <user-agent> |
||
2371 | <ID>id_a_f_010607_2</ID> |
||
2372 | <String>CHttpClient by Open Text Corporation</String> |
||
2373 | <Description>CHttpClient - C++ class using WinInet</Description> |
||
2374 | <Type></Type> |
||
2375 | <Comment></Comment> |
||
2376 | <Link1>http://www.codeproject.com/library/lyoulhttpclient.asp</Link1> |
||
2377 | <Link2></Link2> |
||
2378 | </user-agent> |
||
2379 | <user-agent> |
||
2380 | <ID>id_a_f_158</ID> |
||
2381 | <String>CipinetBot (http://www.cipinet.com/bot.html)</String> |
||
2382 | <Description>CipinetBot -Cipinet Search Engine Web Crawler</Description> |
||
2383 | <Type>R</Type> |
||
2384 | <Comment></Comment> |
||
2385 | <Link1>http://www.cipinet.com</Link1> |
||
2386 | <Link2></Link2> |
||
2387 | </user-agent> |
||
2388 | <user-agent> |
||
2389 | <ID>id_a_f_130108_1</ID> |
||
2390 | <String>Cityreview Robot (+http://www.cityreview.org/crawler/)</String> |
||
2391 | <Description>Cityreview regional search (Germany) link checking</Description> |
||
2392 | <Type>C</Type> |
||
2393 | <Comment>88.198.212.5x</Comment> |
||
2394 | <Link1>http://www.cityreview.de/</Link1> |
||
2395 | <Link2>http://www.cityreview.org/crawler/</Link2> |
||
2396 | </user-agent> |
||
2397 | <user-agent> |
||
2398 | <ID>id_a_f_159</ID> |
||
2399 | <String>CJ Spider/</String> |
||
2400 | <Description>Commision Junction link checking spider</Description> |
||
2401 | <Type>C</Type> |
||
2402 | <Comment></Comment> |
||
2403 | <Link1>http://www.cj.com/</Link1> |
||
2404 | <Link2></Link2> |
||
2405 | </user-agent> |
||
2406 | <user-agent> |
||
2407 | <ID>id_a_f_050606_1</ID> |
||
2408 | <String>CJB.NET Proxy</String> |
||
2409 | <Description>CJB Net anonymous socks proxy service (216.194.70.x)</Description> |
||
2410 | <Type>P</Type> |
||
2411 | <Comment></Comment> |
||
2412 | <Link1>http://proxy.cjb.net/</Link1> |
||
2413 | <Link2></Link2> |
||
2414 | </user-agent> |
||
2415 | <user-agent> |
||
2416 | <ID>id_a_f_160</ID> |
||
2417 | <String>ClariaBot/1.0</String> |
||
2418 | <Description>Claria (ex Gator) SearchScout robot (64.152.73.xx)</Description> |
||
2419 | <Type>R</Type> |
||
2420 | <Comment>s. also Diamond</Comment> |
||
2421 | <Link1>http://www.searchscout.com</Link1> |
||
2422 | <Link2></Link2> |
||
2423 | </user-agent> |
||
2424 | <user-agent> |
||
2425 | <ID>id_a_f_161</ID> |
||
2426 | <String>Claymont.com</String> |
||
2427 | <Description>Claymont Search robot</Description> |
||
2428 | <Type>R</Type> |
||
2429 | <Comment></Comment> |
||
2430 | <Link1>http://www.claymont.com</Link1> |
||
2431 | <Link2></Link2> |
||
2432 | </user-agent> |
||
2433 | <user-agent> |
||
2434 | <ID>id_a_f_100307_1</ID> |
||
2435 | <String>CloakDetect/0.9 (+http://fulltext.seznam.cz/)</String> |
||
2436 | <Description>Seznam Search (Czech Republic) robot</Description> |
||
2437 | <Type>R</Type> |
||
2438 | <Comment>212.80.76.xx</Comment> |
||
2439 | <Link1>http://www.seznam.cz/</Link1> |
||
2440 | <Link2></Link2> |
||
2441 | </user-agent> |
||
2442 | <user-agent> |
||
2443 | <ID>id_a_f_162</ID> |
||
2444 | <String>Clushbot/2.x (+http://www.clush.com/bot.html)</String> |
||
2445 | <Description>Clush clustered search robot</Description> |
||
2446 | <Type>R</Type> |
||
2447 | <Comment></Comment> |
||
2448 | <Link1>http://www.clush.com</Link1> |
||
2449 | <Link2></Link2> |
||
2450 | </user-agent> |
||
2451 | <user-agent> |
||
2452 | <ID>id_a_f_163</ID> |
||
2453 | <String>Clushbot/3.x-BinaryFury (+http://www.clush.com/bot.html)</String> |
||
2454 | <Description>Clush clustered search robot</Description> |
||
2455 | <Type>R</Type> |
||
2456 | <Comment></Comment> |
||
2457 | <Link1>http://www.clush.com</Link1> |
||
2458 | <Link2></Link2> |
||
2459 | </user-agent> |
||
2460 | <user-agent> |
||
2461 | <ID>id_a_f_164</ID> |
||
2462 | <String>Clushbot/3.xx-Ajax (+http://www.clush.com/bot.html)</String> |
||
2463 | <Description>Clush clustered search robot</Description> |
||
2464 | <Type>R</Type> |
||
2465 | <Comment></Comment> |
||
2466 | <Link1>http://www.clush.com</Link1> |
||
2467 | <Link2></Link2> |
||
2468 | </user-agent> |
||
2469 | <user-agent> |
||
2470 | <ID>id_a_f_165</ID> |
||
2471 | <String>Clushbot/3.xx-Hector (+http://www.clush.com/bot.html)</String> |
||
2472 | <Description>Clush clustered search robot</Description> |
||
2473 | <Type>R</Type> |
||
2474 | <Comment></Comment> |
||
2475 | <Link1>http://www.clush.com</Link1> |
||
2476 | <Link2></Link2> |
||
2477 | </user-agent> |
||
2478 | <user-agent> |
||
2479 | <ID>id_a_f_166</ID> |
||
2480 | <String>Clushbot/3.xx-Peleus (+http://www.clush.com/bot.html)</String> |
||
2481 | <Description>Clush clustered search robot</Description> |
||
2482 | <Type>R</Type> |
||
2483 | <Comment></Comment> |
||
2484 | <Link1>http://www.clush.com</Link1> |
||
2485 | <Link2></Link2> |
||
2486 | </user-agent> |
||
2487 | <user-agent> |
||
2488 | <ID>id_a_f_070506_1</ID> |
||
2489 | <String>COAST WebMaster Pro/4.x.x.xx (Windows NT)</String> |
||
2490 | <Description>COAST Webmaster - Web management and maintenance software</Description> |
||
2491 | <Type>C</Type> |
||
2492 | <Comment></Comment> |
||
2493 | <Link1>http://www.extablish.com/cwm.htm</Link1> |
||
2494 | <Link2></Link2> |
||
2495 | </user-agent> |
||
2496 | <user-agent> |
||
2497 | <ID>id_a_f_150306_1</ID> |
||
2498 | <String>CoBITSProbe</String> |
||
2499 | <Description>Proposed Content-Based Image Tracking System (CoBITS) P2P crawler</Description> |
||
2500 | <Type>R C</Type> |
||
2501 | <Comment></Comment> |
||
2502 | <Link1>http://www.iis.sinica.edu.tw/~hungchi/CBIT/</Link1> |
||
2503 | <Link2></Link2> |
||
2504 | </user-agent> |
||
2505 | <user-agent> |
||
2506 | <ID>id_a_f_167</ID> |
||
2507 | <String>Cocoal.icio.us/1.0 (v36) (Mac OS X; http://www.scifihifi.com/cocoalicious)</String> |
||
2508 | <Description>Cocoa del.icio.us (social bookmarks manager) client for Mac OS X</Description> |
||
2509 | <Type>C</Type> |
||
2510 | <Comment></Comment> |
||
2511 | <Link1>http://www.scifihifi.com</Link1> |
||
2512 | <Link2></Link2> |
||
2513 | </user-agent> |
||
2514 | <user-agent> |
||
2515 | <ID>id_a_f_070209_2</ID> |
||
2516 | <String>Cogentbot/1.X (+http://www.cogentsoftwaresolutions.com/bot.html)</String> |
||
2517 | <Description>Cogent Search Bot from Cogent Software Solutions for unknown purposes</Description> |
||
2518 | <Type>R</Type> |
||
2519 | <Comment>72.81.252.9x</Comment> |
||
2520 | <Link1>http://www.cogentsoftwaresolutions.com/bot.html</Link1> |
||
2521 | <Link2></Link2> |
||
2522 | </user-agent> |
||
2523 | <user-agent> |
||
2524 | <ID>id_a_f_168</ID> |
||
2525 | <String>ColdFusion</String> |
||
2526 | <Description>Cold Fusion server used by various IPs i.e.: - NetWORLD web catalogue link checking</Description> |
||
2527 | <Type>P C</Type> |
||
2528 | <Comment></Comment> |
||
2529 | <Link1>http://www.networld.com</Link1> |
||
2530 | <Link2>http://www.macromedia.com/software/coldfusion/</Link2> |
||
2531 | </user-agent> |
||
2532 | <user-agent> |
||
2533 | <ID>id_a_f_169</ID> |
||
2534 | <String>ColdFusion (BookmarkTracker.com)</String> |
||
2535 | <Description>Cold Fusion server used by Bookmark Tracker - online favourites managment</Description> |
||
2536 | <Type>C</Type> |
||
2537 | <Comment></Comment> |
||
2538 | <Link1>http://www.bookmarktracker.com</Link1> |
||
2539 | <Link2>http://www.macromedia.com/software/coldfusion/</Link2> |
||
2540 | </user-agent> |
||
2541 | <user-agent> |
||
2542 | <ID>id_a_f_170</ID> |
||
2543 | <String>collage.cgi/1.xx</String> |
||
2544 | <Description>WebCollage Syndicator graphics crawler/collector</Description> |
||
2545 | <Type>R D</Type> |
||
2546 | <Comment></Comment> |
||
2547 | <Link1>http://www.webcollage.com</Link1> |
||
2548 | <Link2></Link2> |
||
2549 | </user-agent> |
||
2550 | <user-agent> |
||
2551 | <ID>id_a_f_171</ID> |
||
2552 | <String>combine/0.0</String> |
||
2553 | <Description>Combine harvesting & indexing robot</Description> |
||
2554 | <Type>R</Type> |
||
2555 | <Comment>130.235.4.xx</Comment> |
||
2556 | <Link1>http://combine.it.lth.se/</Link1> |
||
2557 | <Link2></Link2> |
||
2558 | </user-agent> |
||
2559 | <user-agent> |
||
2560 | <ID>id_a_f_080406_1</ID> |
||
2561 | <String>Combine/2.0 http://combine.it.lth.se/</String> |
||
2562 | <Description>Combine harvesting & indexing robot</Description> |
||
2563 | <Type>R</Type> |
||
2564 | <Comment>130.235.4.xx</Comment> |
||
2565 | <Link1>http://combine.it.lth.se/</Link1> |
||
2566 | <Link2></Link2> |
||
2567 | </user-agent> |
||
2568 | <user-agent> |
||
2569 | <ID>id_a_f_160807_1</ID> |
||
2570 | <String>Combine/3 http://combine.it.lth.se/</String> |
||
2571 | <Description>Combine harvesting & indexing robot</Description> |
||
2572 | <Type>R</Type> |
||
2573 | <Comment>130.235.4.xx</Comment> |
||
2574 | <Link1>http://combine.it.lth.se/</Link1> |
||
2575 | <Link2></Link2> |
||
2576 | </user-agent> |
||
2577 | <user-agent> |
||
2578 | <ID>id_a_f_172</ID> |
||
2579 | <String>Combine/x.0</String> |
||
2580 | <Description>Combine harvesting & indexing robot</Description> |
||
2581 | <Type>R</Type> |
||
2582 | <Comment>130.235.4.xx</Comment> |
||
2583 | <Link1>http://combine.it.lth.se/</Link1> |
||
2584 | <Link2></Link2> |
||
2585 | </user-agent> |
||
2586 | <user-agent> |
||
2587 | <ID>id_a_f_280606_3</ID> |
||
2588 | <String>cometrics-bot, http://www.cometrics.de</String> |
||
2589 | <Description>cometrics Web Content Mining solution - Germany</Description> |
||
2590 | <Type>R</Type> |
||
2591 | <Comment></Comment> |
||
2592 | <Link1>http://www.cometrics.de/</Link1> |
||
2593 | <Link2></Link2> |
||
2594 | </user-agent> |
||
2595 | <user-agent> |
||
2596 | <ID>id_a_f_173</ID> |
||
2597 | <String>Commerce Browser Center</String> |
||
2598 | <Description>Wildsoft Germany (closed) Internet client system user-agent (was www.oskarweb.de)</Description> |
||
2599 | <Type>B</Type> |
||
2600 | <Comment></Comment> |
||
2601 | <Link1></Link1> |
||
2602 | <Link2></Link2> |
||
2603 | </user-agent> |
||
2604 | <user-agent> |
||
2605 | <ID>id_a_f_240107_1</ID> |
||
2606 | <String>complex_network_group/Nutch-0.9-dev (discovering the structure of the world-wide-web; http://cantor.ee.ucla.edu/~networks/crawl; nimakhaj@gmail.com)</String> |
||
2607 | <Description>UCLA Complex Networks Groups Complex Network Analysis</Description> |
||
2608 | <Type>C</Type> |
||
2609 | <Comment>216.182.233.1xx</Comment> |
||
2610 | <Link1>http://cantor.ee.ucla.edu/~networks/</Link1> |
||
2611 | <Link2></Link2> |
||
2612 | </user-agent> |
||
2613 | <user-agent> |
||
2614 | <ID>id_a_f_174</ID> |
||
2615 | <String>Computer_and_Automation_Research_Institute_Crawler crawler@ilab.sztaki.hu</String> |
||
2616 | <Description>Hungarian Academy of Sciences data mining search</Description> |
||
2617 | <Type>R</Type> |
||
2618 | <Comment></Comment> |
||
2619 | <Link1>http://www.ilab.sztaki.hu/websearch/</Link1> |
||
2620 | <Link2></Link2> |
||
2621 | </user-agent> |
||
2622 | <user-agent> |
||
2623 | <ID>id_a_f_010406_2</ID> |
||
2624 | <String>Comrite/0.7.1 (Nutch; http://lucene.apache.org/nutch/bot.html; nutch-agent@lucene.apache.org)</String> |
||
2625 | <Description>ComRite Chinese Search Engine for Oversea Web Sites (69.248.26.xx)</Description> |
||
2626 | <Type>R</Type> |
||
2627 | <Comment>powered by Nutch</Comment> |
||
2628 | <Link1>http://www.comrite.com/</Link1> |
||
2629 | <Link2>http://meidong.comrite.com/</Link2> |
||
2630 | </user-agent> |
||
2631 | <user-agent> |
||
2632 | <ID>id_a_f_175</ID> |
||
2633 | <String>Contact</String> |
||
2634 | <Description>unknown</Description> |
||
2635 | <Type></Type> |
||
2636 | <Comment></Comment> |
||
2637 | <Link1></Link1> |
||
2638 | <Link2></Link2> |
||
2639 | </user-agent> |
||
2640 | <user-agent> |
||
2641 | <ID>id_a_f_200307_1</ID> |
||
2642 | <String>ContactBot/0.2</String> |
||
2643 | <Description>Probably E-Mail harvesting robot - same as LMQueueBot</Description> |
||
2644 | <Type>S</Type> |
||
2645 | <Comment>64.124.152.xx</Comment> |
||
2646 | <Link1></Link1> |
||
2647 | <Link2></Link2> |
||
2648 | </user-agent> |
||
2649 | <user-agent> |
||
2650 | <ID>id_a_f_291105_7</ID> |
||
2651 | <String>ContentSmartz</String> |
||
2652 | <Description>ContentSmartz e-mail harvesting tools</Description> |
||
2653 | <Type>S</Type> |
||
2654 | <Comment></Comment> |
||
2655 | <Link1></Link1> |
||
2656 | <Link2></Link2> |
||
2657 | </user-agent> |
||
2658 | <user-agent> |
||
2659 | <ID>id_a_f_176</ID> |
||
2660 | <String>contype</String> |
||
2661 | <Description>Internet Explorer versions 4.x and 5 plugin content</Description> |
||
2662 | <Type>B</Type> |
||
2663 | <Comment>NOT Contype mime type managment Perl script</Comment> |
||
2664 | <Link1>http://support.microsoft.com/default.aspx?scid=kb;en-us;293792</Link1> |
||
2665 | <Link2></Link2> |
||
2666 | </user-agent> |
||
2667 | <user-agent> |
||
2668 | <ID>id_a_f_177</ID> |
||
2669 | <String>Convera Internet Spider V6.x</String> |
||
2670 | <Description>Converas RetrievalWare Internet Spider (63.241.61.x)</Description> |
||
2671 | <Type>R</Type> |
||
2672 | <Comment> s. also - infoConveraCrawler... - CrawlConvera ...</Comment> |
||
2673 | <Link1>http://www.convera.com</Link1> |
||
2674 | <Link2></Link2> |
||
2675 | </user-agent> |
||
2676 | <user-agent> |
||
2677 | <ID>id_a_f_178</ID> |
||
2678 | <String>ConveraCrawler/0.2</String> |
||
2679 | <Description>Converas RetrievalWare Internet Spider (63.241.61.x)</Description> |
||
2680 | <Type>R</Type> |
||
2681 | <Comment> s. also - infoConveraCrawler... - CrawlConvera ...</Comment> |
||
2682 | <Link1>http://www.convera.com</Link1> |
||
2683 | <Link2></Link2> |
||
2684 | </user-agent> |
||
2685 | <user-agent> |
||
2686 | <ID>id_a_f_051205_1</ID> |
||
2687 | <String>ConveraCrawler/0.9d (+http://www.authoritativeweb.com/crawl)</String> |
||
2688 | <Description>Converas RetrievalWare Internet Spider (63.241.61.x)</Description> |
||
2689 | <Type>R</Type> |
||
2690 | <Comment> s. also - infoConveraCrawler... - CrawlConvera ...</Comment> |
||
2691 | <Link1>http://www.convera.com/</Link1> |
||
2692 | <Link2></Link2> |
||
2693 | </user-agent> |
||
2694 | <user-agent> |
||
2695 | <ID>id_a_f_179</ID> |
||
2696 | <String>ConveraMultiMediaCrawler/0.1 (+http://www.authoritativeweb.com/crawl)</String> |
||
2697 | <Description>Converas RetrievalWare Internet Spider (63.241.61.x)</Description> |
||
2698 | <Type>R</Type> |
||
2699 | <Comment> s. also - infoConveraCrawler... - CrawlConvera ...</Comment> |
||
2700 | <Link1>http://www.convera.com</Link1> |
||
2701 | <Link2></Link2> |
||
2702 | </user-agent> |
||
2703 | <user-agent> |
||
2704 | <ID>id_a_f_180</ID> |
||
2705 | <String>CoolBot</String> |
||
2706 | <Description>Suchmaschine21 (Germany) robot</Description> |
||
2707 | <Type>R</Type> |
||
2708 | <Comment></Comment> |
||
2709 | <Link1>http://www.suchmaschine21.de/</Link1> |
||
2710 | <Link2></Link2> |
||
2711 | </user-agent> |
||
2712 | <user-agent> |
||
2713 | <ID>id_a_f_030110_2</ID> |
||
2714 | <String>Cooliris/1.5 CFNetwork/459 Darwin/10.0.0d3</String> |
||
2715 | <Description>Cooliris photo and video browser</Description> |
||
2716 | <Type>B</Type> |
||
2717 | <Comment></Comment> |
||
2718 | <Link1>http://www.cooliris.com/</Link1> |
||
2719 | <Link2></Link2> |
||
2720 | </user-agent> |
||
2721 | <user-agent> |
||
2722 | <ID>id_a_f_040406_1</ID> |
||
2723 | <String>CoralWebPrx/0.1.1x (See http://coralcdn.org/)</String> |
||
2724 | <Description>Coral Content Distribution Network</Description> |
||
2725 | <Type>P C</Type> |
||
2726 | <Comment></Comment> |
||
2727 | <Link1>http://coralcdn.org/</Link1> |
||
2728 | <Link2></Link2> |
||
2729 | </user-agent> |
||
2730 | <user-agent> |
||
2731 | <ID>id_a_f_181</ID> |
||
2732 | <String>cosmos/0.8_(robot@xyleme.com)</String> |
||
2733 | <Description>Xyleme SA France robot</Description> |
||
2734 | <Type>R</Type> |
||
2735 | <Comment></Comment> |
||
2736 | <Link1>http://www.xyleme.com/en/index.jsp</Link1> |
||
2737 | <Link2></Link2> |
||
2738 | </user-agent> |
||
2739 | <user-agent> |
||
2740 | <ID>id_a_f_182</ID> |
||
2741 | <String>cosmos/0.9_(robot@xyleme.com)</String> |
||
2742 | <Description>Xyleme SA France robot</Description> |
||
2743 | <Type>R</Type> |
||
2744 | <Comment></Comment> |
||
2745 | <Link1>http://www.xyleme.com/en/index.jsp</Link1> |
||
2746 | <Link2></Link2> |
||
2747 | </user-agent> |
||
2748 | <user-agent> |
||
2749 | <ID>id_a_f_040607_1</ID> |
||
2750 | <String>CoteoNutchCrawler/Nutch-0.9 (info [at] coteo [dot] com)</String> |
||
2751 | <Description>Coteo.com - local French directory link checking</Description> |
||
2752 | <Type>C</Type> |
||
2753 | <Comment></Comment> |
||
2754 | <Link1>http://www.coteo.com/</Link1> |
||
2755 | <Link2></Link2> |
||
2756 | </user-agent> |
||
2757 | <user-agent> |
||
2758 | <ID>id_a_f_030206_3</ID> |
||
2759 | <String>CougarSearch/0.x (+http://www.cougarsearch.com/faq.shtml)</String> |
||
2760 | <Description>Cougarsearch.com robot</Description> |
||
2761 | <Type>R</Type> |
||
2762 | <Comment></Comment> |
||
2763 | <Link1>http://www.cougarsearch.com/</Link1> |
||
2764 | <Link2></Link2> |
||
2765 | </user-agent> |
||
2766 | <user-agent> |
||
2767 | <ID>id_a_f_280408_2</ID> |
||
2768 | <String>Covac TexAs Arachbot</String> |
||
2769 | <Description>Covac Arachnid Web Crawler</Description> |
||
2770 | <Type>R</Type> |
||
2771 | <Comment>s.also ArachBot</Comment> |
||
2772 | <Link1>http://www.covac-software.com/</Link1> |
||
2773 | <Link2></Link2> |
||
2774 | </user-agent> |
||
2775 | <user-agent> |
||
2776 | <ID>id_a_f_211208_1</ID> |
||
2777 | <String>CoverScout%203/3.0.1 CFNetwork/339.5 Darwin/9.5.0 (i386) (iMac5,1)</String> |
||
2778 | <Description>CoverScout for iTunes - CD cover search tool</Description> |
||
2779 | <Type>B</Type> |
||
2780 | <Comment></Comment> |
||
2781 | <Link1>http://www.equinux.com/de/products/coverscout/index.html</Link1> |
||
2782 | <Link2></Link2> |
||
2783 | </user-agent> |
||
2784 | <user-agent> |
||
2785 | <ID>id_a_f_183</ID> |
||
2786 | <String>Cowbot-0.1 (NHN Corp. / +82-2-3011-1954 / nhnbot@naver.com)</String> |
||
2787 | <Description>Naver Japan / Korea robot</Description> |
||
2788 | <Type>R</Type> |
||
2789 | <Comment> s. also Python-urllib/1.15 - nabot - NaverBot & dloader</Comment> |
||
2790 | <Link1>http://www.naver.co.jp</Link1> |
||
2791 | <Link2></Link2> |
||
2792 | </user-agent> |
||
2793 | <user-agent> |
||
2794 | <ID>id_a_f_184</ID> |
||
2795 | <String>Cowbot-0.1.x (NHN Corp. / +82-2-3011-1954 / nhnbot@naver.com)</String> |
||
2796 | <Description>Naver Japan / Korea robot</Description> |
||
2797 | <Type>R</Type> |
||
2798 | <Comment> s. also Python-urllib/1.15 - nabot - NaverBot & dloader</Comment> |
||
2799 | <Link1>http://www.naver.co.jp</Link1> |
||
2800 | <Link2></Link2> |
||
2801 | </user-agent> |
||
2802 | <user-agent> |
||
2803 | <ID>id_a_f_185</ID> |
||
2804 | <String>CrawlConvera0.1 (CrawlConvera@yahoo.com)</String> |
||
2805 | <Description>Converas RetrievalWare Internet Spider</Description> |
||
2806 | <Type>R</Type> |
||
2807 | <Comment>s. also - Convera Internet Spider .. - infoConveraCrawler...</Comment> |
||
2808 | <Link1>http://www.convera.com</Link1> |
||
2809 | <Link2></Link2> |
||
2810 | </user-agent> |
||
2811 | <user-agent> |
||
2812 | <ID>id_a_f_186</ID> |
||
2813 | <String>Crawler</String> |
||
2814 | <Description>unknown robot via Level3.net</Description> |
||
2815 | <Type></Type> |
||
2816 | <Comment></Comment> |
||
2817 | <Link1></Link1> |
||
2818 | <Link2></Link2> |
||
2819 | </user-agent> |
||
2820 | <user-agent> |
||
2821 | <ID>id_a_f_187</ID> |
||
2822 | <String>Crawler (cometsearch@cometsystems.com)</String> |
||
2823 | <Description>Cometsystems Comet Search robot via Findwhat (now Miva)</Description> |
||
2824 | <Type>R</Type> |
||
2825 | <Comment></Comment> |
||
2826 | <Link1>http://www.cometsystems.com</Link1> |
||
2827 | <Link2>http://www.miva.com/</Link2> |
||
2828 | </user-agent> |
||
2829 | <user-agent> |
||
2830 | <ID>id_a_f_188</ID> |
||
2831 | <String>Crawler admin@crawler.de</String> |
||
2832 | <Description>Crawler.de / Abacho robot</Description> |
||
2833 | <Type>R</Type> |
||
2834 | <Comment></Comment> |
||
2835 | <Link1>http://www.crawler.de</Link1> |
||
2836 | <Link2>http://www.abacho.de/</Link2> |
||
2837 | </user-agent> |
||
2838 | <user-agent> |
||
2839 | <ID>id_a_f_189</ID> |
||
2840 | <String>Crawler V 0.2.x admin@crawler.de</String> |
||
2841 | <Description>Crawler.de / Abacho robot</Description> |
||
2842 | <Type>R</Type> |
||
2843 | <Comment></Comment> |
||
2844 | <Link1>http://www.crawler.de</Link1> |
||
2845 | <Link2>http://www.abacho.de/</Link2> |
||
2846 | </user-agent> |
||
2847 | <user-agent> |
||
2848 | <ID>id_a_f_190</ID> |
||
2849 | <String>crawler@alexa.com</String> |
||
2850 | <Description>Alexa crawler</Description> |
||
2851 | <Type>R</Type> |
||
2852 | <Comment></Comment> |
||
2853 | <Link1>http://www.alexa.com</Link1> |
||
2854 | <Link2></Link2> |
||
2855 | </user-agent> |
||
2856 | <user-agent> |
||
2857 | <ID>id_a_f_191</ID> |
||
2858 | <String>CrawlerBoy Pinpoint.com</String> |
||
2859 | <Description>Pinpoint WAP search robot</Description> |
||
2860 | <Type>R</Type> |
||
2861 | <Comment></Comment> |
||
2862 | <Link1>http://www.pinpoint.com</Link1> |
||
2863 | <Link2></Link2> |
||
2864 | </user-agent> |
||
2865 | <user-agent> |
||
2866 | <ID>id_a_f_130506_1</ID> |
||
2867 | <String>Crawllybot/0.1 (Crawllybot; +http://www.crawlly.com; crawler@crawlly.com)</String> |
||
2868 | <Description>Crawlly Beta search - Germany (72.232.194.2xx)</Description> |
||
2869 | <Type>R</Type> |
||
2870 | <Comment>powered by Nutch</Comment> |
||
2871 | <Link1>http://www.crawlly.com/</Link1> |
||
2872 | <Link2></Link2> |
||
2873 | </user-agent> |
||
2874 | <user-agent> |
||
2875 | <ID>id_a_f_192</ID> |
||
2876 | <String>CreativeCommons/0.06-dev (Nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@lists.sourceforge.net)</String> |
||
2877 | <Description>Creatice Commons using Nutch open source robot</Description> |
||
2878 | <Type>R</Type> |
||
2879 | <Comment></Comment> |
||
2880 | <Link1>http://www.nutch.org</Link1> |
||
2881 | <Link2></Link2> |
||
2882 | </user-agent> |
||
2883 | <user-agent> |
||
2884 | <ID>id_a_f_030110_3</ID> |
||
2885 | <String>Cricket-A100/1.0 UP.Browser/6.3.0.7 (GUI) MMP/2.0</String> |
||
2886 | <Description>Cricket A100 cell phone browser</Description> |
||
2887 | <Type>B</Type> |
||
2888 | <Comment></Comment> |
||
2889 | <Link1>http://www.mycricket.com/cell-phones/details/Cricket-A100</Link1> |
||
2890 | <Link2></Link2> |
||
2891 | </user-agent> |
||
2892 | <user-agent> |
||
2893 | <ID>id_a_f_193</ID> |
||
2894 | <String>CrocCrawler vx.3 [en] (http://www.croccrawler.com) (X11; I; Linux 2.0.44 i686)</String> |
||
2895 | <Description>Croccrawler robot</Description> |
||
2896 | <Type>R</Type> |
||
2897 | <Comment></Comment> |
||
2898 | <Link1>http://www.croccrawler.com</Link1> |
||
2899 | <Link2></Link2> |
||
2900 | </user-agent> |
||
2901 | <user-agent> |
||
2902 | <ID>id_a_f_090306_2</ID> |
||
2903 | <String>csci_b659/0.13</String> |
||
2904 | <Description>Web mining project from CSCI 659 (computer science course) at Indiana Univerity</Description> |
||
2905 | <Type>R</Type> |
||
2906 | <Comment></Comment> |
||
2907 | <Link1>http://informatics.indiana.edu/fil/Class/b659/</Link1> |
||
2908 | <Link2></Link2> |
||
2909 | </user-agent> |
||
2910 | <user-agent> |
||
2911 | <ID>id_a_f_180906_1</ID> |
||
2912 | <String>CSE HTML Validator Professional (http://www.htmlvalidator.com/)</String> |
||
2913 | <Description>CSE HTML Validator for Windows</Description> |
||
2914 | <Type>C</Type> |
||
2915 | <Comment></Comment> |
||
2916 | <Link1>http://www.htmlvalidator.com/</Link1> |
||
2917 | <Link2></Link2> |
||
2918 | </user-agent> |
||
2919 | <user-agent> |
||
2920 | <ID>id_a_f_194</ID> |
||
2921 | <String>Cuam Ver0.050bx</String> |
||
2922 | <Description>Cuam - IE based browser</Description> |
||
2923 | <Type>B</Type> |
||
2924 | <Comment>site is dead</Comment> |
||
2925 | <Link1>http://cuam.virtualave.net</Link1> |
||
2926 | <Link2></Link2> |
||
2927 | </user-agent> |
||
2928 | <user-agent> |
||
2929 | <ID>id_a_f_195</ID> |
||
2930 | <String>Cuasarbot/0.9b http://www.cuasar.com/spider_beta/ </String> |
||
2931 | <Description>Cuasar (Spain) music / ringtone search spider</Description> |
||
2932 | <Type>R</Type> |
||
2933 | <Comment></Comment> |
||
2934 | <Link1>http://www.cuasar.com</Link1> |
||
2935 | <Link2></Link2> |
||
2936 | </user-agent> |
||
2937 | <user-agent> |
||
2938 | <ID>id_a_f_196</ID> |
||
2939 | <String>curl/7.10.x (i386-redhat-linux-gnu) libcurl/7.10.x OpenSSL/0.9.7a ipv6 zlib/1.1.4</String> |
||
2940 | <Description>Curl file transferring tool</Description> |
||
2941 | <Type>D</Type> |
||
2942 | <Comment></Comment> |
||
2943 | <Link1>http://curl.haxx.se/</Link1> |
||
2944 | <Link2></Link2> |
||
2945 | </user-agent> |
||
2946 | <user-agent> |
||
2947 | <ID>id_a_f_197</ID> |
||
2948 | <String>curl/7.7.x (i386--freebsd4.3) libcurl 7.7.x (SSL 0.9.6) (ipv6 enabled)</String> |
||
2949 | <Description>Curl file transferring tool</Description> |
||
2950 | <Type>D</Type> |
||
2951 | <Comment></Comment> |
||
2952 | <Link1>http://curl.haxx.se/</Link1> |
||
2953 | <Link2></Link2> |
||
2954 | </user-agent> |
||
2955 | <user-agent> |
||
2956 | <ID>id_a_f_198</ID> |
||
2957 | <String>curl/7.8 (i686-pc-linux-gnu) libcurl 7.8 (OpenSSL 0.9.6)</String> |
||
2958 | <Description>Curl file transferring tool</Description> |
||
2959 | <Type>D</Type> |
||
2960 | <Comment></Comment> |
||
2961 | <Link1>http://curl.haxx.se/</Link1> |
||
2962 | <Link2></Link2> |
||
2963 | </user-agent> |
||
2964 | <user-agent> |
||
2965 | <ID>id_a_f_199</ID> |
||
2966 | <String>curl/7.9.x (win32) libcurl 7.9.x</String> |
||
2967 | <Description>Curl file transferring tool</Description> |
||
2968 | <Type>D</Type> |
||
2969 | <Comment></Comment> |
||
2970 | <Link1>http://curl.haxx.se/</Link1> |
||
2971 | <Link2></Link2> |
||
2972 | </user-agent> |
||
2973 | <user-agent> |
||
2974 | <ID>id_a_f_200</ID> |
||
2975 | <String>CurryGuide SiteScan 1.1</String> |
||
2976 | <Description>CurryGuide UK link check robot</Description> |
||
2977 | <Type>R</Type> |
||
2978 | <Comment></Comment> |
||
2979 | <Link1>http://uk.curryguide.com/</Link1> |
||
2980 | <Link2></Link2> |
||
2981 | </user-agent> |
||
2982 | <user-agent> |
||
2983 | <ID>id_a_f_201</ID> |
||
2984 | <String>Custo x.x (www.netwu.com)</String> |
||
2985 | <Description>Custo web site spidering tool (link checking)</Description> |
||
2986 | <Type>C</Type> |
||
2987 | <Comment>s. also - - Mozilla/5.0 (compatible; Custo 3...</Comment> |
||
2988 | <Link1>http://www.netwu.com</Link1> |
||
2989 | <Link2></Link2> |
||
2990 | </user-agent> |
||
2991 | <user-agent> |
||
2992 | <ID>id_a_f_202</ID> |
||
2993 | <String>Custom Spider www.bisnisseek.com /1.0</String> |
||
2994 | <Description>Bisnisseek (was www.bisnisseek.com) robot</Description> |
||
2995 | <Type>R</Type> |
||
2996 | <Comment></Comment> |
||
2997 | <Link1></Link1> |
||
2998 | <Link2></Link2> |
||
2999 | </user-agent> |
||
3000 | <user-agent> |
||
3001 | <ID>id_a_f_203</ID> |
||
3002 | <String>Cyberdog/2.0 (Macintosh; 68k)</String> |
||
3003 | <Description>Cyberdog Mac Browser (was www.cyberdog.org)</Description> |
||
3004 | <Type>B</Type> |
||
3005 | <Comment></Comment> |
||
3006 | <Link1></Link1> |
||
3007 | <Link2></Link2> |
||
3008 | </user-agent> |
||
3009 | <user-agent> |
||
3010 | <ID>id_a_f_260608_2</ID> |
||
3011 | <String>CyberPatrol SiteCat Webbot (http://www.cyberpatrol.com/cyberpatrolcrawler.asp)</String> |
||
3012 | <Description>CyberPatrol LLC robot for web filtering software</Description> |
||
3013 | <Type>R</Type> |
||
3014 | <Comment>38.103.17.16x</Comment> |
||
3015 | <Link1>http://www.cyberpatrol.com/cyberpatrolcrawler.asp</Link1> |
||
3016 | <Link2></Link2> |
||
3017 | </user-agent> |
||
3018 | <user-agent> |
||
3019 | <ID>id_a_f_204</ID> |
||
3020 | <String>CyberSpyder Link Test/2.1.12 (admin@mspennyworth.com)</String> |
||
3021 | <Description>CyberSpyder Link Test software</Description> |
||
3022 | <Type>C</Type> |
||
3023 | <Comment></Comment> |
||
3024 | <Link1>http://www.cyberspyder.com/cslnkts1.html</Link1> |
||
3025 | <Link2></Link2> |
||
3026 | </user-agent> |
||
3027 | <user-agent> |
||
3028 | <ID>id_a_f_205</ID> |
||
3029 | <String>CydralSpider/1.x (Cydral Web Image Search; http://www.cydral.com)</String> |
||
3030 | <Description>Cydral image & site search spider</Description> |
||
3031 | <Type>R</Type> |
||
3032 | <Comment></Comment> |
||
3033 | <Link1>http://www.cydral.com</Link1> |
||
3034 | <Link2></Link2> |
||
3035 | </user-agent> |
||
3036 | <user-agent> |
||
3037 | <ID>id_a_f_060508_1</ID> |
||
3038 | <String>CydralSpider/3.0 (Cydral Image Search; http://www.cydral.com)</String> |
||
3039 | <Description>Cydral image & site search spider</Description> |
||
3040 | <Type>R</Type> |
||
3041 | <Comment></Comment> |
||
3042 | <Link1>http://www.cydral.com</Link1> |
||
3043 | <Link2></Link2> |
||
3044 | </user-agent> |
||
3045 | <user-agent> |
||
3046 | <ID>id_a_f_206</ID> |
||
3047 | <String>DA 3.5 (www.lidan.com)</String> |
||
3048 | <Description>Downloadaccelerator download manager</Description> |
||
3049 | <Type>D</Type> |
||
3050 | <Comment></Comment> |
||
3051 | <Link1>http://www.downloadaccelerator.com</Link1> |
||
3052 | <Link2></Link2> |
||
3053 | </user-agent> |
||
3054 | <user-agent> |
||
3055 | <ID>id_a_f_207</ID> |
||
3056 | <String>DA 4.0</String> |
||
3057 | <Description>Downloadaccelerator download manager</Description> |
||
3058 | <Type>D</Type> |
||
3059 | <Comment></Comment> |
||
3060 | <Link1>http://www.downloadaccelerator.com</Link1> |
||
3061 | <Link2></Link2> |
||
3062 | </user-agent> |
||
3063 | <user-agent> |
||
3064 | <ID>id_a_f_208</ID> |
||
3065 | <String>DA 4.0 (www.downloadaccelerator.com)</String> |
||
3066 | <Description>Downloadaccelerator download manager</Description> |
||
3067 | <Type>D</Type> |
||
3068 | <Comment></Comment> |
||
3069 | <Link1>http://www.downloadaccelerator.com</Link1> |
||
3070 | <Link2></Link2> |
||
3071 | </user-agent> |
||
3072 | <user-agent> |
||
3073 | <ID>id_a_f_209</ID> |
||
3074 | <String>DA 5.0</String> |
||
3075 | <Description>Downloadaccelerator download manager</Description> |
||
3076 | <Type>D</Type> |
||
3077 | <Comment></Comment> |
||
3078 | <Link1>http://www.downloadaccelerator.com</Link1> |
||
3079 | <Link2></Link2> |
||
3080 | </user-agent> |
||
3081 | <user-agent> |
||
3082 | <ID>id_a_f_210</ID> |
||
3083 | <String>DA 7.0</String> |
||
3084 | <Description>Downloadaccelerator download manager</Description> |
||
3085 | <Type>D</Type> |
||
3086 | <Comment></Comment> |
||
3087 | <Link1>http://www.downloadaccelerator.com</Link1> |
||
3088 | <Link2></Link2> |
||
3089 | </user-agent> |
||
3090 | <user-agent> |
||
3091 | <ID>id_a_f_070209_3</ID> |
||
3092 | <String>DAP x.x</String> |
||
3093 | <Description>Download Accelerator Plus download manager</Description> |
||
3094 | <Type>D</Type> |
||
3095 | <Comment></Comment> |
||
3096 | <Link1>http://www.speedbit.com/</Link1> |
||
3097 | <Link2></Link2> |
||
3098 | </user-agent> |
||
3099 | <user-agent> |
||
3100 | <ID>id_a_f_211</ID> |
||
3101 | <String>Dart Communications PowerTCP</String> |
||
3102 | <Description>PowerTCP ActiveX control tool</Description> |
||
3103 | <Type></Type> |
||
3104 | <Comment></Comment> |
||
3105 | <Link1>http://www.dart.com</Link1> |
||
3106 | <Link2></Link2> |
||
3107 | </user-agent> |
||
3108 | <user-agent> |
||
3109 | <ID>id_a_f_212</ID> |
||
3110 | <String>DataCha0s/2.0</String> |
||
3111 | <Description>Unknown bot from Kornet Korea (218.149.129.xxx) scans for Perl Awstats</Description> |
||
3112 | <Type>S</Type> |
||
3113 | <Comment></Comment> |
||
3114 | <Link1></Link1> |
||
3115 | <Link2></Link2> |
||
3116 | </user-agent> |
||
3117 | <user-agent> |
||
3118 | <ID>id_a_f_101106_1</ID> |
||
3119 | <String>DataCha0s/2.0</String> |
||
3120 | <Description>Unknown UA looking for Awstats Perl components</Description> |
||
3121 | <Type>S</Type> |
||
3122 | <Comment>from various IPs</Comment> |
||
3123 | <Link1></Link1> |
||
3124 | <Link2></Link2> |
||
3125 | </user-agent> |
||
3126 | <user-agent> |
||
3127 | <ID>id_a_f_213</ID> |
||
3128 | <String>DataFountains/DMOZ Downloader</String> |
||
3129 | <Description>INFOMINE/iVia Scholary Internet Resource Collections robot</Description> |
||
3130 | <Type>R</Type> |
||
3131 | <Comment>138.23.85.xx</Comment> |
||
3132 | <Link1>http://infomine.ucr.edu/</Link1> |
||
3133 | <Link2>http://ivia.ucr.edu/useragents.shtml</Link2> |
||
3134 | </user-agent> |
||
3135 | <user-agent> |
||
3136 | <ID>id_a_f_040307_1</ID> |
||
3137 | <String>DataFountains/Dmoz Downloader (http://ivia.ucr.edu/useragents.shtml)</String> |
||
3138 | <Description>INFOMINE/iVia Scholary Internet Resource Collections robot</Description> |
||
3139 | <Type>R</Type> |
||
3140 | <Comment>138.23.85.xx</Comment> |
||
3141 | <Link1>http://infomine.ucr.edu/</Link1> |
||
3142 | <Link2>http://ivia.ucr.edu/useragents.shtml</Link2> |
||
3143 | </user-agent> |
||
3144 | <user-agent> |
||
3145 | <ID>id_a_f_110307_1</ID> |
||
3146 | <String>DataFountains/DMOZ Feature Vector Corpus Creator (http://ivia.ucr.edu/useragents.shtml)</String> |
||
3147 | <Description>INFOMINE/iVia Scholary Internet Resource Collections robot</Description> |
||
3148 | <Type>R</Type> |
||
3149 | <Comment>138.23.85.xx</Comment> |
||
3150 | <Link1>http://infomine.ucr.edu/</Link1> |
||
3151 | <Link2>http://ivia.ucr.edu/useragents.shtml</Link2> |
||
3152 | </user-agent> |
||
3153 | <user-agent> |
||
3154 | <ID>id_a_f_050907_1</ID> |
||
3155 | <String>DataparkSearch/4.47 (+http://dataparksearch.org/bot)</String> |
||
3156 | <Description>DataparkSearch open source search engine</Description> |
||
3157 | <Type>R</Type> |
||
3158 | <Comment></Comment> |
||
3159 | <Link1>http://www.dataparksearch.org</Link1> |
||
3160 | <Link2></Link2> |
||
3161 | </user-agent> |
||
3162 | <user-agent> |
||
3163 | <ID>id_a_f_214</ID> |
||
3164 | <String>DataparkSearch/4.xx (http://www.dataparksearch.org/)</String> |
||
3165 | <Description>DataparkSearch open source search engine</Description> |
||
3166 | <Type>R</Type> |
||
3167 | <Comment></Comment> |
||
3168 | <Link1>http://www.dataparksearch.org</Link1> |
||
3169 | <Link2></Link2> |
||
3170 | </user-agent> |
||
3171 | <user-agent> |
||
3172 | <ID>id_a_f_080206_1</ID> |
||
3173 | <String>DataSpear/1.0 (Spider; http://www.dataspear.com/spider.html; spider@dataspear.com)</String> |
||
3174 | <Description>DataSpear Directory robot (24.109.29.xx)</Description> |
||
3175 | <Type>R</Type> |
||
3176 | <Comment></Comment> |
||
3177 | <Link1>http://www.dataspear.com/</Link1> |
||
3178 | <Link2></Link2> |
||
3179 | </user-agent> |
||
3180 | <user-agent> |
||
3181 | <ID>id_a_f_215</ID> |
||
3182 | <String>DataSpearSpiderBot/0.2 (DataSpear Spider Bot; http://dssb.dataspear.com/bot.html; dssb@dataspear.com)</String> |
||
3183 | <Description>DataSpear Directory robot (24.109.29.xx)</Description> |
||
3184 | <Type>R</Type> |
||
3185 | <Comment></Comment> |
||
3186 | <Link1>http://www.dataspear.com/</Link1> |
||
3187 | <Link2></Link2> |
||
3188 | </user-agent> |
||
3189 | <user-agent> |
||
3190 | <ID>id_a_f_161105_1</ID> |
||
3191 | <String>DatenBot( http://www.sicher-durchs-netz.de/bot.html)</String> |
||
3192 | <Description>Sicher-durchs-Netz German security related search (62.75.220.xxx)</Description> |
||
3193 | <Type>R</Type> |
||
3194 | <Comment></Comment> |
||
3195 | <Link1>http://www.sicher-durchs-netz.de/suche</Link1> |
||
3196 | <Link2></Link2> |
||
3197 | </user-agent> |
||
3198 | <user-agent> |
||
3199 | <ID>id_a_f_216</ID> |
||
3200 | <String>DaviesBot/1.7 (www.wholeweb.net)</String> |
||
3201 | <Description>Wholeweb robot</Description> |
||
3202 | <Type>R</Type> |
||
3203 | <Comment>site is closed</Comment> |
||
3204 | <Link1>http://www.wholeweb.net</Link1> |
||
3205 | <Link2></Link2> |
||
3206 | </user-agent> |
||
3207 | <user-agent> |
||
3208 | <ID>id_a_f_217</ID> |
||
3209 | <String>daypopbot/0.x</String> |
||
3210 | <Description>Daypop blog - weblog - online mag search spider</Description> |
||
3211 | <Type>R</Type> |
||
3212 | <Comment></Comment> |
||
3213 | <Link1>http://www.daypop.com/info/about.htm</Link1> |
||
3214 | <Link2></Link2> |
||
3215 | </user-agent> |
||
3216 | <user-agent> |
||
3217 | <ID>id_a_f_218</ID> |
||
3218 | <String>dbDig(http://www.prairielandconsulting.com)</String> |
||
3219 | <Description>dbDig search engine</Description> |
||
3220 | <Type>R</Type> |
||
3221 | <Comment></Comment> |
||
3222 | <Link1>http://www.prairielandconsulting.com</Link1> |
||
3223 | <Link2></Link2> |
||
3224 | </user-agent> |
||
3225 | <user-agent> |
||
3226 | <ID>id_a_f_219</ID> |
||
3227 | <String>DBrowse 1.4b</String> |
||
3228 | <Description>Some site scanning tool via diff. IPs i.e.: - wanweb.net (208.6.163.xxx) - cox.net (68.4.xxx.xxx)</Description> |
||
3229 | <Type>S</Type> |
||
3230 | <Comment>UA sometimes - DSurf15a 01 - DBrowse 1.4d</Comment> |
||
3231 | <Link1></Link1> |
||
3232 | <Link2></Link2> |
||
3233 | </user-agent> |
||
3234 | <user-agent> |
||
3235 | <ID>id_a_f_220</ID> |
||
3236 | <String>DBrowse 1.4d</String> |
||
3237 | <Description>Some site scanning tool via diff. IPs i.e.: - pacbell.net (67.112.xxx.xxx)</Description> |
||
3238 | <Type>S</Type> |
||
3239 | <Comment>see also DSurf15a 01 - DBrowse 1.4b</Comment> |
||
3240 | <Link1></Link1> |
||
3241 | <Link2></Link2> |
||
3242 | </user-agent> |
||
3243 | <user-agent> |
||
3244 | <ID>id_a_f_221</ID> |
||
3245 | <String>DC-Sakura/x.xx</String> |
||
3246 | <Description>DC-Sakura download manager</Description> |
||
3247 | <Type>D</Type> |
||
3248 | <Comment></Comment> |
||
3249 | <Link1>http://www.dc-sakura.com/</Link1> |
||
3250 | <Link2></Link2> |
||
3251 | </user-agent> |
||
3252 | <user-agent> |
||
3253 | <ID>id_a_f_222</ID> |
||
3254 | <String>dCSbot/1.1</String> |
||
3255 | <Description>unknown divine/Openmarket.com robot</Description> |
||
3256 | <Type>R</Type> |
||
3257 | <Comment></Comment> |
||
3258 | <Link1>http://www.openmarket.com/</Link1> |
||
3259 | <Link2></Link2> |
||
3260 | </user-agent> |
||
3261 | <user-agent> |
||
3262 | <ID>id_a_f_223</ID> |
||
3263 | <String>DDD</String> |
||
3264 | <Description>some (website) downloading tool</Description> |
||
3265 | <Type>D</Type> |
||
3266 | <Comment></Comment> |
||
3267 | <Link1></Link1> |
||
3268 | <Link2></Link2> |
||
3269 | </user-agent> |
||
3270 | <user-agent> |
||
3271 | <ID>id_a_f_224</ID> |
||
3272 | <String>dds explorer v1.0 beta</String> |
||
3273 | <Description>Unknown user agent</Description> |
||
3274 | <Type></Type> |
||
3275 | <Comment></Comment> |
||
3276 | <Link1></Link1> |
||
3277 | <Link2></Link2> |
||
3278 | </user-agent> |
||
3279 | <user-agent> |
||
3280 | <ID>id_a_f_225</ID> |
||
3281 | <String>de.searchengine.comBot 1.2 (http://de.searchengine.com/spider)</String> |
||
3282 | <Description>Searchengine.com (Germany) submission checking / robot (84.73.57.xx)</Description> |
||
3283 | <Type>R</Type> |
||
3284 | <Comment></Comment> |
||
3285 | <Link1>http://de.searchengine.com</Link1> |
||
3286 | <Link2></Link2> |
||
3287 | </user-agent> |
||
3288 | <user-agent> |
||
3289 | <ID>id_a_f_226</ID> |
||
3290 | <String>DeadLinkCheck/0.4.0 libwww-perl/5.xx</String> |
||
3291 | <Description>DLC Perl HTTP link checking</Description> |
||
3292 | <Type>C</Type> |
||
3293 | <Comment></Comment> |
||
3294 | <Link1>http://dlc.sourceforge.net/</Link1> |
||
3295 | <Link2></Link2> |
||
3296 | </user-agent> |
||
3297 | <user-agent> |
||
3298 | <ID>id_a_f_111206_3</ID> |
||
3299 | <String>Deep Link Calculator v1.0</String> |
||
3300 | <Description>Sootle Web Directory deep link checker</Description> |
||
3301 | <Type>C</Type> |
||
3302 | <Comment>216.89.111.x</Comment> |
||
3303 | <Link1>http://directory.sootle.com/deep-links/</Link1> |
||
3304 | <Link2></Link2> |
||
3305 | </user-agent> |
||
3306 | <user-agent> |
||
3307 | <ID>id_a_f_227</ID> |
||
3308 | <String>deepak-USC/ISI</String> |
||
3309 | <Description>deepak-USC/ISI robot from USC/Information Science Institute</Description> |
||
3310 | <Type>R</Type> |
||
3311 | <Comment></Comment> |
||
3312 | <Link1>http://www.isi.edu/%7Eravichan/deepak-usc-isi.html</Link1> |
||
3313 | <Link2>http://www.isi.edu/</Link2> |
||
3314 | </user-agent> |
||
3315 | <user-agent> |
||
3316 | <ID>id_a_f_228</ID> |
||
3317 | <String>DeepIndex</String> |
||
3318 | <Description>Deepindex robot</Description> |
||
3319 | <Type>R</Type> |
||
3320 | <Comment></Comment> |
||
3321 | <Link1>http://www.deepindex.net/utilisateurs.php?referral=deepindex</Link1> |
||
3322 | <Link2></Link2> |
||
3323 | </user-agent> |
||
3324 | <user-agent> |
||
3325 | <ID>id_a_f_229</ID> |
||
3326 | <String>DeepIndex ( http://www.zetbot.com )</String> |
||
3327 | <Description>Zetbot search Belgium (213.41.128.xx) using Deepindex robot</Description> |
||
3328 | <Type>R</Type> |
||
3329 | <Comment></Comment> |
||
3330 | <Link1>http://www.zetbot.com/</Link1> |
||
3331 | <Link2>http://www.deepindex.net/utilisateurs.php?referral=deepindex</Link2> |
||
3332 | </user-agent> |
||
3333 | <user-agent> |
||
3334 | <ID>id_a_f_230</ID> |
||
3335 | <String>DeepIndex (www.en.deepindex.com)</String> |
||
3336 | <Description>Deepindex robot</Description> |
||
3337 | <Type>R</Type> |
||
3338 | <Comment></Comment> |
||
3339 | <Link1>http://www.deepindex.net/utilisateurs.php?referral=deepindex</Link1> |
||
3340 | <Link2></Link2> |
||
3341 | </user-agent> |
||
3342 | <user-agent> |
||
3343 | <ID>id_a_f_231</ID> |
||
3344 | <String>DeepIndexer.ca</String> |
||
3345 | <Description>Deepindex robot (via Paragon.net Canada)</Description> |
||
3346 | <Type>R</Type> |
||
3347 | <Comment></Comment> |
||
3348 | <Link1>http://www.deepindex.net/utilisateurs.php?referral=deepindex</Link1> |
||
3349 | <Link2></Link2> |
||
3350 | </user-agent> |
||
3351 | <user-agent> |
||
3352 | <ID>id_a_f_011006_2</ID> |
||
3353 | <String>del.icio.us-thumbnails/1.0 Mozilla/5.0 (compatible; Konqueror/3.4; FreeBSD) KHTML/3.4.2 (like Gecko)</String> |
||
3354 | <Description>del.icio.us picture robot for thumbnail preview via Yahoo</Description> |
||
3355 | <Type>D</Type> |
||
3356 | <Comment>66.94.237.1xx</Comment> |
||
3357 | <Link1>http://del.icio.us/</Link1> |
||
3358 | <Link2></Link2> |
||
3359 | </user-agent> |
||
3360 | <user-agent> |
||
3361 | <ID>id_a_f_250106_1</ID> |
||
3362 | <String>DeleGate/9.0.5-fix1</String> |
||
3363 | <Description>DeleGate application level gateway / proxy server</Description> |
||
3364 | <Type>P</Type> |
||
3365 | <Comment></Comment> |
||
3366 | <Link1>http://www.delegate.org/delegate/</Link1> |
||
3367 | <Link2></Link2> |
||
3368 | </user-agent> |
||
3369 | <user-agent> |
||
3370 | <ID>id_a_f_232</ID> |
||
3371 | <String>Demo Bot DOT 16b</String> |
||
3372 | <Description>Some site scanning tool from 217.34.59.xxx (btopenworld.com)</Description> |
||
3373 | <Type>S</Type> |
||
3374 | <Comment></Comment> |
||
3375 | <Link1></Link1> |
||
3376 | <Link2></Link2> |
||
3377 | </user-agent> |
||
3378 | <user-agent> |
||
3379 | <ID>id_a_f_233</ID> |
||
3380 | <String>Demo Bot Z 16b</String> |
||
3381 | <Description>Some site scanning tool from 68.154.96.xx (bellsouth.net)</Description> |
||
3382 | <Type>S</Type> |
||
3383 | <Comment>appears also as - MFC Foundation Class Library - Full Web Bot 0516B</Comment> |
||
3384 | <Link1></Link1> |
||
3385 | <Link2></Link2> |
||
3386 | </user-agent> |
||
3387 | <user-agent> |
||
3388 | <ID>id_a_f_234</ID> |
||
3389 | <String>Denmex websearch (http://search.denmex.com)</String> |
||
3390 | <Description>Denmex Websearch robot/link checking</Description> |
||
3391 | <Type>R</Type> |
||
3392 | <Comment></Comment> |
||
3393 | <Link1>http://search.denmex.com</Link1> |
||
3394 | <Link2></Link2> |
||
3395 | </user-agent> |
||
3396 | <user-agent> |
||
3397 | <ID>id_a_f_235</ID> |
||
3398 | <String>Der große BilderSauger 2.00u</String> |
||
3399 | <Description>DataBecker Bilder Sauger (discontinued) web graphics downloader</Description> |
||
3400 | <Type>D</Type> |
||
3401 | <Comment></Comment> |
||
3402 | <Link1>http://www.databecker.de</Link1> |
||
3403 | <Link2></Link2> |
||
3404 | </user-agent> |
||
3405 | <user-agent> |
||
3406 | <ID>id_a_f_230206_1</ID> |
||
3407 | <String>dev-spider2.searchpsider.com/1.3b</String> |
||
3408 | <Description>Searchspider.com robot (72.245.225.xxx)</Description> |
||
3409 | <Type>R</Type> |
||
3410 | <Comment></Comment> |
||
3411 | <Link1>http://www.searchspider.com/</Link1> |
||
3412 | <Link2></Link2> |
||
3413 | </user-agent> |
||
3414 | <user-agent> |
||
3415 | <ID>id_a_f_236</ID> |
||
3416 | <String>DevComponents.com HtmlDocument Object</String> |
||
3417 | <Description>DevComponents HTMLDocument Class Library for Visual Studio.net</Description> |
||
3418 | <Type></Type> |
||
3419 | <Comment></Comment> |
||
3420 | <Link1>http://www.devcomponents.com</Link1> |
||
3421 | <Link2></Link2> |
||
3422 | </user-agent> |
||
3423 | <user-agent> |
||
3424 | <ID>id_a_f_237</ID> |
||
3425 | <String>DiaGem/1.1 (http://www.skyrocket.gr.jp/diagem.html)</String> |
||
3426 | <Description>DiaGem Japan web crawler</Description> |
||
3427 | <Type>R</Type> |
||
3428 | <Comment>(site is offline)</Comment> |
||
3429 | <Link1>http://www.skyrocket.gr.jp</Link1> |
||
3430 | <Link2></Link2> |
||
3431 | </user-agent> |
||
3432 | <user-agent> |
||
3433 | <ID>id_a_f_238</ID> |
||
3434 | <String>Diamond/x.0</String> |
||
3435 | <Description>Claria (ex Gator) SearchScout robot (64.152.73.xx)</Description> |
||
3436 | <Type>R</Type> |
||
3437 | <Comment>s. also Claria</Comment> |
||
3438 | <Link1>http://www.searchscout.com</Link1> |
||
3439 | <Link2></Link2> |
||
3440 | </user-agent> |
||
3441 | <user-agent> |
||
3442 | <ID>id_a_f_239</ID> |
||
3443 | <String>DiamondBot</String> |
||
3444 | <Description>Claria (ex Gator) SearchScout robot (64.152.73.xx)</Description> |
||
3445 | <Type>R</Type> |
||
3446 | <Comment>s. also Claria</Comment> |
||
3447 | <Link1>http://www.searchscout.com</Link1> |
||
3448 | <Link2></Link2> |
||
3449 | </user-agent> |
||
3450 | <user-agent> |
||
3451 | <ID>id_a_f_240</ID> |
||
3452 | <String>Digger/1.0 JDK/1.3.0rc3</String> |
||
3453 | <Description>Diggit! robot</Description> |
||
3454 | <Type>R</Type> |
||
3455 | <Comment></Comment> |
||
3456 | <Link1>http://www.diggit.com</Link1> |
||
3457 | <Link2></Link2> |
||
3458 | </user-agent> |
||
3459 | <user-agent> |
||
3460 | <ID>id_a_f_241</ID> |
||
3461 | <String>DigOut4U</String> |
||
3462 | <Description>OpenPortal4U robot</Description> |
||
3463 | <Type>R</Type> |
||
3464 | <Comment></Comment> |
||
3465 | <Link1>http://www.arisem.com</Link1> |
||
3466 | <Link2></Link2> |
||
3467 | </user-agent> |
||
3468 | <user-agent> |
||
3469 | <ID>id_a_f_242</ID> |
||
3470 | <String>DIIbot/1.2</String> |
||
3471 | <Description>Findsame.com (site is offline) / Digital-Integrity robot</Description> |
||
3472 | <Type>R</Type> |
||
3473 | <Comment></Comment> |
||
3474 | <Link1>http://www.digital-integrity.com/</Link1> |
||
3475 | <Link2></Link2> |
||
3476 | </user-agent> |
||
3477 | <user-agent> |
||
3478 | <ID>id_a_f_100206_1</ID> |
||
3479 | <String>Dillo/0.8.5-i18n-misc</String> |
||
3480 | <Description>Dillo Web Browser</Description> |
||
3481 | <Type>B</Type> |
||
3482 | <Comment></Comment> |
||
3483 | <Link1>http://www.dillo.org/</Link1> |
||
3484 | <Link2></Link2> |
||
3485 | </user-agent> |
||
3486 | <user-agent> |
||
3487 | <ID>id_a_f_243</ID> |
||
3488 | <String>Dillo/0.x.x</String> |
||
3489 | <Description>Dillo Web Browser</Description> |
||
3490 | <Type>B</Type> |
||
3491 | <Comment></Comment> |
||
3492 | <Link1>http://www.dillo.org/</Link1> |
||
3493 | <Link2></Link2> |
||
3494 | </user-agent> |
||
3495 | <user-agent> |
||
3496 | <ID>id_a_f_100109_1</ID> |
||
3497 | <String>disastrous/1.0.5 (running with Python 2.5.1; http://www.bortzmeyer.org/disastrous.html; archangel77@del.icio.us)</String> |
||
3498 | <Description>disastrous - a del.icio.us link checker based on Python</Description> |
||
3499 | <Type>C</Type> |
||
3500 | <Comment></Comment> |
||
3501 | <Link1>http://www.bortzmeyer.org/disastrous.html</Link1> |
||
3502 | <Link2></Link2> |
||
3503 | </user-agent> |
||
3504 | <user-agent> |
||
3505 | <ID>id_a_f_140306_1</ID> |
||
3506 | <String>DISCo Pump x.x</String> |
||
3507 | <Description>DISCo Pump offline browser / website ripper</Description> |
||
3508 | <Type>D</Type> |
||
3509 | <Comment>No active homepage</Comment> |
||
3510 | <Link1>http://www.arssoft.com/</Link1> |
||
3511 | <Link2>http://www.filetransit.com/view.php?id=3870</Link2> |
||
3512 | </user-agent> |
||
3513 | <user-agent> |
||
3514 | <ID>id_a_f_300907_1</ID> |
||
3515 | <String>disco/Nutch-0.9 (experimental crawler; www.discoveryengine.com; disco-crawl@discoveryengine.com)</String> |
||
3516 | <Description>Unkown robot from Discovery Engine Corp.</Description> |
||
3517 | <Type>R</Type> |
||
3518 | <Comment>208.96.54.xx</Comment> |
||
3519 | <Link1>http://www.discoveryengine.com/</Link1> |
||
3520 | <Link2></Link2> |
||
3521 | </user-agent> |
||
3522 | <user-agent> |
||
3523 | <ID>id_a_f_300907_2</ID> |
||
3524 | <String>disco/Nutch-1.0-dev (experimental crawler; www.discoveryengine.com; disco-crawl@discoveryengine.com)</String> |
||
3525 | <Description>Unkown robot from Discovery Engine Corp.</Description> |
||
3526 | <Type>R</Type> |
||
3527 | <Comment>208.96.54.xx</Comment> |
||
3528 | <Link1>http://www.discoveryengine.com/</Link1> |
||
3529 | <Link2></Link2> |
||
3530 | </user-agent> |
||
3531 | <user-agent> |
||
3532 | <ID>id_a_f_244</ID> |
||
3533 | <String>DittoSpyder</String> |
||
3534 | <Description>Ditto picture search robot</Description> |
||
3535 | <Type>R</Type> |
||
3536 | <Comment></Comment> |
||
3537 | <Link1>http://www.ditto.com</Link1> |
||
3538 | <Link2></Link2> |
||
3539 | </user-agent> |
||
3540 | <user-agent> |
||
3541 | <ID>id_a_f_245</ID> |
||
3542 | <String>dlman</String> |
||
3543 | <Description>some download agent</Description> |
||
3544 | <Type>D</Type> |
||
3545 | <Comment>Wildsoft Surfer</Comment> |
||
3546 | <Link1></Link1> |
||
3547 | <Link2></Link2> |
||
3548 | </user-agent> |
||
3549 | <user-agent> |
||
3550 | <ID>id_a_f_246</ID> |
||
3551 | <String>dloader(NaverRobot)/1.0</String> |
||
3552 | <Description>Naver Japan / Korea robot</Description> |
||
3553 | <Type>R</Type> |
||
3554 | <Comment>s. also Python-urllib/1.15 - nabot - NaverBot & Cowbot</Comment> |
||
3555 | <Link1>http://www.naver.co.jp</Link1> |
||
3556 | <Link2></Link2> |
||
3557 | </user-agent> |
||
3558 | <user-agent> |
||
3559 | <ID>id_a_f_100408_1</ID> |
||
3560 | <String>DNSRight.com WebBot Link Ckeck Tool. Report abuse to: dnsr@dnsright.com</String> |
||
3561 | <Description>DNS Right - Online DNS tools</Description> |
||
3562 | <Type>C</Type> |
||
3563 | <Comment>203.161.71.17x</Comment> |
||
3564 | <Link1>http://www.dnsright.com/</Link1> |
||
3565 | <Link2></Link2> |
||
3566 | </user-agent> |
||
3567 | <user-agent> |
||
3568 | <ID>id_a_f_247</ID> |
||
3569 | <String>DoCoMo/1.0/Nxxxi/c10</String> |
||
3570 | <Description>NTT DoCoMo (Japan) robot</Description> |
||
3571 | <Type>R</Type> |
||
3572 | <Comment></Comment> |
||
3573 | <Link1>http://www.nttdocomo.co.jp/</Link1> |
||
3574 | <Link2></Link2> |
||
3575 | </user-agent> |
||
3576 | <user-agent> |
||
3577 | <ID>id_a_f_248</ID> |
||
3578 | <String>DoCoMo/1.0/Nxxxi/c10/TB</String> |
||
3579 | <Description>NTT DoCoMo (Japan) robot</Description> |
||
3580 | <Type>R</Type> |
||
3581 | <Comment></Comment> |
||
3582 | <Link1>http://www.nttdocomo.co.jp/</Link1> |
||
3583 | <Link2></Link2> |
||
3584 | </user-agent> |
||
3585 | <user-agent> |
||
3586 | <ID>id_a_f_249</ID> |
||
3587 | <String>DoCoMo/1.0/P502i/c10 (Google CHTML Proxy/1.0)</String> |
||
3588 | <Description>Google (216.239.39.x) proxy server</Description> |
||
3589 | <Type>P</Type> |
||
3590 | <Comment></Comment> |
||
3591 | <Link1></Link1> |
||
3592 | <Link2></Link2> |
||
3593 | </user-agent> |
||
3594 | <user-agent> |
||
3595 | <ID>id_a_f_250</ID> |
||
3596 | <String>DoCoMo/2.0 P900iV(c100;TB;W24H11) </String> |
||
3597 | <Description>NTT DoCoMo (Japan) robot</Description> |
||
3598 | <Type>R</Type> |
||
3599 | <Comment></Comment> |
||
3600 | <Link1>http://www.nttdocomo.co.jp/</Link1> |
||
3601 | <Link2></Link2> |
||
3602 | </user-agent> |
||
3603 | <user-agent> |
||
3604 | <ID>id_a_f_141205_1</ID> |
||
3605 | <String>DoCoMo/2.0 SH901iS(c100;TB;W24H12),gzip(gfe) (via translate.google.com)</String> |
||
3606 | <Description>NTT DoCoMo (Japan) proxy server (210.136.161.1xx)</Description> |
||
3607 | <Type>P</Type> |
||
3608 | <Comment></Comment> |
||
3609 | <Link1>http://www.nttdocomo.co.jp/</Link1> |
||
3610 | <Link2></Link2> |
||
3611 | </user-agent> |
||
3612 | <user-agent> |
||
3613 | <ID>id_a_f_081207_1</ID> |
||
3614 | <String>DoCoMo/2.0 SH902i (compatible; Y!J-SRD/1.0; http://help.yahoo.co.jp/help/jp/search/indexing/indexing-27.html)</String> |
||
3615 | <Description>Yahoo Search Japan robot (203.216.197.xxx)</Description> |
||
3616 | <Type>R</Type> |
||
3617 | <Comment>s. also Y!J-SRD/1.0</Comment> |
||
3618 | <Link1>http://www.yahoo.co.jp/</Link1> |
||
3619 | <Link2></Link2> |
||
3620 | </user-agent> |
||
3621 | <user-agent> |
||
3622 | <ID>id_a_f_271006_3</ID> |
||
3623 | <String>DoCoMo/2.0/SO502i (compatible; Y!J-SRD/1.0; http://help.yahoo.co.jp/help/jp/search/indexing/indexing-27.html)</String> |
||
3624 | <Description>Yahoo Search Japan robot (203.216.197.xxx)</Description> |
||
3625 | <Type>R</Type> |
||
3626 | <Comment>s. also Y!J-SRD/1.0</Comment> |
||
3627 | <Link1>http://www.yahoo.co.jp/</Link1> |
||
3628 | <Link2></Link2> |
||
3629 | </user-agent> |
||
3630 | <user-agent> |
||
3631 | <ID>id_a_f_251</ID> |
||
3632 | <String>DocZilla/1.0 (Windows; U; WinNT4.0; en-US; rv:1.0.0) Gecko/20020804</String> |
||
3633 | <Description>DocZilla - Mozilla-based SGML/XML/HTML- browser</Description> |
||
3634 | <Type>B</Type> |
||
3635 | <Comment></Comment> |
||
3636 | <Link1>http://www.doczilla.com</Link1> |
||
3637 | <Link2></Link2> |
||
3638 | </user-agent> |
||
3639 | <user-agent> |
||
3640 | <ID>id_a_f_210607_1</ID> |
||
3641 | <String>dodgebot/experimental</String> |
||
3642 | <Description>unknown robot from AGMLAB Information Technologies (Information retrieval system ?)</Description> |
||
3643 | <Type>R</Type> |
||
3644 | <Comment>212.174.130.1xx</Comment> |
||
3645 | <Link1>http://www.agmlab.com/agmlab_eng.html</Link1> |
||
3646 | <Link2></Link2> |
||
3647 | </user-agent> |
||
3648 | <user-agent> |
||
3649 | <ID>id_a_f_180606_1</ID> |
||
3650 | <String>DonutP; Windows98SE</String> |
||
3651 | <Description>Donut P - Japanese IE based browser</Description> |
||
3652 | <Type>B</Type> |
||
3653 | <Comment></Comment> |
||
3654 | <Link1>http://donutp.com/</Link1> |
||
3655 | <Link2></Link2> |
||
3656 | </user-agent> |
||
3657 | <user-agent> |
||
3658 | <ID>id_a_f_250907_2</ID> |
||
3659 | <String>Doubanbot/1.0 (bot@douban.com http://www.douban.com)</String> |
||
3660 | <Description>Unknown robot from douban search (China) - maybe image crawling</Description> |
||
3661 | <Type></Type> |
||
3662 | <Comment>59.151.41.xx</Comment> |
||
3663 | <Link1>http://www.douban.com/</Link1> |
||
3664 | <Link2></Link2> |
||
3665 | </user-agent> |
||
3666 | <user-agent> |
||
3667 | <ID>id_a_f_252</ID> |
||
3668 | <String>Download Demon/3.x.x.x</String> |
||
3669 | <Description>Download Demon/Netzip download manager</Description> |
||
3670 | <Type>D</Type> |
||
3671 | <Comment></Comment> |
||
3672 | <Link1>http://www.netzip.com</Link1> |
||
3673 | <Link2></Link2> |
||
3674 | </user-agent> |
||
3675 | <user-agent> |
||
3676 | <ID>id_a_f_191105_4</ID> |
||
3677 | <String>Download Druid 2.x</String> |
||
3678 | <Description>Download Druid IE plugin download manager</Description> |
||
3679 | <Type>D</Type> |
||
3680 | <Comment></Comment> |
||
3681 | <Link1>http://www.xemico.com/druid/index.html</Link1> |
||
3682 | <Link2></Link2> |
||
3683 | </user-agent> |
||
3684 | <user-agent> |
||
3685 | <ID>id_a_f_253</ID> |
||
3686 | <String>Download Express 1.0</String> |
||
3687 | <Description>Download Express download manager</Description> |
||
3688 | <Type>D</Type> |
||
3689 | <Comment></Comment> |
||
3690 | <Link1>http://www.metaproducts.com</Link1> |
||
3691 | <Link2></Link2> |
||
3692 | </user-agent> |
||
3693 | <user-agent> |
||
3694 | <ID>id_a_f_254</ID> |
||
3695 | <String>Download Master</String> |
||
3696 | <Description>Download Master download manager</Description> |
||
3697 | <Type>D</Type> |
||
3698 | <Comment></Comment> |
||
3699 | <Link1>http://www.westbyte.com/dm/index.phtml</Link1> |
||
3700 | <Link2></Link2> |
||
3701 | </user-agent> |
||
3702 | <user-agent> |
||
3703 | <ID>id_a_f_191105_5</ID> |
||
3704 | <String>Download Ninja 3.0</String> |
||
3705 | <Description>Download Ninja download manager (Japan)</Description> |
||
3706 | <Type>D</Type> |
||
3707 | <Comment></Comment> |
||
3708 | <Link1>http://www.h-fd.org/mkro/mt/archives/2002/09/download_ninja_1.html</Link1> |
||
3709 | <Link2></Link2> |
||
3710 | </user-agent> |
||
3711 | <user-agent> |
||
3712 | <ID>id_a_f_255</ID> |
||
3713 | <String>Download Wonder</String> |
||
3714 | <Description>Download Wonder download manager</Description> |
||
3715 | <Type>D</Type> |
||
3716 | <Comment></Comment> |
||
3717 | <Link1>http://www.forty.com</Link1> |
||
3718 | <Link2></Link2> |
||
3719 | </user-agent> |
||
3720 | <user-agent> |
||
3721 | <ID>id_a_f_256</ID> |
||
3722 | <String>Download-Tipp Linkcheck (http://download-tipp.de/)</String> |
||
3723 | <Description>Download-Tipp Germany link checking</Description> |
||
3724 | <Type>R</Type> |
||
3725 | <Comment></Comment> |
||
3726 | <Link1>http://download-tipp.de/</Link1> |
||
3727 | <Link2></Link2> |
||
3728 | </user-agent> |
||
3729 | <user-agent> |
||
3730 | <ID>id_a_f_257</ID> |
||
3731 | <String>Download.exe(1.1) (+http://www.sql-und-xml.de/freeware-tools/)</String> |
||
3732 | <Description>download.exe .NET based downloading tool</Description> |
||
3733 | <Type>D</Type> |
||
3734 | <Comment></Comment> |
||
3735 | <Link1>http://www.sql-und-xml.de/freeware-tools/</Link1> |
||
3736 | <Link2></Link2> |
||
3737 | </user-agent> |
||
3738 | <user-agent> |
||
3739 | <ID>id_a_f_300907_3</ID> |
||
3740 | <String>DownloadDirect.1.0</String> |
||
3741 | <Description>Download Direct download manager</Description> |
||
3742 | <Type>D</Type> |
||
3743 | <Comment></Comment> |
||
3744 | <Link1>http://senbit.com/</Link1> |
||
3745 | <Link2></Link2> |
||
3746 | </user-agent> |
||
3747 | <user-agent> |
||
3748 | <ID>id_a_f_258</ID> |
||
3749 | <String>Dr.Web (R) online scanner: http://online.drweb.com/</String> |
||
3750 | <Description>Dr.WEB online virus scanner</Description> |
||
3751 | <Type></Type> |
||
3752 | <Comment></Comment> |
||
3753 | <Link1>http://online.drweb.com</Link1> |
||
3754 | <Link2></Link2> |
||
3755 | </user-agent> |
||
3756 | <user-agent> |
||
3757 | <ID>id_a_f_259</ID> |
||
3758 | <String>Dragonfly File Reader</String> |
||
3759 | <Description>Dragonfly CMS - Open Source content management system</Description> |
||
3760 | <Type>B</Type> |
||
3761 | <Comment></Comment> |
||
3762 | <Link1>http://www.cpgnuke.com</Link1> |
||
3763 | <Link2></Link2> |
||
3764 | </user-agent> |
||
3765 | <user-agent> |
||
3766 | <ID>id_a_f_260</ID> |
||
3767 | <String>Drecombot/1.0 (http://career.drecom.jp/bot.html)</String> |
||
3768 | <Description>Drecom Japan (210.233.67.xxx) - Blog search ??</Description> |
||
3769 | <Type>R</Type> |
||
3770 | <Comment></Comment> |
||
3771 | <Link1>http://www.drecom.co.jp</Link1> |
||
3772 | <Link2></Link2> |
||
3773 | </user-agent> |
||
3774 | <user-agent> |
||
3775 | <ID>id_a_f_3090906_1</ID> |
||
3776 | <String>Drupal (+http://drupal.org/)</String> |
||
3777 | <Description>Drupal - open source content management platform</Description> |
||
3778 | <Type>C</Type> |
||
3779 | <Comment></Comment> |
||
3780 | <Link1>http://drupal.org/</Link1> |
||
3781 | <Link2></Link2> |
||
3782 | </user-agent> |
||
3783 | <user-agent> |
||
3784 | <ID>id_a_f_261</ID> |
||
3785 | <String>DSurf15a 01</String> |
||
3786 | <Description>Some site scanning tool via diff. IPs i.e.: - cox.net (68.5.xxx.xxx) - pacbell.net (64.16x.xxx.xxx)</Description> |
||
3787 | <Type>S</Type> |
||
3788 | <Comment>DBrowse 1.4d</Comment> |
||
3789 | <Link1></Link1> |
||
3790 | <Link2></Link2> |
||
3791 | </user-agent> |
||
3792 | <user-agent> |
||
3793 | <ID>id_a_f_262</ID> |
||
3794 | <String>DSurf15a 71</String> |
||
3795 | <Description>Some site scanning tool via diff. IPs i.e.: - cox.net (68.4.xxx.xxx)</Description> |
||
3796 | <Type>S</Type> |
||
3797 | <Comment>TRPMFHXE</Comment> |
||
3798 | <Link1></Link1> |
||
3799 | <Link2></Link2> |
||
3800 | </user-agent> |
||
3801 | <user-agent> |
||
3802 | <ID>id_a_f_263</ID> |
||
3803 | <String>DSurf15a 81</String> |
||
3804 | <Description>Some site scanning tool via diff. IPs i.e.: - verizon.net (4.47.xxx.xxx)</Description> |
||
3805 | <Type>S</Type> |
||
3806 | <Comment>WFRIKXVNFL</Comment> |
||
3807 | <Link1></Link1> |
||
3808 | <Link2></Link2> |
||
3809 | </user-agent> |
||
3810 | <user-agent> |
||
3811 | <ID>id_a_f_264</ID> |
||
3812 | <String>DSurf15a VA</String> |
||
3813 | <Description>Some site scanning tool via diff. IPs i.e.: - eastlink.ca (24.222.xxx.xxx) - cogeco.net (216.221.8x.xxx)</Description> |
||
3814 | <Type>S</Type> |
||
3815 | <Comment></Comment> |
||
3816 | <Link1></Link1> |
||
3817 | <Link2></Link2> |
||
3818 | </user-agent> |
||
3819 | <user-agent> |
||
3820 | <ID>id_a_f_020506_2</ID> |
||
3821 | <String>DTAAgent</String> |
||
3822 | <Description>DTAAgent Java object for data collecting</Description> |
||
3823 | <Type>R D</Type> |
||
3824 | <Comment></Comment> |
||
3825 | <Link1>http://www.ibr.cs.tu-bs.de/courses/ss00/sep-vs/gruppe1/jdoc/DTA/agent/DTAAgent.html</Link1> |
||
3826 | <Link2></Link2> |
||
3827 | </user-agent> |
||
3828 | <user-agent> |
||
3829 | <ID>id_a_f_265</ID> |
||
3830 | <String>dtSearchSpider</String> |
||
3831 | <Description>dt Search Spider software</Description> |
||
3832 | <Type>R</Type> |
||
3833 | <Comment></Comment> |
||
3834 | <Link1>http://www.dtsearch.com/spider.html</Link1> |
||
3835 | <Link2></Link2> |
||
3836 | </user-agent> |
||
3837 | <user-agent> |
||
3838 | <ID>id_a_f_266</ID> |
||
3839 | <String>Dual Proxy</String> |
||
3840 | <Description>Fourelle Venturi proxy server</Description> |
||
3841 | <Type>P</Type> |
||
3842 | <Comment></Comment> |
||
3843 | <Link1>http://www.fourelle.com/news/articles/148457.htm</Link1> |
||
3844 | <Link2></Link2> |
||
3845 | </user-agent> |
||
3846 | <user-agent> |
||
3847 | <ID>id_a_f_290308_2</ID> |
||
3848 | <String>DuckDuckBot/1.0; (+http://duckduckgo.com/duckduckbot.html)</String> |
||
3849 | <Description>Duck Duck Go search crawler</Description> |
||
3850 | <Type>R</Type> |
||
3851 | <Comment>72.94.249.34</Comment> |
||
3852 | <Link1>http://duckduckgo.com/</Link1> |
||
3853 | <Link2>http://duckduckgo.com/duckduckbot.html</Link2> |
||
3854 | </user-agent> |
||
3855 | <user-agent> |
||
3856 | <ID>id_a_f_267</ID> |
||
3857 | <String>Dumbot(version 0.1 beta - dumbfind.com)</String> |
||
3858 | <Description>DumbFind.com robot</Description> |
||
3859 | <Type>R</Type> |
||
3860 | <Comment></Comment> |
||
3861 | <Link1>http://www.dumbfind.com</Link1> |
||
3862 | <Link2></Link2> |
||
3863 | </user-agent> |
||
3864 | <user-agent> |
||
3865 | <ID>id_a_f_268</ID> |
||
3866 | <String>Dumbot(version 0.1 beta - http://www.dumbfind.com/dumbot.html)</String> |
||
3867 | <Description>DumbFind.com robot</Description> |
||
3868 | <Type>R</Type> |
||
3869 | <Comment></Comment> |
||
3870 | <Link1>http://www.dumbfind.com</Link1> |
||
3871 | <Link2></Link2> |
||
3872 | </user-agent> |
||
3873 | <user-agent> |
||
3874 | <ID>id_a_f_269</ID> |
||
3875 | <String>Dumbot(version 0.1 beta)</String> |
||
3876 | <Description>DumbFind.com robot</Description> |
||
3877 | <Type>R</Type> |
||
3878 | <Comment></Comment> |
||
3879 | <Link1>http://www.dumbfind.com</Link1> |
||
3880 | <Link2></Link2> |
||
3881 | </user-agent> |
||
3882 | <user-agent> |
||
3883 | <ID>id_a_f_270</ID> |
||
3884 | <String>e-sense 1.0 ea(www.vigiltech.com/esensedisclaim.html)</String> |
||
3885 | <Description>Vigiltech e-Sense user research robot (website is offline)</Description> |
||
3886 | <Type>R</Type> |
||
3887 | <Comment></Comment> |
||
3888 | <Link1></Link1> |
||
3889 | <Link2></Link2> |
||
3890 | </user-agent> |
||
3891 | <user-agent> |
||
3892 | <ID>id_a_f_271</ID> |
||
3893 | <String>e-SocietyRobot(http://www.yama.info.waseda.ac.jp/~yamana/es/)</String> |
||
3894 | <Description>e-Society Project (Japan) crawler (133.9.238.xx)</Description> |
||
3895 | <Type>R</Type> |
||
3896 | <Comment></Comment> |
||
3897 | <Link1>http://www.yama.info.waseda.ac.jp</Link1> |
||
3898 | <Link2></Link2> |
||
3899 | </user-agent> |
||
3900 | <user-agent> |
||
3901 | <ID>id_a_f_280108_1</ID> |
||
3902 | <String>eApolloBot/2.0 (compatible; heritrix/2.0.0-SNAPSHOT-20071024.170148 +http://www.eapollo-opto.com)</String> |
||
3903 | <Description>Global Opto's eApollo Flash based search engine - Taiwan</Description> |
||
3904 | <Type>R</Type> |
||
3905 | <Comment></Comment> |
||
3906 | <Link1>http://www.eapollo.com/eaSE.jsp?language=eng</Link1> |
||
3907 | <Link2>http://www.global-opto.com/</Link2> |
||
3908 | </user-agent> |
||
3909 | <user-agent> |
||
3910 | <ID>id_a_f_272</ID> |
||
3911 | <String>EARTHCOM.info/1.x [www.earthcom.info]</String> |
||
3912 | <Description>Earthcom (Czech Republic) search robot (194.108.39.xx)</Description> |
||
3913 | <Type>R</Type> |
||
3914 | <Comment>s. also Mozilla/5.0 (compatible; EARTHCOM.info/2.01 ...</Comment> |
||
3915 | <Link1>http://www.earthcom.info</Link1> |
||
3916 | <Link2></Link2> |
||
3917 | </user-agent> |
||
3918 | <user-agent> |
||
3919 | <ID>id_a_f_273</ID> |
||
3920 | <String>EARTHCOM.info/1.xbeta [www.earthcom.info]</String> |
||
3921 | <Description>Earthcom (Czech Republic) search robot (194.108.39.xx)</Description> |
||
3922 | <Type>R</Type> |
||
3923 | <Comment>s. also Mozilla/5.0 (compatible; EARTHCOM.info/2.01 ...</Comment> |
||
3924 | <Link1>http://www.earthcom.info</Link1> |
||
3925 | <Link2></Link2> |
||
3926 | </user-agent> |
||
3927 | <user-agent> |
||
3928 | <ID>id_a_f_274</ID> |
||
3929 | <String>EasyDL/3.xx</String> |
||
3930 | <Description>Keywen Encyclopedia Bot</Description> |
||
3931 | <Type>R</Type> |
||
3932 | <Comment></Comment> |
||
3933 | <Link1>http://keywen.com/Encyclopedia/Bot/</Link1> |
||
3934 | <Link2></Link2> |
||
3935 | </user-agent> |
||
3936 | <user-agent> |
||
3937 | <ID>id_a_f_275</ID> |
||
3938 | <String>EasyDL/3.xx http://keywen.com/Encyclopedia/Bot</String> |
||
3939 | <Description>Keywen Encyclopedia Bot</Description> |
||
3940 | <Type>R</Type> |
||
3941 | <Comment></Comment> |
||
3942 | <Link1>http://keywen.com/Encyclopedia/Bot/</Link1> |
||
3943 | <Link2></Link2> |
||
3944 | </user-agent> |
||
3945 | <user-agent> |
||
3946 | <ID>id_a_f_276</ID> |
||
3947 | <String>EBrowse 1.4b</String> |
||
3948 | <Description>Some site scanning tool via diff. IPs i.e.: - swbell.net (65.66.xxx.xxx)</Description> |
||
3949 | <Type>S</Type> |
||
3950 | <Comment></Comment> |
||
3951 | <Link1></Link1> |
||
3952 | <Link2></Link2> |
||
3953 | </user-agent> |
||
3954 | <user-agent> |
||
3955 | <ID>id_a_f_277</ID> |
||
3956 | <String>eCatch/3.0</String> |
||
3957 | <Description>eCatch (now Wysigot) offline browser</Description> |
||
3958 | <Type>B D</Type> |
||
3959 | <Comment></Comment> |
||
3960 | <Link1>http://www.ecatch.com</Link1> |
||
3961 | <Link2></Link2> |
||
3962 | </user-agent> |
||
3963 | <user-agent> |
||
3964 | <ID>id_a_f_278</ID> |
||
3965 | <String>EchO!/2.0</String> |
||
3966 | <Description>Echo.fr robot</Description> |
||
3967 | <Type>R</Type> |
||
3968 | <Comment></Comment> |
||
3969 | <Link1>http://echo.fr/</Link1> |
||
3970 | <Link2></Link2> |
||
3971 | </user-agent> |
||
3972 | <user-agent> |
||
3973 | <ID>id_a_f_279</ID> |
||
3974 | <String>Educate Search VxB</String> |
||
3975 | <Description>Some site scanning tool via diff. IPs i.e.: - cox.net (68.4.xxx.xxx)</Description> |
||
3976 | <Type>S</Type> |
||
3977 | <Comment>s. also DSurf - 66.118.1xx.xxx (sagonet.com) - see also Full Web Bot - Industry Program 1.0.5</Comment> |
||
3978 | <Link1></Link1> |
||
3979 | <Link2></Link2> |
||
3980 | </user-agent> |
||
3981 | <user-agent> |
||
3982 | <ID>id_a_f_280</ID> |
||
3983 | <String>egothor/3.0a (+http://www.xdefine.org/robot.html)</String> |
||
3984 | <Description>Xdefine text search engine robot - based on Egothor open source crawler</Description> |
||
3985 | <Type>R</Type> |
||
3986 | <Comment></Comment> |
||
3987 | <Link1>http://www.xdefine.com/</Link1> |
||
3988 | <Link2>http://www.egothor.org/</Link2> |
||
3989 | </user-agent> |
||
3990 | <user-agent> |
||
3991 | <ID>id_a_f_281</ID> |
||
3992 | <String>EgotoBot/4.8 (+http://www.egoto.com/about.htm)</String> |
||
3993 | <Description>Egoto Search robot</Description> |
||
3994 | <Type>R</Type> |
||
3995 | <Comment></Comment> |
||
3996 | <Link1>http://www.egoto.com</Link1> |
||
3997 | <Link2></Link2> |
||
3998 | </user-agent> |
||
3999 | <user-agent> |
||
4000 | <ID>id_a_f_211105_1</ID> |
||
4001 | <String>ejupiter.com</String> |
||
4002 | <Description>eJupiter searcg robot (206.191.49.xx)</Description> |
||
4003 | <Type>R</Type> |
||
4004 | <Comment></Comment> |
||
4005 | <Link1>http://search.ejupiter.com/</Link1> |
||
4006 | <Link2></Link2> |
||
4007 | </user-agent> |
||
4008 | <user-agent> |
||
4009 | <ID>id_a_f_282</ID> |
||
4010 | <String>EldoS TimelyWeb/3.x</String> |
||
4011 | <Description>TimelyWeb web page monitoring tool</Description> |
||
4012 | <Type>C</Type> |
||
4013 | <Comment>s. also TimelyWeb/...</Comment> |
||
4014 | <Link1>http://www.eldos.org/timelyweb/timelyweb.html</Link1> |
||
4015 | <Link2></Link2> |
||
4016 | </user-agent> |
||
4017 | <user-agent> |
||
4018 | <ID>id_a_f_283</ID> |
||
4019 | <String>elfbot/1.0 (+http://www.uchoose.de/crawler/elfbot/)</String> |
||
4020 | <Description>Elftales crawler for uChoose theme based search (Germany)</Description> |
||
4021 | <Type>R</Type> |
||
4022 | <Comment></Comment> |
||
4023 | <Link1>http://www.uchoose.de</Link1> |
||
4024 | <Link2></Link2> |
||
4025 | </user-agent> |
||
4026 | <user-agent> |
||
4027 | <ID>id_a_f_300707_1</ID> |
||
4028 | <String>ELI/20070402:2.0 (DAUM RSS Robot, Daum Communications Corp.; +http://ws.daum.net/aboutkr.html)</String> |
||
4029 | <Description>DAUMOA - RSS search robot of Daum</Description> |
||
4030 | <Type>R</Type> |
||
4031 | <Comment>211.115.109.1xx</Comment> |
||
4032 | <Link1>http://ws.daum.net/abouten.html</Link1> |
||
4033 | <Link2></Link2> |
||
4034 | </user-agent> |
||
4035 | <user-agent> |
||
4036 | <ID>id_a_f_284</ID> |
||
4037 | <String>ELinks (0.x.x; Linux 2.4.20 i586; 132x60)</String> |
||
4038 | <Description>ELinks text mode browser</Description> |
||
4039 | <Type>B</Type> |
||
4040 | <Comment></Comment> |
||
4041 | <Link1>http://elinks.or.cz/</Link1> |
||
4042 | <Link2></Link2> |
||
4043 | </user-agent> |
||
4044 | <user-agent> |
||
4045 | <ID>id_a_f_285</ID> |
||
4046 | <String>ELinks/0.x.x (textmode; NetBSD 1.6.2 sparc; 132x43)</String> |
||
4047 | <Description>ELinks text mode browser</Description> |
||
4048 | <Type>B</Type> |
||
4049 | <Comment></Comment> |
||
4050 | <Link1>http://elinks.or.cz/</Link1> |
||
4051 | <Link2></Link2> |
||
4052 | </user-agent> |
||
4053 | <user-agent> |
||
4054 | <ID>id_a_f_286</ID> |
||
4055 | <String>EmailSiphon</String> |
||
4056 | <Description>Sonic E-mail collector</Description> |
||
4057 | <Type>S</Type> |
||
4058 | <Comment></Comment> |
||
4059 | <Link1>http://www.americaint.com/superstore/elist.html</Link1> |
||
4060 | <Link2></Link2> |
||
4061 | </user-agent> |
||
4062 | <user-agent> |
||
4063 | <ID>id_a_f_220508_2</ID> |
||
4064 | <String>EmailSpider</String> |
||
4065 | <Description>EmailSpider E-mail harvesting software</Description> |
||
4066 | <Type>S</Type> |
||
4067 | <Comment></Comment> |
||
4068 | <Link1>http://www.emailspider.net/index.php?kat=11</Link1> |
||
4069 | <Link2></Link2> |
||
4070 | </user-agent> |
||
4071 | <user-agent> |
||
4072 | <ID>id_a_f_287</ID> |
||
4073 | <String>EmailWolf 1.00</String> |
||
4074 | <Description>Trellian EMailWolf E-mail collector</Description> |
||
4075 | <Type>S</Type> |
||
4076 | <Comment></Comment> |
||
4077 | <Link1>http://www.trellian.com</Link1> |
||
4078 | <Link2></Link2> |
||
4079 | </user-agent> |
||
4080 | <user-agent> |
||
4081 | <ID>id_a_f_288</ID> |
||
4082 | <String>EmeraldShield.com WebBot</String> |
||
4083 | <Description>EmeraldShield spam and web filtration services</Description> |
||
4084 | <Type>P R</Type> |
||
4085 | <Comment></Comment> |
||
4086 | <Link1>http://www.emeraldshield.com</Link1> |
||
4087 | <Link2></Link2> |
||
4088 | </user-agent> |
||
4089 | <user-agent> |
||
4090 | <ID>id_a_f_289</ID> |
||
4091 | <String>EmeraldShield.com WebBot (http://www.emeraldshield.com/webbot.aspx)</String> |
||
4092 | <Description>EmeraldShield spam and web filtration services</Description> |
||
4093 | <Type>P R</Type> |
||
4094 | <Comment></Comment> |
||
4095 | <Link1>http://www.emeraldshield.com</Link1> |
||
4096 | <Link2></Link2> |
||
4097 | </user-agent> |
||
4098 | <user-agent> |
||
4099 | <ID>id_a_f_070606_2</ID> |
||
4100 | <String>EMPAS_ROBOT</String> |
||
4101 | <Description>Empas search Korea robot (220.95.22x.xxx)</Description> |
||
4102 | <Type>R</Type> |
||
4103 | <Comment></Comment> |
||
4104 | <Link1>http://www.empas.com/</Link1> |
||
4105 | <Link2></Link2> |
||
4106 | </user-agent> |
||
4107 | <user-agent> |
||
4108 | <ID>id_a_f_280208_1</ID> |
||
4109 | <String>EnaBot/1.x (http://www.enaball.com/crawler.html)</String> |
||
4110 | <Description>Enabot - Enaball semantic search project crawler</Description> |
||
4111 | <Type>R</Type> |
||
4112 | <Comment></Comment> |
||
4113 | <Link1>http://www.enaball.com/crawler.html</Link1> |
||
4114 | <Link2></Link2> |
||
4115 | </user-agent> |
||
4116 | <user-agent> |
||
4117 | <ID>id_a_f_110506_4</ID> |
||
4118 | <String>endo/1.0 (Mac OS X; ppc i386; http://kula.jp/endo)</String> |
||
4119 | <Description>endo - Mac news site and blog aggregator</Description> |
||
4120 | <Type>B</Type> |
||
4121 | <Comment></Comment> |
||
4122 | <Link1>http://kula.jp/software/endo/</Link1> |
||
4123 | <Link2></Link2> |
||
4124 | </user-agent> |
||
4125 | <user-agent> |
||
4126 | <ID>id_a_f_290</ID> |
||
4127 | <String>Enfish Tracker</String> |
||
4128 | <Description>Enfish Personal search tool</Description> |
||
4129 | <Type>R</Type> |
||
4130 | <Comment></Comment> |
||
4131 | <Link1>http://www.enfish.com</Link1> |
||
4132 | <Link2></Link2> |
||
4133 | </user-agent> |
||
4134 | <user-agent> |
||
4135 | <ID>id_a_f_291</ID> |
||
4136 | <String>Enterprise_Search/1.0</String> |
||
4137 | <Description>Enterprise Search engine software (64.202.165.xxx)</Description> |
||
4138 | <Type>R</Type> |
||
4139 | <Comment> s. also - ES.NET_Crawler - InnerpriseBot</Comment> |
||
4140 | <Link1>http://www.innerprise.net</Link1> |
||
4141 | <Link2></Link2> |
||
4142 | </user-agent> |
||
4143 | <user-agent> |
||
4144 | <ID>id_a_f_292</ID> |
||
4145 | <String>Enterprise_Search/1.0.xxx</String> |
||
4146 | <Description>Enterprise Search engine software (64.202.165.xxx)</Description> |
||
4147 | <Type>R</Type> |
||
4148 | <Comment> s. also - ES.NET_Crawler - InnerpriseBot</Comment> |
||
4149 | <Link1>http://www.innerprise.net</Link1> |
||
4150 | <Link2></Link2> |
||
4151 | </user-agent> |
||
4152 | <user-agent> |
||
4153 | <ID>id_a_f_293</ID> |
||
4154 | <String>Enterprise_Search/1.00.xxx;MSSQL (http://www.innerprise.net/es-spider.asp)</String> |
||
4155 | <Description>Enterprise Search engine software (64.202.165.xxx)</Description> |
||
4156 | <Type>R</Type> |
||
4157 | <Comment> s. also - ES.NET_Crawler - InnerpriseBot</Comment> |
||
4158 | <Link1>http://www.innerprise.net</Link1> |
||
4159 | <Link2></Link2> |
||
4160 | </user-agent> |
||
4161 | <user-agent> |
||
4162 | <ID>id_a_f_230706_1</ID> |
||
4163 | <String>envolk/1.7 (+http://www.envolk.com/envolkspiderinfo.php)</String> |
||
4164 | <Description>Envolk Web Search robot</Description> |
||
4165 | <Type>R</Type> |
||
4166 | <Comment>70.169.191.x</Comment> |
||
4167 | <Link1>http://www.envolk.com/</Link1> |
||
4168 | <Link2></Link2> |
||
4169 | </user-agent> |
||
4170 | <user-agent> |
||
4171 | <ID>id_a_f_294</ID> |
||
4172 | <String>envolk[ITS]spider/1.6(+http://www.envolk.com/envolkspider.html)</String> |
||
4173 | <Description>Envolk Web Search robot</Description> |
||
4174 | <Type>R</Type> |
||
4175 | <Comment>70.169.191.x</Comment> |
||
4176 | <Link1>http://www.envolk.com/</Link1> |
||
4177 | <Link2></Link2> |
||
4178 | </user-agent> |
||
4179 | <user-agent> |
||
4180 | <ID>id_a_f_295</ID> |
||
4181 | <String>EroCrawler</String> |
||
4182 | <Description>EroCrawler adult search robot</Description> |
||
4183 | <Type>R</Type> |
||
4184 | <Comment></Comment> |
||
4185 | <Link1>http://www.erocrawler.com</Link1> |
||
4186 | <Link2></Link2> |
||
4187 | </user-agent> |
||
4188 | <user-agent> |
||
4189 | <ID>id_a_f_296</ID> |
||
4190 | <String>ES.NET_Crawler/2.0 (http://search.innerprise.net/)</String> |
||
4191 | <Description>Enterprise Search engine software (64.202.165.xxx)</Description> |
||
4192 | <Type>R</Type> |
||
4193 | <Comment>s. also - Enterprise_Search - InnerpriseBot</Comment> |
||
4194 | <Link1>http://search.innerprise.net</Link1> |
||
4195 | <Link2></Link2> |
||
4196 | </user-agent> |
||
4197 | <user-agent> |
||
4198 | <ID>id_a_f_297</ID> |
||
4199 | <String>eseek-larbin_2.6.2 (crawler@exactseek.com)</String> |
||
4200 | <Description>ExactSEEK (Jayde Online) robot</Description> |
||
4201 | <Type>R</Type> |
||
4202 | <Comment>see also ExactSeek Crawler / eseek-larbin / exactseek.com</Comment> |
||
4203 | <Link1>http://www.exactseek.com</Link1> |
||
4204 | <Link2></Link2> |
||
4205 | </user-agent> |
||
4206 | <user-agent> |
||
4207 | <ID>id_a_f_298</ID> |
||
4208 | <String>ESISmartSpider</String> |
||
4209 | <Description>ESI Smart-Spider toolkit</Description> |
||
4210 | <Type>R</Type> |
||
4211 | <Comment></Comment> |
||
4212 | <Link1>http://www.smart-spider.com/</Link1> |
||
4213 | <Link2></Link2> |
||
4214 | </user-agent> |
||
4215 | <user-agent> |
||
4216 | <ID>id_a_f_299</ID> |
||
4217 | <String>eStyleSearch 4 (compatible; MSIE 6.0; Windows NT 5.0)</String> |
||
4218 | <Description>e-Style ISP search (Russia) robot (217.174.103.xxx)</Description> |
||
4219 | <Type>R</Type> |
||
4220 | <Comment></Comment> |
||
4221 | <Link1>http://www.e-styleisp.ru/</Link1> |
||
4222 | <Link2></Link2> |
||
4223 | </user-agent> |
||
4224 | <user-agent> |
||
4225 | <ID>id_a_f_300</ID> |
||
4226 | <String>ESurf15a 15</String> |
||
4227 | <Description>Some site scanning tool via diff. IPs</Description> |
||
4228 | <Type>S</Type> |
||
4229 | <Comment>s. also DSurf - PBrowse ...</Comment> |
||
4230 | <Link1></Link1> |
||
4231 | <Link2></Link2> |
||
4232 | </user-agent> |
||
4233 | <user-agent> |
||
4234 | <ID>id_a_f_301</ID> |
||
4235 | <String>EuripBot/0.x (+http://www.eurip.com) GetFile</String> |
||
4236 | <Description>Eurip.com - European Internet Portal robot</Description> |
||
4237 | <Type>R</Type> |
||
4238 | <Comment></Comment> |
||
4239 | <Link1>http://www.eurip.com</Link1> |
||
4240 | <Link2></Link2> |
||
4241 | </user-agent> |
||
4242 | <user-agent> |
||
4243 | <ID>id_a_f_302</ID> |
||
4244 | <String>EuripBot/0.x (+http://www.eurip.com) GetRobots</String> |
||
4245 | <Description>Eurip.com - European Internet Portal robot</Description> |
||
4246 | <Type>R</Type> |
||
4247 | <Comment></Comment> |
||
4248 | <Link1>http://www.eurip.com</Link1> |
||
4249 | <Link2></Link2> |
||
4250 | </user-agent> |
||
4251 | <user-agent> |
||
4252 | <ID>id_a_f_303</ID> |
||
4253 | <String>EuripBot/0.x (+http://www.eurip.com) PreCheck</String> |
||
4254 | <Description>Eurip.com - European Internet Portal robot</Description> |
||
4255 | <Type>R</Type> |
||
4256 | <Comment></Comment> |
||
4257 | <Link1>http://www.eurip.com</Link1> |
||
4258 | <Link2></Link2> |
||
4259 | </user-agent> |
||
4260 | <user-agent> |
||
4261 | <ID>id_a_f_220508_3</ID> |
||
4262 | <String>Eurobot/1.0 (http://www.ayell.eu)</String> |
||
4263 | <Description>Ayell Euronet business directory robot</Description> |
||
4264 | <Type>R</Type> |
||
4265 | <Comment></Comment> |
||
4266 | <Link1>http://www.ayell.eu/</Link1> |
||
4267 | <Link2></Link2> |
||
4268 | </user-agent> |
||
4269 | <user-agent> |
||
4270 | <ID>id_a_f_030206_4</ID> |
||
4271 | <String>EvaalSE - bot@evaal.com</String> |
||
4272 | <Description>Evaal Search Engine robot</Description> |
||
4273 | <Type>R</Type> |
||
4274 | <Comment>based on Nutch</Comment> |
||
4275 | <Link1>http://www.evaal.com/</Link1> |
||
4276 | <Link2>http://search.evaal.com/en/about.html</Link2> |
||
4277 | </user-agent> |
||
4278 | <user-agent> |
||
4279 | <ID>id_a_f_304</ID> |
||
4280 | <String>eventax/1.3 (eventax; http://www.eventax.de/; info@eventax.de)</String> |
||
4281 | <Description>Eventax event search (Germany)</Description> |
||
4282 | <Type>R</Type> |
||
4283 | <Comment></Comment> |
||
4284 | <Link1>http://www.eventax.de</Link1> |
||
4285 | <Link2></Link2> |
||
4286 | </user-agent> |
||
4287 | <user-agent> |
||
4288 | <ID>id_a_f_291205_1</ID> |
||
4289 | <String>Everest-Vulcan Inc./0.1 (R&D project; host=e-1-24; http://everest.vulcan.com/crawlerhelp)</String> |
||
4290 | <Description>Vulcan Inc. Everest crawler (in development)</Description> |
||
4291 | <Type>R</Type> |
||
4292 | <Comment></Comment> |
||
4293 | <Link1>http://www.vulcan.com/</Link1> |
||
4294 | <Link2></Link2> |
||
4295 | </user-agent> |
||
4296 | <user-agent> |
||
4297 | <ID>id_a_f_305</ID> |
||
4298 | <String>Everest-Vulcan Inc./0.1 (R&D project; http://everest.vulcan.com/crawlerhelp)</String> |
||
4299 | <Description>Vulcan Inc. Everest crawler (in development)</Description> |
||
4300 | <Type>R</Type> |
||
4301 | <Comment></Comment> |
||
4302 | <Link1>http://www.vulcan.com/</Link1> |
||
4303 | <Link2></Link2> |
||
4304 | </user-agent> |
||
4305 | <user-agent> |
||
4306 | <ID>id_a_f_050406_2</ID> |
||
4307 | <String>Exabot-Images/1.0</String> |
||
4308 | <Description>Exalead Websearch image crawler (193.47.80.xx)</Description> |
||
4309 | <Type>R</Type> |
||
4310 | <Comment>Exabot-Images only requests robots.txt - image crawling under UA NG/4.0.1229</Comment> |
||
4311 | <Link1>http://www.exalead.com/search</Link1> |
||
4312 | <Link2></Link2> |
||
4313 | </user-agent> |
||
4314 | <user-agent> |
||
4315 | <ID>id_a_f_211206_1</ID> |
||
4316 | <String>Exabot-Test/1.0</String> |
||
4317 | <Description>Exalead (France) search robot (193.47.80.xx)</Description> |
||
4318 | <Type>R</Type> |
||
4319 | <Comment>s. Harvest-NG/1.0.2 and Exalead NG...</Comment> |
||
4320 | <Link1>http://www.exabot.com/</Link1> |
||
4321 | <Link2></Link2> |
||
4322 | </user-agent> |
||
4323 | <user-agent> |
||
4324 | <ID>id_a_f_190106_1</ID> |
||
4325 | <String>Exabot/2.0</String> |
||
4326 | <Description>Exalead (France) search robot (193.47.80.xx)</Description> |
||
4327 | <Type>R</Type> |
||
4328 | <Comment>s. Harvest-NG/1.0.2 and Exalead NG...</Comment> |
||
4329 | <Link1>http://www.exabot.com/</Link1> |
||
4330 | <Link2></Link2> |
||
4331 | </user-agent> |
||
4332 | <user-agent> |
||
4333 | <ID>id_a_f_211206_2</ID> |
||
4334 | <String>Exabot/3.0</String> |
||
4335 | <Description>Exalead (France) search robot (193.47.80.xx)</Description> |
||
4336 | <Type>R</Type> |
||
4337 | <Comment>s. Harvest-NG/1.0.2 and Exalead NG...</Comment> |
||
4338 | <Link1>http://www.exabot.com/</Link1> |
||
4339 | <Link2></Link2> |
||
4340 | </user-agent> |
||
4341 | <user-agent> |
||
4342 | <ID>id_a_f_306</ID> |
||
4343 | <String>ExactSearch</String> |
||
4344 | <Description>eXact Search Bar for IE</Description> |
||
4345 | <Type>B</Type> |
||
4346 | <Comment></Comment> |
||
4347 | <Link1>http://www.exactsearchbar.com/exact04</Link1> |
||
4348 | <Link2></Link2> |
||
4349 | </user-agent> |
||
4350 | <user-agent> |
||
4351 | <ID>id_a_f_307</ID> |
||
4352 | <String>ExactSeek Crawler/0.1</String> |
||
4353 | <Description>ExactSEEK (Jayde Online) robot</Description> |
||
4354 | <Type>R</Type> |
||
4355 | <Comment>see also eseek-larbin / exactseek.com</Comment> |
||
4356 | <Link1>http://www.exactseek.com</Link1> |
||
4357 | <Link2></Link2> |
||
4358 | </user-agent> |
||
4359 | <user-agent> |
||
4360 | <ID>id_a_f_308</ID> |
||
4361 | <String>exactseek-crawler-2.63 (crawler@exactseek.com)</String> |
||
4362 | <Description>ExactSEEK (Jayde Online) robot</Description> |
||
4363 | <Type>R</Type> |
||
4364 | <Comment>see also eseek-larbin / exactseek.com</Comment> |
||
4365 | <Link1>http://www.exactseek.com</Link1> |
||
4366 | <Link2></Link2> |
||
4367 | </user-agent> |
||
4368 | <user-agent> |
||
4369 | <ID>id_a_f_309</ID> |
||
4370 | <String>exactseek-pagereaper-2.63 (crawler@exactseek.com)</String> |
||
4371 | <Description>ExactSEEK (Jayde Online) robot</Description> |
||
4372 | <Type>R</Type> |
||
4373 | <Comment>see also eseek-larbin / exactseek.com</Comment> |
||
4374 | <Link1>http://www.exactseek.com</Link1> |
||
4375 | <Link2></Link2> |
||
4376 | </user-agent> |
||
4377 | <user-agent> |
||
4378 | <ID>id_a_f_050606_2</ID> |
||
4379 | <String>exactseek.com</String> |
||
4380 | <Description>ExactSEEK (Jayde Online) robot (69.9.181.1xx)</Description> |
||
4381 | <Type>R</Type> |
||
4382 | <Comment>see also eseek-larbin</Comment> |
||
4383 | <Link1>http://www.exactseek.com</Link1> |
||
4384 | <Link2></Link2> |
||
4385 | </user-agent> |
||
4386 | <user-agent> |
||
4387 | <ID>id_a_f_310</ID> |
||
4388 | <String>Exalead NG/MimeLive Client (convert/http/0.120)</String> |
||
4389 | <Description>Exalead (France) search robot (193.47.80.xx)</Description> |
||
4390 | <Type>R</Type> |
||
4391 | <Comment>s. Harvest-NG/1.0.2 and NG/1.0</Comment> |
||
4392 | <Link1>http://www.exabot.com</Link1> |
||
4393 | <Link2></Link2> |
||
4394 | </user-agent> |
||
4395 | <user-agent> |
||
4396 | <ID>id_a_f_311</ID> |
||
4397 | <String>Excalibur Internet Spider V6.5.4</String> |
||
4398 | <Description>Excalibur (now Convera) spider software</Description> |
||
4399 | <Type>R</Type> |
||
4400 | <Comment></Comment> |
||
4401 | <Link1>http://www.excalib.com</Link1> |
||
4402 | <Link2></Link2> |
||
4403 | </user-agent> |
||
4404 | <user-agent> |
||
4405 | <ID>id_a_f_191206_1</ID> |
||
4406 | <String>Execrawl/1.0 (Execrawl; http://www.execrawl.com/; bot@execrawl.com)</String> |
||
4407 | <Description>Execrawl software search using nutch</Description> |
||
4408 | <Type>R</Type> |
||
4409 | <Comment>72.36.179.1xx</Comment> |
||
4410 | <Link1>http://www.execrawl.com/</Link1> |
||
4411 | <Link2></Link2> |
||
4412 | </user-agent> |
||
4413 | <user-agent> |
||
4414 | <ID>id_a_f_060608_1</ID> |
||
4415 | <String>exooba crawler/exooba crawler (crawler for exooba.com; http://www.exooba.com/; info at exooba dot com)</String> |
||
4416 | <Description>exooba crawler for exooba search pre-alpha development</Description> |
||
4417 | <Type>R</Type> |
||
4418 | <Comment>216.195.184.xx</Comment> |
||
4419 | <Link1>http://www.exooba.com/</Link1> |
||
4420 | <Link2></Link2> |
||
4421 | </user-agent> |
||
4422 | <user-agent> |
||
4423 | <ID>id_a_f_060608_2</ID> |
||
4424 | <String>exooba/exooba crawler (exooba; exooba)</String> |
||
4425 | <Description>exooba crawler for exooba search pre-alpha development</Description> |
||
4426 | <Type>R</Type> |
||
4427 | <Comment>216.195.184.xx</Comment> |
||
4428 | <Link1>http://www.exooba.com/</Link1> |
||
4429 | <Link2></Link2> |
||
4430 | </user-agent> |
||
4431 | <user-agent> |
||
4432 | <ID>id_a_f_312</ID> |
||
4433 | <String>ExperimentalHenrytheMiragoRobot</String> |
||
4434 | <Description>Mirago UK Robot</Description> |
||
4435 | <Type>R</Type> |
||
4436 | <Comment></Comment> |
||
4437 | <Link1>http://www.mirago.co.uk</Link1> |
||
4438 | <Link2></Link2> |
||
4439 | </user-agent> |
||
4440 | <user-agent> |
||
4441 | <ID>id_a_f_313</ID> |
||
4442 | <String>Expired Domain Sleuth</String> |
||
4443 | <Description>Expired Domain Sleuth domain name tool</Description> |
||
4444 | <Type>R C</Type> |
||
4445 | <Comment></Comment> |
||
4446 | <Link1>http://expireddomainsleuth.com/</Link1> |
||
4447 | <Link2></Link2> |
||
4448 | </user-agent> |
||
4449 | <user-agent> |
||
4450 | <ID>id_a_f_314</ID> |
||
4451 | <String>Express WebPictures (www.express-soft.com)</String> |
||
4452 | <Description>Express Web Pictures image browser</Description> |
||
4453 | <Type>B D</Type> |
||
4454 | <Comment></Comment> |
||
4455 | <Link1>http://www.express-soft.com/</Link1> |
||
4456 | <Link2></Link2> |
||
4457 | </user-agent> |
||
4458 | <user-agent> |
||
4459 | <ID>id_a_f_315</ID> |
||
4460 | <String>ExtractorPro</String> |
||
4461 | <Description>Extractor Pro e-mail collector</Description> |
||
4462 | <Type>S</Type> |
||
4463 | <Comment></Comment> |
||
4464 | <Link1>http://www.extractorpro.com</Link1> |
||
4465 | <Link2></Link2> |
||
4466 | </user-agent> |
||
4467 | <user-agent> |
||
4468 | <ID>id_a_f_170106_1</ID> |
||
4469 | <String>Extreme Picture Finder</String> |
||
4470 | <Description>Exisoftware image grabber and downloading tool</Description> |
||
4471 | <Type>D</Type> |
||
4472 | <Comment></Comment> |
||
4473 | <Link1>http://www.exisoftware.com/picture_finder/</Link1> |
||
4474 | <Link2></Link2> |
||
4475 | </user-agent> |
||
4476 | <user-agent> |
||
4477 | <ID>id_a_f_316</ID> |
||
4478 | <String>EyeCatcher (Download-tipp.de)/1.0</String> |
||
4479 | <Description>Download-Tipp Germany robot</Description> |
||
4480 | <Type>R</Type> |
||
4481 | <Comment></Comment> |
||
4482 | <Link1>http://download-tipp.de</Link1> |
||
4483 | <Link2></Link2> |
||
4484 | </user-agent> |
||
4485 | <user-agent> |
||
4486 | <ID>id_a_f_091006_1</ID> |
||
4487 | <String>Factbot 1.09 (see http://www.factbites.com/webmasters.php)</String> |
||
4488 | <Description>Factbites search robot</Description> |
||
4489 | <Type>R</Type> |
||
4490 | <Comment>70.86.159.1xx</Comment> |
||
4491 | <Link1>http://www.factbites.com/</Link1> |
||
4492 | <Link2></Link2> |
||
4493 | </user-agent> |
||
4494 | <user-agent> |
||
4495 | <ID>id_a_f_220906_1</ID> |
||
4496 | <String>factbot : http://www.factbites.com/robots</String> |
||
4497 | <Description>Factbites search robot</Description> |
||
4498 | <Type>R</Type> |
||
4499 | <Comment>70.86.159.1xx</Comment> |
||
4500 | <Link1>http://www.factbites.com/</Link1> |
||
4501 | <Link2></Link2> |
||
4502 | </user-agent> |
||
4503 | <user-agent> |
||
4504 | <ID>id_a_f_221006_1</ID> |
||
4505 | <String>FaEdit/2.0.x</String> |
||
4506 | <Description>FaEdit Professional - Japanese bookmark manager</Description> |
||
4507 | <Type>C</Type> |
||
4508 | <Comment></Comment> |
||
4509 | <Link1>https://sw.vector.co.jp/swreg/step1.reserve?srno=SR040433&site=y</Link1> |
||
4510 | <Link2></Link2> |
||
4511 | </user-agent> |
||
4512 | <user-agent> |
||
4513 | <ID>id_a_f_317</ID> |
||
4514 | <String>FairAd Client</String> |
||
4515 | <Description>FairAd user</Description> |
||
4516 | <Type>P</Type> |
||
4517 | <Comment></Comment> |
||
4518 | <Link1>http://www.fairad.de</Link1> |
||
4519 | <Link2></Link2> |
||
4520 | </user-agent> |
||
4521 | <user-agent> |
||
4522 | <ID>id_a_f_051206_1</ID> |
||
4523 | <String>FANGCrawl/0.01</String> |
||
4524 | <Description>Safe-t.net web filtering service</Description> |
||
4525 | <Type>P</Type> |
||
4526 | <Comment>63.167.160.1xx</Comment> |
||
4527 | <Link1>http://www.safe-t.net/</Link1> |
||
4528 | <Link2></Link2> |
||
4529 | </user-agent> |
||
4530 | <user-agent> |
||
4531 | <ID>id_a_f_210206_1</ID> |
||
4532 | <String>FARK.com link verifier</String> |
||
4533 | <Description>Drew Curtis' FARK.com link checking</Description> |
||
4534 | <Type>C</Type> |
||
4535 | <Comment></Comment> |
||
4536 | <Link1>http://www.fark.com/</Link1> |
||
4537 | <Link2></Link2> |
||
4538 | </user-agent> |
||
4539 | <user-agent> |
||
4540 | <ID>id_a_f_318</ID> |
||
4541 | <String>Fast Crawler Gold Edition</String> |
||
4542 | <Description>Fast/Alltheweb crawler (66.151.181.xx)</Description> |
||
4543 | <Type>R</Type> |
||
4544 | <Comment></Comment> |
||
4545 | <Link1>http://www.alltheweb.com</Link1> |
||
4546 | <Link2></Link2> |
||
4547 | </user-agent> |
||
4548 | <user-agent> |
||
4549 | <ID>id_a_f_319</ID> |
||
4550 | <String>FAST Enterprise Crawler 6 (Experimental)</String> |
||
4551 | <Description>Fast/Alltheweb crawler (66.151.181.xx)</Description> |
||
4552 | <Type>R</Type> |
||
4553 | <Comment></Comment> |
||
4554 | <Link1>http://www.alltheweb.com</Link1> |
||
4555 | <Link2></Link2> |
||
4556 | </user-agent> |
||
4557 | <user-agent> |
||
4558 | <ID>id_a_f_040206_1</ID> |
||
4559 | <String>FAST Enterprise Crawler 6 / Scirus scirus-crawler@fast.no; http://www.scirus.com/srsapp/contactus/</String> |
||
4560 | <Description>Fast Enterprise Crawler (66.151.181.xx) for Scirus scienctific information search</Description> |
||
4561 | <Type>R</Type> |
||
4562 | <Comment></Comment> |
||
4563 | <Link1>http://www.scirus.com/srsapp/</Link1> |
||
4564 | <Link2>http://www.alltheweb.com</Link2> |
||
4565 | </user-agent> |
||
4566 | <user-agent> |
||
4567 | <ID>id_a_f_320</ID> |
||
4568 | <String>FAST Enterprise Crawler 6 used by Cobra Development (admin@fastsearch.com)</String> |
||
4569 | <Description>Fast/Alltheweb crawler (66.151.181.xx)</Description> |
||
4570 | <Type>R</Type> |
||
4571 | <Comment></Comment> |
||
4572 | <Link1>http://www.alltheweb.com</Link1> |
||
4573 | <Link2></Link2> |
||
4574 | </user-agent> |
||
4575 | <user-agent> |
||
4576 | <ID>id_a_f_070507_1</ID> |
||
4577 | <String>FAST Enterprise Crawler 6 used by Comperio AS (sts@comperio.no)</String> |
||
4578 | <Description>Comperio Web Miner based on Fast ESP</Description> |
||
4579 | <Type>R</Type> |
||
4580 | <Comment></Comment> |
||
4581 | <Link1>http://www.comperio.no/index.php?option=com_content&task=blogcategory&id=7&Itemid=27</Link1> |
||
4582 | <Link2></Link2> |
||
4583 | </user-agent> |
||
4584 | <user-agent> |
||
4585 | <ID>id_a_f_321</ID> |
||
4586 | <String>FAST Enterprise Crawler 6 used by FAST (FAST)</String> |
||
4587 | <Description>Fast/Alltheweb crawler (66.151.181.xx)</Description> |
||
4588 | <Type>R</Type> |
||
4589 | <Comment></Comment> |
||
4590 | <Link1>http://www.alltheweb.com</Link1> |
||
4591 | <Link2></Link2> |
||
4592 | </user-agent> |
||
4593 | <user-agent> |
||
4594 | <ID>id_a_f_161106_1</ID> |
||
4595 | <String>FAST Enterprise Crawler 6 used by Pages Jaunes (pvincent@pagesjaunes.fr)</String> |
||
4596 | <Description>Pages Jaunes business search (France) robot using Fast Enterprise Crawler</Description> |
||
4597 | <Type>R</Type> |
||
4598 | <Comment>193.252.242.xx</Comment> |
||
4599 | <Link1>http://www.pagesjaunes.fr/</Link1> |
||
4600 | <Link2></Link2> |
||
4601 | </user-agent> |
||
4602 | <user-agent> |
||
4603 | <ID>id_a_f_322</ID> |
||
4604 | <String>FAST Enterprise Crawler 6 used by Sensis.com.au Web Crawler (search_comments\at\sensis\dot\com\dot\au)</String> |
||
4605 | <Description>Fast/Alltheweb crawler for Sensis.com.au Australian search (66.151.181.xx)</Description> |
||
4606 | <Type>R</Type> |
||
4607 | <Comment></Comment> |
||
4608 | <Link1>http://www.sensis.com.au/</Link1> |
||
4609 | <Link2>http://www.alltheweb.com</Link2> |
||
4610 | </user-agent> |
||
4611 | <user-agent> |
||
4612 | <ID>id_a_f_251007_2</ID> |
||
4613 | <String>FAST Enterprise Crawler 6 used by Singapore Press Holdings (crawler@sphsearch.sg)</String> |
||
4614 | <Description>SPH Search - Singapore related search using Fast crawler</Description> |
||
4615 | <Type>R</Type> |
||
4616 | <Comment>202.176.220.xx</Comment> |
||
4617 | <Link1>http://www.sphsearch.sg/</Link1> |
||
4618 | <Link2></Link2> |
||
4619 | </user-agent> |
||
4620 | <user-agent> |
||
4621 | <ID>id_a_f_280606_2</ID> |
||
4622 | <String>FAST Enterprise Crawler 6 used by WWU (wardi@uni-muenster.de)</String> |
||
4623 | <Description>FAST Enterprise Crawler used by WWU (University of Muenster - Germany)</Description> |
||
4624 | <Type>C</Type> |
||
4625 | <Comment>128.176.188.2xx</Comment> |
||
4626 | <Link1>http://www.uni-muenster.de/en/index.html</Link1> |
||
4627 | <Link2>http://www.alltheweb.com</Link2> |
||
4628 | </user-agent> |
||
4629 | <user-agent> |
||
4630 | <ID>id_a_f_323</ID> |
||
4631 | <String>FAST Enterprise Crawler/6 (www.fastsearch.com)</String> |
||
4632 | <Description>Fast/Alltheweb crawler (66.151.181.xx)</Description> |
||
4633 | <Type>R</Type> |
||
4634 | <Comment></Comment> |
||
4635 | <Link1>http://www.alltheweb.com</Link1> |
||
4636 | <Link2></Link2> |
||
4637 | </user-agent> |
||
4638 | <user-agent> |
||
4639 | <ID>id_a_f_324</ID> |
||
4640 | <String>FAST Enterprise Crawler/6.4 (helpdesk at fast.no)</String> |
||
4641 | <Description>Fast/Alltheweb crawler (66.151.181.xx)</Description> |
||
4642 | <Type>R</Type> |
||
4643 | <Comment></Comment> |
||
4644 | <Link1>http://www.alltheweb.com</Link1> |
||
4645 | <Link2></Link2> |
||
4646 | </user-agent> |
||
4647 | <user-agent> |
||
4648 | <ID>id_a_f_325</ID> |
||
4649 | <String>FAST FirstPage retriever (compatible; MSIE 5.5; Mozilla/4.0)</String> |
||
4650 | <Description>Fast/Alltheweb crawler (66.151.181.xx)</Description> |
||
4651 | <Type>R</Type> |
||
4652 | <Comment></Comment> |
||
4653 | <Link1>http://www.alltheweb.com</Link1> |
||
4654 | <Link2></Link2> |
||
4655 | </user-agent> |
||
4656 | <user-agent> |
||
4657 | <ID>id_a_f_326</ID> |
||
4658 | <String>FAST MetaWeb Crawler (helpdesk at fastsearch dot com)</String> |
||
4659 | <Description>Fast/Alltheweb crawler (66.151.181.xx)</Description> |
||
4660 | <Type>R</Type> |
||
4661 | <Comment></Comment> |
||
4662 | <Link1>http://www.alltheweb.com</Link1> |
||
4663 | <Link2></Link2> |
||
4664 | </user-agent> |
||
4665 | <user-agent> |
||
4666 | <ID>id_a_f_327</ID> |
||
4667 | <String>Fast PartnerSite Crawler</String> |
||
4668 | <Description>Fast/Alltheweb crawler (66.151.181.xx)</Description> |
||
4669 | <Type>R</Type> |
||
4670 | <Comment></Comment> |
||
4671 | <Link1>http://www.alltheweb.com</Link1> |
||
4672 | <Link2></Link2> |
||
4673 | </user-agent> |
||
4674 | <user-agent> |
||
4675 | <ID>id_a_f_328</ID> |
||
4676 | <String>FAST-WebCrawler/2.2.10 (Multimedia Search) (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)</String> |
||
4677 | <Description>Fast/Alltheweb multimedia crawler</Description> |
||
4678 | <Type>R</Type> |
||
4679 | <Comment>see also Yahoo-MMCrawler/3.x</Comment> |
||
4680 | <Link1>http://www.alltheweb.com</Link1> |
||
4681 | <Link2></Link2> |
||
4682 | </user-agent> |
||
4683 | <user-agent> |
||
4684 | <ID>id_a_f_329</ID> |
||
4685 | <String>FAST-WebCrawler/2.2.6 (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)</String> |
||
4686 | <Description>Fast/Alltheweb crawler</Description> |
||
4687 | <Type>R</Type> |
||
4688 | <Comment></Comment> |
||
4689 | <Link1>http://www.alltheweb.com</Link1> |
||
4690 | <Link2></Link2> |
||
4691 | </user-agent> |
||
4692 | <user-agent> |
||
4693 | <ID>id_a_f_330</ID> |
||
4694 | <String>FAST-WebCrawler/2.2.7 (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)http://www.fast.no</String> |
||
4695 | <Description>Fast/Alltheweb crawler</Description> |
||
4696 | <Type>R</Type> |
||
4697 | <Comment></Comment> |
||
4698 | <Link1>http://www.alltheweb.com</Link1> |
||
4699 | <Link2></Link2> |
||
4700 | </user-agent> |
||
4701 | <user-agent> |
||
4702 | <ID>id_a_f_331</ID> |
||
4703 | <String>FAST-WebCrawler/2.2.8 (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)http://www.fast.no</String> |
||
4704 | <Description>Fast/Alltheweb crawler</Description> |
||
4705 | <Type>R</Type> |
||
4706 | <Comment></Comment> |
||
4707 | <Link1>http://www.alltheweb.com</Link1> |
||
4708 | <Link2></Link2> |
||
4709 | </user-agent> |
||
4710 | <user-agent> |
||
4711 | <ID>id_a_f_332</ID> |
||
4712 | <String>FAST-WebCrawler/3.2 test</String> |
||
4713 | <Description>Fast/Alltheweb crawler</Description> |
||
4714 | <Type>R</Type> |
||
4715 | <Comment></Comment> |
||
4716 | <Link1>http://www.alltheweb.com</Link1> |
||
4717 | <Link2></Link2> |
||
4718 | </user-agent> |
||
4719 | <user-agent> |
||
4720 | <ID>id_a_f_333</ID> |
||
4721 | <String>FAST-WebCrawler/3.3 (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)</String> |
||
4722 | <Description>Fast/Alltheweb crawler</Description> |
||
4723 | <Type>R</Type> |
||
4724 | <Comment></Comment> |
||
4725 | <Link1>http://www.alltheweb.com</Link1> |
||
4726 | <Link2></Link2> |
||
4727 | </user-agent> |
||
4728 | <user-agent> |
||
4729 | <ID>id_a_f_334</ID> |
||
4730 | <String>FAST-WebCrawler/3.4/Nirvana (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)</String> |
||
4731 | <Description>Fast/Alltheweb crawler</Description> |
||
4732 | <Type>R</Type> |
||
4733 | <Comment></Comment> |
||
4734 | <Link1>http://www.alltheweb.com</Link1> |
||
4735 | <Link2></Link2> |
||
4736 | </user-agent> |
||
4737 | <user-agent> |
||
4738 | <ID>id_a_f_335</ID> |
||
4739 | <String>FAST-WebCrawler/3.4/PartnerSite (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)</String> |
||
4740 | <Description>Fast/Alltheweb crawler</Description> |
||
4741 | <Type>R</Type> |
||
4742 | <Comment></Comment> |
||
4743 | <Link1>http://www.alltheweb.com</Link1> |
||
4744 | <Link2></Link2> |
||
4745 | </user-agent> |
||
4746 | <user-agent> |
||
4747 | <ID>id_a_f_336</ID> |
||
4748 | <String>FAST-WebCrawler/3.5 (atw-crawler at fast dot no; http://fast.no/support.php?c=faqs/crawler)</String> |
||
4749 | <Description>Fast/Alltheweb crawler</Description> |
||
4750 | <Type>R</Type> |
||
4751 | <Comment></Comment> |
||
4752 | <Link1>http://www.alltheweb.com</Link1> |
||
4753 | <Link2></Link2> |
||
4754 | </user-agent> |
||
4755 | <user-agent> |
||
4756 | <ID>id_a_f_337</ID> |
||
4757 | <String>FAST-WebCrawler/3.6 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)</String> |
||
4758 | <Description>Fast/Alltheweb crawler</Description> |
||
4759 | <Type>R</Type> |
||
4760 | <Comment></Comment> |
||
4761 | <Link1>http://www.alltheweb.com</Link1> |
||
4762 | <Link2></Link2> |
||
4763 | </user-agent> |
||
4764 | <user-agent> |
||
4765 | <ID>id_a_f_338</ID> |
||
4766 | <String>FAST-WebCrawler/3.6/FirstPage (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)</String> |
||
4767 | <Description>Fast/Alltheweb crawler</Description> |
||
4768 | <Type>R</Type> |
||
4769 | <Comment></Comment> |
||
4770 | <Link1>http://www.alltheweb.com</Link1> |
||
4771 | <Link2></Link2> |
||
4772 | </user-agent> |
||
4773 | <user-agent> |
||
4774 | <ID>id_a_f_339</ID> |
||
4775 | <String>FAST-WebCrawler/3.7 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)</String> |
||
4776 | <Description>Fast/Alltheweb crawler</Description> |
||
4777 | <Type>R</Type> |
||
4778 | <Comment></Comment> |
||
4779 | <Link1>http://www.alltheweb.com</Link1> |
||
4780 | <Link2></Link2> |
||
4781 | </user-agent> |
||
4782 | <user-agent> |
||
4783 | <ID>id_a_f_340</ID> |
||
4784 | <String>FAST-WebCrawler/3.7/FirstPage (atw-crawler at fast dot no;http://fast.no/support/crawler.asp)</String> |
||
4785 | <Description>Fast/Alltheweb crawler</Description> |
||
4786 | <Type>R</Type> |
||
4787 | <Comment></Comment> |
||
4788 | <Link1>http://www.alltheweb.com</Link1> |
||
4789 | <Link2></Link2> |
||
4790 | </user-agent> |
||
4791 | <user-agent> |
||
4792 | <ID>id_a_f_341</ID> |
||
4793 | <String>FAST-WebCrawler/3.8 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)</String> |
||
4794 | <Description>Fast/Alltheweb crawler</Description> |
||
4795 | <Type>R</Type> |
||
4796 | <Comment></Comment> |
||
4797 | <Link1>http://www.alltheweb.com</Link1> |
||
4798 | <Link2></Link2> |
||
4799 | </user-agent> |
||
4800 | <user-agent> |
||
4801 | <ID>id_a_f_342</ID> |
||
4802 | <String>FAST-WebCrawler/3.8/Fresh (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)</String> |
||
4803 | <Description>Fast/Alltheweb crawler</Description> |
||
4804 | <Type>R</Type> |
||
4805 | <Comment></Comment> |
||
4806 | <Link1>http://www.alltheweb.com</Link1> |
||
4807 | <Link2></Link2> |
||
4808 | </user-agent> |
||
4809 | <user-agent> |
||
4810 | <ID>id_a_f_343</ID> |
||
4811 | <String>FAST-WebCrawler/3.x Multimedia</String> |
||
4812 | <Description>Fast/Alltheweb multimedia crawler</Description> |
||
4813 | <Type>R</Type> |
||
4814 | <Comment>see also Yahoo-MMCrawler/3.x</Comment> |
||
4815 | <Link1>http://www.alltheweb.com</Link1> |
||
4816 | <Link2></Link2> |
||
4817 | </user-agent> |
||
4818 | <user-agent> |
||
4819 | <ID>id_a_f_344</ID> |
||
4820 | <String>FAST-WebCrawler/3.x Multimedia (mm dash crawler at fast dot no)</String> |
||
4821 | <Description>Fast/Alltheweb multimedia crawler</Description> |
||
4822 | <Type>R</Type> |
||
4823 | <Comment>see also Yahoo-MMCrawler/3.x</Comment> |
||
4824 | <Link1>http://www.alltheweb.com</Link1> |
||
4825 | <Link2></Link2> |
||
4826 | </user-agent> |
||
4827 | <user-agent> |
||
4828 | <ID>id_a_f_121205_2</ID> |
||
4829 | <String>fastbot crawler beta 2.0 (+http://www.fastbot.de)</String> |
||
4830 | <Description>Fastbot search Germany crawler (80.252.104.1xx)</Description> |
||
4831 | <Type>R</Type> |
||
4832 | <Comment></Comment> |
||
4833 | <Link1>http://www.fastbot.de/</Link1> |
||
4834 | <Link2></Link2> |
||
4835 | </user-agent> |
||
4836 | <user-agent> |
||
4837 | <ID>id_a_f_345</ID> |
||
4838 | <String>FastBug http://www.ay-up.com</String> |
||
4839 | <Description>Ay-Up geo sync search robot</Description> |
||
4840 | <Type>R</Type> |
||
4841 | <Comment></Comment> |
||
4842 | <Link1>http://www.ay-up.com</Link1> |
||
4843 | <Link2></Link2> |
||
4844 | </user-agent> |
||
4845 | <user-agent> |
||
4846 | <ID>id_a_f_346</ID> |
||
4847 | <String>FastCrawler 3.0.1 (crawler@1klik.dk)</String> |
||
4848 | <Description>Fast/Alltheweb crawler (66.151.181.xx)</Description> |
||
4849 | <Type>R</Type> |
||
4850 | <Comment></Comment> |
||
4851 | <Link1>http://www.alltheweb.com</Link1> |
||
4852 | <Link2></Link2> |
||
4853 | </user-agent> |
||
4854 | <user-agent> |
||
4855 | <ID>id_a_f_347</ID> |
||
4856 | <String>FastSearch Web Crawler for Verizon SuperPages (kevin.watters@fastsearch.com)</String> |
||
4857 | <Description>Fast/Alltheweb crawler used by SuperPages.com</Description> |
||
4858 | <Type>R</Type> |
||
4859 | <Comment></Comment> |
||
4860 | <Link1>http://www.superpages.com</Link1> |
||
4861 | <Link2>http://www.alltheweb.com</Link2> |
||
4862 | </user-agent> |
||
4863 | <user-agent> |
||
4864 | <ID>id_a_f_170408_3</ID> |
||
4865 | <String>Favcollector/2.0 (info@favcollector.com http://www.favcollector.com/)</String> |
||
4866 | <Description>Favcollector Favicon collecting robot</Description> |
||
4867 | <Type>R</Type> |
||
4868 | <Comment>66.207.217.13x</Comment> |
||
4869 | <Link1>http://www.favcollector.com/</Link1> |
||
4870 | <Link2></Link2> |
||
4871 | </user-agent> |
||
4872 | <user-agent> |
||
4873 | <ID>id_a_f_161006_1</ID> |
||
4874 | <String>FavIconizer</String> |
||
4875 | <Description>FavIconizer - IE favorites icons refreshing tool</Description> |
||
4876 | <Type>D</Type> |
||
4877 | <Comment></Comment> |
||
4878 | <Link1>http://www.codeproject.com/tools/faviconizer.asp</Link1> |
||
4879 | <Link2></Link2> |
||
4880 | </user-agent> |
||
4881 | <user-agent> |
||
4882 | <ID>id_a_f_151206_1</ID> |
||
4883 | <String>favo.eu crawler/0.6 (http://www.favo.eu)</String> |
||
4884 | <Description>favo.eu (Germany) search robot</Description> |
||
4885 | <Type>R</Type> |
||
4886 | <Comment>84.19.186.1xx</Comment> |
||
4887 | <Link1>http://www.favo.eu/</Link1> |
||
4888 | <Link2></Link2> |
||
4889 | </user-agent> |
||
4890 | <user-agent> |
||
4891 | <ID>id_a_f_348</ID> |
||
4892 | <String>FavOrg</String> |
||
4893 | <Description>ZD's FavOrg favourites managing program</Description> |
||
4894 | <Type>C</Type> |
||
4895 | <Comment></Comment> |
||
4896 | <Link1>http://www.pcmag.com/article2/0,4149,108438,00.asp</Link1> |
||
4897 | <Link2></Link2> |
||
4898 | </user-agent> |
||
4899 | <user-agent> |
||
4900 | <ID>id_a_f_260108_1</ID> |
||
4901 | <String>Favorites Checking (http://campulka.net)</String> |
||
4902 | <Description>Campulka.net Favorites checking tool</Description> |
||
4903 | <Type>C</Type> |
||
4904 | <Comment></Comment> |
||
4905 | <Link1>http://campulka.net/?dir=Utility</Link1> |
||
4906 | <Link2></Link2> |
||
4907 | </user-agent> |
||
4908 | <user-agent> |
||
4909 | <ID>id_a_f_349</ID> |
||
4910 | <String>Favorites Sweeper v.2.03</String> |
||
4911 | <Description>Favorites Sweeper bookmark checker</Description> |
||
4912 | <Type>C</Type> |
||
4913 | <Comment></Comment> |
||
4914 | <Link1>http://www.manitoolssoftware.cjb.net</Link1> |
||
4915 | <Link2></Link2> |
||
4916 | </user-agent> |
||
4917 | <user-agent> |
||
4918 | <ID>id_a_f_350</ID> |
||
4919 | <String>Faxobot/1.0</String> |
||
4920 | <Description>FaXo Search robot (69.152.89.xx)</Description> |
||
4921 | <Type>R</Type> |
||
4922 | <Comment></Comment> |
||
4923 | <Link1>http://www.faxo.com</Link1> |
||
4924 | <Link2></Link2> |
||
4925 | </user-agent> |
||
4926 | <user-agent> |
||
4927 | <ID>id_a_f_351</ID> |
||
4928 | <String>FDM 1.x</String> |
||
4929 | <Description>Free Download Manager (FDM) download accelerator </Description> |
||
4930 | <Type>D</Type> |
||
4931 | <Comment></Comment> |
||
4932 | <Link1>http://www.freedownloadmanager.org</Link1> |
||
4933 | <Link2></Link2> |
||
4934 | </user-agent> |
||
4935 | <user-agent> |
||
4936 | <ID>id_a_f_180207_1</ID> |
||
4937 | <String>FDM 2.x</String> |
||
4938 | <Description>Free Download Manager (FDM) download accelerator </Description> |
||
4939 | <Type>D</Type> |
||
4940 | <Comment></Comment> |
||
4941 | <Link1>http://www.freedownloadmanager.org</Link1> |
||
4942 | <Link2></Link2> |
||
4943 | </user-agent> |
||
4944 | <user-agent> |
||
4945 | <ID>id_a_f_352</ID> |
||
4946 | <String>Feed Seeker Bot (RSS Feed Seeker http://www.MyNewFavoriteThing.com/fsb.php)</String> |
||
4947 | <Description>RSS Feed Seeker bot (68.225.95.2xx)</Description> |
||
4948 | <Type>R</Type> |
||
4949 | <Comment></Comment> |
||
4950 | <Link1>http://www.MyNewFavoriteThing.com</Link1> |
||
4951 | <Link2></Link2> |
||
4952 | </user-agent> |
||
4953 | <user-agent> |
||
4954 | <ID>id_a_f_241206_1</ID> |
||
4955 | <String>Feed24.com</String> |
||
4956 | <Description>Feed24 news feed and blog search</Description> |
||
4957 | <Type>R</Type> |
||
4958 | <Comment>194.105.139.2xx</Comment> |
||
4959 | <Link1>http://www.feed24.com/</Link1> |
||
4960 | <Link2></Link2> |
||
4961 | </user-agent> |
||
4962 | <user-agent> |
||
4963 | <ID>id_a_f_050306_1</ID> |
||
4964 | <String>Feed::Find/0.0x</String> |
||
4965 | <Description>Feed::Find - Syndication feed (RSS/Atom) auto-discovery</Description> |
||
4966 | <Type>D</Type> |
||
4967 | <Comment></Comment> |
||
4968 | <Link1>http://search.cpan.org/~btrott/Feed-Find-0.06/lib/Feed/Find.pm</Link1> |
||
4969 | <Link2></Link2> |
||
4970 | </user-agent> |
||
4971 | <user-agent> |
||
4972 | <ID>id_a_f_250707_1</ID> |
||
4973 | <String>Feedable/0.1 (compatible; MSIE 6.0; Windows NT 5.1)</String> |
||
4974 | <Description>Feedable beta web based RSS service</Description> |
||
4975 | <Type>B</Type> |
||
4976 | <Comment>64.27.19.25x</Comment> |
||
4977 | <Link1>http://reader.feedable.com/</Link1> |
||
4978 | <Link2></Link2> |
||
4979 | </user-agent> |
||
4980 | <user-agent> |
||
4981 | <ID>id_a_f_230406_2</ID> |
||
4982 | <String>FeedChecker/0.01</String> |
||
4983 | <Description>Unknown robot from the University of Tokyo (157.82.157.xx)</Description> |
||
4984 | <Type>R</Type> |
||
4985 | <Comment>reads robots.txt</Comment> |
||
4986 | <Link1>http://www.u-tokyo.ac.jp/index_e.html</Link1> |
||
4987 | <Link2></Link2> |
||
4988 | </user-agent> |
||
4989 | <user-agent> |
||
4990 | <ID>id_a_f_140608_2</ID> |
||
4991 | <String>FeedDemon/2.7 (http://www.newsgator.com/; Microsoft Windows XP)</String> |
||
4992 | <Description>FeedDemon RSS reader</Description> |
||
4993 | <Type>B</Type> |
||
4994 | <Comment></Comment> |
||
4995 | <Link1>http://www.newsgator.com/individuals/feeddemon/</Link1> |
||
4996 | <Link2></Link2> |
||
4997 | </user-agent> |
||
4998 | <user-agent> |
||
4999 | <ID>id_a_f_160308_2</ID> |
||
5000 | <String>Feedfetcher-Google-iGoogleGadgets; (+http://www.google.com/feedfetcher.html)</String> |
||
5001 | <Description>Google news feed feetcher for iGoogle gadgets</Description> |
||
5002 | <Type>C</Type> |
||
5003 | <Comment>72.14.[1-2]xx.[X]xx</Comment> |
||
5004 | <Link1>http://www.google.com/feedfetcher.html</Link1> |
||
5005 | <Link2></Link2> |
||
5006 | </user-agent> |
||
5007 | <user-agent> |
||
5008 | <ID>id_a_f_010906_1</ID> |
||
5009 | <String>Feedfetcher-Google; (+http://www.google.com/feedfetcher.html)</String> |
||
5010 | <Description>Google Feedfetcher - RSS and Atom feed crawler</Description> |
||
5011 | <Type>R</Type> |
||
5012 | <Comment>72.14.199.x[xx]</Comment> |
||
5013 | <Link1>http://www.google.com/feedfetcher.html</Link1> |
||
5014 | <Link2></Link2> |
||
5015 | </user-agent> |
||
5016 | <user-agent> |
||
5017 | <ID>id_a_f_010307_1</ID> |
||
5018 | <String>FeedForAll rss2html.php v2</String> |
||
5019 | <Description>FeedForAll RSS feed robot</Description> |
||
5020 | <Type>C</Type> |
||
5021 | <Comment>216.92.192.1xx</Comment> |
||
5022 | <Link1>http://www.feedforall.com/</Link1> |
||
5023 | <Link2></Link2> |
||
5024 | </user-agent> |
||
5025 | <user-agent> |
||
5026 | <ID>id_a_f_010308_1</ID> |
||
5027 | <String>FeedHub FeedDiscovery/1.0 (http://www.feedhub.com)</String> |
||
5028 | <Description>FeedHub news feed personalization engine powered by mSpoke</Description> |
||
5029 | <Type>R</Type> |
||
5030 | <Comment>216.134.194.xx</Comment> |
||
5031 | <Link1>http://www.feedhub.com/</Link1> |
||
5032 | <Link2>http://www.mspoke.com/</Link2> |
||
5033 | </user-agent> |
||
5034 | <user-agent> |
||
5035 | <ID>id_a_f_060608_3</ID> |
||
5036 | <String>FeedHub MetaDataFetcher/1.0 (http://www.feedhub.com)</String> |
||
5037 | <Description>FeedHub news feed personalization engine powered by mSpoke</Description> |
||
5038 | <Type>R</Type> |
||
5039 | <Comment>216.134.194.xx</Comment> |
||
5040 | <Link1>http://www.feedhub.com/</Link1> |
||
5041 | <Link2>http://www.mspoke.com/</Link2> |
||
5042 | </user-agent> |
||
5043 | <user-agent> |
||
5044 | <ID>id_a_f_260608_3</ID> |
||
5045 | <String>Feedjit Favicon Crawler 1.0</String> |
||
5046 | <Description>Feedjit news feed service favicon crawler</Description> |
||
5047 | <Type>R</Type> |
||
5048 | <Comment>69.46.36.x</Comment> |
||
5049 | <Link1>http://feedjit.com/</Link1> |
||
5050 | <Link2></Link2> |
||
5051 | </user-agent> |
||
5052 | <user-agent> |
||
5053 | <ID>id_a_f_150108_1</ID> |
||
5054 | <String>Feedreader 3.xx (Powered by Newsbrain)</String> |
||
5055 | <Description>Newsbrain Feedreader3</Description> |
||
5056 | <Type>B</Type> |
||
5057 | <Comment></Comment> |
||
5058 | <Link1>http://www.feedreader.com/</Link1> |
||
5059 | <Link2></Link2> |
||
5060 | </user-agent> |
||
5061 | <user-agent> |
||
5062 | <ID>id_a_f_281106_3</ID> |
||
5063 | <String>Feedshow/x.0 (http://www.feedshow.com; 1 subscriber)</String> |
||
5064 | <Description>FeedShow online RSS feed reader</Description> |
||
5065 | <Type>B</Type> |
||
5066 | <Comment></Comment> |
||
5067 | <Link1>http://www.feedshow.com/</Link1> |
||
5068 | <Link2></Link2> |
||
5069 | </user-agent> |
||
5070 | <user-agent> |
||
5071 | <ID>id_a_f_051206_2</ID> |
||
5072 | <String>FeedshowOnline (http://www.feedshow.com)</String> |
||
5073 | <Description>FeedShow online RSS feed reader</Description> |
||
5074 | <Type>B</Type> |
||
5075 | <Comment></Comment> |
||
5076 | <Link1>http://www.feedshow.com/</Link1> |
||
5077 | <Link2></Link2> |
||
5078 | </user-agent> |
||
5079 | <user-agent> |
||
5080 | <ID>id_a_f_021206_1</ID> |
||
5081 | <String>Feedster Crawler/3.0; Feedster, Inc.</String> |
||
5082 | <Description>Feedster RSS feed search</Description> |
||
5083 | <Type>R</Type> |
||
5084 | <Comment>64.95.116.x[x]</Comment> |
||
5085 | <Link1>http://www.feedster.com/</Link1> |
||
5086 | <Link2></Link2> |
||
5087 | </user-agent> |
||
5088 | <user-agent> |
||
5089 | <ID>id_a_f_040207_1</ID> |
||
5090 | <String>FeedZcollector v1.x (Platinum) http://www.feeds4all.com/feedzcollector</String> |
||
5091 | <Description>FeedZcollector - Feed (RSS, ATOM and RDF) capturing software</Description> |
||
5092 | <Type>B</Type> |
||
5093 | <Comment></Comment> |
||
5094 | <Link1>http://www.feeds4all.com/feedzcollector/</Link1> |
||
5095 | <Link2></Link2> |
||
5096 | </user-agent> |
||
5097 | <user-agent> |
||
5098 | <ID>id_a_f_353</ID> |
||
5099 | <String>Felix - Mixcat Crawler (+http://mixcat.com)</String> |
||
5100 | <Description>MixCat robot</Description> |
||
5101 | <Type>R</Type> |
||
5102 | <Comment>s. also Morris</Comment> |
||
5103 | <Link1>http://mixcat.com</Link1> |
||
5104 | <Link2></Link2> |
||
5105 | </user-agent> |
||
5106 | <user-agent> |
||
5107 | <ID>id_a_f_354</ID> |
||
5108 | <String>fetch libfetch/2.0</String> |
||
5109 | <Description>FreeBSD download tool</Description> |
||
5110 | <Type>D</Type> |
||
5111 | <Comment></Comment> |
||
5112 | <Link1></Link1> |
||
5113 | <Link2></Link2> |
||
5114 | </user-agent> |
||
5115 | <user-agent> |
||
5116 | <ID>id_a_f_355</ID> |
||
5117 | <String>FFC Trap Door Spider</String> |
||
5118 | <Description>Frequent Finders spider via Sitefusion.com</Description> |
||
5119 | <Type>R</Type> |
||
5120 | <Comment></Comment> |
||
5121 | <Link1>http://www.frequentfinders.com</Link1> |
||
5122 | <Link2></Link2> |
||
5123 | </user-agent> |
||
5124 | <user-agent> |
||
5125 | <ID>id_a_f_356</ID> |
||
5126 | <String>Filangy/0.01-beta (Filangy; http://www.nutch.org/docs/en/bot.html; filangy-agent@filangy.com)</String> |
||
5127 | <Description>Filangy search and bookmark service</Description> |
||
5128 | <Type>R C</Type> |
||
5129 | <Comment></Comment> |
||
5130 | <Link1>http://www.filangy.com</Link1> |
||
5131 | <Link2></Link2> |
||
5132 | </user-agent> |
||
5133 | <user-agent> |
||
5134 | <ID>id_a_f_357</ID> |
||
5135 | <String>Filangy/1.0x (Filangy; http://www.filangy.com/filangyinfo.jsp?inc=robots.jsp; filangy-agent@filangy.com)</String> |
||
5136 | <Description>Filangy search and bookmark service</Description> |
||
5137 | <Type>R C</Type> |
||
5138 | <Comment></Comment> |
||
5139 | <Link1>http://www.filangy.com</Link1> |
||
5140 | <Link2></Link2> |
||
5141 | </user-agent> |
||
5142 | <user-agent> |
||
5143 | <ID>id_a_f_358</ID> |
||
5144 | <String>Filangy/1.0x (Filangy; http://www.nutch.org/docs/en/bot.html; filangy-agent@filangy.com)</String> |
||
5145 | <Description>Filangy search and bookmark service</Description> |
||
5146 | <Type>R C</Type> |
||
5147 | <Comment></Comment> |
||
5148 | <Link1>http://www.filangy.com</Link1> |
||
5149 | <Link2></Link2> |
||
5150 | </user-agent> |
||
5151 | <user-agent> |
||
5152 | <ID>id_a_f_359</ID> |
||
5153 | <String>fileboost.net/1.0 (+http://www.fileboost.net)</String> |
||
5154 | <Description>File Boost Network link checking</Description> |
||
5155 | <Type>R C</Type> |
||
5156 | <Comment></Comment> |
||
5157 | <Link1>http://www.fileboost.net</Link1> |
||
5158 | <Link2></Link2> |
||
5159 | </user-agent> |
||
5160 | <user-agent> |
||
5161 | <ID>id_a_f_360</ID> |
||
5162 | <String>FileHound x.x</String> |
||
5163 | <Description>FileHound download manager</Description> |
||
5164 | <Type>D</Type> |
||
5165 | <Comment></Comment> |
||
5166 | <Link1>http://www.allabout.com</Link1> |
||
5167 | <Link2></Link2> |
||
5168 | </user-agent> |
||
5169 | <user-agent> |
||
5170 | <ID>id_a_f_180208_1</ID> |
||
5171 | <String>Filtrbox/1.0</String> |
||
5172 | <Description>filtrbox media content (news) monitoring</Description> |
||
5173 | <Type>R</Type> |
||
5174 | <Comment>72.47.203.8x</Comment> |
||
5175 | <Link1>http://www.filtrbox.com/</Link1> |
||
5176 | <Link2></Link2> |
||
5177 | </user-agent> |
||
5178 | <user-agent> |
||
5179 | <ID>id_a_f_361</ID> |
||
5180 | <String>FindAnISP.com_ISP_Finder_v99a</String> |
||
5181 | <Description>Find An ISP robot</Description> |
||
5182 | <Type>R C</Type> |
||
5183 | <Comment>site is down</Comment> |
||
5184 | <Link1>http://www.findanisp.com/</Link1> |
||
5185 | <Link2></Link2> |
||
5186 | </user-agent> |
||
5187 | <user-agent> |
||
5188 | <ID>id_a_f_141205_2</ID> |
||
5189 | <String>Findexa Crawler (http://www.findexa.no/gulesider/article26548.ece)</String> |
||
5190 | <Description>Yelo.no business search (Norway) via Findexa</Description> |
||
5191 | <Type>R</Type> |
||
5192 | <Comment></Comment> |
||
5193 | <Link1>http://www.findexa.no/english/article27709.ece</Link1> |
||
5194 | <Link2></Link2> |
||
5195 | </user-agent> |
||
5196 | <user-agent> |
||
5197 | <ID>id_a_f_362</ID> |
||
5198 | <String>findlinks/x.xxx (+http://wortschatz.uni-leipzig.de/findlinks/) </String> |
||
5199 | <Description>NextLinks - German vocabulary and hyperlink search</Description> |
||
5200 | <Type>R</Type> |
||
5201 | <Comment></Comment> |
||
5202 | <Link1>http://wortschatz.uni-leipzig.de/nextlinks/findlinks.html</Link1> |
||
5203 | <Link2></Link2> |
||
5204 | </user-agent> |
||
5205 | <user-agent> |
||
5206 | <ID>id_a_f_363</ID> |
||
5207 | <String>FineBot</String> |
||
5208 | <Description>Finesearch robot</Description> |
||
5209 | <Type>R</Type> |
||
5210 | <Comment></Comment> |
||
5211 | <Link1>http://www.finesearch.com</Link1> |
||
5212 | <Link2></Link2> |
||
5213 | </user-agent> |
||
5214 | <user-agent> |
||
5215 | <ID>id_a_f_080306_1</ID> |
||
5216 | <String>Finjan-prefetch</String> |
||
5217 | <Description>Finjan Vital Security Web Appliance security solution</Description> |
||
5218 | <Type>P</Type> |
||
5219 | <Comment></Comment> |
||
5220 | <Link1>http://www.finjan.com/</Link1> |
||
5221 | <Link2></Link2> |
||
5222 | </user-agent> |
||
5223 | <user-agent> |
||
5224 | <ID>id_a_f_364</ID> |
||
5225 | <String>Firefly/1.0</String> |
||
5226 | <Description>Fireball.de robot</Description> |
||
5227 | <Type>R</Type> |
||
5228 | <Comment></Comment> |
||
5229 | <Link1>http://www.fireball.de</Link1> |
||
5230 | <Link2></Link2> |
||
5231 | </user-agent> |
||
5232 | <user-agent> |
||
5233 | <ID>id_a_f_365</ID> |
||
5234 | <String>Firefly/1.0 (compatible; Mozilla 4.0; MSIE 5.5)</String> |
||
5235 | <Description>Fireball.de robot</Description> |
||
5236 | <Type>R</Type> |
||
5237 | <Comment></Comment> |
||
5238 | <Link1>http://www.fireball.de</Link1> |
||
5239 | <Link2></Link2> |
||
5240 | </user-agent> |
||
5241 | <user-agent> |
||
5242 | <ID>id_a_f_210906_1</ID> |
||
5243 | <String>Firefox (kastaneta03@hotmail.com)</String> |
||
5244 | <Description>Unknown robot from Czech Technical University Prague (147.32.141.xx)</Description> |
||
5245 | <Type>R</Type> |
||
5246 | <Comment>reads robots.txt</Comment> |
||
5247 | <Link1>http://www.cvut.cz/</Link1> |
||
5248 | <Link2></Link2> |
||
5249 | </user-agent> |
||
5250 | <user-agent> |
||
5251 | <ID>id_a_f_190306_2</ID> |
||
5252 | <String>Firefox_1.0.6 (kasparek@naparek.cz)</String> |
||
5253 | <Description>Unknown robot from Czech Technical University Prague (147.32.141.xx)</Description> |
||
5254 | <Type>R</Type> |
||
5255 | <Comment>reads robots.txt</Comment> |
||
5256 | <Link1>http://www.cvut.cz/</Link1> |
||
5257 | <Link2></Link2> |
||
5258 | </user-agent> |
||
5259 | <user-agent> |
||
5260 | <ID>id_a_f_366</ID> |
||
5261 | <String>FirstGov.gov Search - POC:firstgov.webmasters@gsa.gov</String> |
||
5262 | <Description>AT&T/Fast Search robot for FirstGov (U.S.Government) portal</Description> |
||
5263 | <Type>R</Type> |
||
5264 | <Comment></Comment> |
||
5265 | <Link1>http://www.firstgov.gov</Link1> |
||
5266 | <Link2></Link2> |
||
5267 | </user-agent> |
||
5268 | <user-agent> |
||
5269 | <ID>id_a_f_367</ID> |
||
5270 | <String>firstsbot</String> |
||
5271 | <Description>Firstsfind Germany robot / link checking</Description> |
||
5272 | <Type>R</Type> |
||
5273 | <Comment></Comment> |
||
5274 | <Link1>http://www.firstsfind.de</Link1> |
||
5275 | <Link2></Link2> |
||
5276 | </user-agent> |
||
5277 | <user-agent> |
||
5278 | <ID>id_a_f_020906_1</ID> |
||
5279 | <String>Flapbot/0.7.2 (Flaptor Crawler; http://www.flaptor.com; crawler at flaptor period com)</String> |
||
5280 | <Description>Flaptor information retrieval solutions robot</Description> |
||
5281 | <Type>R</Type> |
||
5282 | <Comment></Comment> |
||
5283 | <Link1>http://www.flaptor.com/index.htm</Link1> |
||
5284 | <Link2></Link2> |
||
5285 | </user-agent> |
||
5286 | <user-agent> |
||
5287 | <ID>id_a_f_368</ID> |
||
5288 | <String>FlashGet</String> |
||
5289 | <Description>JetCar/FlashGet download manager</Description> |
||
5290 | <Type>D</Type> |
||
5291 | <Comment></Comment> |
||
5292 | <Link1>http://www.amazesoft.com</Link1> |
||
5293 | <Link2></Link2> |
||
5294 | </user-agent> |
||
5295 | <user-agent> |
||
5296 | <ID>id_a_f_161205_1</ID> |
||
5297 | <String>FLATARTS_FAVICO</String> |
||
5298 | <Description>FlatArts Favorites Icon Tool</Description> |
||
5299 | <Type>C D</Type> |
||
5300 | <Comment></Comment> |
||
5301 | <Link1>http://flatarts.jp/contents/software/information.php?name=rico</Link1> |
||
5302 | <Link2></Link2> |
||
5303 | </user-agent> |
||
5304 | <user-agent> |
||
5305 | <ID>id_a_f_100308_1</ID> |
||
5306 | <String>Flexum spider</String> |
||
5307 | <Description>Flexum.ru search service</Description> |
||
5308 | <Type>R</Type> |
||
5309 | <Comment>81.176.76.93</Comment> |
||
5310 | <Link1>http://www.flexum.ru/</Link1> |
||
5311 | <Link2></Link2> |
||
5312 | </user-agent> |
||
5313 | <user-agent> |
||
5314 | <ID>id_a_f_280508_2</ID> |
||
5315 | <String>Flexum/2.0</String> |
||
5316 | <Description>Flexum.ru search service</Description> |
||
5317 | <Type>R</Type> |
||
5318 | <Comment>81.176.76.93</Comment> |
||
5319 | <Link1>http://www.flexum.ru/</Link1> |
||
5320 | <Link2></Link2> |
||
5321 | </user-agent> |
||
5322 | <user-agent> |
||
5323 | <ID>id_a_f_369</ID> |
||
5324 | <String>FlickBot 2.0 RPT-HTTPClient/0.3-3</String> |
||
5325 | <Description>DivX.com Movie Find robot</Description> |
||
5326 | <Type>R</Type> |
||
5327 | <Comment></Comment> |
||
5328 | <Link1>http://www.divx.com</Link1> |
||
5329 | <Link2></Link2> |
||
5330 | </user-agent> |
||
5331 | <user-agent> |
||
5332 | <ID>id_a_f_370</ID> |
||
5333 | <String>flunky</String> |
||
5334 | <Description>Metacarta / Cogent robot</Description> |
||
5335 | <Type>R</Type> |
||
5336 | <Comment></Comment> |
||
5337 | <Link1>http://www.metacarta.com</Link1> |
||
5338 | <Link2></Link2> |
||
5339 | </user-agent> |
||
5340 | <user-agent> |
||
5341 | <ID>id_a_f_371</ID> |
||
5342 | <String>fly/6.01 libwww/4.0D</String> |
||
5343 | <Description>unknown</Description> |
||
5344 | <Type></Type> |
||
5345 | <Comment></Comment> |
||
5346 | <Link1></Link1> |
||
5347 | <Link2></Link2> |
||
5348 | </user-agent> |
||
5349 | <user-agent> |
||
5350 | <ID>id_a_f_110107_1</ID> |
||
5351 | <String>flyindex.net 1.0/http://www.flyindex.net</String> |
||
5352 | <Description>FLY Index Metasearch link checking</Description> |
||
5353 | <Type>C</Type> |
||
5354 | <Comment>62.141.52.2xx</Comment> |
||
5355 | <Link1>http://www.flyindex.net/</Link1> |
||
5356 | <Link2></Link2> |
||
5357 | </user-agent> |
||
5358 | <user-agent> |
||
5359 | <ID>id_a_f_021108_1</ID> |
||
5360 | <String>FnooleBot/2.5.2 (+http://www.fnoole.com/addurl.html)</String> |
||
5361 | <Description>Fnoole news crawler</Description> |
||
5362 | <Type>R</Type> |
||
5363 | <Comment>209.205.65.9x</Comment> |
||
5364 | <Link1>http://www.fnoole.com/</Link1> |
||
5365 | <Link2></Link2> |
||
5366 | </user-agent> |
||
5367 | <user-agent> |
||
5368 | <ID>id_a_f_372</ID> |
||
5369 | <String>FocusedSampler/1.0</String> |
||
5370 | <Description>IBM's Almaden Research robot</Description> |
||
5371 | <Type>R</Type> |
||
5372 | <Comment> s. also: - - WFARC</Comment> |
||
5373 | <Link1>http://www.almaden.ibm.com</Link1> |
||
5374 | <Link2></Link2> |
||
5375 | </user-agent> |
||
5376 | <user-agent> |
||
5377 | <ID>id_a_f_080108_1</ID> |
||
5378 | <String>Folkd.com Spider/0.1 beta 1 (www.folkd.com)</String> |
||
5379 | <Description>folkd.com social search robot</Description> |
||
5380 | <Type>R</Type> |
||
5381 | <Comment>212.227.95.3x</Comment> |
||
5382 | <Link1>http://www.folkd.com/</Link1> |
||
5383 | <Link2></Link2> |
||
5384 | </user-agent> |
||
5385 | <user-agent> |
||
5386 | <ID>id_a_f_070209_4</ID> |
||
5387 | <String>FollowSite Bot ( http://www.followsite.com/bot.html )</String> |
||
5388 | <Description>FollowSite robot - website monitoring</Description> |
||
5389 | <Type>C</Type> |
||
5390 | <Comment>77.232.77.13x</Comment> |
||
5391 | <Link1>http://www.followsite.com/bot.html</Link1> |
||
5392 | <Link2></Link2> |
||
5393 | </user-agent> |
||
5394 | <user-agent> |
||
5395 | <ID>id_a_f_140209_1</ID> |
||
5396 | <String>FollowSite.com ( http://www.followsite.com/b.html )</String> |
||
5397 | <Description>FollowSite robot - website monitoring</Description> |
||
5398 | <Type>C</Type> |
||
5399 | <Comment>77.232.77.13x</Comment> |
||
5400 | <Link1>http://www.followsite.com/bot.html</Link1> |
||
5401 | <Link2></Link2> |
||
5402 | </user-agent> |
||
5403 | <user-agent> |
||
5404 | <ID>id_a_f_141105_1</ID> |
||
5405 | <String>Fooky.com/ScorpionBot/ScoutOut; http://www.fooky.com/scorpionbots</String> |
||
5406 | <Description>Fooky search Scorpionbots robot (65.12.170.xxx)</Description> |
||
5407 | <Type>R</Type> |
||
5408 | <Comment></Comment> |
||
5409 | <Link1>http://www.fooky.com/</Link1> |
||
5410 | <Link2></Link2> |
||
5411 | </user-agent> |
||
5412 | <user-agent> |
||
5413 | <ID>id_a_f_373</ID> |
||
5414 | <String>Francis/1.0 (francis@neomo.de http://www.neomo.de/)</String> |
||
5415 | <Description>Neomo Search (Germany) robot (85.10.197.1xx)</Description> |
||
5416 | <Type>R</Type> |
||
5417 | <Comment></Comment> |
||
5418 | <Link1>http://www.neomo.de</Link1> |
||
5419 | <Link2></Link2> |
||
5420 | </user-agent> |
||
5421 | <user-agent> |
||
5422 | <ID>id_a_f_374</ID> |
||
5423 | <String>Franklin Locator 1.8</String> |
||
5424 | <Description>Some spam bot</Description> |
||
5425 | <Type>S</Type> |
||
5426 | <Comment></Comment> |
||
5427 | <Link1></Link1> |
||
5428 | <Link2></Link2> |
||
5429 | </user-agent> |
||
5430 | <user-agent> |
||
5431 | <ID>id_a_f_110506_1</ID> |
||
5432 | <String>free-downloads.net download-link validator /0.1</String> |
||
5433 | <Description>Free Downloads shareware directory link checking</Description> |
||
5434 | <Type>C</Type> |
||
5435 | <Comment></Comment> |
||
5436 | <Link1>http://www.free-downloads.net/</Link1> |
||
5437 | <Link2></Link2> |
||
5438 | </user-agent> |
||
5439 | <user-agent> |
||
5440 | <ID>id_a_f_375</ID> |
||
5441 | <String>FreeFind.com-SiteSearchEngine/1.0 (http://freefind.com; spiderinfo@freefind.com)</String> |
||
5442 | <Description>FreeFind.com robot</Description> |
||
5443 | <Type>R</Type> |
||
5444 | <Comment></Comment> |
||
5445 | <Link1>http://freefind.com</Link1> |
||
5446 | <Link2></Link2> |
||
5447 | </user-agent> |
||
5448 | <user-agent> |
||
5449 | <ID>id_a_f_221008_2</ID> |
||
5450 | <String>Frelicbot/1.0 +http://www.frelic.com/</String> |
||
5451 | <Description>Frelics backlink checking bot (beta)</Description> |
||
5452 | <Type>C</Type> |
||
5453 | <Comment></Comment> |
||
5454 | <Link1>http://www.frelic.com/</Link1> |
||
5455 | <Link2></Link2> |
||
5456 | </user-agent> |
||
5457 | <user-agent> |
||
5458 | <ID>id_a_f_376</ID> |
||
5459 | <String>FreshDownload/x.xx</String> |
||
5460 | <Description>Fresh Download download manager</Description> |
||
5461 | <Type>D</Type> |
||
5462 | <Comment></Comment> |
||
5463 | <Link1>http://www.freshdevices.com</Link1> |
||
5464 | <Link2></Link2> |
||
5465 | </user-agent> |
||
5466 | <user-agent> |
||
5467 | <ID>id_a_f_230306_2</ID> |
||
5468 | <String>FreshNotes crawler< report problems to crawler-at-freshnotes-dot-com</String> |
||
5469 | <Description>FreshNotes - music related artist search (72.3.225.xx)</Description> |
||
5470 | <Type>R</Type> |
||
5471 | <Comment></Comment> |
||
5472 | <Link1>http://freshnotes.com/fn/</Link1> |
||
5473 | <Link2></Link2> |
||
5474 | </user-agent> |
||
5475 | <user-agent> |
||
5476 | <ID>id_a_f_377</ID> |
||
5477 | <String>FSurf15a 01</String> |
||
5478 | <Description>Some site scanning tool via diff. IPs</Description> |
||
5479 | <Type>S</Type> |
||
5480 | <Comment>s. also DSurf - PBrowse ...</Comment> |
||
5481 | <Link1></Link1> |
||
5482 | <Link2></Link2> |
||
5483 | </user-agent> |
||
5484 | <user-agent> |
||
5485 | <ID>id_a_f_070209_5</ID> |
||
5486 | <String>FTB-Bot http://www.findthebest.co.uk/</String> |
||
5487 | <Description>Find the Best search robot</Description> |
||
5488 | <Type>R</Type> |
||
5489 | <Comment>83.105.71.16x</Comment> |
||
5490 | <Link1>http://www.findthebest.co.uk/</Link1> |
||
5491 | <Link2></Link2> |
||
5492 | </user-agent> |
||
5493 | <user-agent> |
||
5494 | <ID>id_a_f_378</ID> |
||
5495 | <String>Full Web Bot 0416B</String> |
||
5496 | <Description>Some site scanning tool from diff. IPs i.e.: - 66.28.240.xx (cogentco.com) - 68.5.174.xx (cox.net)</Description> |
||
5497 | <Type>S</Type> |
||
5498 | <Comment></Comment> |
||
5499 | <Link1></Link1> |
||
5500 | <Link2></Link2> |
||
5501 | </user-agent> |
||
5502 | <user-agent> |
||
5503 | <ID>id_a_f_379</ID> |
||
5504 | <String>Full Web Bot 0516B</String> |
||
5505 | <Description>Some site scanning tool i.e. from - 68.154.96.xx (bellsouth.net)</Description> |
||
5506 | <Type>S</Type> |
||
5507 | <Comment>appears also as MFC Foundation Class Library & Demo Bot Z 16b - 66.118.1xx.xxx (sagonet.com) - s. also Educate Search VxB - Industry Program 1.0.5</Comment> |
||
5508 | <Link1></Link1> |
||
5509 | <Link2></Link2> |
||
5510 | </user-agent> |
||
5511 | <user-agent> |
||
5512 | <ID>id_a_f_380</ID> |
||
5513 | <String>Full Web Bot 2816B</String> |
||
5514 | <Description>Some site scanning tool from 66.255.6.xxx (uslec.com)</Description> |
||
5515 | <Type>S</Type> |
||
5516 | <Comment></Comment> |
||
5517 | <Link1></Link1> |
||
5518 | <Link2></Link2> |
||
5519 | </user-agent> |
||
5520 | <user-agent> |
||
5521 | <ID>id_a_f_190807_1</ID> |
||
5522 | <String>FuseBulb.Com</String> |
||
5523 | <Description>FuseBulb search</Description> |
||
5524 | <Type>R</Type> |
||
5525 | <Comment>208.109.126.1xx</Comment> |
||
5526 | <Link1>http://www.fusebulb.com/</Link1> |
||
5527 | <Link2></Link2> |
||
5528 | </user-agent> |
||
5529 | <user-agent> |
||
5530 | <ID>id_a_f_381</ID> |
||
5531 | <String>FyberSpider (+http://www.fybersearch.com/fyberspider.php)</String> |
||
5532 | <Description>FyberSearch FyberSpider robot</Description> |
||
5533 | <Type>R</Type> |
||
5534 | <Comment></Comment> |
||
5535 | <Link1>http://www.fybersearch.com</Link1> |
||
5536 | <Link2></Link2> |
||
5537 | </user-agent> |
||
5538 | <user-agent> |
||
5539 | <ID>id_g_m_382</ID> |
||
5540 | <String>Gagglebot</String> |
||
5541 | <Description>Some user from bbnplanet.net (4.63.218.2xx) using an Innerprise robot tool</Description> |
||
5542 | <Type>R C ?</Type> |
||
5543 | <Comment></Comment> |
||
5544 | <Link1>http://www.innerprise.net</Link1> |
||
5545 | <Link2></Link2> |
||
5546 | </user-agent> |
||
5547 | <user-agent> |
||
5548 | <ID>id_g_m_383</ID> |
||
5549 | <String>GAIS Robot/1.0B2</String> |
||
5550 | <Description>Seed Search robot</Description> |
||
5551 | <Type>R</Type> |
||
5552 | <Comment></Comment> |
||
5553 | <Link1>http://www.seed.net.tw</Link1> |
||
5554 | <Link2></Link2> |
||
5555 | </user-agent> |
||
5556 | <user-agent> |
||
5557 | <ID>id_g_m_384</ID> |
||
5558 | <String>Gaisbot/3.0 (indexer@gais.cs.ccu.edu.tw; http://gais.cs.ccu.edu.tw/robot.php)</String> |
||
5559 | <Description>Gaislab Taiwan robot</Description> |
||
5560 | <Type>R</Type> |
||
5561 | <Comment>140.123.100.x</Comment> |
||
5562 | <Link1>http://gais.cs.ccu.edu.tw</Link1> |
||
5563 | <Link2></Link2> |
||
5564 | </user-agent> |
||
5565 | <user-agent> |
||
5566 | <ID>id_g_m_160706_1</ID> |
||
5567 | <String>Gaisbot/3.0+(robot06@gais.cs.ccu.edu.tw;+http://gais.cs.ccu.edu.tw/robot.php)</String> |
||
5568 | <Description>Gaislab Taiwan robot</Description> |
||
5569 | <Type>R</Type> |
||
5570 | <Comment>140.123.100.x</Comment> |
||
5571 | <Link1>http://gais.cs.ccu.edu.tw</Link1> |
||
5572 | <Link2></Link2> |
||
5573 | </user-agent> |
||
5574 | <user-agent> |
||
5575 | <ID>id_g_m_385</ID> |
||
5576 | <String>GalaxyBot/1.0 (http://www.galaxy.com/galaxybot.html)</String> |
||
5577 | <Description>Galaxy robot (63.121.41.xxx)</Description> |
||
5578 | <Type>R</Type> |
||
5579 | <Comment> s. also Mozilla/4.0 (compatible; MSIE 5.0; www.galaxy.com....)</Comment> |
||
5580 | <Link1>http://www.galaxy.com</Link1> |
||
5581 | <Link2></Link2> |
||
5582 | </user-agent> |
||
5583 | <user-agent> |
||
5584 | <ID>id_g_m_130407_2</ID> |
||
5585 | <String>Gallent Search Spider v1.4 Robot 2 (http://robot.GallentSearch.com)</String> |
||
5586 | <Description>Gallent Search directory (UK)</Description> |
||
5587 | <Type>R</Type> |
||
5588 | <Comment>88.208.223.xx</Comment> |
||
5589 | <Link1>http://www.gallent.co.uk/</Link1> |
||
5590 | <Link2>http://robot.gallentsearch.com/</Link2> |
||
5591 | </user-agent> |
||
5592 | <user-agent> |
||
5593 | <ID>id_g_m_010107_1</ID> |
||
5594 | <String>gamekitbot/1.0 (+http://www.uchoose.de/crawler/gamekitbot/)</String> |
||
5595 | <Description>Gamekit game search engine - Germany</Description> |
||
5596 | <Type>R</Type> |
||
5597 | <Comment>80.65.45.xx</Comment> |
||
5598 | <Link1>http://www.gamekit.de/</Link1> |
||
5599 | <Link2></Link2> |
||
5600 | </user-agent> |
||
5601 | <user-agent> |
||
5602 | <ID>id_g_m_386</ID> |
||
5603 | <String>Gamespy_Arcade</String> |
||
5604 | <Description>GameSpyHTTP/1.0</Description> |
||
5605 | <Type>D</Type> |
||
5606 | <Comment>GameSpy Arcade download manager (FilePlanet)</Comment> |
||
5607 | <Link1>http://www.gamespyarcade.com/features/</Link1> |
||
5608 | <Link2></Link2> |
||
5609 | </user-agent> |
||
5610 | <user-agent> |
||
5611 | <ID>id_g_m_387</ID> |
||
5612 | <String>GammaSpider/1.0</String> |
||
5613 | <Description>GammaWare GammaSpider</Description> |
||
5614 | <Type>R</Type> |
||
5615 | <Comment></Comment> |
||
5616 | <Link1>http://www.gammasite.com</Link1> |
||
5617 | <Link2></Link2> |
||
5618 | </user-agent> |
||
5619 | <user-agent> |
||
5620 | <ID>id_g_m_388</ID> |
||
5621 | <String>gazz/x.x (gazz@nttrd.com)</String> |
||
5622 | <Description>nttrd.com / Infobee.ne.jp robot</Description> |
||
5623 | <Type>R</Type> |
||
5624 | <Comment></Comment> |
||
5625 | <Link1></Link1> |
||
5626 | <Link2></Link2> |
||
5627 | </user-agent> |
||
5628 | <user-agent> |
||
5629 | <ID>id_g_m_389</ID> |
||
5630 | <String>geckobot</String> |
||
5631 | <Description>Geckobot user robot</Description> |
||
5632 | <Type></Type> |
||
5633 | <Comment>no active website</Comment> |
||
5634 | <Link1>http://www.geckobot.com/</Link1> |
||
5635 | <Link2></Link2> |
||
5636 | </user-agent> |
||
5637 | <user-agent> |
||
5638 | <ID>id_g_m_280406_1</ID> |
||
5639 | <String>Generic Mobile Phone (compatible; Googlebot-Mobile/2.1; +http://www.google.com/bot.html)</String> |
||
5640 | <Description>Google Mobile Search crawler</Description> |
||
5641 | <Type>R P</Type> |
||
5642 | <Comment>66.249.72.1xx</Comment> |
||
5643 | <Link1>http://www.google.com/mobile/formats.html</Link1> |
||
5644 | <Link2></Link2> |
||
5645 | </user-agent> |
||
5646 | <user-agent> |
||
5647 | <ID>id_g_m_390</ID> |
||
5648 | <String>generic_crawler/01.0217/</String> |
||
5649 | <Description>Unknown robot from Carnegie Mellon University (128.2.211.xxx)</Description> |
||
5650 | <Type>R</Type> |
||
5651 | <Comment></Comment> |
||
5652 | <Link1>http://www.cmu.edu</Link1> |
||
5653 | <Link2></Link2> |
||
5654 | </user-agent> |
||
5655 | <user-agent> |
||
5656 | <ID>id_g_m_100109_2</ID> |
||
5657 | <String>GenesisBrowser (HTTP 1.1; 0.9; XP SP2; .NET CLR 2.0.50727)</String> |
||
5658 | <Description>Lunascape Genesis browser</Description> |
||
5659 | <Type>B</Type> |
||
5660 | <Comment></Comment> |
||
5661 | <Link1>http://www.lunascape.tv/</Link1> |
||
5662 | <Link2></Link2> |
||
5663 | </user-agent> |
||
5664 | <user-agent> |
||
5665 | <ID>id_g_m_231205_1</ID> |
||
5666 | <String>genieBot (http://64.5.245.11/faq/faq.html)</String> |
||
5667 | <Description>GenieKnows.com search</Description> |
||
5668 | <Type>R</Type> |
||
5669 | <Comment> s. also: - larbin_2.6.3 (wgao@genieknows.com)</Comment> |
||
5670 | <Link1>http://www.genieknows.com/</Link1> |
||
5671 | <Link2></Link2> |
||
5672 | </user-agent> |
||
5673 | <user-agent> |
||
5674 | <ID>id_g_m_391</ID> |
||
5675 | <String>geniebot wgao@genieknows.com</String> |
||
5676 | <Description>GenieKnows.com search</Description> |
||
5677 | <Type>R</Type> |
||
5678 | <Comment> s. also: - larbin_2.6.3 (wgao@genieknows.com)</Comment> |
||
5679 | <Link1>http://www.genieknows.com/</Link1> |
||
5680 | <Link2></Link2> |
||
5681 | </user-agent> |
||
5682 | <user-agent> |
||
5683 | <ID>id_g_m_050606_3</ID> |
||
5684 | <String>GeoBot/1.0</String> |
||
5685 | <Description>Unknown robot from wavepath.com (65.254.33.1xx)</Description> |
||
5686 | <Type></Type> |
||
5687 | <Comment>no active website</Comment> |
||
5688 | <Link1></Link1> |
||
5689 | <Link2></Link2> |
||
5690 | </user-agent> |
||
5691 | <user-agent> |
||
5692 | <ID>id_g_m_392</ID> |
||
5693 | <String>GeonaBot 1.x; http://www.geona.com/</String> |
||
5694 | <Description>Geona Search robot / link checking</Description> |
||
5695 | <Type>R</Type> |
||
5696 | <Comment></Comment> |
||
5697 | <Link1>http://www.geona.com</Link1> |
||
5698 | <Link2></Link2> |
||
5699 | </user-agent> |
||
5700 | <user-agent> |
||
5701 | <ID>id_g_m_160206_3</ID> |
||
5702 | <String>geourl/2.0b2</String> |
||
5703 | <Description>GeoURL ICBM Address Server - a location-to-URL reverse directory</Description> |
||
5704 | <Type>C</Type> |
||
5705 | <Comment></Comment> |
||
5706 | <Link1>http://geourl.org/</Link1> |
||
5707 | <Link2></Link2> |
||
5708 | </user-agent> |
||
5709 | <user-agent> |
||
5710 | <ID>id_g_m_160206_2</ID> |
||
5711 | <String>GeoURLBot 1.0 (http://geourl.org)</String> |
||
5712 | <Description>GeoURL ICBM Address Server - a location-to-URL reverse directory</Description> |
||
5713 | <Type>C</Type> |
||
5714 | <Comment></Comment> |
||
5715 | <Link1>http://geourl.org/</Link1> |
||
5716 | <Link2></Link2> |
||
5717 | </user-agent> |
||
5718 | <user-agent> |
||
5719 | <ID>id_g_m_393</ID> |
||
5720 | <String>GetBot</String> |
||
5721 | <Description>Getbot web downloading tool / site grabber</Description> |
||
5722 | <Type>D</Type> |
||
5723 | <Comment></Comment> |
||
5724 | <Link1>http://www.getbot.com</Link1> |
||
5725 | <Link2></Link2> |
||
5726 | </user-agent> |
||
5727 | <user-agent> |
||
5728 | <ID>id_g_m_394</ID> |
||
5729 | <String>GetRight/3.x.x</String> |
||
5730 | <Description>GetRight download manager</Description> |
||
5731 | <Type>D</Type> |
||
5732 | <Comment></Comment> |
||
5733 | <Link1>http://www.getright.com</Link1> |
||
5734 | <Link2></Link2> |
||
5735 | </user-agent> |
||
5736 | <user-agent> |
||
5737 | <ID>id_g_m_395</ID> |
||
5738 | <String>GetRight/4.5xx</String> |
||
5739 | <Description>GetRight download manager</Description> |
||
5740 | <Type>D</Type> |
||
5741 | <Comment></Comment> |
||
5742 | <Link1>http://www.getright.com</Link1> |
||
5743 | <Link2></Link2> |
||
5744 | </user-agent> |
||
5745 | <user-agent> |
||
5746 | <ID>id_g_m_396</ID> |
||
5747 | <String>GetRight/4.x</String> |
||
5748 | <Description>GetRight download manager</Description> |
||
5749 | <Type>D</Type> |
||
5750 | <Comment></Comment> |
||
5751 | <Link1>http://www.getright.com</Link1> |
||
5752 | <Link2></Link2> |
||
5753 | </user-agent> |
||
5754 | <user-agent> |
||
5755 | <ID>id_g_m_397</ID> |
||
5756 | <String>GetRight/4.x[a-e]</String> |
||
5757 | <Description>GetRight download manager</Description> |
||
5758 | <Type>D</Type> |
||
5759 | <Comment></Comment> |
||
5760 | <Link1>http://www.getright.com</Link1> |
||
5761 | <Link2></Link2> |
||
5762 | </user-agent> |
||
5763 | <user-agent> |
||
5764 | <ID>id_g_m_260807_1</ID> |
||
5765 | <String>GetRight/6.1 (Pro)</String> |
||
5766 | <Description>GetRight download manager</Description> |
||
5767 | <Type>D</Type> |
||
5768 | <Comment></Comment> |
||
5769 | <Link1>http://www.getright.com</Link1> |
||
5770 | <Link2></Link2> |
||
5771 | </user-agent> |
||
5772 | <user-agent> |
||
5773 | <ID>id_g_m_398</ID> |
||
5774 | <String>GetRightPro/6.0beta2</String> |
||
5775 | <Description>GetRight download manager</Description> |
||
5776 | <Type>D</Type> |
||
5777 | <Comment></Comment> |
||
5778 | <Link1>http://www.getright.com</Link1> |
||
5779 | <Link2></Link2> |
||
5780 | </user-agent> |
||
5781 | <user-agent> |
||
5782 | <ID>id_g_m_170706_3</ID> |
||
5783 | <String>GetWeb/0.1 libwww-perl/5.16</String> |
||
5784 | <Description>GetWeb - web page to email service</Description> |
||
5785 | <Type>D</Type> |
||
5786 | <Comment>216.204.133.xxx</Comment> |
||
5787 | <Link1>http://www.healthnet.org/getweb.php</Link1> |
||
5788 | <Link2></Link2> |
||
5789 | </user-agent> |
||
5790 | <user-agent> |
||
5791 | <ID>id_g_m_399</ID> |
||
5792 | <String>GhostRouteHunter/20021130 (https://www.sixxs.net/tools/grh/; info@sixxs.net)</String> |
||
5793 | <Description>Sixxs Ghost Route Hunter</Description> |
||
5794 | <Type>C</Type> |
||
5795 | <Comment></Comment> |
||
5796 | <Link1>http://www.sixxs.net/tools/grh/</Link1> |
||
5797 | <Link2></Link2> |
||
5798 | </user-agent> |
||
5799 | <user-agent> |
||
5800 | <ID>id_g_m_400</ID> |
||
5801 | <String>gigabaz/3.1x (baz@gigabaz.com; http://gigabaz.com/gigabaz/)</String> |
||
5802 | <Description>GigaBaz Brainbot (Germany) robot</Description> |
||
5803 | <Type>R</Type> |
||
5804 | <Comment> s. also - MicroBaz</Comment> |
||
5805 | <Link1>http://gigabaz.com</Link1> |
||
5806 | <Link2></Link2> |
||
5807 | </user-agent> |
||
5808 | <user-agent> |
||
5809 | <ID>id_g_m_401</ID> |
||
5810 | <String>Gigabot/2.0 (gigablast.com)</String> |
||
5811 | <Description>Gigablast robot (64.62.168.xx)</Description> |
||
5812 | <Type>R</Type> |
||
5813 | <Comment></Comment> |
||
5814 | <Link1>http://www.gigablast.com</Link1> |
||
5815 | <Link2></Link2> |
||
5816 | </user-agent> |
||
5817 | <user-agent> |
||
5818 | <ID>id_g_m_140106_1</ID> |
||
5819 | <String>Gigabot/2.0/gigablast.com/spider.html</String> |
||
5820 | <Description>Gigablast robot</Description> |
||
5821 | <Type>R</Type> |
||
5822 | <Comment>comes from 64.62.168.xx AND 66.154.102.xx</Comment> |
||
5823 | <Link1>http://www.gigablast.com</Link1> |
||
5824 | <Link2></Link2> |
||
5825 | </user-agent> |
||
5826 | <user-agent> |
||
5827 | <ID>id_g_m_170506_1</ID> |
||
5828 | <String>Gigabot/2.0; http://www.gigablast.com/spider.html</String> |
||
5829 | <Description>Gigablast robot</Description> |
||
5830 | <Type>R</Type> |
||
5831 | <Comment>comes from 64.62.168.xx AND 66.154.102.xx</Comment> |
||
5832 | <Link1>http://www.gigablast.com</Link1> |
||
5833 | <Link2></Link2> |
||
5834 | </user-agent> |
||
5835 | <user-agent> |
||
5836 | <ID>id_g_m_190507_1</ID> |
||
5837 | <String>Gigabot/2.0att</String> |
||
5838 | <Description>Gigablast robot</Description> |
||
5839 | <Type>R</Type> |
||
5840 | <Comment>66.231.188.1xx</Comment> |
||
5841 | <Link1>http://www.gigablast.com</Link1> |
||
5842 | <Link2></Link2> |
||
5843 | </user-agent> |
||
5844 | <user-agent> |
||
5845 | <ID>id_g_m_230508_1</ID> |
||
5846 | <String>Gigabot/3.0 (http://www.gigablast.com/spider.html)</String> |
||
5847 | <Description>Gigablast robot</Description> |
||
5848 | <Type>R</Type> |
||
5849 | <Comment>66.231.18x.[x]xx</Comment> |
||
5850 | <Link1>http://www.gigablast.com</Link1> |
||
5851 | <Link2></Link2> |
||
5852 | </user-agent> |
||
5853 | <user-agent> |
||
5854 | <ID>id_g_m_402</ID> |
||
5855 | <String>Gigabot/x.0</String> |
||
5856 | <Description>Gigablast robot (64.62.168.xx)</Description> |
||
5857 | <Type>R</Type> |
||
5858 | <Comment></Comment> |
||
5859 | <Link1>http://www.gigablast.com</Link1> |
||
5860 | <Link2></Link2> |
||
5861 | </user-agent> |
||
5862 | <user-agent> |
||
5863 | <ID>id_g_m_403</ID> |
||
5864 | <String>GigabotSiteSearch/2.0 (sitesearch.gigablast.com)</String> |
||
5865 | <Description>Gigablast robot (64.62.168.xx)</Description> |
||
5866 | <Type>R</Type> |
||
5867 | <Comment></Comment> |
||
5868 | <Link1>http://www.gigablast.com</Link1> |
||
5869 | <Link2></Link2> |
||
5870 | </user-agent> |
||
5871 | <user-agent> |
||
5872 | <ID>id_g_m_404</ID> |
||
5873 | <String>GNODSPIDER (www.gnod.net)</String> |
||
5874 | <Description>www.gnod.net spider</Description> |
||
5875 | <Type>R</Type> |
||
5876 | <Comment></Comment> |
||
5877 | <Link1>http://www.gnod.net</Link1> |
||
5878 | <Link2></Link2> |
||
5879 | </user-agent> |
||
5880 | <user-agent> |
||
5881 | <ID>id_g_m_406</ID> |
||
5882 | <String>Go!Zilla 3.x (www.gozilla.com)</String> |
||
5883 | <Description>Go!Zilla download manager</Description> |
||
5884 | <Type>D</Type> |
||
5885 | <Comment></Comment> |
||
5886 | <Link1>http://www.gozilla.com</Link1> |
||
5887 | <Link2></Link2> |
||
5888 | </user-agent> |
||
5889 | <user-agent> |
||
5890 | <ID>id_g_m_407</ID> |
||
5891 | <String>Go!Zilla/4.x.x.xx</String> |
||
5892 | <Description>Go!Zilla download manager</Description> |
||
5893 | <Type>D</Type> |
||
5894 | <Comment></Comment> |
||
5895 | <Link1>http://www.gozilla.com</Link1> |
||
5896 | <Link2></Link2> |
||
5897 | </user-agent> |
||
5898 | <user-agent> |
||
5899 | <ID>id_g_m_405</ID> |
||
5900 | <String>Go-Ahead-Got-It/1.1</String> |
||
5901 | <Description>GotIt web accelerator (discontinued)</Description> |
||
5902 | <Type>P D</Type> |
||
5903 | <Comment></Comment> |
||
5904 | <Link1></Link1> |
||
5905 | <Link2></Link2> |
||
5906 | </user-agent> |
||
5907 | <user-agent> |
||
5908 | <ID>id_g_m_408</ID> |
||
5909 | <String>Goblin/0.9 (http://www.goguides.org/)</String> |
||
5910 | <Description>GoGuides.Org (195.226.137.xx) robot</Description> |
||
5911 | <Type>R</Type> |
||
5912 | <Comment></Comment> |
||
5913 | <Link1>http://www.goguides.org/goblin-info.html</Link1> |
||
5914 | <Link2></Link2> |
||
5915 | </user-agent> |
||
5916 | <user-agent> |
||
5917 | <ID>id_g_m_409</ID> |
||
5918 | <String>Goblin/0.9.x (http://www.goguides.org/goblin-info.html)</String> |
||
5919 | <Description>GoGuides.Org (195.226.137.xx) robot</Description> |
||
5920 | <Type>R</Type> |
||
5921 | <Comment></Comment> |
||
5922 | <Link1>http://www.goguides.org/goblin-info.html</Link1> |
||
5923 | <Link2></Link2> |
||
5924 | </user-agent> |
||
5925 | <user-agent> |
||
5926 | <ID>id_g_m_410</ID> |
||
5927 | <String>GoForIt.com</String> |
||
5928 | <Description>GoForIt Search robot</Description> |
||
5929 | <Type>R</Type> |
||
5930 | <Comment>208.109.236.xx</Comment> |
||
5931 | <Link1>http://www.goforit.com</Link1> |
||
5932 | <Link2></Link2> |
||
5933 | </user-agent> |
||
5934 | <user-agent> |
||
5935 | <ID>id_g_m_411</ID> |
||
5936 | <String>GOFORITBOT ( http://www.goforit.com/about/ )</String> |
||
5937 | <Description>GoForIt Search robot</Description> |
||
5938 | <Type>R</Type> |
||
5939 | <Comment>208.109.236.xx</Comment> |
||
5940 | <Link1>http://www.goforit.com</Link1> |
||
5941 | <Link2></Link2> |
||
5942 | </user-agent> |
||
5943 | <user-agent> |
||
5944 | <ID>id_g_m_020306_1</ID> |
||
5945 | <String>GoGuides.Org Link Check</String> |
||
5946 | <Description>GoGuides.org directory & search link checking</Description> |
||
5947 | <Type>C</Type> |
||
5948 | <Comment></Comment> |
||
5949 | <Link1>http://www.goguides.org/</Link1> |
||
5950 | <Link2></Link2> |
||
5951 | </user-agent> |
||
5952 | <user-agent> |
||
5953 | <ID>id_g_m_230207_2</ID> |
||
5954 | <String>GoldenFeed Spider 1.0 (http://www.goldenfeed.com)</String> |
||
5955 | <Description>GoldenFeed.com - RSS search engine</Description> |
||
5956 | <Type>C</Type> |
||
5957 | <Comment>74.52.41.1xx</Comment> |
||
5958 | <Link1>http://www.goldenfeed.com/</Link1> |
||
5959 | <Link2></Link2> |
||
5960 | </user-agent> |
||
5961 | <user-agent> |
||
5962 | <ID>id_g_m_412</ID> |
||
5963 | <String>Goldfire Server</String> |
||
5964 | <Description>Invention Machines Goldfire Server</Description> |
||
5965 | <Type>P</Type> |
||
5966 | <Comment></Comment> |
||
5967 | <Link1>http://www.invention-machine.com/custsupport/GFR_install.cfm</Link1> |
||
5968 | <Link2></Link2> |
||
5969 | </user-agent> |
||
5970 | <user-agent> |
||
5971 | <ID>id_g_m_041006_1</ID> |
||
5972 | <String>gonzo1[P] +http://www.suchen.de/popups/faq.jsp</String> |
||
5973 | <Description>suchen.de German local search robot</Description> |
||
5974 | <Type>R</Type> |
||
5975 | <Comment>212.34.185.xx</Comment> |
||
5976 | <Link1>http://www.suchen.de/</Link1> |
||
5977 | <Link2></Link2> |
||
5978 | </user-agent> |
||
5979 | <user-agent> |
||
5980 | <ID>id_g_m_130108_2</ID> |
||
5981 | <String>gonzo2[P] +http://www.suchen.de/faq.html</String> |
||
5982 | <Description>suchen.de German local search robot</Description> |
||
5983 | <Type>R</Type> |
||
5984 | <Comment>212.34.185.xx</Comment> |
||
5985 | <Link1>http://www.suchen.de/</Link1> |
||
5986 | <Link2></Link2> |
||
5987 | </user-agent> |
||
5988 | <user-agent> |
||
5989 | <ID>id_g_m_413</ID> |
||
5990 | <String>Goofer/0.2</String> |
||
5991 | <Description>Some private robot (Wanadoo.fr client)</Description> |
||
5992 | <Type>R</Type> |
||
5993 | <Comment></Comment> |
||
5994 | <Link1></Link1> |
||
5995 | <Link2></Link2> |
||
5996 | </user-agent> |
||
5997 | <user-agent> |
||
5998 | <ID>id_g_m_300606_1</ID> |
||
5999 | <String>Google Talk</String> |
||
6000 | <Description>Google instant messenger</Description> |
||
6001 | <Type>B</Type> |
||
6002 | <Comment></Comment> |
||
6003 | <Link1>http://www.google.com/talk/</Link1> |
||
6004 | <Link2></Link2> |
||
6005 | </user-agent> |
||
6006 | <user-agent> |
||
6007 | <ID>id_g_m_414</ID> |
||
6008 | <String>googlebot (larbin2.6.0@unspecified.mail)</String> |
||
6009 | <Description>Packard Bell Net user robot (*not* Google)</Description> |
||
6010 | <Type></Type> |
||
6011 | <Comment></Comment> |
||
6012 | <Link1></Link1> |
||
6013 | <Link2></Link2> |
||
6014 | </user-agent> |
||
6015 | <user-agent> |
||
6016 | <ID>id_g_m_050106_1</ID> |
||
6017 | <String>Googlebot-Image/1.0</String> |
||
6018 | <Description>Google image crawler (66.249.72.xxx)</Description> |
||
6019 | <Type>R</Type> |
||
6020 | <Comment></Comment> |
||
6021 | <Link1>http://www.google.com</Link1> |
||
6022 | <Link2></Link2> |
||
6023 | </user-agent> |
||
6024 | <user-agent> |
||
6025 | <ID>id_g_m_415</ID> |
||
6026 | <String>Googlebot-Image/1.0 ( http://www.googlebot.com/bot.html)</String> |
||
6027 | <Description>Google image crawler (66.249.72.xxx)</Description> |
||
6028 | <Type>R</Type> |
||
6029 | <Comment></Comment> |
||
6030 | <Link1>http://www.google.com</Link1> |
||
6031 | <Link2></Link2> |
||
6032 | </user-agent> |
||
6033 | <user-agent> |
||
6034 | <ID>id_g_m_416</ID> |
||
6035 | <String>Googlebot/2.1 ( http://www.google.com/bot.html)</String> |
||
6036 | <Description>Google robot 66.249.64.XXX</Description> |
||
6037 | <Type>R</Type> |
||
6038 | <Comment> s. also: - Mozilla/4.0 (MobilePhone SCP ... - Mozilla/5.0 (compatible; Googlebot/2.1...</Comment> |
||
6039 | <Link1>http://www.google.com</Link1> |
||
6040 | <Link2></Link2> |
||
6041 | </user-agent> |
||
6042 | <user-agent> |
||
6043 | <ID>id_g_m_417</ID> |
||
6044 | <String>Googlebot/2.1 ( http://www.googlebot.com/bot.html)</String> |
||
6045 | <Description>Google robot 66.249.64.XXX</Description> |
||
6046 | <Type>R</Type> |
||
6047 | <Comment></Comment> |
||
6048 | <Link1>http://www.google.com</Link1> |
||
6049 | <Link2></Link2> |
||
6050 | </user-agent> |
||
6051 | <user-agent> |
||
6052 | <ID>id_g_m_418</ID> |
||
6053 | <String>Googlebot/Test ( http://www.googlebot.com/bot.html)</String> |
||
6054 | <Description>Google robot 66.249.64.XXX</Description> |
||
6055 | <Type>R</Type> |
||
6056 | <Comment></Comment> |
||
6057 | <Link1>http://www.google.com</Link1> |
||
6058 | <Link2></Link2> |
||
6059 | </user-agent> |
||
6060 | <user-agent> |
||
6061 | <ID>id_g_m_280209_2</ID> |
||
6062 | <String>Gordon's Spider/Nutch-0.9 (http://www.sharethis.com; gordon@sharethis.com)</String> |
||
6063 | <Description>ShareThis social networking service via Amazon Web Services</Description> |
||
6064 | <Type>C</Type> |
||
6065 | <Comment>174.129.242.x</Comment> |
||
6066 | <Link1>http://sharethis.com/</Link1> |
||
6067 | <Link2>http://www.amazonaws.com/</Link2> |
||
6068 | </user-agent> |
||
6069 | <user-agent> |
||
6070 | <ID>id_g_m_419</ID> |
||
6071 | <String>GrapeFX/0.3 libwww/5.4.0</String> |
||
6072 | <Description>Grapeshot web search system API</Description> |
||
6073 | <Type>R</Type> |
||
6074 | <Comment></Comment> |
||
6075 | <Link1>http://www.grapeshot.co.uk/html/Index.html</Link1> |
||
6076 | <Link2></Link2> |
||
6077 | </user-agent> |
||
6078 | <user-agent> |
||
6079 | <ID>id_g_m_300907_4</ID> |
||
6080 | <String>great-plains-web-spider/flatlandbot (Flatland Industries Web Spider; http://www.flatlandindustries.com/flatlandbot.php; jason@flatlandindustries.com)</String> |
||
6081 | <Description>Flatland Industries vertical search solution</Description> |
||
6082 | <Type>R</Type> |
||
6083 | <Comment>74.62.161.xx</Comment> |
||
6084 | <Link1>http://www.flatlandindustries.com/</Link1> |
||
6085 | <Link2>http://www.flatlandindustries.com/flatlandbot.php</Link2> |
||
6086 | </user-agent> |
||
6087 | <user-agent> |
||
6088 | <ID>id_g_m_250707_2</ID> |
||
6089 | <String>GreatNews/1.0</String> |
||
6090 | <Description>GreatNews 1.0 Beta RSS reader</Description> |
||
6091 | <Type>B</Type> |
||
6092 | <Comment></Comment> |
||
6093 | <Link1>http://www.curiostudio.com/</Link1> |
||
6094 | <Link2></Link2> |
||
6095 | </user-agent> |
||
6096 | <user-agent> |
||
6097 | <ID>id_g_m_170207_2</ID> |
||
6098 | <String>GreenBrowser</String> |
||
6099 | <Description>GreenBrowser - IE based browser (China)</Description> |
||
6100 | <Type>B</Type> |
||
6101 | <Comment></Comment> |
||
6102 | <Link1>http://www.morequick.com/indexen.htm</Link1> |
||
6103 | <Link2></Link2> |
||
6104 | </user-agent> |
||
6105 | <user-agent> |
||
6106 | <ID>id_g_m_100307_2</ID> |
||
6107 | <String>gridwell (http://search.gridwell.com)</String> |
||
6108 | <Description>search gridwell favicon display</Description> |
||
6109 | <Type>D</Type> |
||
6110 | <Comment>212.227.127.xx</Comment> |
||
6111 | <Link1>http://search.gridwell.com/</Link1> |
||
6112 | <Link2></Link2> |
||
6113 | </user-agent> |
||
6114 | <user-agent> |
||
6115 | <ID>id_g_m_420</ID> |
||
6116 | <String>GrigorBot 0.8 (http://www.grigor.biz/bot.html)</String> |
||
6117 | <Description>Grigor Search bot</Description> |
||
6118 | <Type>R</Type> |
||
6119 | <Comment></Comment> |
||
6120 | <Link1>http://www.grigor.biz</Link1> |
||
6121 | <Link2></Link2> |
||
6122 | </user-agent> |
||
6123 | <user-agent> |
||
6124 | <ID>id_g_m_161206_1</ID> |
||
6125 | <String>Gromit/1.0</String> |
||
6126 | <Description>Australasian Legal Information Institute (AustLII) robot</Description> |
||
6127 | <Type>R</Type> |
||
6128 | <Comment></Comment> |
||
6129 | <Link1>http://www.austlii.edu.au/</Link1> |
||
6130 | <Link2>http://www2.austlii.edu.au/~dan/gromit/</Link2> |
||
6131 | </user-agent> |
||
6132 | <user-agent> |
||
6133 | <ID>id_g_m_421</ID> |
||
6134 | <String>grub crawler(http://www.grub.org)</String> |
||
6135 | <Description>Grub open source crawler</Description> |
||
6136 | <Type>R</Type> |
||
6137 | <Comment></Comment> |
||
6138 | <Link1>http://www.grub.org</Link1> |
||
6139 | <Link2></Link2> |
||
6140 | </user-agent> |
||
6141 | <user-agent> |
||
6142 | <ID>id_g_m_422</ID> |
||
6143 | <String>grub-client</String> |
||
6144 | <Description>Grub open source crawler</Description> |
||
6145 | <Type>R</Type> |
||
6146 | <Comment></Comment> |
||
6147 | <Link1>http://www.grub.org</Link1> |
||
6148 | <Link2></Link2> |
||
6149 | </user-agent> |
||
6150 | <user-agent> |
||
6151 | <ID>id_g_m_423</ID> |
||
6152 | <String>gsa-crawler (Enterprise; GID-01422; jplastiras@google.com)</String> |
||
6153 | <Description>Google Search Appliance robot (216.239.xx.xx)</Description> |
||
6154 | <Type>R</Type> |
||
6155 | <Comment></Comment> |
||
6156 | <Link1>http://www.google.com/enterprise/gsa/</Link1> |
||
6157 | <Link2></Link2> |
||
6158 | </user-agent> |
||
6159 | <user-agent> |
||
6160 | <ID>id_g_m_424</ID> |
||
6161 | <String>gsa-crawler (Enterprise; GID-01742;gsatesting@rediffmail.com)</String> |
||
6162 | <Description>Google Search Appliance robot (216.239.xx.xx)</Description> |
||
6163 | <Type>R</Type> |
||
6164 | <Comment></Comment> |
||
6165 | <Link1>http://www.google.com/enterprise/gsa/</Link1> |
||
6166 | <Link2></Link2> |
||
6167 | </user-agent> |
||
6168 | <user-agent> |
||
6169 | <ID>id_g_m_060506_1</ID> |
||
6170 | <String>gsa-crawler (Enterprise; GIX-02057; dm@enhesa.com)</String> |
||
6171 | <Description>Google Enterprise Search Appliance used by Enhesa (212.35.100.1xx)</Description> |
||
6172 | <Type>R</Type> |
||
6173 | <Comment></Comment> |
||
6174 | <Link1>http://www.enhesa.com/enhesa/en/default.asp</Link1> |
||
6175 | <Link2>http://www.google.com/enterprise/gsa/</Link2> |
||
6176 | </user-agent> |
||
6177 | <user-agent> |
||
6178 | <ID>id_g_m_311205_1</ID> |
||
6179 | <String>gsa-crawler (Enterprise; GIX-03519; cknuetter@stubhub.com)</String> |
||
6180 | <Description>Google Enterprise Search Appliance used by IBM (129.41.20.1xx)</Description> |
||
6181 | <Type>R</Type> |
||
6182 | <Comment></Comment> |
||
6183 | <Link1>http://www.google.com/enterprise/gsa/</Link1> |
||
6184 | <Link2></Link2> |
||
6185 | </user-agent> |
||
6186 | <user-agent> |
||
6187 | <ID>id_g_m_425</ID> |
||
6188 | <String>gsa-crawler (Enterprise; GIX-0xxxx; enterprise-training@google.com)</String> |
||
6189 | <Description>Google Search Appliance robot (216.239.xx.xx)</Description> |
||
6190 | <Type>R</Type> |
||
6191 | <Comment></Comment> |
||
6192 | <Link1>http://www.google.com/enterprise/gsa/</Link1> |
||
6193 | <Link2></Link2> |
||
6194 | </user-agent> |
||
6195 | <user-agent> |
||
6196 | <ID>id_g_m_081006_1</ID> |
||
6197 | <String>GSiteCrawler/v1.xx rev. xxx (http://gsitecrawler.com/)</String> |
||
6198 | <Description>GSiteCrawler - Google sitemap generator for Windows</Description> |
||
6199 | <Type>C</Type> |
||
6200 | <Comment></Comment> |
||
6201 | <Link1>http://gsitecrawler.com/</Link1> |
||
6202 | <Link2></Link2> |
||
6203 | </user-agent> |
||
6204 | <user-agent> |
||
6205 | <ID>id_g_m_260207_1</ID> |
||
6206 | <String>Guestbook Auto Submitter</String> |
||
6207 | <Description>Guestbook spamming tool</Description> |
||
6208 | <Type>S</Type> |
||
6209 | <Comment></Comment> |
||
6210 | <Link1></Link1> |
||
6211 | <Link2></Link2> |
||
6212 | </user-agent> |
||
6213 | <user-agent> |
||
6214 | <ID>id_g_m_426</ID> |
||
6215 | <String>Gulliver/1.3</String> |
||
6216 | <Description>Northernlight robot</Description> |
||
6217 | <Type>R</Type> |
||
6218 | <Comment></Comment> |
||
6219 | <Link1>http://www.northernlight.com</Link1> |
||
6220 | <Link2></Link2> |
||
6221 | </user-agent> |
||
6222 | <user-agent> |
||
6223 | <ID>id_g_m_427</ID> |
||
6224 | <String>Gulper Web Bot 0.2.4 (www.ecsl.cs.sunysb.edu/~maxim/cgi-bin/Link/GulperBot)</String> |
||
6225 | <Description>Yuntis Collaborative Web Resource Categorization and Ranking Project robot</Description> |
||
6226 | <Type>R</Type> |
||
6227 | <Comment></Comment> |
||
6228 | <Link1>http://www.ecsl.cs.sunysb.edu/yuntis/</Link1> |
||
6229 | <Link2></Link2> |
||
6230 | </user-agent> |
||
6231 | <user-agent> |
||
6232 | <ID>id_g_m_140907_1</ID> |
||
6233 | <String>Gungho/0.08004 (http://code.google.com/p/gungho-crawler/wiki/Index)</String> |
||
6234 | <Description>Gungho - Extensible web crawler written in Perl by Google Code</Description> |
||
6235 | <Type>R</Type> |
||
6236 | <Comment></Comment> |
||
6237 | <Link1>http://code.google.com/p/gungho-crawler/wiki/Index</Link1> |
||
6238 | <Link2></Link2> |
||
6239 | </user-agent> |
||
6240 | <user-agent> |
||
6241 | <ID>id_g_m_211106_1</ID> |
||
6242 | <String>GurujiBot/1.0 (+http://www.guruji.com/WebmasterFAQ.html)</String> |
||
6243 | <Description>guruji : the Indian search engine robot</Description> |
||
6244 | <Type>R</Type> |
||
6245 | <Comment>209.128.80.1xx / 72.20.109.xx</Comment> |
||
6246 | <Link1>http://www.guruji.com/</Link1> |
||
6247 | <Link2></Link2> |
||
6248 | </user-agent> |
||
6249 | <user-agent> |
||
6250 | <ID>id_g_m_100508_2</ID> |
||
6251 | <String>GurujiImageBot/1.0 (+http://www.guruji.com/en/WebmasterFAQ.html)</String> |
||
6252 | <Description>guruji : the Indian search engine picture crawler</Description> |
||
6253 | <Type>R</Type> |
||
6254 | <Comment>72.20.109.xx</Comment> |
||
6255 | <Link1>http://www.guruji.com/</Link1> |
||
6256 | <Link2></Link2> |
||
6257 | </user-agent> |
||
6258 | <user-agent> |
||
6259 | <ID>id_g_m_291108_3</ID> |
||
6260 | <String>Haier-T10C/1.0 iPanel/2.0 WAP2.0 (compatible; UP.Browser/6.2.2.4; UPG1; UP/4.0; Embedded)</String> |
||
6261 | <Description>Openwave Mobile Browser on Haier T10C mobile</Description> |
||
6262 | <Type>B</Type> |
||
6263 | <Comment></Comment> |
||
6264 | <Link1>http://www.openwave.com</Link1> |
||
6265 | <Link2></Link2> |
||
6266 | </user-agent> |
||
6267 | <user-agent> |
||
6268 | <ID>id_g_m_171105_5</ID> |
||
6269 | <String>HappyFunBot/1.1</String> |
||
6270 | <Description>Happy Fun Search robot</Description> |
||
6271 | <Type>R</Type> |
||
6272 | <Comment></Comment> |
||
6273 | <Link1>http://www.happyfunsearch.com/bot.html</Link1> |
||
6274 | <Link2></Link2> |
||
6275 | </user-agent> |
||
6276 | <user-agent> |
||
6277 | <ID>id_g_m_428</ID> |
||
6278 | <String>Harvest-NG/1.0.2</String> |
||
6279 | <Description>Harvest-NG web crawler used by search.yahoo.com</Description> |
||
6280 | <Type>R</Type> |
||
6281 | <Comment>see also Exalead NG and NG/1.0</Comment> |
||
6282 | <Link1>http://search.yahoo.com</Link1> |
||
6283 | <Link2></Link2> |
||
6284 | </user-agent> |
||
6285 | <user-agent> |
||
6286 | <ID>id_g_m_429</ID> |
||
6287 | <String>Haste/0.12 (HOME: http://haste.kytoon.com/)</String> |
||
6288 | <Description>Haste - web mapping and monitoring system</Description> |
||
6289 | <Type>R C</Type> |
||
6290 | <Comment>site is closed</Comment> |
||
6291 | <Link1>http://haste.kytoon.com</Link1> |
||
6292 | <Link2></Link2> |
||
6293 | </user-agent> |
||
6294 | <user-agent> |
||
6295 | <ID>id_g_m_430</ID> |
||
6296 | <String>Hatena Antenna/0.4 (http://a.hatena.ne.jp/help#robot)</String> |
||
6297 | <Description>Hatena::Antenna Japan robot</Description> |
||
6298 | <Type>R</Type> |
||
6299 | <Comment>221.186.146.xx</Comment> |
||
6300 | <Link1>http://a.hatena.ne.jp</Link1> |
||
6301 | <Link2></Link2> |
||
6302 | </user-agent> |
||
6303 | <user-agent> |
||
6304 | <ID>id_g_m_110606_2</ID> |
||
6305 | <String>Hatena Mobile Gateway/1.0</String> |
||
6306 | <Description>Hatena Japan proxy for handheld/mobile clients</Description> |
||
6307 | <Type>P</Type> |
||
6308 | <Comment>221.186.146.xx</Comment> |
||
6309 | <Link1>http://www.hatena.ne.jp/</Link1> |
||
6310 | <Link2></Link2> |
||
6311 | </user-agent> |
||
6312 | <user-agent> |
||
6313 | <ID>id_g_m_431</ID> |
||
6314 | <String>Hatena Pagetitle Agent/1.0</String> |
||
6315 | <Description>Hatena Japan robot</Description> |
||
6316 | <Type>R</Type> |
||
6317 | <Comment>221.186.146.xx</Comment> |
||
6318 | <Link1>http://www.hatena.ne.jp</Link1> |
||
6319 | <Link2></Link2> |
||
6320 | </user-agent> |
||
6321 | <user-agent> |
||
6322 | <ID>id_g_m_240207_1</ID> |
||
6323 | <String>Hatena RSS/0.3 (http://r.hatena.ne.jp)</String> |
||
6324 | <Description>Hatena Japan RSS feed robot</Description> |
||
6325 | <Type>R</Type> |
||
6326 | <Comment>221.186.146.xx</Comment> |
||
6327 | <Link1>http://www.hatena.ne.jp</Link1> |
||
6328 | <Link2></Link2> |
||
6329 | </user-agent> |
||
6330 | <user-agent> |
||
6331 | <ID>id_g_m_110606_1</ID> |
||
6332 | <String>HatenaScreenshot/1.0 (checker)</String> |
||
6333 | <Description>Hatena::Diary (Japan) web page screenshot robot</Description> |
||
6334 | <Type>R D</Type> |
||
6335 | <Comment>221.186.146.xx</Comment> |
||
6336 | <Link1>http://www.hatena.ne.jp/</Link1> |
||
6337 | <Link2></Link2> |
||
6338 | </user-agent> |
||
6339 | <user-agent> |
||
6340 | <ID>id_g_m_120108_1</ID> |
||
6341 | <String>hbtronix.spider.2 -- http://hbtronix.de/spider.php</String> |
||
6342 | <Description>hbtronix.spider - Domain name spider (Germany)</Description> |
||
6343 | <Type>R</Type> |
||
6344 | <Comment>89.110.157.*</Comment> |
||
6345 | <Link1>http://hbtronix.de/spider.php</Link1> |
||
6346 | <Link2></Link2> |
||
6347 | </user-agent> |
||
6348 | <user-agent> |
||
6349 | <ID>id_g_m_432</ID> |
||
6350 | <String>HeinrichderMiragoRobot</String> |
||
6351 | <Description>Mirago Germany robot</Description> |
||
6352 | <Type>R</Type> |
||
6353 | <Comment></Comment> |
||
6354 | <Link1>http://www.mirago.de/</Link1> |
||
6355 | <Link2></Link2> |
||
6356 | </user-agent> |
||
6357 | <user-agent> |
||
6358 | <ID>id_g_m_433</ID> |
||
6359 | <String>HeinrichderMiragoRobot (http://www.miragorobot.com/scripts/deinfo.asp)</String> |
||
6360 | <Description>Mirago Germany robot</Description> |
||
6361 | <Type>R</Type> |
||
6362 | <Comment></Comment> |
||
6363 | <Link1>http://www.mirago.de/</Link1> |
||
6364 | <Link2></Link2> |
||
6365 | </user-agent> |
||
6366 | <user-agent> |
||
6367 | <ID>id_g_m_434</ID> |
||
6368 | <String>Helix/1.x ( http://www.sitesearch.ca/helix/)</String> |
||
6369 | <Description>Helix - The SiteSearch (Canada) web crawler</Description> |
||
6370 | <Type>R</Type> |
||
6371 | <Comment></Comment> |
||
6372 | <Link1>http://www.sitesearch.ca</Link1> |
||
6373 | <Link2></Link2> |
||
6374 | </user-agent> |
||
6375 | <user-agent> |
||
6376 | <ID>id_g_m_080206_3</ID> |
||
6377 | <String>HenriLeRobotMirago (http://www.miragorobot.com/scripts/frinfo.asp)</String> |
||
6378 | <Description>Mirago France robot</Description> |
||
6379 | <Type>R</Type> |
||
6380 | <Comment></Comment> |
||
6381 | <Link1>http://www.mirago.fr/</Link1> |
||
6382 | <Link2></Link2> |
||
6383 | </user-agent> |
||
6384 | <user-agent> |
||
6385 | <ID>id_g_m_435</ID> |
||
6386 | <String>HenrytheMiragoRobot</String> |
||
6387 | <Description>Mirago search (UK) robot</Description> |
||
6388 | <Type>R</Type> |
||
6389 | <Comment>217.154.245.2xx</Comment> |
||
6390 | <Link1>http://www.mirago.co.uk</Link1> |
||
6391 | <Link2></Link2> |
||
6392 | </user-agent> |
||
6393 | <user-agent> |
||
6394 | <ID>id_g_m_060806_3</ID> |
||
6395 | <String>HenryTheMiragoRobot (http://www.miragorobot.com/scripts/mrinfo.asp)</String> |
||
6396 | <Description>Mirago search (UK) robot</Description> |
||
6397 | <Type>R</Type> |
||
6398 | <Comment>217.154.245.2xx</Comment> |
||
6399 | <Link1>http://www.mirago.co.uk</Link1> |
||
6400 | <Link2></Link2> |
||
6401 | </user-agent> |
||
6402 | <user-agent> |
||
6403 | <ID>id_g_m_436</ID> |
||
6404 | <String>hgrepurl/1.0</String> |
||
6405 | <Description>O'Reilly's Perl LWP example client program from Web Client Programming with Perl</Description> |
||
6406 | <Type></Type> |
||
6407 | <Comment></Comment> |
||
6408 | <Link1></Link1> |
||
6409 | <Link2></Link2> |
||
6410 | </user-agent> |
||
6411 | <user-agent> |
||
6412 | <ID>id_g_m_437</ID> |
||
6413 | <String>Hi! I'm CsCrawler my homepage: http://www.kde.cs.uni-kassel.de/lehre/ss2005/googlespam/crawler.html RPT-HTTPClient/0.3-3</String> |
||
6414 | <Description>University of Kassel Germany CsCrawler using the HTTPClient library</Description> |
||
6415 | <Type>R</Type> |
||
6416 | <Comment></Comment> |
||
6417 | <Link1>http://www.kde.cs.uni-kassel.de/lehre/ss2005/googlespam/crawler.html</Link1> |
||
6418 | <Link2>http://www.innovation.ch/java/HTTPClient/</Link2> |
||
6419 | </user-agent> |
||
6420 | <user-agent> |
||
6421 | <ID>id_g_m_438</ID> |
||
6422 | <String>HiDownload</String> |
||
6423 | <Description>HiDownload download manager</Description> |
||
6424 | <Type>D</Type> |
||
6425 | <Comment></Comment> |
||
6426 | <Link1>http://www.streamingstar.com/hidownload.htm</Link1> |
||
6427 | <Link2></Link2> |
||
6428 | </user-agent> |
||
6429 | <user-agent> |
||
6430 | <ID>id_g_m_439</ID> |
||
6431 | <String>Hippias/0.9 Beta</String> |
||
6432 | <Description>Hippias robot</Description> |
||
6433 | <Type>R</Type> |
||
6434 | <Comment>site is offline</Comment> |
||
6435 | <Link1>http://hippias.evansville.edu</Link1> |
||
6436 | <Link2></Link2> |
||
6437 | </user-agent> |
||
6438 | <user-agent> |
||
6439 | <ID>id_g_m_440</ID> |
||
6440 | <String>HitList</String> |
||
6441 | <Description>Pilot Hitlist web analytics solution</Description> |
||
6442 | <Type>R</Type> |
||
6443 | <Comment></Comment> |
||
6444 | <Link1>http://www.pilotsoftware.com/products_solutions/hitlist.html</Link1> |
||
6445 | <Link2></Link2> |
||
6446 | </user-agent> |
||
6447 | <user-agent> |
||
6448 | <ID>id_g_m_441</ID> |
||
6449 | <String>Hitwise Spider v1.0 http://www.hitwise.com</String> |
||
6450 | <Description>Hitwise spider</Description> |
||
6451 | <Type>R</Type> |
||
6452 | <Comment></Comment> |
||
6453 | <Link1>http://www.hitwise.com</Link1> |
||
6454 | <Link2></Link2> |
||
6455 | </user-agent> |
||
6456 | <user-agent> |
||
6457 | <ID>id_g_m_442</ID> |
||
6458 | <String>HLoader</String> |
||
6459 | <Description>diff. IPs / unknown services</Description> |
||
6460 | <Type></Type> |
||
6461 | <Comment> i.e.: - 204.95.207.xxx user agent ? - 66.27.113.xx link checking ?</Comment> |
||
6462 | <Link1></Link1> |
||
6463 | <Link2></Link2> |
||
6464 | </user-agent> |
||
6465 | <user-agent> |
||
6466 | <ID>id_g_m_040907_1</ID> |
||
6467 | <String>holmes/3.11 (http://morfeo.centrum.cz/bot)</String> |
||
6468 | <Description>Morfeo / Centrum Search (Czech Republic) robot from 65.102.46.xxx</Description> |
||
6469 | <Type>R</Type> |
||
6470 | <Comment></Comment> |
||
6471 | <Link1>http://morfeo.centrum.cz/</Link1> |
||
6472 | <Link2></Link2> |
||
6473 | </user-agent> |
||
6474 | <user-agent> |
||
6475 | <ID>id_g_m_220906_2</ID> |
||
6476 | <String>holmes/3.9 (onet.pl)</String> |
||
6477 | <Description>Onet.pl (Poland) search robot</Description> |
||
6478 | <Type>R</Type> |
||
6479 | <Comment>213.180.137.xx</Comment> |
||
6480 | <Link1>http://szukaj.onet.pl/</Link1> |
||
6481 | <Link2></Link2> |
||
6482 | </user-agent> |
||
6483 | <user-agent> |
||
6484 | <ID>id_g_m_181006_1</ID> |
||
6485 | <String>holmes/3.xx (OnetSzukaj/5.0; +http://szukaj.onet.pl)</String> |
||
6486 | <Description>Onet.pl (Poland) search robot</Description> |
||
6487 | <Type>R</Type> |
||
6488 | <Comment>213.180.137.xx</Comment> |
||
6489 | <Link1>http://szukaj.onet.pl/</Link1> |
||
6490 | <Link2></Link2> |
||
6491 | </user-agent> |
||
6492 | <user-agent> |
||
6493 | <ID>id_g_m_443</ID> |
||
6494 | <String>holmes/x.x</String> |
||
6495 | <Description>Morfeo / Centrum Search (Czech Republic) robot from 65.102.46.xxx</Description> |
||
6496 | <Type>R</Type> |
||
6497 | <Comment></Comment> |
||
6498 | <Link1>http://morfeo.centrum.cz/</Link1> |
||
6499 | <Link2></Link2> |
||
6500 | </user-agent> |
||
6501 | <user-agent> |
||
6502 | <ID>id_g_m_021108_2</ID> |
||
6503 | <String>HolmesBot (http://holmes.ge)</String> |
||
6504 | <Description>Holes search robot (Georgia)</Description> |
||
6505 | <Type>R</Type> |
||
6506 | <Comment>77.92.229.3x</Comment> |
||
6507 | <Link1>http://holmes.ge/</Link1> |
||
6508 | <Link2></Link2> |
||
6509 | </user-agent> |
||
6510 | <user-agent> |
||
6511 | <ID>id_g_m_444</ID> |
||
6512 | <String>HomePageSearch(hpsearch.uni-trier.de)</String> |
||
6513 | <Description>HomePageSearch robot</Description> |
||
6514 | <Type>R</Type> |
||
6515 | <Comment></Comment> |
||
6516 | <Link1>http://hpsearch.uni-trier.de/</Link1> |
||
6517 | <Link2></Link2> |
||
6518 | </user-agent> |
||
6519 | <user-agent> |
||
6520 | <ID>id_g_m_445</ID> |
||
6521 | <String>Homerbot: www.homerweb.com</String> |
||
6522 | <Description>Homerweb search robot</Description> |
||
6523 | <Type>R</Type> |
||
6524 | <Comment></Comment> |
||
6525 | <Link1>http://www.homerweb.com</Link1> |
||
6526 | <Link2></Link2> |
||
6527 | </user-agent> |
||
6528 | <user-agent> |
||
6529 | <ID>id_g_m_220606_1</ID> |
||
6530 | <String>Honda-Search/0.7.2 (Nutch; http://lucene.apache.org/nutch/bot.html; search@honda-search.com)</String> |
||
6531 | <Description>Honda-Search.com - Honda cars related search robot</Description> |
||
6532 | <Type>R</Type> |
||
6533 | <Comment>69.16.227.1xx</Comment> |
||
6534 | <Link1>http://www.honda-search.com/</Link1> |
||
6535 | <Link2></Link2> |
||
6536 | </user-agent> |
||
6537 | <user-agent> |
||
6538 | <ID>id_g_m_090206_1</ID> |
||
6539 | <String>HooWWWer/2.1.3 (debugging run) (+http://cosco.hiit.fi/search/hoowwwer/ | mailto:crawler-info<at>hiit.fi)</String> |
||
6540 | <Description>HooWWer - Next Generation Information Retrieval robot </Description> |
||
6541 | <Type>R</Type> |
||
6542 | <Comment></Comment> |
||
6543 | <Link1>http://cosco.hiit.fi</Link1> |
||
6544 | <Link2></Link2> |
||
6545 | </user-agent> |
||
6546 | <user-agent> |
||
6547 | <ID>id_g_m_446</ID> |
||
6548 | <String>HooWWWer/2.1.x ( http://cosco.hiit.fi/search/hoowwwer/ | mailto:crawler-info<at>hiit.fi)</String> |
||
6549 | <Description>HooWWer - Next Generation Information Retrieval robot (128.214.112.xx)</Description> |
||
6550 | <Type>R</Type> |
||
6551 | <Comment></Comment> |
||
6552 | <Link1>http://cosco.hiit.fi/</Link1> |
||
6553 | <Link2></Link2> |
||
6554 | </user-agent> |
||
6555 | <user-agent> |
||
6556 | <ID>id_g_m_447</ID> |
||
6557 | <String>HotJava/1.0.1/JRE1.1.x</String> |
||
6558 | <Description>HotJava browser plus HTML Component 1.1.x</Description> |
||
6559 | <Type>B</Type> |
||
6560 | <Comment></Comment> |
||
6561 | <Link1></Link1> |
||
6562 | <Link2></Link2> |
||
6563 | </user-agent> |
||
6564 | <user-agent> |
||
6565 | <ID>id_g_m_448</ID> |
||
6566 | <String>Hotzonu/x.0</String> |
||
6567 | <Description>Hotzuno - Japanese BBS reader client</Description> |
||
6568 | <Type>B</Type> |
||
6569 | <Comment></Comment> |
||
6570 | <Link1>http://hotzonu.hp.infoseek.co.jp/</Link1> |
||
6571 | <Link2></Link2> |
||
6572 | </user-agent> |
||
6573 | <user-agent> |
||
6574 | <ID>id_g_m_040507_1</ID> |
||
6575 | <String>HPL/Nutch-0.9 -</String> |
||
6576 | <Description>Unknown robot from HP Labs</Description> |
||
6577 | <Type>R</Type> |
||
6578 | <Comment>15.203.249.12x</Comment> |
||
6579 | <Link1>http://hpl.hp.com/</Link1> |
||
6580 | <Link2></Link2> |
||
6581 | </user-agent> |
||
6582 | <user-agent> |
||
6583 | <ID>id_g_m_449</ID> |
||
6584 | <String>htdig/3.1.6 (http://computerorgs.com)</String> |
||
6585 | <Description>COMPUTERorgs.com robot (205.134.190.xxx) using htdig</Description> |
||
6586 | <Type>R</Type> |
||
6587 | <Comment></Comment> |
||
6588 | <Link1>http://www.computerorgs.com/</Link1> |
||
6589 | <Link2>http://www.htdig.org</Link2> |
||
6590 | </user-agent> |
||
6591 | <user-agent> |
||
6592 | <ID>id_g_m_210106_1</ID> |
||
6593 | <String>htdig/3.1.6 (unconfigured@htdig.searchengine.maintainer)</String> |
||
6594 | <Description>htdig used by the Academie de Toulouse</Description> |
||
6595 | <Type>R</Type> |
||
6596 | <Comment>reads robots.txt</Comment> |
||
6597 | <Link1>http://www.ac-toulouse.fr/html/_.php</Link1> |
||
6598 | <Link2>http://www.htdig.org</Link2> |
||
6599 | </user-agent> |
||
6600 | <user-agent> |
||
6601 | <ID>id_g_m_450</ID> |
||
6602 | <String>htdig/3.1.x (root@localhost)</String> |
||
6603 | <Description>htdig search tool</Description> |
||
6604 | <Type>R</Type> |
||
6605 | <Comment></Comment> |
||
6606 | <Link1>http://www.htdig.org</Link1> |
||
6607 | <Link2></Link2> |
||
6608 | </user-agent> |
||
6609 | <user-agent> |
||
6610 | <ID>id_g_m_451</ID> |
||
6611 | <String>Html Link Validator (www.lithopssoft.com)</String> |
||
6612 | <Description>Lithops Software link validation tool</Description> |
||
6613 | <Type>C</Type> |
||
6614 | <Comment></Comment> |
||
6615 | <Link1>http://www.lithopssoft.com</Link1> |
||
6616 | <Link2></Link2> |
||
6617 | </user-agent> |
||
6618 | <user-agent> |
||
6619 | <ID>id_g_m_110506_3</ID> |
||
6620 | <String>HTML2JPG Blackbox, http://www.html2jpg.com</String> |
||
6621 | <Description>HTML2JPG webpage to image converter</Description> |
||
6622 | <Type>D</Type> |
||
6623 | <Comment></Comment> |
||
6624 | <Link1>http://www.html2jpg.com</Link1> |
||
6625 | <Link2></Link2> |
||
6626 | </user-agent> |
||
6627 | <user-agent> |
||
6628 | <ID>id_g_m_452</ID> |
||
6629 | <String>HTML2JPG Enterprise</String> |
||
6630 | <Description>HTML2JPG webpage to image converter</Description> |
||
6631 | <Type>D</Type> |
||
6632 | <Comment></Comment> |
||
6633 | <Link1>http://www.html2jpg.com</Link1> |
||
6634 | <Link2></Link2> |
||
6635 | </user-agent> |
||
6636 | <user-agent> |
||
6637 | <ID>id_g_m_101205_1</ID> |
||
6638 | <String>HTMLParser/1.x</String> |
||
6639 | <Description>HTML Parser Java library to parse HTML</Description> |
||
6640 | <Type>D</Type> |
||
6641 | <Comment></Comment> |
||
6642 | <Link1>http://sourceforge.net/projects/htmlparser</Link1> |
||
6643 | <Link2></Link2> |
||
6644 | </user-agent> |
||
6645 | <user-agent> |
||
6646 | <ID>id_g_m_071006_1</ID> |
||
6647 | <String>HTTP Retriever</String> |
||
6648 | <Description>PHP HTTP client to access Web servers</Description> |
||
6649 | <Type>D</Type> |
||
6650 | <Comment></Comment> |
||
6651 | <Link1>http://code.blitzaffe.com/pages/home/</Link1> |
||
6652 | <Link2></Link2> |
||
6653 | </user-agent> |
||
6654 | <user-agent> |
||
6655 | <ID>id_g_m_240306_1</ID> |
||
6656 | <String>http://Anonymouse.org/ (Unix)</String> |
||
6657 | <Description>Anonymous web proxy service</Description> |
||
6658 | <Type>P</Type> |
||
6659 | <Comment></Comment> |
||
6660 | <Link1>http://anonymouse.org/</Link1> |
||
6661 | <Link2></Link2> |
||
6662 | </user-agent> |
||
6663 | <user-agent> |
||
6664 | <ID>id_g_m_453</ID> |
||
6665 | <String>http://Ask.24x.Info/ (http://narres.it/)</String> |
||
6666 | <Description>Ask 24x Info (Germany) DMOZ related robot</Description> |
||
6667 | <Type>R</Type> |
||
6668 | <Comment></Comment> |
||
6669 | <Link1>http://narres.it</Link1> |
||
6670 | <Link2></Link2> |
||
6671 | </user-agent> |
||
6672 | <user-agent> |
||
6673 | <ID>id_g_m_070209_6</ID> |
||
6674 | <String>http://hilfe.acont.de/bot.html ACONTBOT</String> |
||
6675 | <Description>ACONTBOT - Acont search Germany robot</Description> |
||
6676 | <Type>R</Type> |
||
6677 | <Comment>82.149.246.2x</Comment> |
||
6678 | <Link1>http://acont.de/</Link1> |
||
6679 | <Link2>http://hilfe.acont.de/bot.htm</Link2> |
||
6680 | </user-agent> |
||
6681 | <user-agent> |
||
6682 | <ID>id_g_m_230408_1</ID> |
||
6683 | <String>http://OzySoftware.com/Index.html</String> |
||
6684 | <Description>OzySoftware.com software directory link checking</Description> |
||
6685 | <Type>C</Type> |
||
6686 | <Comment>202.173.141.x</Comment> |
||
6687 | <Link1>http://ozysoftware.com/index.html</Link1> |
||
6688 | <Link2></Link2> |
||
6689 | </user-agent> |
||
6690 | <user-agent> |
||
6691 | <ID>id_g_m_454</ID> |
||
6692 | <String>http://www.almaden.ibm.com/cs/crawler</String> |
||
6693 | <Description>IBM's Almaden Research robot</Description> |
||
6694 | <Type>R</Type> |
||
6695 | <Comment> s. also: - FocusedSampler - WFARC</Comment> |
||
6696 | <Link1>http://www.almaden.ibm.com</Link1> |
||
6697 | <Link2></Link2> |
||
6698 | </user-agent> |
||
6699 | <user-agent> |
||
6700 | <ID>id_g_m_455</ID> |
||
6701 | <String>http://www.almaden.ibm.com/cs/crawler [rc1.wf.ibm.com]</String> |
||
6702 | <Description>IBM's Almaden Research robot</Description> |
||
6703 | <Type>R</Type> |
||
6704 | <Comment></Comment> |
||
6705 | <Link1>http://www.almaden.ibm.com</Link1> |
||
6706 | <Link2></Link2> |
||
6707 | </user-agent> |
||
6708 | <user-agent> |
||
6709 | <ID>id_g_m_456</ID> |
||
6710 | <String>http://www.almaden.ibm.com/cs/crawler [wf216]</String> |
||
6711 | <Description>IBM's Almaden Research robot</Description> |
||
6712 | <Type>R</Type> |
||
6713 | <Comment></Comment> |
||
6714 | <Link1>http://www.almaden.ibm.com</Link1> |
||
6715 | <Link2></Link2> |
||
6716 | </user-agent> |
||
6717 | <user-agent> |
||
6718 | <ID>id_g_m_271105_4</ID> |
||
6719 | <String>http://www.istarthere.com_spider@istarthere.com</String> |
||
6720 | <Description>Istarthere.com search robot</Description> |
||
6721 | <Type>R</Type> |
||
6722 | <Comment></Comment> |
||
6723 | <Link1>http://www.istarthere.com/</Link1> |
||
6724 | <Link2></Link2> |
||
6725 | </user-agent> |
||
6726 | <user-agent> |
||
6727 | <ID>id_g_m_070106_1</ID> |
||
6728 | <String>http://www.monogol.de</String> |
||
6729 | <Description>Monogol - German open source search engine project (195.226.167.1xx)</Description> |
||
6730 | <Type>R</Type> |
||
6731 | <Comment></Comment> |
||
6732 | <Link1>http://www.monogol.de/</Link1> |
||
6733 | <Link2></Link2> |
||
6734 | </user-agent> |
||
6735 | <user-agent> |
||
6736 | <ID>id_g_m_060806_4</ID> |
||
6737 | <String>http://www.trendtech.dk/spider.asp)</String> |
||
6738 | <Description>TrendTech Search Engine (Denmark) robot</Description> |
||
6739 | <Type>R</Type> |
||
6740 | <Comment>87.104.18.xx</Comment> |
||
6741 | <Link1>http://www.trendtech.dk/</Link1> |
||
6742 | <Link2></Link2> |
||
6743 | </user-agent> |
||
6744 | <user-agent> |
||
6745 | <ID>id_g_m_290106_1</ID> |
||
6746 | <String>HTTP::Lite/2.x.x</String> |
||
6747 | <Description>HTTP::Lite - Standalone Perl module for retreiving HTTP documents</Description> |
||
6748 | <Type>D</Type> |
||
6749 | <Comment></Comment> |
||
6750 | <Link1>http://www.toybox.ca/http-lite/</Link1> |
||
6751 | <Link2></Link2> |
||
6752 | </user-agent> |
||
6753 | <user-agent> |
||
6754 | <ID>id_g_m_050108_1</ID> |
||
6755 | <String>HTTPEyes</String> |
||
6756 | <Description>HTTPEyes - Web proxy cache</Description> |
||
6757 | <Type>P</Type> |
||
6758 | <Comment></Comment> |
||
6759 | <Link1>http://bachue.com/httpeyes/</Link1> |
||
6760 | <Link2></Link2> |
||
6761 | </user-agent> |
||
6762 | <user-agent> |
||
6763 | <ID>id_g_m_457</ID> |
||
6764 | <String>HTTPResume v. 1.x</String> |
||
6765 | <Description>HTTPResume Amiga download manager</Description> |
||
6766 | <Type>D</Type> |
||
6767 | <Comment></Comment> |
||
6768 | <Link1>http://tesla.rcub.bg.ac.yu/%7Eantony/HTTPResume/</Link1> |
||
6769 | <Link2></Link2> |
||
6770 | </user-agent> |
||
6771 | <user-agent> |
||
6772 | <ID>id_g_m_031107_2</ID> |
||
6773 | <String>httpunit/1.5</String> |
||
6774 | <Description>HttpUnit - Java test code for emulating browser behaviour</Description> |
||
6775 | <Type>B</Type> |
||
6776 | <Comment></Comment> |
||
6777 | <Link1>http://httpunit.sourceforge.net/</Link1> |
||
6778 | <Link2></Link2> |
||
6779 | </user-agent> |
||
6780 | <user-agent> |
||
6781 | <ID>id_g_m_090306_1</ID> |
||
6782 | <String>httpunit/1.x</String> |
||
6783 | <Description>HttpUnit - Java browser behavior simulation tool</Description> |
||
6784 | <Type>B</Type> |
||
6785 | <Comment></Comment> |
||
6786 | <Link1>http://httpunit.sourceforge.net/</Link1> |
||
6787 | <Link2></Link2> |
||
6788 | </user-agent> |
||
6789 | <user-agent> |
||
6790 | <ID>id_g_m_010807_1</ID> |
||
6791 | <String>Hybrid/1.2 [en] (OS Independent)</String> |
||
6792 | <Description>Hybrid Share mono C#/Gtk# application for file sharing</Description> |
||
6793 | <Type></Type> |
||
6794 | <Comment></Comment> |
||
6795 | <Link1>http://hybrid-share.sourceforge.net/index.php</Link1> |
||
6796 | <Link2></Link2> |
||
6797 | </user-agent> |
||
6798 | <user-agent> |
||
6799 | <ID>id_g_m_300507_1</ID> |
||
6800 | <String>HyperEstraier/1.x.xx</String> |
||
6801 | <Description>Hyper Estraier full-text search system</Description> |
||
6802 | <Type>D</Type> |
||
6803 | <Comment></Comment> |
||
6804 | <Link1>http://hyperestraier.sourceforge.net/</Link1> |
||
6805 | <Link2></Link2> |
||
6806 | </user-agent> |
||
6807 | <user-agent> |
||
6808 | <ID>id_g_m_170906_1</ID> |
||
6809 | <String>i1searchbot/2.0 (i1search web crawler; http://www.i1search.com; crawler@i1search.com)</String> |
||
6810 | <Description>i1search robot</Description> |
||
6811 | <Type>R</Type> |
||
6812 | <Comment>65.111.164.1xx</Comment> |
||
6813 | <Link1>http://www.i1search.com/</Link1> |
||
6814 | <Link2></Link2> |
||
6815 | </user-agent> |
||
6816 | <user-agent> |
||
6817 | <ID>id_g_m_461</ID> |
||
6818 | <String>IAArchiver-1.0</String> |
||
6819 | <Description>Alexa / The Internet Archive (209.237.238.1xx)</Description> |
||
6820 | <Type>R</Type> |
||
6821 | <Comment></Comment> |
||
6822 | <Link1>http://www.alexa.com</Link1> |
||
6823 | <Link2></Link2> |
||
6824 | </user-agent> |
||
6825 | <user-agent> |
||
6826 | <ID>id_g_m_091205_2</ID> |
||
6827 | <String>iaskspider</String> |
||
6828 | <Description>Unknown robot (reads robots.txt) from chinatelecom (219.142.78.xx)</Description> |
||
6829 | <Type></Type> |
||
6830 | <Comment>Not from iask.com.cn - s. also Mozilla/5.0 (compatible; iaskspider/1.0 ..</Comment> |
||
6831 | <Link1></Link1> |
||
6832 | <Link2></Link2> |
||
6833 | </user-agent> |
||
6834 | <user-agent> |
||
6835 | <ID>id_g_m_111106_1</ID> |
||
6836 | <String>iaskspider2 (iask@staff.sina.com.cn)</String> |
||
6837 | <Description>Iask search / Sina portal robot (China)</Description> |
||
6838 | <Type>R</Type> |
||
6839 | <Comment>202.106.184.xxx</Comment> |
||
6840 | <Link1>http://iask.com/</Link1> |
||
6841 | <Link2>http://english.sina.com/index.html</Link2> |
||
6842 | </user-agent> |
||
6843 | <user-agent> |
||
6844 | <ID>id_g_m_458</ID> |
||
6845 | <String>ia_archiver</String> |
||
6846 | <Description>Alexa / The Internet Archive (209.237.238.1xx)</Description> |
||
6847 | <Type>R</Type> |
||
6848 | <Comment></Comment> |
||
6849 | <Link1>http://www.alexa.com</Link1> |
||
6850 | <Link2></Link2> |
||
6851 | </user-agent> |
||
6852 | <user-agent> |
||
6853 | <ID>id_g_m_459</ID> |
||
6854 | <String>ia_archiver-web.archive.org</String> |
||
6855 | <Description>Alexa / The Internet Archive (209.237.238.1xx)</Description> |
||
6856 | <Type>R</Type> |
||
6857 | <Comment></Comment> |
||
6858 | <Link1>http://www.alexa.com</Link1> |
||
6859 | <Link2></Link2> |
||
6860 | </user-agent> |
||
6861 | <user-agent> |
||
6862 | <ID>id_g_m_460</ID> |
||
6863 | <String>ia_archiver/1.6</String> |
||
6864 | <Description>Alexa / The Internet Archive (209.237.238.1xx)</Description> |
||
6865 | <Type>R</Type> |
||
6866 | <Comment></Comment> |
||
6867 | <Link1>http://www.alexa.com</Link1> |
||
6868 | <Link2></Link2> |
||
6869 | </user-agent> |
||
6870 | <user-agent> |
||
6871 | <ID>id_g_m_462</ID> |
||
6872 | <String>IBrowse/2.2 (AmigaOS 3.5)</String> |
||
6873 | <Description>IOSpirit iBrowse Amiga Browser</Description> |
||
6874 | <Type>B</Type> |
||
6875 | <Comment>was Hisoft (http://www.hisoft.co.uk)</Comment> |
||
6876 | <Link1>http://amiga.iospirit.de/</Link1> |
||
6877 | <Link2></Link2> |
||
6878 | </user-agent> |
||
6879 | <user-agent> |
||
6880 | <ID>id_g_m_463</ID> |
||
6881 | <String>IBrowse/2.2 (Windows 3.1)</String> |
||
6882 | <Description>IOSpirit iBrowse Amiga Browser</Description> |
||
6883 | <Type>B</Type> |
||
6884 | <Comment>was Hisoft (http://www.hisoft.co.uk)</Comment> |
||
6885 | <Link1>http://amiga.iospirit.de/</Link1> |
||
6886 | <Link2></Link2> |
||
6887 | </user-agent> |
||
6888 | <user-agent> |
||
6889 | <ID>id_g_m_464</ID> |
||
6890 | <String>iCab/2.5.2 (Macintosh; I; PPC)</String> |
||
6891 | <Description>iCab MAC Web browser</Description> |
||
6892 | <Type>B</Type> |
||
6893 | <Comment></Comment> |
||
6894 | <Link1>http://www.icab.de</Link1> |
||
6895 | <Link2></Link2> |
||
6896 | </user-agent> |
||
6897 | <user-agent> |
||
6898 | <ID>id_g_m_110207_2</ID> |
||
6899 | <String>ICC-Crawler(Mozilla-compatible; http://kc.nict.go.jp/icc/crawl.html; icc-crawl(at)ml(dot)nict(dot)go(dot)jp)</String> |
||
6900 | <Description>Knowledge Clustered Group ICC-Crawler (University of Tokyo - Japan)</Description> |
||
6901 | <Type>R</Type> |
||
6902 | <Comment>202.180.34.1xx</Comment> |
||
6903 | <Link1>http://kc.nict.go.jp/icc/crawl.html</Link1> |
||
6904 | <Link2></Link2> |
||
6905 | </user-agent> |
||
6906 | <user-agent> |
||
6907 | <ID>id_g_m_250607_1</ID> |
||
6908 | <String>ICC-Crawler(Mozilla-compatible;http://kc.nict.go.jp/icc/crawl.html;icc-crawl-contact(at)ml(dot)nict(dot)go(dot)jp)</String> |
||
6909 | <Description>Knowledge Clustered Group ICC-Crawler (University of Tokyo - Japan)</Description> |
||
6910 | <Type>R</Type> |
||
6911 | <Comment>202.180.34.1xx</Comment> |
||
6912 | <Link1>http://kc.nict.go.jp/icc/crawl.html</Link1> |
||
6913 | <Link2></Link2> |
||
6914 | </user-agent> |
||
6915 | <user-agent> |
||
6916 | <ID>id_g_m_465</ID> |
||
6917 | <String>iCCrawler (http://www.iccenter.net)</String> |
||
6918 | <Description>ICJobs - Intelligence Competence Center (Germany) robot</Description> |
||
6919 | <Type>R</Type> |
||
6920 | <Comment>212.227.76.xx</Comment> |
||
6921 | <Link1>http://www.iccenter.net</Link1> |
||
6922 | <Link2></Link2> |
||
6923 | </user-agent> |
||
6924 | <user-agent> |
||
6925 | <ID>id_g_m_121006_1</ID> |
||
6926 | <String>ICCrawler - ICjobs (http://www.icjobs.de/bot.htm)</String> |
||
6927 | <Description>ICJobs - Intelligence Competence Center (Germany) robot</Description> |
||
6928 | <Type>R</Type> |
||
6929 | <Comment>212.227.76.xx</Comment> |
||
6930 | <Link1>http://www.iccenter.net</Link1> |
||
6931 | <Link2></Link2> |
||
6932 | </user-agent> |
||
6933 | <user-agent> |
||
6934 | <ID>id_g_m_466</ID> |
||
6935 | <String>ICE Browser/5.05 (Java 1.4.0; Windows 2000 5.0 x86)</String> |
||
6936 | <Description>ICE Java browser</Description> |
||
6937 | <Type>B</Type> |
||
6938 | <Comment></Comment> |
||
6939 | <Link1>http://www.ii.uib.no/~alexey/jb/</Link1> |
||
6940 | <Link2></Link2> |
||
6941 | </user-agent> |
||
6942 | <user-agent> |
||
6943 | <ID>id_g_m_040206_2</ID> |
||
6944 | <String>ichiro/x.0 (http://help.goo.ne.jp/door/crawler.html)</String> |
||
6945 | <Description>Goo Japan / Inktomi robot (210.173.179.xx)</Description> |
||
6946 | <Type>R</Type> |
||
6947 | <Comment> s. also moget / mogimogi</Comment> |
||
6948 | <Link1>http://www.goo.ne.jp</Link1> |
||
6949 | <Link2></Link2> |
||
6950 | </user-agent> |
||
6951 | <user-agent> |
||
6952 | <ID>id_g_m_468</ID> |
||
6953 | <String>ichiro/x.0 (ichiro@nttr.co.jp)</String> |
||
6954 | <Description>Goo Japan / Inktomi robot (210.173.179.xx)</Description> |
||
6955 | <Type>R</Type> |
||
6956 | <Comment> s. also moget / mogimogi</Comment> |
||
6957 | <Link1>http://www.goo.ne.jp</Link1> |
||
6958 | <Link2></Link2> |
||
6959 | </user-agent> |
||
6960 | <user-agent> |
||
6961 | <ID>id_g_m_469</ID> |
||
6962 | <String>IconSurf/2.0 favicon finder (see http://iconsurf.com/robot.html)</String> |
||
6963 | <Description>Iconsurf.com - Visual Surf Engine / favicon finder</Description> |
||
6964 | <Type>R</Type> |
||
6965 | <Comment></Comment> |
||
6966 | <Link1>http://iconsurf.com</Link1> |
||
6967 | <Link2></Link2> |
||
6968 | </user-agent> |
||
6969 | <user-agent> |
||
6970 | <ID>id_g_m_470</ID> |
||
6971 | <String>IconSurf/2.0 favicon monitor (see http://iconsurf.com/robot.html)</String> |
||
6972 | <Description>Iconsurf.com - Visual Surf Engine / favicon finder</Description> |
||
6973 | <Type>R</Type> |
||
6974 | <Comment></Comment> |
||
6975 | <Link1>http://iconsurf.com</Link1> |
||
6976 | <Link2></Link2> |
||
6977 | </user-agent> |
||
6978 | <user-agent> |
||
6979 | <ID>id_g_m_471</ID> |
||
6980 | <String>ICOO Loader v.x.x.x</String> |
||
6981 | <Description>icooLoader download manager</Description> |
||
6982 | <Type>D</Type> |
||
6983 | <Comment></Comment> |
||
6984 | <Link1>http://www.icoonet.com</Link1> |
||
6985 | <Link2></Link2> |
||
6986 | </user-agent> |
||
6987 | <user-agent> |
||
6988 | <ID>id_g_m_472</ID> |
||
6989 | <String>ICRA_label_spider/x.0</String> |
||
6990 | <Description>ICRA (Internet Content Rating Association) label spider</Description> |
||
6991 | <Type>R</Type> |
||
6992 | <Comment></Comment> |
||
6993 | <Link1>http://www.icra.org</Link1> |
||
6994 | <Link2></Link2> |
||
6995 | </user-agent> |
||
6996 | <user-agent> |
||
6997 | <ID>id_g_m_473</ID> |
||
6998 | <String>icsbot-0.1</String> |
||
6999 | <Description>ICS Robot Search Engine (International Christian school of Seoul)</Description> |
||
7000 | <Type>R</Type> |
||
7001 | <Comment></Comment> |
||
7002 | <Link1>http://icseoul.org/</Link1> |
||
7003 | <Link2></Link2> |
||
7004 | </user-agent> |
||
7005 | <user-agent> |
||
7006 | <ID>id_g_m_260306_1</ID> |
||
7007 | <String>IDA</String> |
||
7008 | <Description>Internet Download Accelerator</Description> |
||
7009 | <Type>D</Type> |
||
7010 | <Comment></Comment> |
||
7011 | <Link1>http://www.westbyte.com/ida/</Link1> |
||
7012 | <Link2></Link2> |
||
7013 | </user-agent> |
||
7014 | <user-agent> |
||
7015 | <ID>id_g_m_474</ID> |
||
7016 | <String>ideare - SignSite/1.x</String> |
||
7017 | <Description>Janas (Ideare.com / Tiscali.it) robot</Description> |
||
7018 | <Type>R</Type> |
||
7019 | <Comment></Comment> |
||
7020 | <Link1></Link1> |
||
7021 | <Link2></Link2> |
||
7022 | </user-agent> |
||
7023 | <user-agent> |
||
7024 | <ID>id_g_m_200806_1</ID> |
||
7025 | <String>iearthworm/1.0, iearthworm@yahoo.com.cn</String> |
||
7026 | <Description>Unknown UA from Yahoo China</Description> |
||
7027 | <Type></Type> |
||
7028 | <Comment>202.165.105.x</Comment> |
||
7029 | <Link1></Link1> |
||
7030 | <Link2></Link2> |
||
7031 | </user-agent> |
||
7032 | <user-agent> |
||
7033 | <ID>id_g_m_475</ID> |
||
7034 | <String>IEFav172Free</String> |
||
7035 | <Description>Some bookmark manager</Description> |
||
7036 | <Type>C</Type> |
||
7037 | <Comment> possibly Visit URL ??</Comment> |
||
7038 | <Link1>http://www.lodz.pdi.net/%7Eeristic/free/index.html</Link1> |
||
7039 | <Link2></Link2> |
||
7040 | </user-agent> |
||
7041 | <user-agent> |
||
7042 | <ID>id_g_m_060608_4</ID> |
||
7043 | <String>iFeed.jp/2.0 (www.psychedelix.com/agents/agents.rss; 0 subscribers)</String> |
||
7044 | <Description>iFeed.jp - online rss aggregator (in development)</Description> |
||
7045 | <Type>R</Type> |
||
7046 | <Comment>67.15.2[3-4][X].xxx</Comment> |
||
7047 | <Link1>http://www.ifeed.jp/</Link1> |
||
7048 | <Link2></Link2> |
||
7049 | </user-agent> |
||
7050 | <user-agent> |
||
7051 | <ID>id_g_m_281207_1</ID> |
||
7052 | <String>igdeSpyder (compatible; igde.ru; +http://igde.ru/doc/tech.html)</String> |
||
7053 | <Description>Igde search (Russia) robot</Description> |
||
7054 | <Type>R</Type> |
||
7055 | <Comment>87.118.118.12x</Comment> |
||
7056 | <Link1>http://igde.ru/</Link1> |
||
7057 | <Link2></Link2> |
||
7058 | </user-agent> |
||
7059 | <user-agent> |
||
7060 | <ID>id_g_m_476</ID> |
||
7061 | <String>iGetter/1.x (Macintosh;G;PPC)</String> |
||
7062 | <Description>iGetter download manager</Description> |
||
7063 | <Type>D</Type> |
||
7064 | <Comment></Comment> |
||
7065 | <Link1>http://www.igetter.net</Link1> |
||
7066 | <Link2></Link2> |
||
7067 | </user-agent> |
||
7068 | <user-agent> |
||
7069 | <ID>id_g_m_477</ID> |
||
7070 | <String>iGetter/2 (Macintosh; U; PPC Mac OS X; en)</String> |
||
7071 | <Description>iGetter download manager</Description> |
||
7072 | <Type>D</Type> |
||
7073 | <Comment></Comment> |
||
7074 | <Link1>http://www.igetter.net</Link1> |
||
7075 | <Link2></Link2> |
||
7076 | </user-agent> |
||
7077 | <user-agent> |
||
7078 | <ID>id_g_m_120507_1</ID> |
||
7079 | <String>IIITBOT/1.1 (Indian Language Web Search Engine; http://webkhoj.iiit.net; pvvpr at iiit dot ac dot in)</String> |
||
7080 | <Description>Webkhoj - Indian language search engine</Description> |
||
7081 | <Type>R</Type> |
||
7082 | <Comment>196.12.53.xx</Comment> |
||
7083 | <Link1>http://webkhoj.iiit.net/</Link1> |
||
7084 | <Link2></Link2> |
||
7085 | </user-agent> |
||
7086 | <user-agent> |
||
7087 | <ID>id_g_m_040607_2</ID> |
||
7088 | <String>ilial/Nutch-0.9 (Ilial, Inc. is a Los Angeles based Internet startup company. For more information please visit http://www.ilial.com/crawler; http://www.ilial.com/crawler; crawl@ilial.com)</String> |
||
7089 | <Description>Ilial Knowledge Search robot</Description> |
||
7090 | <Type>R</Type> |
||
7091 | <Comment>72.44.58.2xx</Comment> |
||
7092 | <Link1>http://www.ilial.com/crawler/</Link1> |
||
7093 | <Link2></Link2> |
||
7094 | </user-agent> |
||
7095 | <user-agent> |
||
7096 | <ID>id_g_m_290906_1</ID> |
||
7097 | <String>ilial/Nutch-0.9-dev</String> |
||
7098 | <Description>Unknown robot from UCLA using Nutch</Description> |
||
7099 | <Type>R</Type> |
||
7100 | <Comment>164.67.195.xx</Comment> |
||
7101 | <Link1>http://www.ucla.edu/</Link1> |
||
7102 | <Link2>http://lucene.apache.org/nutch/</Link2> |
||
7103 | </user-agent> |
||
7104 | <user-agent> |
||
7105 | <ID>id_g_m_270806_1</ID> |
||
7106 | <String>IlseBot/1.x</String> |
||
7107 | <Description>Ilse Netherlands robot (62.69.178.xx)</Description> |
||
7108 | <Type>R</Type> |
||
7109 | <Comment>s. also INGRID/3.0 .. / Mozilla/3.0 (INGRID/3.0 ..</Comment> |
||
7110 | <Link1>http://www.ilse.nl/</Link1> |
||
7111 | <Link2></Link2> |
||
7112 | </user-agent> |
||
7113 | <user-agent> |
||
7114 | <ID>id_g_m_478</ID> |
||
7115 | <String>IlTrovatore-Setaccio ( http://www.iltrovatore.it)</String> |
||
7116 | <Description>Il Trovatore - Italian search engine robot</Description> |
||
7117 | <Type>R</Type> |
||
7118 | <Comment>213.215.201.2xx</Comment> |
||
7119 | <Link1>http://www.iltrovatore.it</Link1> |
||
7120 | <Link2></Link2> |
||
7121 | </user-agent> |
||
7122 | <user-agent> |
||
7123 | <ID>id_g_m_479</ID> |
||
7124 | <String>Iltrovatore-Setaccio/0.3-dev (Indexing; http://www.iltrovatore.it/bot.html; info@iltrovatore.it)</String> |
||
7125 | <Description>Il Trovatore - Italian search engine robot</Description> |
||
7126 | <Type>R</Type> |
||
7127 | <Comment>213.215.201.2xx</Comment> |
||
7128 | <Link1>http://www.iltrovatore.it</Link1> |
||
7129 | <Link2></Link2> |
||
7130 | </user-agent> |
||
7131 | <user-agent> |
||
7132 | <ID>id_g_m_480</ID> |
||
7133 | <String>IlTrovatore-Setaccio/1.2 ( http://www.iltrovatore.it/aiuto/faq.html)</String> |
||
7134 | <Description>Il Trovatore - Italian search engine robot</Description> |
||
7135 | <Type>R</Type> |
||
7136 | <Comment>213.215.201.2xx</Comment> |
||
7137 | <Link1>http://www.iltrovatore.it</Link1> |
||
7138 | <Link2></Link2> |
||
7139 | </user-agent> |
||
7140 | <user-agent> |
||
7141 | <ID>id_g_m_481</ID> |
||
7142 | <String>Iltrovatore-Setaccio/1.2 (It-bot; http://www.iltrovatore.it/bot.html; info@iltrovatore.it)</String> |
||
7143 | <Description>Il Trovatore - Italian search engine robot</Description> |
||
7144 | <Type>R</Type> |
||
7145 | <Comment>213.215.201.2xx</Comment> |
||
7146 | <Link1>http://www.iltrovatore.it</Link1> |
||
7147 | <Link2></Link2> |
||
7148 | </user-agent> |
||
7149 | <user-agent> |
||
7150 | <ID>id_g_m_482</ID> |
||
7151 | <String>iltrovatore-setaccio/1.2-dev (spidering; http://www.iltrovatore.it/aiuto/.....)</String> |
||
7152 | <Description>Il Trovatore - Italian search engine robot</Description> |
||
7153 | <Type>R</Type> |
||
7154 | <Comment>213.215.201.2xx</Comment> |
||
7155 | <Link1>http://www.iltrovatore.it</Link1> |
||
7156 | <Link2></Link2> |
||
7157 | </user-agent> |
||
7158 | <user-agent> |
||
7159 | <ID>id_g_m_040506_1</ID> |
||
7160 | <String>IlTrovatore/1.2 (IlTrovatore; http://www.iltrovatore.it/bot.html; bot@iltrovatore.it)</String> |
||
7161 | <Description>Il Trovatore - Italian search engine robot</Description> |
||
7162 | <Type>R</Type> |
||
7163 | <Comment>213.215.201.2xx</Comment> |
||
7164 | <Link1>http://www.iltrovatore.it</Link1> |
||
7165 | <Link2></Link2> |
||
7166 | </user-agent> |
||
7167 | <user-agent> |
||
7168 | <ID>id_g_m_060107_2</ID> |
||
7169 | <String>ImageVisu/v4.x.x</String> |
||
7170 | <Description>ImageVisu image and graphics viewer - display files from the Web (HTTP and ECWP)</Description> |
||
7171 | <Type>B</Type> |
||
7172 | <Comment></Comment> |
||
7173 | <Link1>http://geovisu.free.fr/imagvisu/english/</Link1> |
||
7174 | <Link2></Link2> |
||
7175 | </user-agent> |
||
7176 | <user-agent> |
||
7177 | <ID>id_g_m_080907_1</ID> |
||
7178 | <String>ImageWalker/2.0 (www.bdbrandprotect.com)</String> |
||
7179 | <Description>BD-Brandprotect copyright infringement crawler</Description> |
||
7180 | <Type>R</Type> |
||
7181 | <Comment>72.14.164.1xx</Comment> |
||
7182 | <Link1>http://www.bdbrandprotect.com/</Link1> |
||
7183 | <Link2>http://www.bdbrandprotect.com/solutions_5.html</Link2> |
||
7184 | </user-agent> |
||
7185 | <user-agent> |
||
7186 | <ID>id_g_m_110306_1</ID> |
||
7187 | <String>Incutio HttpClient v0.x</String> |
||
7188 | <Description>HttpClient - a PHP Web Client Class</Description> |
||
7189 | <Type></Type> |
||
7190 | <Comment></Comment> |
||
7191 | <Link1>http://scripts.incutio.com/httpclient/index.php</Link1> |
||
7192 | <Link2></Link2> |
||
7193 | </user-agent> |
||
7194 | <user-agent> |
||
7195 | <ID>id_g_m_483</ID> |
||
7196 | <String>IncyWincy data gatherer(webmaster@loopimprovements.com</String> |
||
7197 | <Description>IncyWincy search engine using DMOZ Open Directory database</Description> |
||
7198 | <Type>R</Type> |
||
7199 | <Comment></Comment> |
||
7200 | <Link1>http://www.loopimprovements.com</Link1> |
||
7201 | <Link2></Link2> |
||
7202 | </user-agent> |
||
7203 | <user-agent> |
||
7204 | <ID>id_g_m_484</ID> |
||
7205 | <String>IncyWincy page crawler(webmaster@loopimprovements.com</String> |
||
7206 | <Description>IncyWincy search engine using DMOZ Open Directory database</Description> |
||
7207 | <Type>R</Type> |
||
7208 | <Comment></Comment> |
||
7209 | <Link1>http://www.loopimprovements.com</Link1> |
||
7210 | <Link2></Link2> |
||
7211 | </user-agent> |
||
7212 | <user-agent> |
||
7213 | <ID>id_g_m_485</ID> |
||
7214 | <String>IncyWincy(http://www.look.com)</String> |
||
7215 | <Description>Look.com robot using IncyWincy search engine</Description> |
||
7216 | <Type>R</Type> |
||
7217 | <Comment></Comment> |
||
7218 | <Link1>http://www.loopimprovements.com</Link1> |
||
7219 | <Link2></Link2> |
||
7220 | </user-agent> |
||
7221 | <user-agent> |
||
7222 | <ID>id_g_m_486</ID> |
||
7223 | <String>IncyWincy(http://www.loopimprovements.com/robot.html)</String> |
||
7224 | <Description>IncyWincy search engine using DMOZ Open Directory database</Description> |
||
7225 | <Type>R</Type> |
||
7226 | <Comment></Comment> |
||
7227 | <Link1>http://www.loopimprovements.com</Link1> |
||
7228 | <Link2></Link2> |
||
7229 | </user-agent> |
||
7230 | <user-agent> |
||
7231 | <ID>id_g_m_487</ID> |
||
7232 | <String>IncyWincy/2.1(loopimprovements.com/robot.html)</String> |
||
7233 | <Description>IncyWincy search engine using DMOZ Open Directory database</Description> |
||
7234 | <Type>R</Type> |
||
7235 | <Comment></Comment> |
||
7236 | <Link1>http://www.loopimprovements.com</Link1> |
||
7237 | <Link2></Link2> |
||
7238 | </user-agent> |
||
7239 | <user-agent> |
||
7240 | <ID>id_g_m_488</ID> |
||
7241 | <String>IndexTheWeb.com Crawler7</String> |
||
7242 | <Description>Index the Web (69.57.134.xx) crawler</Description> |
||
7243 | <Type>R</Type> |
||
7244 | <Comment></Comment> |
||
7245 | <Link1>http://www.indextheweb.com/</Link1> |
||
7246 | <Link2></Link2> |
||
7247 | </user-agent> |
||
7248 | <user-agent> |
||
7249 | <ID>id_g_m_489</ID> |
||
7250 | <String>Industry Program 1.0.x</String> |
||
7251 | <Description>Spam bot from diff. IPs</Description> |
||
7252 | <Type>S</Type> |
||
7253 | <Comment>see also Educate Search VxB - Full Web Bot</Comment> |
||
7254 | <Link1></Link1> |
||
7255 | <Link2></Link2> |
||
7256 | </user-agent> |
||
7257 | <user-agent> |
||
7258 | <ID>id_g_m_490</ID> |
||
7259 | <String>Inet library</String> |
||
7260 | <Description>Inet Library Resource Center robot</Description> |
||
7261 | <Type>R</Type> |
||
7262 | <Comment></Comment> |
||
7263 | <Link1>http://www.inetlibrary.com</Link1> |
||
7264 | <Link2></Link2> |
||
7265 | </user-agent> |
||
7266 | <user-agent> |
||
7267 | <ID>id_g_m_491</ID> |
||
7268 | <String>InetURL/1.0</String> |
||
7269 | <Description>InetURL IVM (phone software) plugin for web server access ?</Description> |
||
7270 | <Type></Type> |
||
7271 | <Comment></Comment> |
||
7272 | <Link1>http://www.nch.com.au/ivm/plugins.html</Link1> |
||
7273 | <Link2></Link2> |
||
7274 | </user-agent> |
||
7275 | <user-agent> |
||
7276 | <ID>id_g_m_270607_1</ID> |
||
7277 | <String>info@pubblisito.com- (http://www.pubblisito.com) il Sud dei Motori di Ricerca</String> |
||
7278 | <Description>Pubblisito.com search - Italia</Description> |
||
7279 | <Type>R</Type> |
||
7280 | <Comment>88.149.164.2xx</Comment> |
||
7281 | <Link1>http://www.pubblisito.com/search/</Link1> |
||
7282 | <Link2></Link2> |
||
7283 | </user-agent> |
||
7284 | <user-agent> |
||
7285 | <ID>id_g_m_211208_2</ID> |
||
7286 | <String>Infoaxe./Nutch-0.9</String> |
||
7287 | <Description>Infoaxe - search history and bookmark service</Description> |
||
7288 | <Type>C</Type> |
||
7289 | <Comment>75.126.48.17x</Comment> |
||
7290 | <Link1>http://www.infoaxe.com/</Link1> |
||
7291 | <Link2></Link2> |
||
7292 | </user-agent> |
||
7293 | <user-agent> |
||
7294 | <ID>id_g_m_492</ID> |
||
7295 | <String>infoConveraCrawler/0.8 ( http://www.authoritativeweb.com/crawl)</String> |
||
7296 | <Description>Converas RetrievalWare Internet Spider (63.241.61.x)</Description> |
||
7297 | <Type>R S ?</Type> |
||
7298 | <Comment>s.also - Convera... Maybe does guestbook / forum spamming s. here http://www.webmasterworld.com/forum11/2871.htm</Comment> |
||
7299 | <Link1>http://www.convera.com/Products/</Link1> |
||
7300 | <Link2></Link2> |
||
7301 | </user-agent> |
||
7302 | <user-agent> |
||
7303 | <ID>id_g_m_493</ID> |
||
7304 | <String>InfoFly/1.0 (http://www.versions-project.org/)</String> |
||
7305 | <Description>Versions-project.org Ingelin spider</Description> |
||
7306 | <Type>R</Type> |
||
7307 | <Comment></Comment> |
||
7308 | <Link1>http://www.versions-project.org/</Link1> |
||
7309 | <Link2></Link2> |
||
7310 | </user-agent> |
||
7311 | <user-agent> |
||
7312 | <ID>id_g_m_494</ID> |
||
7313 | <String>InfoLink/1.x</String> |
||
7314 | <Description>InfoLink link checking tool</Description> |
||
7315 | <Type>C</Type> |
||
7316 | <Comment></Comment> |
||
7317 | <Link1>http://www.biggbyte.com/biggbyte3/index.html</Link1> |
||
7318 | <Link2></Link2> |
||
7319 | </user-agent> |
||
7320 | <user-agent> |
||
7321 | <ID>id_g_m_495</ID> |
||
7322 | <String>INFOMINE/8.0 Adders</String> |
||
7323 | <Description>INFOMINE Scholary Internet Resource Collection crawler</Description> |
||
7324 | <Type>R</Type> |
||
7325 | <Comment></Comment> |
||
7326 | <Link1>http://infomine.ucr.edu</Link1> |
||
7327 | <Link2></Link2> |
||
7328 | </user-agent> |
||
7329 | <user-agent> |
||
7330 | <ID>id_g_m_496</ID> |
||
7331 | <String>INFOMINE/8.0 RemoteServices</String> |
||
7332 | <Description>INFOMINE Scholary Internet Resource Collection crawler</Description> |
||
7333 | <Type>R</Type> |
||
7334 | <Comment></Comment> |
||
7335 | <Link1>http://infomine.ucr.edu</Link1> |
||
7336 | <Link2></Link2> |
||
7337 | </user-agent> |
||
7338 | <user-agent> |
||
7339 | <ID>id_g_m_497</ID> |
||
7340 | <String>INFOMINE/8.0 VLCrawler (http://infomine.ucr.edu/useragents)</String> |
||
7341 | <Description>INFOMINE Scholary Internet Resource Collection crawler</Description> |
||
7342 | <Type>R</Type> |
||
7343 | <Comment></Comment> |
||
7344 | <Link1>http://infomine.ucr.edu</Link1> |
||
7345 | <Link2></Link2> |
||
7346 | </user-agent> |
||
7347 | <user-agent> |
||
7348 | <ID>id_g_m_498</ID> |
||
7349 | <String>InfoNaviRobot(F107)</String> |
||
7350 | <Description>164.71.1.1xx jp.co.fujitsu.t2 Robot</Description> |
||
7351 | <Type>R</Type> |
||
7352 | <Comment></Comment> |
||
7353 | <Link1></Link1> |
||
7354 | <Link2></Link2> |
||
7355 | </user-agent> |
||
7356 | <user-agent> |
||
7357 | <ID>id_g_m_499</ID> |
||
7358 | <String>InfoSeek Sidewinder/0.9</String> |
||
7359 | <Description>Infoseek robot</Description> |
||
7360 | <Type>R</Type> |
||
7361 | <Comment></Comment> |
||
7362 | <Link1>http://www.infoseek.com</Link1> |
||
7363 | <Link2></Link2> |
||
7364 | </user-agent> |
||
7365 | <user-agent> |
||
7366 | <ID>id_g_m_500</ID> |
||
7367 | <String>InfoSeek Sidewinder/1.0A</String> |
||
7368 | <Description>Infoseek robot</Description> |
||
7369 | <Type>R</Type> |
||
7370 | <Comment></Comment> |
||
7371 | <Link1>http://www.infoseek.com</Link1> |
||
7372 | <Link2></Link2> |
||
7373 | </user-agent> |
||
7374 | <user-agent> |
||
7375 | <ID>id_g_m_501</ID> |
||
7376 | <String>InfoSeek Sidewinder/1.1A</String> |
||
7377 | <Description>Infoseek robot</Description> |
||
7378 | <Type>R</Type> |
||
7379 | <Comment></Comment> |
||
7380 | <Link1>http://www.infoseek.com</Link1> |
||
7381 | <Link2></Link2> |
||
7382 | </user-agent> |
||
7383 | <user-agent> |
||
7384 | <ID>id_g_m_502</ID> |
||
7385 | <String>Infoseek SideWinder/1.45 (Compatible; MSIE 10.0; UNIX)</String> |
||
7386 | <Description>Infoseek robot</Description> |
||
7387 | <Type>R</Type> |
||
7388 | <Comment></Comment> |
||
7389 | <Link1>http://www.infoseek.com</Link1> |
||
7390 | <Link2></Link2> |
||
7391 | </user-agent> |
||
7392 | <user-agent> |
||
7393 | <ID>id_g_m_503</ID> |
||
7394 | <String>Infoseek SideWinder/2.0B (Linux 2.4 i686)</String> |
||
7395 | <Description>Infoseek Japan robot</Description> |
||
7396 | <Type>R</Type> |
||
7397 | <Comment>210.148.160.1xx</Comment> |
||
7398 | <Link1>http://www.infoseek.com</Link1> |
||
7399 | <Link2></Link2> |
||
7400 | </user-agent> |
||
7401 | <user-agent> |
||
7402 | <ID>id_g_m_504</ID> |
||
7403 | <String>INGRID/3.0 MT (webcrawler@NOSPAMexperimental.net; http://webmaster.ilse.nl/jsp/webmaster.jsp)</String> |
||
7404 | <Description>Ilse Netherlands robot (62.69.178.xx)</Description> |
||
7405 | <Type>R</Type> |
||
7406 | <Comment> s.also - Mozilla/3.0 (INGRID/3.0 .. / IlseBot/1.0 ..</Comment> |
||
7407 | <Link1>http://www.ilse.nl/</Link1> |
||
7408 | <Link2></Link2> |
||
7409 | </user-agent> |
||
7410 | <user-agent> |
||
7411 | <ID>id_g_m_505</ID> |
||
7412 | <String>Inktomi Search</String> |
||
7413 | <Description>Inktomi (Hotbot-Lycos NBCi etc.) robot</Description> |
||
7414 | <Type>R</Type> |
||
7415 | <Comment></Comment> |
||
7416 | <Link1>http://www.inktomi.com/</Link1> |
||
7417 | <Link2></Link2> |
||
7418 | </user-agent> |
||
7419 | <user-agent> |
||
7420 | <ID>id_g_m_506</ID> |
||
7421 | <String>InnerpriseBot/1.0 (http://www.innerprise.com/)</String> |
||
7422 | <Description>Enterprise Search engine software (64.202.165.xxx) </Description> |
||
7423 | <Type>R</Type> |
||
7424 | <Comment>s. also - Enterprise_Search - ES.NET_Crawler</Comment> |
||
7425 | <Link1>http://www.innerprise.net</Link1> |
||
7426 | <Link2></Link2> |
||
7427 | </user-agent> |
||
7428 | <user-agent> |
||
7429 | <ID>id_g_m_111205_4</ID> |
||
7430 | <String>Insitor.com search and find world wide!</String> |
||
7431 | <Description>Insitor Search robot (80.67.20.1xx)</Description> |
||
7432 | <Type>R</Type> |
||
7433 | <Comment>s. also Insitornaut</Comment> |
||
7434 | <Link1>http://www.insitor.com/</Link1> |
||
7435 | <Link2></Link2> |
||
7436 | </user-agent> |
||
7437 | <user-agent> |
||
7438 | <ID>id_g_m_121205_3</ID> |
||
7439 | <String>Insitornaut</String> |
||
7440 | <Description>Insitor Search robot (80.67.20.1xx)</Description> |
||
7441 | <Type>R</Type> |
||
7442 | <Comment>s. also Insitor.com</Comment> |
||
7443 | <Link1>http://www.insitor.com/</Link1> |
||
7444 | <Link2></Link2> |
||
7445 | </user-agent> |
||
7446 | <user-agent> |
||
7447 | <ID>id_g_m_507</ID> |
||
7448 | <String>InstallShield DigitalWizard</String> |
||
7449 | <Description>download manager</Description> |
||
7450 | <Type>D</Type> |
||
7451 | <Comment></Comment> |
||
7452 | <Link1></Link1> |
||
7453 | <Link2></Link2> |
||
7454 | </user-agent> |
||
7455 | <user-agent> |
||
7456 | <ID>id_g_m_200308_1</ID> |
||
7457 | <String>integrity/1.6</String> |
||
7458 | <Description>Integrity - website broken link checker for MAC OSx</Description> |
||
7459 | <Type>C</Type> |
||
7460 | <Comment></Comment> |
||
7461 | <Link1>http://peacockmedia.co.uk/index.php/products/7-products/4-integrity</Link1> |
||
7462 | <Link2></Link2> |
||
7463 | </user-agent> |
||
7464 | <user-agent> |
||
7465 | <ID>id_g_m_010907_1</ID> |
||
7466 | <String>Intelix/0.x (cs; http://www.microton.cz/intelix/; microton@@microton.cz)</String> |
||
7467 | <Description>Microton Intelix robot for Eurotran translation software ?</Description> |
||
7468 | <Type>D</Type> |
||
7469 | <Comment></Comment> |
||
7470 | <Link1>http://www.microton.cz/intelix/</Link1> |
||
7471 | <Link2></Link2> |
||
7472 | </user-agent> |
||
7473 | <user-agent> |
||
7474 | <ID>id_g_m_508</ID> |
||
7475 | <String>Interarchy/x.x.x (InterarchyCrawler)</String> |
||
7476 | <Description>Interarchy file transfer software - SFTP/FTP client for Mac OS X</Description> |
||
7477 | <Type>D</Type> |
||
7478 | <Comment></Comment> |
||
7479 | <Link1>http://www.interarchy.com</Link1> |
||
7480 | <Link2></Link2> |
||
7481 | </user-agent> |
||
7482 | <user-agent> |
||
7483 | <ID>id_g_m_509</ID> |
||
7484 | <String>Internet Ninja x.0</String> |
||
7485 | <Description>Dream Train (Japan) Internet search robot</Description> |
||
7486 | <Type>R</Type> |
||
7487 | <Comment></Comment> |
||
7488 | <Link1>http://www.dti.ne.jp</Link1> |
||
7489 | <Link2></Link2> |
||
7490 | </user-agent> |
||
7491 | <user-agent> |
||
7492 | <ID>id_g_m_510</ID> |
||
7493 | <String>InternetArchive/0.8-dev(Nutch;http://lucene.apache.org/nutch/bot.html;nutch-agent@lucene.apache</String> |
||
7494 | <Description>Heritrix - The Internet Archive's open-source crawler based on Nutch (207.241.225.2xx)</Description> |
||
7495 | <Type>R</Type> |
||
7496 | <Comment>s.also - archive.org_bot - Mozilla/5.0 (compatible;archive.org_bot/...</Comment> |
||
7497 | <Link1>http://www.archive.org/</Link1> |
||
7498 | <Link2>http://lucene.apache.org</Link2> |
||
7499 | </user-agent> |
||
7500 | <user-agent> |
||
7501 | <ID>id_g_m_511</ID> |
||
7502 | <String>InternetLinkAgent/3.1</String> |
||
7503 | <Description>Internet Link Agent - link checking tool</Description> |
||
7504 | <Type>C</Type> |
||
7505 | <Comment></Comment> |
||
7506 | <Link1>http://www.osk.3web.ne.jp/~goronyan/winprg/sub.shtml</Link1> |
||
7507 | <Link2></Link2> |
||
7508 | </user-agent> |
||
7509 | <user-agent> |
||
7510 | <ID>id_g_m_512</ID> |
||
7511 | <String>InternetSeer.com</String> |
||
7512 | <Description>Internetseer Web site monitoring / Claymont robot</Description> |
||
7513 | <Type>R</Type> |
||
7514 | <Comment></Comment> |
||
7515 | <Link1>http://www.internetseer.com</Link1> |
||
7516 | <Link2></Link2> |
||
7517 | </user-agent> |
||
7518 | <user-agent> |
||
7519 | <ID>id_g_m_513</ID> |
||
7520 | <String>intraVnews/1.x</String> |
||
7521 | <Description>intraVNews - Feed reader & RSS aggregator for Outlook</Description> |
||
7522 | <Type>B</Type> |
||
7523 | <Comment></Comment> |
||
7524 | <Link1>http://www.intravnews.com</Link1> |
||
7525 | <Link2></Link2> |
||
7526 | </user-agent> |
||
7527 | <user-agent> |
||
7528 | <ID>id_g_m_061208_1</ID> |
||
7529 | <String>IOI/2.0 (ISC Open Index crawler; http://index.isc.org/; bot@index.isc.org)</String> |
||
7530 | <Description>Internet Open Index crawler using Nutch</Description> |
||
7531 | <Type>R</Type> |
||
7532 | <Comment>149.20.54.1xx</Comment> |
||
7533 | <Link1>http://index.isc.org/</Link1> |
||
7534 | <Link2>http://www.nutch.org</Link2> |
||
7535 | </user-agent> |
||
7536 | <user-agent> |
||
7537 | <ID>id_g_m_514</ID> |
||
7538 | <String>IP*Works! V5 HTTP/S Component - by /n software - www.nsoftware.com</String> |
||
7539 | <Description>IP*Works! HTTP Component</Description> |
||
7540 | <Type></Type> |
||
7541 | <Comment></Comment> |
||
7542 | <Link1>http://www.nsoftware.com/products/controls/?ctl=HTTP</Link1> |
||
7543 | <Link2></Link2> |
||
7544 | </user-agent> |
||
7545 | <user-agent> |
||
7546 | <ID>id_g_m_515</ID> |
||
7547 | <String>http://www.ip2location.com</String> |
||
7548 | <Description>IP2Location - Reverse lookup geographical data and ISP by IP</Description> |
||
7549 | <Type>R C</Type> |
||
7550 | <Comment></Comment> |
||
7551 | <Link1>http://www.ip2location.com</Link1> |
||
7552 | <Link2></Link2> |
||
7553 | </user-agent> |
||
7554 | <user-agent> |
||
7555 | <ID>id_g_m_270106_1</ID> |
||
7556 | <String>IP2MapBot/1.1 <a href=http://www.ip2map.com>http://www.ip2map.com</a></String> |
||
7557 | <Description>IP2Map - geographical IP mapping</Description> |
||
7558 | <Type>R C</Type> |
||
7559 | <Comment></Comment> |
||
7560 | <Link1>http://www.ip2map.com/</Link1> |
||
7561 | <Link2></Link2> |
||
7562 | </user-agent> |
||
7563 | <user-agent> |
||
7564 | <ID>id_g_m_516</ID> |
||
7565 | <String>IPiumBot laurion(dot)com</String> |
||
7566 | <Description>Laurions Ipium robot</Description> |
||
7567 | <Type>R</Type> |
||
7568 | <Comment></Comment> |
||
7569 | <Link1>http://www.laurion.com</Link1> |
||
7570 | <Link2></Link2> |
||
7571 | </user-agent> |
||
7572 | <user-agent> |
||
7573 | <ID>id_g_m_517</ID> |
||
7574 | <String>IpselonBot/0.xx-beta (Ipselon; http://www.ipselon.com; ipselonbot@ipselon.com)</String> |
||
7575 | <Description>Ipselon Web Search robot</Description> |
||
7576 | <Type>R</Type> |
||
7577 | <Comment></Comment> |
||
7578 | <Link1>http://www.ipselon.com</Link1> |
||
7579 | <Link2></Link2> |
||
7580 | </user-agent> |
||
7581 | <user-agent> |
||
7582 | <ID>id_g_m_518</ID> |
||
7583 | <String>Iria/1.xxa</String> |
||
7584 | <Description>Iria download manager</Description> |
||
7585 | <Type>D</Type> |
||
7586 | <Comment></Comment> |
||
7587 | <Link1>http://www5.tok2.com/home/koteturamu/soft/iria.htm</Link1> |
||
7588 | <Link2></Link2> |
||
7589 | </user-agent> |
||
7590 | <user-agent> |
||
7591 | <ID>id_g_m_519</ID> |
||
7592 | <String>IRLbot/1.0 ( http://irl.cs.tamu.edu/crawler)</String> |
||
7593 | <Description>IRL-crawler - Texas A&M University research project crawler</Description> |
||
7594 | <Type>R</Type> |
||
7595 | <Comment>128.194.135.xx</Comment> |
||
7596 | <Link1>http://irl.cs.tamu.edu</Link1> |
||
7597 | <Link2></Link2> |
||
7598 | </user-agent> |
||
7599 | <user-agent> |
||
7600 | <ID>id_g_m_240308_4</ID> |
||
7601 | <String>IRLbot/3.0 (compatible; MSIE 6.0; http://irl.cs.tamu.edu/crawler/)</String> |
||
7602 | <Description>IRL-crawler - Texas A&M University research project crawler</Description> |
||
7603 | <Type>R</Type> |
||
7604 | <Comment>128.194.135.xx</Comment> |
||
7605 | <Link1>http://irl.cs.tamu.edu</Link1> |
||
7606 | <Link2></Link2> |
||
7607 | </user-agent> |
||
7608 | <user-agent> |
||
7609 | <ID>id_g_m_520</ID> |
||
7610 | <String>IrssiUrlLog/0.2</String> |
||
7611 | <Description>url_log - Irssi Perl url grabber</Description> |
||
7612 | <Type></Type> |
||
7613 | <Comment></Comment> |
||
7614 | <Link1>http://www.irssi.org/scripts/html/url_log.pl.html</Link1> |
||
7615 | <Link2></Link2> |
||
7616 | </user-agent> |
||
7617 | <user-agent> |
||
7618 | <ID>id_g_m_521</ID> |
||
7619 | <String>Irvine/1.x.x</String> |
||
7620 | <Description>Irvine downloading tool</Description> |
||
7621 | <Type>D</Type> |
||
7622 | <Comment></Comment> |
||
7623 | <Link1>http://hp.vector.co.jp/authors/VA024591/</Link1> |
||
7624 | <Link2></Link2> |
||
7625 | </user-agent> |
||
7626 | <user-agent> |
||
7627 | <ID>id_g_m_140506_1</ID> |
||
7628 | <String>ISC Systems iRc Search 2.1</String> |
||
7629 | <Description>Unknown spambot / harvester from diff. IPs</Description> |
||
7630 | <Type>S</Type> |
||
7631 | <Comment></Comment> |
||
7632 | <Link1>http://www.projecthoneypot.org/ip_inspector.php?iph=978231e229521680d11cb93f32de0fa1</Link1> |
||
7633 | <Link2></Link2> |
||
7634 | </user-agent> |
||
7635 | <user-agent> |
||
7636 | <ID>id_g_m_030106_1</ID> |
||
7637 | <String>iSiloX/4.xx Windows/32</String> |
||
7638 | <Description>iSiloX document converter for iSilo reader</Description> |
||
7639 | <Type>B</Type> |
||
7640 | <Comment></Comment> |
||
7641 | <Link1>http://www.isilox.com/</Link1> |
||
7642 | <Link2></Link2> |
||
7643 | </user-agent> |
||
7644 | <user-agent> |
||
7645 | <ID>id_g_m_522</ID> |
||
7646 | <String>isurf (tszhu@canada.com)</String> |
||
7647 | <Description>Unknown University of Alberta link-checking ?</Description> |
||
7648 | <Type>C</Type> |
||
7649 | <Comment></Comment> |
||
7650 | <Link1>http://www.ualberta.ca</Link1> |
||
7651 | <Link2></Link2> |
||
7652 | </user-agent> |
||
7653 | <user-agent> |
||
7654 | <ID>id_g_m_150408_5</ID> |
||
7655 | <String>iTunes/x.x.x</String> |
||
7656 | <Description>iTunes UA name for access and decrypt the iTunes music store pages</Description> |
||
7657 | <Type>B</Type> |
||
7658 | <Comment></Comment> |
||
7659 | <Link1>http://www.apple.com/itunes/</Link1> |
||
7660 | <Link2></Link2> |
||
7661 | </user-agent> |
||
7662 | <user-agent> |
||
7663 | <ID>id_g_m_523</ID> |
||
7664 | <String>IUPUI Research Bot v 1.9a</String> |
||
7665 | <Description>Some spam bot from 66.139.78.xx(x)</Description> |
||
7666 | <Type>S</Type> |
||
7667 | <Comment></Comment> |
||
7668 | <Link1></Link1> |
||
7669 | <Link2></Link2> |
||
7670 | </user-agent> |
||
7671 | <user-agent> |
||
7672 | <ID>id_g_m_280906_1</ID> |
||
7673 | <String>iVia Page Fetcher (http://ivia.ucr.edu/useragents.shtml)</String> |
||
7674 | <Description>iVia robot - Open source Internet portal & virtual library system software</Description> |
||
7675 | <Type>D</Type> |
||
7676 | <Comment></Comment> |
||
7677 | <Link1>http://ivia.ucr.edu/</Link1> |
||
7678 | <Link2></Link2> |
||
7679 | </user-agent> |
||
7680 | <user-agent> |
||
7681 | <ID>id_g_m_524</ID> |
||
7682 | <String>iVia/4.0 CanonizeUrl (http://infomine.ucr.edu/iVia/useragents.shtml</String> |
||
7683 | <Description>iVia robot - Open source Internet portal & virtual library system software</Description> |
||
7684 | <Type>D</Type> |
||
7685 | <Comment></Comment> |
||
7686 | <Link1>http://ivia.ucr.edu/</Link1> |
||
7687 | <Link2></Link2> |
||
7688 | </user-agent> |
||
7689 | <user-agent> |
||
7690 | <ID>id_g_m_180707_1</ID> |
||
7691 | <String>IWAgent/ 1.0 - www.brandprotect.com</String> |
||
7692 | <Description>BD BrandProtect - brand, company or trademarks online monitoring</Description> |
||
7693 | <Type>R</Type> |
||
7694 | <Comment>72.14.164.1xx</Comment> |
||
7695 | <Link1>http://www.brandprotect.com/</Link1> |
||
7696 | <Link2></Link2> |
||
7697 | </user-agent> |
||
7698 | <user-agent> |
||
7699 | <ID>id_g_m_525</ID> |
||
7700 | <String>J-PHONE/3.0/J-SH07</String> |
||
7701 | <Description>Proxy message from jp-q.ne.jp</Description> |
||
7702 | <Type>P</Type> |
||
7703 | <Comment></Comment> |
||
7704 | <Link1></Link1> |
||
7705 | <Link2></Link2> |
||
7706 | </user-agent> |
||
7707 | <user-agent> |
||
7708 | <ID>id_g_m_526</ID> |
||
7709 | <String>Jabot/6.x (http://odin.ingrid.org/)</String> |
||
7710 | <Description>ODIN Directory Japan robot (163.138.95.xx)</Description> |
||
7711 | <Type>R</Type> |
||
7712 | <Comment></Comment> |
||
7713 | <Link1>http://www.ingrid.org</Link1> |
||
7714 | <Link2></Link2> |
||
7715 | </user-agent> |
||
7716 | <user-agent> |
||
7717 | <ID>id_g_m_527</ID> |
||
7718 | <String>Jabot/7.x.x (http://odin.ingrid.org/)</String> |
||
7719 | <Description>ODIN Directory Japan robot (163.138.95.xx)</Description> |
||
7720 | <Type>R</Type> |
||
7721 | <Comment></Comment> |
||
7722 | <Link1>http://www.ingrid.org</Link1> |
||
7723 | <Link2></Link2> |
||
7724 | </user-agent> |
||
7725 | <user-agent> |
||
7726 | <ID>id_g_m_528</ID> |
||
7727 | <String>Jack</String> |
||
7728 | <Description>German Domanova (offline since Feb.02) robot</Description> |
||
7729 | <Type>R</Type> |
||
7730 | <Comment></Comment> |
||
7731 | <Link1></Link1> |
||
7732 | <Link2></Link2> |
||
7733 | </user-agent> |
||
7734 | <user-agent> |
||
7735 | <ID>id_g_m_529</ID> |
||
7736 | <String>Jakarta Commons-HttpClient/2.0xxx</String> |
||
7737 | <Description>Jakarta Commons (Java based) HTTP client</Description> |
||
7738 | <Type>B</Type> |
||
7739 | <Comment></Comment> |
||
7740 | <Link1>http://jakarta.apache.org/commons/httpclient/</Link1> |
||
7741 | <Link2></Link2> |
||
7742 | </user-agent> |
||
7743 | <user-agent> |
||
7744 | <ID>id_g_m_530</ID> |
||
7745 | <String>Jakarta Commons-HttpClient/3.0-rcx</String> |
||
7746 | <Description>Jakarta Commons (Java based) HTTP client</Description> |
||
7747 | <Type>B</Type> |
||
7748 | <Comment></Comment> |
||
7749 | <Link1>http://jakarta.apache.org/commons/httpclient/</Link1> |
||
7750 | <Link2></Link2> |
||
7751 | </user-agent> |
||
7752 | <user-agent> |
||
7753 | <ID>id_g_m_240306_3</ID> |
||
7754 | <String>Jambot/0.1.x (Jambot; http://www.jambot.com/blog; crawler@jambot.com)</String> |
||
7755 | <Description>JamBot search robot (70.146.82.xx)</Description> |
||
7756 | <Type>R</Type> |
||
7757 | <Comment></Comment> |
||
7758 | <Link1>http://www.jambot.com/</Link1> |
||
7759 | <Link2></Link2> |
||
7760 | </user-agent> |
||
7761 | <user-agent> |
||
7762 | <ID>id_g_m_130108_1</ID> |
||
7763 | <String>Jambot/0.2.1 (Jambot; http://www.jambot.com/blog/static.php?page=webmaster-robot; crawler@jambot.com)</String> |
||
7764 | <Description>JamBot search robot</Description> |
||
7765 | <Type>R</Type> |
||
7766 | <Comment>70.146.82.xx</Comment> |
||
7767 | <Link1>http://www.jambot.com/</Link1> |
||
7768 | <Link2></Link2> |
||
7769 | </user-agent> |
||
7770 | <user-agent> |
||
7771 | <ID>id_g_m_531</ID> |
||
7772 | <String>Java 1.1</String> |
||
7773 | <Description>Java VM</Description> |
||
7774 | <Type></Type> |
||
7775 | <Comment></Comment> |
||
7776 | <Link1>http://java.sun.com/</Link1> |
||
7777 | <Link2></Link2> |
||
7778 | </user-agent> |
||
7779 | <user-agent> |
||
7780 | <ID>id_g_m_532</ID> |
||
7781 | <String>Java/1.4.1_01</String> |
||
7782 | <Description>Java VM</Description> |
||
7783 | <Type>R B D</Type> |
||
7784 | <Comment> used as robot from 194.203.40.xx</Comment> |
||
7785 | <Link1>http://java.sun.com/</Link1> |
||
7786 | <Link2></Link2> |
||
7787 | </user-agent> |
||
7788 | <user-agent> |
||
7789 | <ID>id_g_m_533</ID> |
||
7790 | <String>Java1.0.21.0</String> |
||
7791 | <Description>Java VM</Description> |
||
7792 | <Type>B</Type> |
||
7793 | <Comment></Comment> |
||
7794 | <Link1>http://java.sun.com/</Link1> |
||
7795 | <Link2></Link2> |
||
7796 | </user-agent> |
||
7797 | <user-agent> |
||
7798 | <ID>id_g_m_534</ID> |
||
7799 | <String>Java1.1.xx.x</String> |
||
7800 | <Description>Java VM</Description> |
||
7801 | <Type></Type> |
||
7802 | <Comment></Comment> |
||
7803 | <Link1>http://java.sun.com/</Link1> |
||
7804 | <Link2></Link2> |
||
7805 | </user-agent> |
||
7806 | <user-agent> |
||
7807 | <ID>id_g_m_535</ID> |
||
7808 | <String>Java1.3.0rc1</String> |
||
7809 | <Description>Java VM</Description> |
||
7810 | <Type></Type> |
||
7811 | <Comment></Comment> |
||
7812 | <Link1>http://java.sun.com/</Link1> |
||
7813 | <Link2></Link2> |
||
7814 | </user-agent> |
||
7815 | <user-agent> |
||
7816 | <ID>id_g_m_536</ID> |
||
7817 | <String>Java1.3.x</String> |
||
7818 | <Description>Java VM</Description> |
||
7819 | <Type></Type> |
||
7820 | <Comment></Comment> |
||
7821 | <Link1>http://java.sun.com/</Link1> |
||
7822 | <Link2></Link2> |
||
7823 | </user-agent> |
||
7824 | <user-agent> |
||
7825 | <ID>id_g_m_537</ID> |
||
7826 | <String>Java1.4.0</String> |
||
7827 | <Description>Java VM</Description> |
||
7828 | <Type>R B D</Type> |
||
7829 | <Comment>used by diff. IPs for various purposes i.e.: - Dortmund University Java based robot - Roadrunner.net (66.108.xxx.xxx) user robot in conjunction w. RPT-HTTPClient/0.3-3</Comment> |
||
7830 | <Link1>http://java.sun.com/</Link1> |
||
7831 | <Link2>http://www.informatik.uni-dortmund.DE</Link2> |
||
7832 | </user-agent> |
||
7833 | <user-agent> |
||
7834 | <ID>id_g_m_538</ID> |
||
7835 | <String>Jayde Crawler. http://www.jayde.com</String> |
||
7836 | <Description>Jayde B2B Search robot (66.28.139.xx)</Description> |
||
7837 | <Type>R</Type> |
||
7838 | <Comment></Comment> |
||
7839 | <Link1>http://www.jayde.com</Link1> |
||
7840 | <Link2></Link2> |
||
7841 | </user-agent> |
||
7842 | <user-agent> |
||
7843 | <ID>id_g_m_539</ID> |
||
7844 | <String>JBH Agent 2.0</String> |
||
7845 | <Description>some site downloading tool ? via 61.77.51.xxx</Description> |
||
7846 | <Type>D</Type> |
||
7847 | <Comment></Comment> |
||
7848 | <Link1></Link1> |
||
7849 | <Link2></Link2> |
||
7850 | </user-agent> |
||
7851 | <user-agent> |
||
7852 | <ID>id_g_m_540</ID> |
||
7853 | <String>jBrowser/J2ME Profile/MIDP-1.0 Configuration/CLDC-1.0 (Google WAP Proxy/1.0)</String> |
||
7854 | <Description>WAP 2.0 / jBrowser for handhelds</Description> |
||
7855 | <Type>B</Type> |
||
7856 | <Comment></Comment> |
||
7857 | <Link1>http://www.jataayusoft.com/DbWAPHH.htm</Link1> |
||
7858 | <Link2></Link2> |
||
7859 | </user-agent> |
||
7860 | <user-agent> |
||
7861 | <ID>id_g_m_541</ID> |
||
7862 | <String>JCheckLinks/0.1 RPT-HTTPClient/0.3-1</String> |
||
7863 | <Description>JCheckLinks Java hyperlink validator</Description> |
||
7864 | <Type>C</Type> |
||
7865 | <Comment></Comment> |
||
7866 | <Link1>http://web.purplefrog.com/%7Ethoth/jchecklinks/</Link1> |
||
7867 | <Link2></Link2> |
||
7868 | </user-agent> |
||
7869 | <user-agent> |
||
7870 | <ID>id_g_m_542</ID> |
||
7871 | <String>JDK/1.1</String> |
||
7872 | <Description>Java Development Kit</Description> |
||
7873 | <Type></Type> |
||
7874 | <Comment></Comment> |
||
7875 | <Link1>http://developers.sun.com/index.html</Link1> |
||
7876 | <Link2></Link2> |
||
7877 | </user-agent> |
||
7878 | <user-agent> |
||
7879 | <ID>id_g_m_543</ID> |
||
7880 | <String>Jeode/1.x.x</String> |
||
7881 | <Description>Insignias Jeode (PDA) Java platform</Description> |
||
7882 | <Type>B</Type> |
||
7883 | <Comment></Comment> |
||
7884 | <Link1>http://www.insignia.com/content/products/jvmProducts.shtml</Link1> |
||
7885 | <Link2></Link2> |
||
7886 | </user-agent> |
||
7887 | <user-agent> |
||
7888 | <ID>id_g_m_544</ID> |
||
7889 | <String>Jetbot/1.0</String> |
||
7890 | <Description>JetEye Search robot (64.62.142.xxx / 64.71.144.xxx)</Description> |
||
7891 | <Type>R</Type> |
||
7892 | <Comment></Comment> |
||
7893 | <Link1>http://www.jeteye.com</Link1> |
||
7894 | <Link2></Link2> |
||
7895 | </user-agent> |
||
7896 | <user-agent> |
||
7897 | <ID>id_g_m_545</ID> |
||
7898 | <String>JetBrains Omea Reader 1.0.x (http://www.jetbrains.com/omea_reader/)</String> |
||
7899 | <Description>Omea RSS - Atom - newsgroups web page reader </Description> |
||
7900 | <Type>B</Type> |
||
7901 | <Comment></Comment> |
||
7902 | <Link1>http://www.jetbrains.com/omea_reader/</Link1> |
||
7903 | <Link2></Link2> |
||
7904 | </user-agent> |
||
7905 | <user-agent> |
||
7906 | <ID>id_g_m_546</ID> |
||
7907 | <String>JetBrains Omea Reader 2.0 Release Candidate 1 (http://www.jetbrains.com/omea_reader/)</String> |
||
7908 | <Description>Omea RSS - Atom - newsgroups web page reader </Description> |
||
7909 | <Type>B</Type> |
||
7910 | <Comment></Comment> |
||
7911 | <Link1>http://www.jetbrains.com/omea_reader/</Link1> |
||
7912 | <Link2></Link2> |
||
7913 | </user-agent> |
||
7914 | <user-agent> |
||
7915 | <ID>id_g_m_547</ID> |
||
7916 | <String>JetCar</String> |
||
7917 | <Description>JetCar / Flashget download manager</Description> |
||
7918 | <Type>D</Type> |
||
7919 | <Comment></Comment> |
||
7920 | <Link1>http://www.amazesoft.com</Link1> |
||
7921 | <Link2></Link2> |
||
7922 | </user-agent> |
||
7923 | <user-agent> |
||
7924 | <ID>id_g_m_548</ID> |
||
7925 | <String>Jigsaw/2.2.x W3C_CSS_Validator_JFouffa/2.0</String> |
||
7926 | <Description>Jigsaw - W3C's CSS Validator Server</Description> |
||
7927 | <Type>C</Type> |
||
7928 | <Comment></Comment> |
||
7929 | <Link1>http://jigsaw.w3.org/css-validator/validator-uri.html</Link1> |
||
7930 | <Link2></Link2> |
||
7931 | </user-agent> |
||
7932 | <user-agent> |
||
7933 | <ID>id_g_m_550</ID> |
||
7934 | <String>JoBo/1.x (http://www.matuschek.net/jobo.html)</String> |
||
7935 | <Description>Jobo website downloading program</Description> |
||
7936 | <Type>D B</Type> |
||
7937 | <Comment></Comment> |
||
7938 | <Link1>http://www.matuschek.net/software/jobo/index.html</Link1> |
||
7939 | <Link2></Link2> |
||
7940 | </user-agent> |
||
7941 | <user-agent> |
||
7942 | <ID>id_g_m_549</ID> |
||
7943 | <String>JoBo/@JOBO_VERSION@(http://www.matuschek.net/jobo.html)</String> |
||
7944 | <Description>Jobo website downloading program</Description> |
||
7945 | <Type>D B</Type> |
||
7946 | <Comment></Comment> |
||
7947 | <Link1>http://www.matuschek.net/software/jobo/index.html</Link1> |
||
7948 | <Link2></Link2> |
||
7949 | </user-agent> |
||
7950 | <user-agent> |
||
7951 | <ID>id_g_m_551</ID> |
||
7952 | <String>JobSpider_BA/1.1</String> |
||
7953 | <Description>Finacialbot.com - German (213.61.218.xx) job search JobRoboter</Description> |
||
7954 | <Type>R</Type> |
||
7955 | <Comment></Comment> |
||
7956 | <Link1>http://www.finbot.com/jr1.html</Link1> |
||
7957 | <Link2></Link2> |
||
7958 | </user-agent> |
||
7959 | <user-agent> |
||
7960 | <ID>id_g_m_552</ID> |
||
7961 | <String>JOC Web Spider</String> |
||
7962 | <Description>Jocsoft Web Spider - website downloading tool</Description> |
||
7963 | <Type>D B</Type> |
||
7964 | <Comment></Comment> |
||
7965 | <Link1>http://www.jocsoft.com/jws/index.htm</Link1> |
||
7966 | <Link2></Link2> |
||
7967 | </user-agent> |
||
7968 | <user-agent> |
||
7969 | <ID>id_g_m_051206_5</ID> |
||
7970 | <String>JordoMedia/1.0 RSS File Reader (http://www.jordomedia.com)</String> |
||
7971 | <Description>Jordo Media RSS / Atom feed directory link checking</Description> |
||
7972 | <Type>C</Type> |
||
7973 | <Comment>216.227.208.1xx</Comment> |
||
7974 | <Link1>http://www.jordomedia.com/</Link1> |
||
7975 | <Link2></Link2> |
||
7976 | </user-agent> |
||
7977 | <user-agent> |
||
7978 | <ID>id_g_m_090206_2</ID> |
||
7979 | <String>Journster [alpha] (http://journster.com/)</String> |
||
7980 | <Description>Journster.com RSS/Atom aggregator</Description> |
||
7981 | <Type>C</Type> |
||
7982 | <Comment></Comment> |
||
7983 | <Link1>http://beta.journster.com/</Link1> |
||
7984 | <Link2></Link2> |
||
7985 | </user-agent> |
||
7986 | <user-agent> |
||
7987 | <ID>id_g_m_090206_3</ID> |
||
7988 | <String>Journster.com RSS/Atom aggregator 0.5 (http://www.journster.com/bot.phtml)</String> |
||
7989 | <Description>Journster.com RSS/Atom aggregator</Description> |
||
7990 | <Type>C</Type> |
||
7991 | <Comment></Comment> |
||
7992 | <Link1>http://beta.journster.com/</Link1> |
||
7993 | <Link2></Link2> |
||
7994 | </user-agent> |
||
7995 | <user-agent> |
||
7996 | <ID>id_g_m_553</ID> |
||
7997 | <String>JRTS Check Favorites Utility</String> |
||
7998 | <Description>Check Favorites bookmark checking</Description> |
||
7999 | <Type>C</Type> |
||
8000 | <Comment></Comment> |
||
8001 | <Link1>http://www.jrtwine.com/Products/CheckFavs/</Link1> |
||
8002 | <Link2></Link2> |
||
8003 | </user-agent> |
||
8004 | <user-agent> |
||
8005 | <ID>id_g_m_554</ID> |
||
8006 | <String>JRTwine Software Check Favorites Utility</String> |
||
8007 | <Description>Check Favorites bookmark checking</Description> |
||
8008 | <Type>C</Type> |
||
8009 | <Comment></Comment> |
||
8010 | <Link1>http://www.jrtwine.com/Products/CheckFavs/</Link1> |
||
8011 | <Link2></Link2> |
||
8012 | </user-agent> |
||
8013 | <user-agent> |
||
8014 | <ID>id_g_m_555</ID> |
||
8015 | <String>Jyxobot/x</String> |
||
8016 | <Description>Jyxo search (Czech Republic) robot (212.71.128.xx)</Description> |
||
8017 | <Type>R</Type> |
||
8018 | <Comment></Comment> |
||
8019 | <Link1>http://jyxo.cz/</Link1> |
||
8020 | <Link2></Link2> |
||
8021 | </user-agent> |
||
8022 | <user-agent> |
||
8023 | <ID>id_g_m_556</ID> |
||
8024 | <String>K-Meleon/0.6 (Windows; U; Windows NT 5.1; en-US; rv:0.9.5) Gecko/20011011</String> |
||
8025 | <Description>K-meleon browser - Windows 2000</Description> |
||
8026 | <Type>B</Type> |
||
8027 | <Comment></Comment> |
||
8028 | <Link1>http://kmeleon.sourceforge.net/</Link1> |
||
8029 | <Link2></Link2> |
||
8030 | </user-agent> |
||
8031 | <user-agent> |
||
8032 | <ID>id_g_m_557</ID> |
||
8033 | <String>k2spider</String> |
||
8034 | <Description>Verity K2 Spider ( Network search software)</Description> |
||
8035 | <Type>R</Type> |
||
8036 | <Comment></Comment> |
||
8037 | <Link1>http://www.verity.com/products/pdf/MK0368a_K2_Spider.pdf</Link1> |
||
8038 | <Link2></Link2> |
||
8039 | </user-agent> |
||
8040 | <user-agent> |
||
8041 | <ID>id_g_m_010108_3</ID> |
||
8042 | <String>KAIST AITrc Crawler</String> |
||
8043 | <Description>Unknown robot from AITrc (Advanced Information Technology Research Center) - Korea</Description> |
||
8044 | <Type>R</Type> |
||
8045 | <Comment>143.248.134.22x</Comment> |
||
8046 | <Link1>http://aitrc.kaist.ac.kr/english/</Link1> |
||
8047 | <Link2></Link2> |
||
8048 | </user-agent> |
||
8049 | <user-agent> |
||
8050 | <ID>id_g_m_010506_1</ID> |
||
8051 | <String>KakleBot - www.kakle.com/0.1 (KakleBot - www.kakle.com; http:// www.kakle.com/bot.html; support@kakle.com)</String> |
||
8052 | <Description>Kakle ranked metasearch robot</Description> |
||
8053 | <Type>R</Type> |
||
8054 | <Comment>216.139.221.1xx</Comment> |
||
8055 | <Link1>http://www.kakle.com/</Link1> |
||
8056 | <Link2></Link2> |
||
8057 | </user-agent> |
||
8058 | <user-agent> |
||
8059 | <ID>id_g_m_250408_3</ID> |
||
8060 | <String>kalooga/kalooga-4.0-dev-datahouse (Kalooga; http://www.kalooga.com; info@kalooga.com)</String> |
||
8061 | <Description>Kalooga image crawler</Description> |
||
8062 | <Type>R</Type> |
||
8063 | <Comment>195.210.57.1xx</Comment> |
||
8064 | <Link1>http://www.kalooga.com/</Link1> |
||
8065 | <Link2></Link2> |
||
8066 | </user-agent> |
||
8067 | <user-agent> |
||
8068 | <ID>id_g_m_011108_3</ID> |
||
8069 | <String>kalooga/KaloogaBot (Kalooga; http://www.kalooga.com/info.html?page=crawler; crawler@kalooga.com)</String> |
||
8070 | <Description>Kalooga image crawler</Description> |
||
8071 | <Type>R</Type> |
||
8072 | <Comment>195.210.57.1xx</Comment> |
||
8073 | <Link1>http://www.kalooga.com/</Link1> |
||
8074 | <Link2></Link2> |
||
8075 | </user-agent> |
||
8076 | <user-agent> |
||
8077 | <ID>id_g_m_558</ID> |
||
8078 | <String>Kapere (http://www.kapere.com)</String> |
||
8079 | <Description>Kapere site grapper / web downloader</Description> |
||
8080 | <Type>D</Type> |
||
8081 | <Comment></Comment> |
||
8082 | <Link1>http://www.kapere.com</Link1> |
||
8083 | <Link2></Link2> |
||
8084 | </user-agent> |
||
8085 | <user-agent> |
||
8086 | <ID>id_g_m_090807_1</ID> |
||
8087 | <String>Kazehakase/0.x.x.[x]</String> |
||
8088 | <Description>Kazehakase - Gecko based browser (Japan)</Description> |
||
8089 | <Type>B</Type> |
||
8090 | <Comment></Comment> |
||
8091 | <Link1>http://kazehakase.sourceforge.jp/</Link1> |
||
8092 | <Link2></Link2> |
||
8093 | </user-agent> |
||
8094 | <user-agent> |
||
8095 | <ID>id_g_m_559</ID> |
||
8096 | <String>KDDI-SN22 UP.Browser/6.0.7 (GUI) MMP/1.1 (Google WAP Proxy/1.0)</String> |
||
8097 | <Description>Openwave UP.Browser for mobiles via Google WAP Proxy (216.239.33.x)</Description> |
||
8098 | <Type>P</Type> |
||
8099 | <Comment></Comment> |
||
8100 | <Link1>http://www.openwave.com</Link1> |
||
8101 | <Link2></Link2> |
||
8102 | </user-agent> |
||
8103 | <user-agent> |
||
8104 | <ID>id_g_m_561</ID> |
||
8105 | <String>Kenjin Spider</String> |
||
8106 | <Description>Kenjin Spider search agent</Description> |
||
8107 | <Type>R</Type> |
||
8108 | <Comment></Comment> |
||
8109 | <Link1>http://www.kenjin.ne.jp</Link1> |
||
8110 | <Link2></Link2> |
||
8111 | </user-agent> |
||
8112 | <user-agent> |
||
8113 | <ID>id_g_m_562</ID> |
||
8114 | <String>Kevin http://dznet.com/kevin/</String> |
||
8115 | <Description>Dznet.com Kevin crawler (link checking ?) via 68.39.148.xx (nj.comcast.net)</Description> |
||
8116 | <Type>R</Type> |
||
8117 | <Comment></Comment> |
||
8118 | <Link1>http://www.dznet.com</Link1> |
||
8119 | <Link2></Link2> |
||
8120 | </user-agent> |
||
8121 | <user-agent> |
||
8122 | <ID>id_g_m_563</ID> |
||
8123 | <String>Kevin http://websitealert.net/kevin/</String> |
||
8124 | <Description>Website AlertsKevin crawler (website monitoring) via 68.39.148.xx (nj.comcast.net)</Description> |
||
8125 | <Type>R</Type> |
||
8126 | <Comment></Comment> |
||
8127 | <Link1>http://www.websitealert.net</Link1> |
||
8128 | <Link2></Link2> |
||
8129 | </user-agent> |
||
8130 | <user-agent> |
||
8131 | <ID>id_g_m_560</ID> |
||
8132 | <String>KE_1.0/2.0 libwww/5.2.8</String> |
||
8133 | <Description>Voila.fr robot</Description> |
||
8134 | <Type>R</Type> |
||
8135 | <Comment></Comment> |
||
8136 | <Link1>http://www.voila.fr</Link1> |
||
8137 | <Link2></Link2> |
||
8138 | </user-agent> |
||
8139 | <user-agent> |
||
8140 | <ID>id_g_m_301105_5</ID> |
||
8141 | <String>KFSW-Bot (Version: 1.01 powered by KFSW www.kfsw.de)</String> |
||
8142 | <Description>Some Perl search script from KFSW (Germany)</Description> |
||
8143 | <Type>R</Type> |
||
8144 | <Comment></Comment> |
||
8145 | <Link1>http://www.kfsw.de/</Link1> |
||
8146 | <Link2></Link2> |
||
8147 | </user-agent> |
||
8148 | <user-agent> |
||
8149 | <ID>id_g_m_100206_4</ID> |
||
8150 | <String>kinja-imagebot (http://www.kinja.com/)</String> |
||
8151 | <Description>kinja weblog search robot</Description> |
||
8152 | <Type>R</Type> |
||
8153 | <Comment></Comment> |
||
8154 | <Link1>http://www.kinja.com/</Link1> |
||
8155 | <Link2></Link2> |
||
8156 | </user-agent> |
||
8157 | <user-agent> |
||
8158 | <ID>id_g_m_100206_3</ID> |
||
8159 | <String>kinjabot (http://www.kinja.com)</String> |
||
8160 | <Description>kinja weblog search robot</Description> |
||
8161 | <Type>R</Type> |
||
8162 | <Comment></Comment> |
||
8163 | <Link1>http://www.kinja.com/</Link1> |
||
8164 | <Link2></Link2> |
||
8165 | </user-agent> |
||
8166 | <user-agent> |
||
8167 | <ID>id_g_m_564</ID> |
||
8168 | <String>KIT-Fireball/2.0</String> |
||
8169 | <Description>Fireball search (Germany) robot</Description> |
||
8170 | <Type>R</Type> |
||
8171 | <Comment></Comment> |
||
8172 | <Link1>http://www.fireball.de</Link1> |
||
8173 | <Link2></Link2> |
||
8174 | </user-agent> |
||
8175 | <user-agent> |
||
8176 | <ID>id_g_m_565</ID> |
||
8177 | <String>KIT-Fireball/2.0 (compatible; Mozilla 4.0; MSIE 5.5)</String> |
||
8178 | <Description>Fireball search (Germany) robot</Description> |
||
8179 | <Type>R</Type> |
||
8180 | <Comment></Comment> |
||
8181 | <Link1>http://www.fireball.de</Link1> |
||
8182 | <Link2></Link2> |
||
8183 | </user-agent> |
||
8184 | <user-agent> |
||
8185 | <ID>id_g_m_566</ID> |
||
8186 | <String>Klondike/1.50 (WSP Win32) (Google WAP Proxy/1.0)</String> |
||
8187 | <Description>Klondike WAP Browser</Description> |
||
8188 | <Type>B</Type> |
||
8189 | <Comment></Comment> |
||
8190 | <Link1>http://www.apachesoftware.com</Link1> |
||
8191 | <Link2></Link2> |
||
8192 | </user-agent> |
||
8193 | <user-agent> |
||
8194 | <ID>id_g_m_567</ID> |
||
8195 | <String>KnowItAll(knowitall@cs.washington.edu)</String> |
||
8196 | <Description>University of Washington KnowItAll - web information extraction</Description> |
||
8197 | <Type>R</Type> |
||
8198 | <Comment></Comment> |
||
8199 | <Link1>http://www.cs.washington.edu</Link1> |
||
8200 | <Link2></Link2> |
||
8201 | </user-agent> |
||
8202 | <user-agent> |
||
8203 | <ID>id_g_m_568</ID> |
||
8204 | <String>Knowledge.com/0.x</String> |
||
8205 | <Description>The knowledge.com (ODP) directory robot</Description> |
||
8206 | <Type>R</Type> |
||
8207 | <Comment></Comment> |
||
8208 | <Link1>http://www.knowledge.com</Link1> |
||
8209 | <Link2></Link2> |
||
8210 | </user-agent> |
||
8211 | <user-agent> |
||
8212 | <ID>id_g_m_569</ID> |
||
8213 | <String>Kontiki Client x.xx</String> |
||
8214 | <Description>Kontiki Client download manager</Description> |
||
8215 | <Type>D</Type> |
||
8216 | <Comment></Comment> |
||
8217 | <Link1>http://www.kontiki.com/client/userhelp_f.shtml</Link1> |
||
8218 | <Link2></Link2> |
||
8219 | </user-agent> |
||
8220 | <user-agent> |
||
8221 | <ID>id_g_m_280406_2</ID> |
||
8222 | <String>Krugle/Krugle,Nutch/0.8+ (Krugle web crawler; http://www.krugle.com/crawler/info.html; webcrawler@krugle.com)</String> |
||
8223 | <Description>Krugle source code search engine for developers (64.71.164.1xx) </Description> |
||
8224 | <Type>R</Type> |
||
8225 | <Comment>powered by Nutch</Comment> |
||
8226 | <Link1>http://www.krugle.com/</Link1> |
||
8227 | <Link2></Link2> |
||
8228 | </user-agent> |
||
8229 | <user-agent> |
||
8230 | <ID>id_g_m_180606_2</ID> |
||
8231 | <String>KSbot/1.0 (KnowledgeStorm crawler; http://www.knowledgestorm.com/resources/content/crawler/index.html; crawleradmin@knowledgestorm.com)</String> |
||
8232 | <Description>KnowledgeStorm technology industry crawler for Findtech.com</Description> |
||
8233 | <Type>R</Type> |
||
8234 | <Comment>12.129.110.xx</Comment> |
||
8235 | <Link1>http://www.findtech.com/</Link1> |
||
8236 | <Link2>http://www.knowledgestorm.com/resources/content/crawler/index.html</Link2> |
||
8237 | </user-agent> |
||
8238 | <user-agent> |
||
8239 | <ID>id_g_m_570</ID> |
||
8240 | <String>kuloko-bot/0.x</String> |
||
8241 | <Description>Kuloko contextual search robot</Description> |
||
8242 | <Type>R</Type> |
||
8243 | <Comment></Comment> |
||
8244 | <Link1>http://www.kuloko.com/</Link1> |
||
8245 | <Link2></Link2> |
||
8246 | </user-agent> |
||
8247 | <user-agent> |
||
8248 | <ID>id_g_m_571</ID> |
||
8249 | <String>kulokobot www.kuloko.com kuloko@backweave.com</String> |
||
8250 | <Description>Kuloko contextual search robot</Description> |
||
8251 | <Type>R</Type> |
||
8252 | <Comment></Comment> |
||
8253 | <Link1>http://www.kuloko.com</Link1> |
||
8254 | <Link2></Link2> |
||
8255 | </user-agent> |
||
8256 | <user-agent> |
||
8257 | <ID>id_g_m_572</ID> |
||
8258 | <String>kulturarw3/0.1</String> |
||
8259 | <Description>National Library of Sweden Heritage Project robot</Description> |
||
8260 | <Type>R</Type> |
||
8261 | <Comment></Comment> |
||
8262 | <Link1>http://www.kb.se/ENG/kbstart.htm</Link1> |
||
8263 | <Link2></Link2> |
||
8264 | </user-agent> |
||
8265 | <user-agent> |
||
8266 | <ID>id_g_m_301105_2</ID> |
||
8267 | <String>KummHttp/1.1 (compatible; KummClient; Linux rulez)</String> |
||
8268 | <Description>Link or server checking from Sanoma Budapest (195.70.35.xxx)</Description> |
||
8269 | <Type>C R</Type> |
||
8270 | <Comment>Sanoma also runs some web-portals i.e. http://www.startlap.com/</Comment> |
||
8271 | <Link1>http://sanomabp.hu/</Link1> |
||
8272 | <Link2></Link2> |
||
8273 | </user-agent> |
||
8274 | <user-agent> |
||
8275 | <ID>id_g_m_280209_3</ID> |
||
8276 | <String>KWC-KX9/1109 UP.Browser/6.2.3.9.g.1.107 (GUI) MMP/2.0 UP.Link/6.3.0.0.0</String> |
||
8277 | <Description>UP.Browser for mobiles on Kyocera KWC-KX9 cellphone</Description> |
||
8278 | <Type>B</Type> |
||
8279 | <Comment></Comment> |
||
8280 | <Link1>http://www.openwave.com</Link1> |
||
8281 | <Link2></Link2> |
||
8282 | </user-agent> |
||
8283 | <user-agent> |
||
8284 | <ID>id_g_m_211208_3</ID> |
||
8285 | <String>Labrador/0.2; http://ir.dcs.gla.ac.uk/labrador; craigm@dcs.gla.ac.uk</String> |
||
8286 | <Description>TREC Blog Track - Blog and news feed crawler</Description> |
||
8287 | <Type>130.209.241.2xx</Type> |
||
8288 | <Comment>http://ir.dcs.gla.ac.uk/wiki/TREC-Blog</Comment> |
||
8289 | <Link1></Link1> |
||
8290 | <Link2></Link2> |
||
8291 | </user-agent> |
||
8292 | <user-agent> |
||
8293 | <ID>id_g_m_573</ID> |
||
8294 | <String>Lachesis</String> |
||
8295 | <Description>Intels Lachesis web site response time monitoring tool</Description> |
||
8296 | <Type>C</Type> |
||
8297 | <Comment></Comment> |
||
8298 | <Link1>ftp://ftp.imag.fr/pub/labo-LSR/DRAKKAR/internet-performance/lachesis/</Link1> |
||
8299 | <Link2></Link2> |
||
8300 | </user-agent> |
||
8301 | <user-agent> |
||
8302 | <ID>id_g_m_140406_1</ID> |
||
8303 | <String>lanshanbot/1.0</String> |
||
8304 | <Description>Unknown robot from Easten Network China (202.96.51.1xx)</Description> |
||
8305 | <Type></Type> |
||
8306 | <Comment>reads robots.txt</Comment> |
||
8307 | <Link1></Link1> |
||
8308 | <Link2></Link2> |
||
8309 | </user-agent> |
||
8310 | <user-agent> |
||
8311 | <ID>id_g_m_021206_2</ID> |
||
8312 | <String>lanshanbot/1.0 (+http://search.msn.com/msnbot.htm)</String> |
||
8313 | <Description>Unknown robot from Easten Network China (202.96.51.1xx)</Description> |
||
8314 | <Type></Type> |
||
8315 | <Comment>reads robots.txt</Comment> |
||
8316 | <Link1></Link1> |
||
8317 | <Link2></Link2> |
||
8318 | </user-agent> |
||
8319 | <user-agent> |
||
8320 | <ID>id_g_m_271105_1</ID> |
||
8321 | <String>LapozzBot/1.4 ( http://robot.lapozz.com)</String> |
||
8322 | <Description>Lapozz search (Hungary) robot (82.131.195.xx)</Description> |
||
8323 | <Type>R</Type> |
||
8324 | <Comment></Comment> |
||
8325 | <Link1>http://www.lapozz.com/</Link1> |
||
8326 | <Link2></Link2> |
||
8327 | </user-agent> |
||
8328 | <user-agent> |
||
8329 | <ID>id_g_m_280508_3</ID> |
||
8330 | <String>LapozzBot/1.5 (+http://robot.lapozz.hu)</String> |
||
8331 | <Description>Lapozz search (Hungary) robot (82.131.195.xx)</Description> |
||
8332 | <Type>R</Type> |
||
8333 | <Comment></Comment> |
||
8334 | <Link1>http://www.lapozz.com/</Link1> |
||
8335 | <Link2></Link2> |
||
8336 | </user-agent> |
||
8337 | <user-agent> |
||
8338 | <ID>id_g_m_574</ID> |
||
8339 | <String>larbin (samualt9@bigfoot.com)</String> |
||
8340 | <Description>Larbin indexer used as Metacarta.com (66.28.xx.xxx) robot</Description> |
||
8341 | <Type>R</Type> |
||
8342 | <Comment></Comment> |
||
8343 | <Link1>http://www.metacarta.com/</Link1> |
||
8344 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8345 | </user-agent> |
||
8346 | <user-agent> |
||
8347 | <ID>id_g_m_592</ID> |
||
8348 | <String>LARBIN-EXPERIMENTAL (efp@gmx.net)</String> |
||
8349 | <Description>Unknown robot from 66.230.140.xx (argon.oxeo.com)</Description> |
||
8350 | <Type>S</Type> |
||
8351 | <Comment>maybe an e-mail collector - see also Mozilla/4.0 efp@gmx.net</Comment> |
||
8352 | <Link1></Link1> |
||
8353 | <Link2></Link2> |
||
8354 | </user-agent> |
||
8355 | <user-agent> |
||
8356 | <ID>id_g_m_575</ID> |
||
8357 | <String>larbin_2.1.1 larbin2.1.1@somewhere.com</String> |
||
8358 | <Description>Larbin indexer used by Mitsubishi Electric Research Labs</Description> |
||
8359 | <Type>R</Type> |
||
8360 | <Comment></Comment> |
||
8361 | <Link1>http://www.merl.com</Link1> |
||
8362 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8363 | </user-agent> |
||
8364 | <user-agent> |
||
8365 | <ID>id_g_m_576</ID> |
||
8366 | <String>larbin_2.2.0 (crawl@compete.com)</String> |
||
8367 | <Description>Larbin indexer used as Compete.com crawler</Description> |
||
8368 | <Type>R</Type> |
||
8369 | <Comment></Comment> |
||
8370 | <Link1>http://www.compete.com</Link1> |
||
8371 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8372 | </user-agent> |
||
8373 | <user-agent> |
||
8374 | <ID>id_g_m_577</ID> |
||
8375 | <String>larbin_2.2.1_de_Viennot (Laurent.Viennot@inria.fr)</String> |
||
8376 | <Description>Larbin indexer used as Inria robot</Description> |
||
8377 | <Type>R</Type> |
||
8378 | <Comment></Comment> |
||
8379 | <Link1>http://www.inria.fr/index.en.html</Link1> |
||
8380 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8381 | </user-agent> |
||
8382 | <user-agent> |
||
8383 | <ID>id_g_m_578</ID> |
||
8384 | <String>larbin_2.2.2 (sugayama@lab7.kuis.kyoto-u.ac.jp)</String> |
||
8385 | <Description>Larbin indexer used as Kyoto University robot</Description> |
||
8386 | <Type>R</Type> |
||
8387 | <Comment></Comment> |
||
8388 | <Link1>http://www.kyoto-u.ac.jp/</Link1> |
||
8389 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8390 | </user-agent> |
||
8391 | <user-agent> |
||
8392 | <ID>id_g_m_579</ID> |
||
8393 | <String>larbin_2.2.2_guillaume (guillaume@liafa.jussieu.fr)</String> |
||
8394 | <Description>Larbin indexer used as Inria robot</Description> |
||
8395 | <Type>R</Type> |
||
8396 | <Comment></Comment> |
||
8397 | <Link1>http://www.inria.fr/index.en.html</Link1> |
||
8398 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8399 | </user-agent> |
||
8400 | <user-agent> |
||
8401 | <ID>id_g_m_581</ID> |
||
8402 | <String>larbin_2.6.0 (larbin2.6.0@unspecified.mail)</String> |
||
8403 | <Description>Larbin indexer used by an unknown dsl.net client</Description> |
||
8404 | <Type>R</Type> |
||
8405 | <Comment></Comment> |
||
8406 | <Link1>http://larbin.sourceforge.net/index-eng.html</Link1> |
||
8407 | <Link2></Link2> |
||
8408 | </user-agent> |
||
8409 | <user-agent> |
||
8410 | <ID>id_g_m_582</ID> |
||
8411 | <String>larbin_2.6.1 (larbin2.6.1@unspecified.mail)</String> |
||
8412 | <Description>Larbin indexer used by diff. IPs / services</Description> |
||
8413 | <Type>R</Type> |
||
8414 | <Comment> ie.: -Central Host Inc. (client) robot ? - Colt Net France robot</Comment> |
||
8415 | <Link1>http://www.centralhost.com</Link1> |
||
8416 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8417 | </user-agent> |
||
8418 | <user-agent> |
||
8419 | <ID>id_g_m_583</ID> |
||
8420 | <String>larbin_2.6.2 (hamasaki@grad.nii.ac.jp)</String> |
||
8421 | <Description>Larbin indexer used by National Institut of Informatics (NII/Japan)</Description> |
||
8422 | <Type>R</Type> |
||
8423 | <Comment></Comment> |
||
8424 | <Link1>http://www.nii.ac.jp</Link1> |
||
8425 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8426 | </user-agent> |
||
8427 | <user-agent> |
||
8428 | <ID>id_g_m_584</ID> |
||
8429 | <String>larbin_2.6.2 (larbin2.6.2@unspecified.mail)</String> |
||
8430 | <Description>Larbin indexer used by diff. IPs</Description> |
||
8431 | <Type>R</Type> |
||
8432 | <Comment></Comment> |
||
8433 | <Link1>http://larbin.sourceforge.net/index-eng.html</Link1> |
||
8434 | <Link2></Link2> |
||
8435 | </user-agent> |
||
8436 | <user-agent> |
||
8437 | <ID>id_g_m_585</ID> |
||
8438 | <String>larbin_2.6.2 (listonATccDOTgatechDOTedu)</String> |
||
8439 | <Description>Larbin indexer used as robot by Georgia Institute of Technology http://www.gatech.edu/</Description> |
||
8440 | <Type>R</Type> |
||
8441 | <Comment></Comment> |
||
8442 | <Link1>http://www.gatech.edu</Link1> |
||
8443 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8444 | </user-agent> |
||
8445 | <user-agent> |
||
8446 | <ID>id_g_m_586</ID> |
||
8447 | <String>larbin_2.6.2 (pimenas@systems.tuc.gr)</String> |
||
8448 | <Description>Larbin indexer used by Technical University of Crete</Description> |
||
8449 | <Type>R</Type> |
||
8450 | <Comment></Comment> |
||
8451 | <Link1>http://www.systems.tuc.gr</Link1> |
||
8452 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8453 | </user-agent> |
||
8454 | <user-agent> |
||
8455 | <ID>id_g_m_587</ID> |
||
8456 | <String>larbin_2.6.2 (tom@lemurconsulting.com)</String> |
||
8457 | <Description>Larbin indexer used as Lemur Consulting robot</Description> |
||
8458 | <Type>R</Type> |
||
8459 | <Comment></Comment> |
||
8460 | <Link1>http://www.lemurconsulting.com</Link1> |
||
8461 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8462 | </user-agent> |
||
8463 | <user-agent> |
||
8464 | <ID>id_g_m_588</ID> |
||
8465 | <String>larbin_2.6.2 (vitalbox1@hotmail.com)</String> |
||
8466 | <Description>Larbin indexer used as robot via cloud9.net (168.100.192.xxx)</Description> |
||
8467 | <Type>R</Type> |
||
8468 | <Comment></Comment> |
||
8469 | <Link1>http://larbin.sourceforge.net/index-eng.html</Link1> |
||
8470 | <Link2></Link2> |
||
8471 | </user-agent> |
||
8472 | <user-agent> |
||
8473 | <ID>id_g_m_261205_1</ID> |
||
8474 | <String>larbin_2.6.3 (ltaa_web_crawler@groupes.epfl.ch)</String> |
||
8475 | <Description>Unknown robot from EPFL Lausanne Switzerland (128.178.155.1xx)</Description> |
||
8476 | <Type>R</Type> |
||
8477 | <Comment>reads robots.txt</Comment> |
||
8478 | <Link1>http://www.epfl.ch/Eindex.html</Link1> |
||
8479 | <Link2></Link2> |
||
8480 | </user-agent> |
||
8481 | <user-agent> |
||
8482 | <ID>id_g_m_589</ID> |
||
8483 | <String>larbin_2.6.3 (wgao@genieknows.com)</String> |
||
8484 | <Description>Larbin indexer used by GenieKnows.com search</Description> |
||
8485 | <Type>R</Type> |
||
8486 | <Comment> s. also: - geniebot wgao@genieknows.com</Comment> |
||
8487 | <Link1>http://www.genieknows.com</Link1> |
||
8488 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8489 | </user-agent> |
||
8490 | <user-agent> |
||
8491 | <ID>id_g_m_590</ID> |
||
8492 | <String>larbin_2.6.3_for_(http://cosco.hiit.fi/search/) tsilande@hiit.fi</String> |
||
8493 | <Description>Larbin indexer used by Next Generation Information Retrieval (NGIR)</Description> |
||
8494 | <Type>R</Type> |
||
8495 | <Comment></Comment> |
||
8496 | <Link1>http://cosco.hiit.fi</Link1> |
||
8497 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8498 | </user-agent> |
||
8499 | <user-agent> |
||
8500 | <ID>id_g_m_580</ID> |
||
8501 | <String>larbin_2.6_basileocaml (basile.starynkevitch@cea.fr)</String> |
||
8502 | <Description>Larbin indexer used by CEA / DCom Rechercher</Description> |
||
8503 | <Type>R</Type> |
||
8504 | <Comment></Comment> |
||
8505 | <Link1>http://www.cea.fr</Link1> |
||
8506 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8507 | </user-agent> |
||
8508 | <user-agent> |
||
8509 | <ID>id_g_m_591</ID> |
||
8510 | <String>larbin_devel (http://pauillac.inria.fr/~ailleret/prog/larbin/)</String> |
||
8511 | <Description>Larbin indexer used as Inria robot</Description> |
||
8512 | <Type>R</Type> |
||
8513 | <Comment></Comment> |
||
8514 | <Link1>http://pauillac.inria.fr</Link1> |
||
8515 | <Link2>http://larbin.sourceforge.net/index-eng.html</Link2> |
||
8516 | </user-agent> |
||
8517 | <user-agent> |
||
8518 | <ID>id_g_m_160807_2</ID> |
||
8519 | <String>lawinfo-crawler/Nutch-0.9-dev (Crawler for lawinfo.com pages; http://www.lawinfo.com; webmaster@lawinfo.com)</String> |
||
8520 | <Description>LawInfo - Lawyer and attorney directory</Description> |
||
8521 | <Type>R</Type> |
||
8522 | <Comment>216.86.137.xx</Comment> |
||
8523 | <Link1>http://www.lawinfo.com/</Link1> |
||
8524 | <Link2></Link2> |
||
8525 | </user-agent> |
||
8526 | <user-agent> |
||
8527 | <ID>id_g_m_020506_3</ID> |
||
8528 | <String>lc/$ROADS::Version libwww-perl/5.00</String> |
||
8529 | <Description>ROADS - Perl web based subject based gateway tool</Description> |
||
8530 | <Type></Type> |
||
8531 | <Comment></Comment> |
||
8532 | <Link1>http://roads.opensource.ac.uk/</Link1> |
||
8533 | <Link2></Link2> |
||
8534 | </user-agent> |
||
8535 | <user-agent> |
||
8536 | <ID>id_g_m_593</ID> |
||
8537 | <String>lcabotAccept: */*</String> |
||
8538 | <Description>unknown robot via MTT.ca / Aliant.ca</Description> |
||
8539 | <Type></Type> |
||
8540 | <Comment>142.177.168.xxx</Comment> |
||
8541 | <Link1></Link1> |
||
8542 | <Link2></Link2> |
||
8543 | </user-agent> |
||
8544 | <user-agent> |
||
8545 | <ID>id_g_m_140408_1</ID> |
||
8546 | <String>LeapTag/0.8.1.beta081.r3750 (compatible; Mozilla 4.0; MSIE 5.5; robot@yoriwa.com)</String> |
||
8547 | <Description>LeapTag news reader and content discovery tool</Description> |
||
8548 | <Type>B</Type> |
||
8549 | <Comment></Comment> |
||
8550 | <Link1>http://www.leaptag.com/</Link1> |
||
8551 | <Link2></Link2> |
||
8552 | </user-agent> |
||
8553 | <user-agent> |
||
8554 | <ID>id_g_m_594</ID> |
||
8555 | <String>LECodeChecker/3.0 libgetdoc/1.0</String> |
||
8556 | <Description>Linkexchange crawler</Description> |
||
8557 | <Type>R</Type> |
||
8558 | <Comment></Comment> |
||
8559 | <Link1>http://www.linkexchange.com</Link1> |
||
8560 | <Link2></Link2> |
||
8561 | </user-agent> |
||
8562 | <user-agent> |
||
8563 | <ID>id_g_m_595</ID> |
||
8564 | <String>LeechGet 200x (www.leechget.de)</String> |
||
8565 | <Description>Leechget download manager</Description> |
||
8566 | <Type>D</Type> |
||
8567 | <Comment></Comment> |
||
8568 | <Link1>http://www.leechget.de</Link1> |
||
8569 | <Link2></Link2> |
||
8570 | </user-agent> |
||
8571 | <user-agent> |
||
8572 | <ID>id_g_m_596</ID> |
||
8573 | <String>LEIA/2.90</String> |
||
8574 | <Description>Gseek.com (site is offline) robot</Description> |
||
8575 | <Type>R</Type> |
||
8576 | <Comment></Comment> |
||
8577 | <Link1></Link1> |
||
8578 | <Link2></Link2> |
||
8579 | </user-agent> |
||
8580 | <user-agent> |
||
8581 | <ID>id_g_m_597</ID> |
||
8582 | <String>LEIA/3.01pr (LEIAcrawler; [SNIP])</String> |
||
8583 | <Description>Gseek.com (site is offline) robot</Description> |
||
8584 | <Type>R</Type> |
||
8585 | <Comment></Comment> |
||
8586 | <Link1></Link1> |
||
8587 | <Link2></Link2> |
||
8588 | </user-agent> |
||
8589 | <user-agent> |
||
8590 | <ID>id_g_m_210106_2</ID> |
||
8591 | <String>LetsCrawl.com/1.0 +http://letscrawl.com/</String> |
||
8592 | <Description>Maybe logfile spamming for Lets crawl! search (Germany)</Description> |
||
8593 | <Type>S</Type> |
||
8594 | <Comment>website has no function</Comment> |
||
8595 | <Link1>http://letscrawl.com/</Link1> |
||
8596 | <Link2></Link2> |
||
8597 | </user-agent> |
||
8598 | <user-agent> |
||
8599 | <ID>id_g_m_598</ID> |
||
8600 | <String>LexiBot/1.00</String> |
||
8601 | <Description>Lexibot (exMataHari) search software</Description> |
||
8602 | <Type>R</Type> |
||
8603 | <Comment></Comment> |
||
8604 | <Link1>http://www.lexibot.com/index.asp</Link1> |
||
8605 | <Link2></Link2> |
||
8606 | </user-agent> |
||
8607 | <user-agent> |
||
8608 | <ID>id_g_m_140209_2</ID> |
||
8609 | <String>LG-LX260 POLARIS-LX260/2.0 MMP/2.0 Profile/MIDP-2.0 Configuration/CLDC-1.1</String> |
||
8610 | <Description>Polaris mobile browser on LG LX 260 Sprint Rumor phone</Description> |
||
8611 | <Type>B</Type> |
||
8612 | <Comment></Comment> |
||
8613 | <Link1>http://www.infraware.co.kr/eng/01_product/product10.asp</Link1> |
||
8614 | <Link2></Link2> |
||
8615 | </user-agent> |
||
8616 | <user-agent> |
||
8617 | <ID>id_g_m_599</ID> |
||
8618 | <String>LG/U8138/v1.0</String> |
||
8619 | <Description>LG 8138 Mobile Phone browser</Description> |
||
8620 | <Type>B</Type> |
||
8621 | <Comment></Comment> |
||
8622 | <Link1></Link1> |
||
8623 | <Link2></Link2> |
||
8624 | </user-agent> |
||
8625 | <user-agent> |
||
8626 | <ID>id_g_m_600</ID> |
||
8627 | <String>Libby_1.1/libwww-perl/5.47</String> |
||
8628 | <Description>About.com robot</Description> |
||
8629 | <Type>R</Type> |
||
8630 | <Comment></Comment> |
||
8631 | <Link1>http://www.about.com/</Link1> |
||
8632 | <Link2></Link2> |
||
8633 | </user-agent> |
||
8634 | <user-agent> |
||
8635 | <ID>id_g_m_100306_1</ID> |
||
8636 | <String>libcurl-agent/1.0</String> |
||
8637 | <Description>libcurl's (multiprotocol file transfer library) standard user-agent name</Description> |
||
8638 | <Type>D</Type> |
||
8639 | <Comment></Comment> |
||
8640 | <Link1>http://curl.haxx.se/libcurl/</Link1> |
||
8641 | <Link2></Link2> |
||
8642 | </user-agent> |
||
8643 | <user-agent> |
||
8644 | <ID>id_g_m_080507_1</ID> |
||
8645 | <String>LibertyW (+http://www.lw01.com)</String> |
||
8646 | <Description>LibertyW search for mobile (France)</Description> |
||
8647 | <Type>R</Type> |
||
8648 | <Comment>213.251.135.2xx</Comment> |
||
8649 | <Link1>http://www.lw01.com/en/</Link1> |
||
8650 | <Link2></Link2> |
||
8651 | </user-agent> |
||
8652 | <user-agent> |
||
8653 | <ID>id_g_m_601</ID> |
||
8654 | <String>libWeb/clsHTTP -- hiongun@kt.co.kr</String> |
||
8655 | <Description>Korea Telecom Search robot</Description> |
||
8656 | <Type>R</Type> |
||
8657 | <Comment></Comment> |
||
8658 | <Link1>http://www.kt.co.kr/kt_home/eng/index.jsp</Link1> |
||
8659 | <Link2></Link2> |
||
8660 | </user-agent> |
||
8661 | <user-agent> |
||
8662 | <ID>id_g_m_602</ID> |
||
8663 | <String>libwww-perl/5.41</String> |
||
8664 | <Description>CMP United Media robot</Description> |
||
8665 | <Type>R</Type> |
||
8666 | <Comment></Comment> |
||
8667 | <Link1>http://www.cmpnet.com</Link1> |
||
8668 | <Link2></Link2> |
||
8669 | </user-agent> |
||
8670 | <user-agent> |
||
8671 | <ID>id_g_m_603</ID> |
||
8672 | <String>libwww-perl/5.45</String> |
||
8673 | <Description>SplatSearch robot (207.44.142.xx)</Description> |
||
8674 | <Type>R</Type> |
||
8675 | <Comment></Comment> |
||
8676 | <Link1>http://www.splatsearch.com</Link1> |
||
8677 | <Link2></Link2> |
||
8678 | </user-agent> |
||
8679 | <user-agent> |
||
8680 | <ID>id_g_m_604</ID> |
||
8681 | <String>libwww-perl/5.48</String> |
||
8682 | <Description>Alexa robot</Description> |
||
8683 | <Type>R</Type> |
||
8684 | <Comment></Comment> |
||
8685 | <Link1>http://www.alexa.com</Link1> |
||
8686 | <Link2></Link2> |
||
8687 | </user-agent> |
||
8688 | <user-agent> |
||
8689 | <ID>id_g_m_605</ID> |
||
8690 | <String>libwww-perl/5.50</String> |
||
8691 | <Description>diff. IPs / services</Description> |
||
8692 | <Type>R C P</Type> |
||
8693 | <Comment> ie.: - secure-netz.de link checking (in conjunction w. LWP::Simple/5.50) -N2H2 Internet filtering</Comment> |
||
8694 | <Link1>http://www.n2h2.com</Link1> |
||
8695 | <Link2></Link2> |
||
8696 | </user-agent> |
||
8697 | <user-agent> |
||
8698 | <ID>id_g_m_606</ID> |
||
8699 | <String>libwww-perl/5.52 FP/2.1</String> |
||
8700 | <Description>Fast Search robot</Description> |
||
8701 | <Type>R</Type> |
||
8702 | <Comment></Comment> |
||
8703 | <Link1>http://www.alltheweb.com</Link1> |
||
8704 | <Link2></Link2> |
||
8705 | </user-agent> |
||
8706 | <user-agent> |
||
8707 | <ID>id_g_m_607</ID> |
||
8708 | <String>libwww-perl/5.52 FP/4.0</String> |
||
8709 | <Description>Fast Search robot</Description> |
||
8710 | <Type>R</Type> |
||
8711 | <Comment></Comment> |
||
8712 | <Link1>http://www.alltheweb.com</Link1> |
||
8713 | <Link2></Link2> |
||
8714 | </user-agent> |
||
8715 | <user-agent> |
||
8716 | <ID>id_g_m_608</ID> |
||
8717 | <String>libwww-perl/5.53</String> |
||
8718 | <Description>diff. IPs / services</Description> |
||
8719 | <Type>R C P</Type> |
||
8720 | <Comment> ie.: -iPrism Web filtering software - softclub.net link checking</Comment> |
||
8721 | <Link1>http://www.stbernard.com/default.asp</Link1> |
||
8722 | <Link2></Link2> |
||
8723 | </user-agent> |
||
8724 | <user-agent> |
||
8725 | <ID>id_g_m_609</ID> |
||
8726 | <String>libwww-perl/5.63</String> |
||
8727 | <Description>Profile for You internet profiling (?)</Description> |
||
8728 | <Type>R C</Type> |
||
8729 | <Comment></Comment> |
||
8730 | <Link1>http://www.profile4u.com</Link1> |
||
8731 | <Link2></Link2> |
||
8732 | </user-agent> |
||
8733 | <user-agent> |
||
8734 | <ID>id_g_m_610</ID> |
||
8735 | <String>libwww-perl/5.64</String> |
||
8736 | <Description>unknown link checking from Wanadoo.fr (193.253.33.xxx)</Description> |
||
8737 | <Type>R C</Type> |
||
8738 | <Comment></Comment> |
||
8739 | <Link1></Link1> |
||
8740 | <Link2></Link2> |
||
8741 | </user-agent> |
||
8742 | <user-agent> |
||
8743 | <ID>id_g_m_611</ID> |
||
8744 | <String>libwww-perl/5.65</String> |
||
8745 | <Description>Amidalla search engine robot (62.241.33.xx)</Description> |
||
8746 | <Type>R</Type> |
||
8747 | <Comment> s. also amibot</Comment> |
||
8748 | <Link1>http://www.amidalla.com</Link1> |
||
8749 | <Link2></Link2> |
||
8750 | </user-agent> |
||
8751 | <user-agent> |
||
8752 | <ID>id_g_m_612</ID> |
||
8753 | <String>libwww-perl/5.800</String> |
||
8754 | <Description>SplatSearch robot (72.36.210.xx)</Description> |
||
8755 | <Type>R</Type> |
||
8756 | <Comment></Comment> |
||
8757 | <Link1>http://www.splatsearch.com/</Link1> |
||
8758 | <Link2></Link2> |
||
8759 | </user-agent> |
||
8760 | <user-agent> |
||
8761 | <ID>id_g_m_613</ID> |
||
8762 | <String>libwww/5.3.2</String> |
||
8763 | <Description>Mediater Rechercher robot</Description> |
||
8764 | <Type>R</Type> |
||
8765 | <Comment></Comment> |
||
8766 | <Link1>http://www.mediater.net</Link1> |
||
8767 | <Link2></Link2> |
||
8768 | </user-agent> |
||
8769 | <user-agent> |
||
8770 | <ID>id_g_m_160206_1</ID> |
||
8771 | <String>Liferea/0.x.x (Linux; en_US.UTF-8; http://liferea.sf.net/)</String> |
||
8772 | <Description>Liferea - Linux feed reader</Description> |
||
8773 | <Type>B</Type> |
||
8774 | <Comment></Comment> |
||
8775 | <Link1>http://liferea.sourceforge.net/</Link1> |
||
8776 | <Link2></Link2> |
||
8777 | </user-agent> |
||
8778 | <user-agent> |
||
8779 | <ID>id_g_m_140508_4</ID> |
||
8780 | <String>Liferea/1.x.x (Linux; es_ES.UTF-8; http://liferea.sf.net/)</String> |
||
8781 | <Description>Liferea (Linux Feed Reader) news aggregator for Unix and Linux</Description> |
||
8782 | <Type>B</Type> |
||
8783 | <Comment></Comment> |
||
8784 | <Link1>http://liferea.sourceforge.net/</Link1> |
||
8785 | <Link2></Link2> |
||
8786 | </user-agent> |
||
8787 | <user-agent> |
||
8788 | <ID>id_g_m_614</ID> |
||
8789 | <String>LightningDownload/1.0beta2</String> |
||
8790 | <Description>Lightning Download manager</Description> |
||
8791 | <Type>D</Type> |
||
8792 | <Comment></Comment> |
||
8793 | <Link1>http://www.lightningdownload.com</Link1> |
||
8794 | <Link2></Link2> |
||
8795 | </user-agent> |
||
8796 | <user-agent> |
||
8797 | <ID>id_g_m_615</ID> |
||
8798 | <String>LightningDownload/1.x.x</String> |
||
8799 | <Description>Lightning Download manager</Description> |
||
8800 | <Type>D</Type> |
||
8801 | <Comment></Comment> |
||
8802 | <Link1>http://www.lightningdownload.com</Link1> |
||
8803 | <Link2></Link2> |
||
8804 | </user-agent> |
||
8805 | <user-agent> |
||
8806 | <ID>id_g_m_616</ID> |
||
8807 | <String>LightningDownload/1.x.x [Accelerated x]</String> |
||
8808 | <Description>Lightning Download manager</Description> |
||
8809 | <Type>D</Type> |
||
8810 | <Comment></Comment> |
||
8811 | <Link1>http://www.lightningdownload.com</Link1> |
||
8812 | <Link2></Link2> |
||
8813 | </user-agent> |
||
8814 | <user-agent> |
||
8815 | <ID>id_g_m_131207_1</ID> |
||
8816 | <String>LijitSpider/Nutch-0.9 (Reports crawler; http://www.lijit.com/; info(a)lijit(d)com)</String> |
||
8817 | <Description>Lijit blog search spider</Description> |
||
8818 | <Type>R</Type> |
||
8819 | <Comment>216.24.131.1xx</Comment> |
||
8820 | <Link1>http://www.lijit.com/</Link1> |
||
8821 | <Link2></Link2> |
||
8822 | </user-agent> |
||
8823 | <user-agent> |
||
8824 | <ID>id_g_m_617</ID> |
||
8825 | <String>Lincoln State Web Browser</String> |
||
8826 | <Description>Some spam bot</Description> |
||
8827 | <Type>S</Type> |
||
8828 | <Comment>s. this Guestbook http://www.donotenter.com/guestbook/gbook.html</Comment> |
||
8829 | <Link1>http://www.donotenter.com/guestbook/gbook.html</Link1> |
||
8830 | <Link2></Link2> |
||
8831 | </user-agent> |
||
8832 | <user-agent> |
||
8833 | <ID>id_g_m_618</ID> |
||
8834 | <String>Link Valet Online 1.x</String> |
||
8835 | <Description>Link Valet online link checking</Description> |
||
8836 | <Type>C</Type> |
||
8837 | <Comment></Comment> |
||
8838 | <Link1>http://www.htmlhelp.com</Link1> |
||
8839 | <Link2></Link2> |
||
8840 | </user-agent> |
||
8841 | <user-agent> |
||
8842 | <ID>id_g_m_620</ID> |
||
8843 | <String>LinkAlarm/2.x</String> |
||
8844 | <Description>Linkalarm link validation</Description> |
||
8845 | <Type>C</Type> |
||
8846 | <Comment></Comment> |
||
8847 | <Link1>http://www.linkalarm.com</Link1> |
||
8848 | <Link2></Link2> |
||
8849 | </user-agent> |
||
8850 | <user-agent> |
||
8851 | <ID>id_g_m_621</ID> |
||
8852 | <String>Linkbot</String> |
||
8853 | <Description>Linkbot Pro link checking software</Description> |
||
8854 | <Type>C</Type> |
||
8855 | <Comment></Comment> |
||
8856 | <Link1>http://www.watchfire.com</Link1> |
||
8857 | <Link2></Link2> |
||
8858 | </user-agent> |
||
8859 | <user-agent> |
||
8860 | <ID>id_g_m_622</ID> |
||
8861 | <String>linkbot</String> |
||
8862 | <Description>Rpsoft 2000 Site-Crawler</Description> |
||
8863 | <Type>R</Type> |
||
8864 | <Comment></Comment> |
||
8865 | <Link1>http://www.rpsoft2000.com/rps-site-crawler.htm</Link1> |
||
8866 | <Link2></Link2> |
||
8867 | </user-agent> |
||
8868 | <user-agent> |
||
8869 | <ID>id_g_m_623</ID> |
||
8870 | <String>Linkbot x.0</String> |
||
8871 | <Description>Linkbot Pro link checking software</Description> |
||
8872 | <Type>C</Type> |
||
8873 | <Comment></Comment> |
||
8874 | <Link1>http://www.watchfire.com</Link1> |
||
8875 | <Link2></Link2> |
||
8876 | </user-agent> |
||
8877 | <user-agent> |
||
8878 | <ID>id_g_m_624</ID> |
||
8879 | <String>LinkCheck (linkcheck@inter7.com http://www.inter7.com/linkcheck)</String> |
||
8880 | <Description>Linkcheck - linkchecking tool for Unix/Linux</Description> |
||
8881 | <Type>C</Type> |
||
8882 | <Comment></Comment> |
||
8883 | <Link1>http://www.inter7.com</Link1> |
||
8884 | <Link2></Link2> |
||
8885 | </user-agent> |
||
8886 | <user-agent> |
||
8887 | <ID>id_g_m_625</ID> |
||
8888 | <String>LinkLint-checkonly/2.x.x</String> |
||
8889 | <Description>Linklint - Perl html link checker</Description> |
||
8890 | <Type>C</Type> |
||
8891 | <Comment></Comment> |
||
8892 | <Link1>http://www.linklint.org</Link1> |
||
8893 | <Link2></Link2> |
||
8894 | </user-agent> |
||
8895 | <user-agent> |
||
8896 | <ID>id_g_m_626</ID> |
||
8897 | <String>LinkLint-spider/2.x.x</String> |
||
8898 | <Description>Linklint - Perl html link checker</Description> |
||
8899 | <Type>C</Type> |
||
8900 | <Comment></Comment> |
||
8901 | <Link1>http://www.linklint.org</Link1> |
||
8902 | <Link2></Link2> |
||
8903 | </user-agent> |
||
8904 | <user-agent> |
||
8905 | <ID>id_g_m_627</ID> |
||
8906 | <String>linknzbot</String> |
||
8907 | <Description>Linknz - The Kiwi Search Engine (New Zealand)</Description> |
||
8908 | <Type>R</Type> |
||
8909 | <Comment></Comment> |
||
8910 | <Link1>http://www.linknz.co.nz</Link1> |
||
8911 | <Link2></Link2> |
||
8912 | </user-agent> |
||
8913 | <user-agent> |
||
8914 | <ID>id_g_m_280606_1</ID> |
||
8915 | <String>LinkPimpin v1.0</String> |
||
8916 | <Description>Link-Pimp web directory link checking</Description> |
||
8917 | <Type>C</Type> |
||
8918 | <Comment>216.89.111.x</Comment> |
||
8919 | <Link1>http://www.link-pimp.com/</Link1> |
||
8920 | <Link2></Link2> |
||
8921 | </user-agent> |
||
8922 | <user-agent> |
||
8923 | <ID>id_g_m_628</ID> |
||
8924 | <String>LinkProver 2.1</String> |
||
8925 | <Description>TafWeb link checking program</Description> |
||
8926 | <Type>C</Type> |
||
8927 | <Comment></Comment> |
||
8928 | <Link1>http://www.tafweb.com</Link1> |
||
8929 | <Link2></Link2> |
||
8930 | </user-agent> |
||
8931 | <user-agent> |
||
8932 | <ID>id_g_m_630</ID> |
||
8933 | <String>Links (0.9x; Linux 2.4.7-10 i686)</String> |
||
8934 | <Description>Links text browser for Unix & OS/2</Description> |
||
8935 | <Type>B</Type> |
||
8936 | <Comment></Comment> |
||
8937 | <Link1>http://artax.karlin.mff.cuni.cz/%7Emikulas/links/</Link1> |
||
8938 | <Link2></Link2> |
||
8939 | </user-agent> |
||
8940 | <user-agent> |
||
8941 | <ID>id_g_m_631</ID> |
||
8942 | <String>Links (0.9xpre12; Linux 2.2.14-5.0 i686; 80x24)</String> |
||
8943 | <Description>Links text browser for Unix & OS/2</Description> |
||
8944 | <Type>B</Type> |
||
8945 | <Comment></Comment> |
||
8946 | <Link1>http://artax.karlin.mff.cuni.cz/%7Emikulas/links/</Link1> |
||
8947 | <Link2></Link2> |
||
8948 | </user-agent> |
||
8949 | <user-agent> |
||
8950 | <ID>id_g_m_632</ID> |
||
8951 | <String>Links (2.xpre7; Linux 2.4.18 i586; x)</String> |
||
8952 | <Description>Links text browser for Unix & OS/2</Description> |
||
8953 | <Type>B</Type> |
||
8954 | <Comment></Comment> |
||
8955 | <Link1>http://artax.karlin.mff.cuni.cz/%7Emikulas/links/</Link1> |
||
8956 | <Link2></Link2> |
||
8957 | </user-agent> |
||
8958 | <user-agent> |
||
8959 | <ID>id_g_m_629</ID> |
||
8960 | <String>Links - http://gossamer-threads.com/scripts/links/</String> |
||
8961 | <Description>Links SQL directory management program</Description> |
||
8962 | <Type>C</Type> |
||
8963 | <Comment></Comment> |
||
8964 | <Link1>http://gossamer-threads.com/scripts/links/</Link1> |
||
8965 | <Link2></Link2> |
||
8966 | </user-agent> |
||
8967 | <user-agent> |
||
8968 | <ID>id_g_m_633</ID> |
||
8969 | <String>Links 2.0 (http://gossamer-threads.com/scripts/links/)</String> |
||
8970 | <Description>Links SQL directory management program</Description> |
||
8971 | <Type>R</Type> |
||
8972 | <Comment></Comment> |
||
8973 | <Link1>http://gossamer-threads.com/scripts/links/</Link1> |
||
8974 | <Link2></Link2> |
||
8975 | </user-agent> |
||
8976 | <user-agent> |
||
8977 | <ID>id_g_m_634</ID> |
||
8978 | <String>Links SQL (http://gossamer-threads.com/scripts/links-sql/)</String> |
||
8979 | <Description>Links SQL directory management program</Description> |
||
8980 | <Type>R</Type> |
||
8981 | <Comment></Comment> |
||
8982 | <Link1>http://gossamer-threads.com/scripts/links-sql/</Link1> |
||
8983 | <Link2></Link2> |
||
8984 | </user-agent> |
||
8985 | <user-agent> |
||
8986 | <ID>id_g_m_280406_3</ID> |
||
8987 | <String>Links4US-Crawler, (+http://links4us.com/)</String> |
||
8988 | <Description>Links4us ODP based directory link checking</Description> |
||
8989 | <Type>C</Type> |
||
8990 | <Comment>209.190.5.2xx</Comment> |
||
8991 | <Link1>http://links4us.com/</Link1> |
||
8992 | <Link2></Link2> |
||
8993 | </user-agent> |
||
8994 | <user-agent> |
||
8995 | <ID>id_g_m_635</ID> |
||
8996 | <String>LinkScan/11.0beta2 UnixShareware robot from Elsop.com (used by Indiafocus/Indiainfo)</String> |
||
8997 | <Description>Shareware robot from Elsop.com (used by Indiafocus/Indiainfo and others)</Description> |
||
8998 | <Type>R</Type> |
||
8999 | <Comment></Comment> |
||
9000 | <Link1>http://www.elsop.com</Link1> |
||
9001 | <Link2>http://indiafocus.indiainfo.com/</Link2> |
||
9002 | </user-agent> |
||
9003 | <user-agent> |
||
9004 | <ID>id_g_m_636</ID> |
||
9005 | <String>LinkScan/9.0g Unix</String> |
||
9006 | <Description>Shareware robot from Elsop.com (used by Indiafocus/Indiainfo and others)</Description> |
||
9007 | <Type>R</Type> |
||
9008 | <Comment></Comment> |
||
9009 | <Link1>http://www.elsop.com</Link1> |
||
9010 | <Link2>http://indiafocus.indiainfo.com/</Link2> |
||
9011 | </user-agent> |
||
9012 | <user-agent> |
||
9013 | <ID>id_g_m_637</ID> |
||
9014 | <String>LinkScan/x.x Unix</String> |
||
9015 | <Description>Shareware robot from Elsop.com</Description> |
||
9016 | <Type>R</Type> |
||
9017 | <Comment></Comment> |
||
9018 | <Link1>http://www.elsop.com</Link1> |
||
9019 | <Link2></Link2> |
||
9020 | </user-agent> |
||
9021 | <user-agent> |
||
9022 | <ID>id_g_m_638</ID> |
||
9023 | <String>LinksManager.com (http://linksmanager.com/linkchecker.html)</String> |
||
9024 | <Description>Linksmanager bookmark checking</Description> |
||
9025 | <Type>C</Type> |
||
9026 | <Comment>s.also Mozilla/5.0 (compatible; LinksManager.com_bot...</Comment> |
||
9027 | <Link1>http://linksmanager.com/linkchecker.html</Link1> |
||
9028 | <Link2></Link2> |
||
9029 | </user-agent> |
||
9030 | <user-agent> |
||
9031 | <ID>id_g_m_639</ID> |
||
9032 | <String>LinkSonar/1.35</String> |
||
9033 | <Description>LinkSonar (Japan) link checking tool</Description> |
||
9034 | <Type>C</Type> |
||
9035 | <Comment></Comment> |
||
9036 | <Link1>http://hp.vector.co.jp/authors/VA014575/chicchi/linksonar/readme.html</Link1> |
||
9037 | <Link2></Link2> |
||
9038 | </user-agent> |
||
9039 | <user-agent> |
||
9040 | <ID>id_g_m_640</ID> |
||
9041 | <String>LinkSweeper/1.x</String> |
||
9042 | <Description>Left Side Software's LinkSweeper (ceased) bookmark utility</Description> |
||
9043 | <Type>C</Type> |
||
9044 | <Comment></Comment> |
||
9045 | <Link1>http://www.lss.com.au/lss/lss_main.htm</Link1> |
||
9046 | <Link2></Link2> |
||
9047 | </user-agent> |
||
9048 | <user-agent> |
||
9049 | <ID>id_g_m_641</ID> |
||
9050 | <String>LinkWalker</String> |
||
9051 | <Description>Seventwentyfour link checking robot</Description> |
||
9052 | <Type>C</Type> |
||
9053 | <Comment></Comment> |
||
9054 | <Link1>http://www.seventwentyfour.com</Link1> |
||
9055 | <Link2></Link2> |
||
9056 | </user-agent> |
||
9057 | <user-agent> |
||
9058 | <ID>id_g_m_619</ID> |
||
9059 | <String>link_check3.plx libwww-perl/5.65</String> |
||
9060 | <Description>link check 3 - Perl HTML link checker (from Perl for Web Site Management)</Description> |
||
9061 | <Type>C</Type> |
||
9062 | <Comment></Comment> |
||
9063 | <Link1>http://www.elanus.net/cgi/examples.cgi/view/ex_1102.txt</Link1> |
||
9064 | <Link2></Link2> |
||
9065 | </user-agent> |
||
9066 | <user-agent> |
||
9067 | <ID>id_g_m_642</ID> |
||
9068 | <String>ListBidBot (freelance job spider http://listbid.com)<a href=http://listbid.com>Freelance</a></String> |
||
9069 | <Description>Listbid.com / Directnic.com link checking ?</Description> |
||
9070 | <Type>R C</Type> |
||
9071 | <Comment></Comment> |
||
9072 | <Link1>http://listbid.com</Link1> |
||
9073 | <Link2></Link2> |
||
9074 | </user-agent> |
||
9075 | <user-agent> |
||
9076 | <ID>id_g_m_031107_3</ID> |
||
9077 | <String>LiveTrans/Nutch-0.9 (maintainer: cobain at iis dot sinica dot edu dot tw; http://wkd.iis.sinica.edu.tw/LiveTrans/)</String> |
||
9078 | <Description>WKD Lab: LiveTrans - Online query and terminology translation service</Description> |
||
9079 | <Type>R</Type> |
||
9080 | <Comment>140.109.19.1xx</Comment> |
||
9081 | <Link1>http://wkd.iis.sinica.edu.tw/LiveTrans/</Link1> |
||
9082 | <Link2></Link2> |
||
9083 | </user-agent> |
||
9084 | <user-agent> |
||
9085 | <ID>id_g_m_643</ID> |
||
9086 | <String>Llaut/1.0 (http://mnm.uib.es/~gallir/llaut/bot.html)</String> |
||
9087 | <Description>llaut robot - Universitat de les Illes Balears (Spain)</Description> |
||
9088 | <Type>R</Type> |
||
9089 | <Comment></Comment> |
||
9090 | <Link1>http://mnm.uib.es</Link1> |
||
9091 | <Link2></Link2> |
||
9092 | </user-agent> |
||
9093 | <user-agent> |
||
9094 | <ID>id_g_m_200307_2</ID> |
||
9095 | <String>LMQueueBot/0.2</String> |
||
9096 | <Description>E-Mail harvesting robot - same as ContactBot</Description> |
||
9097 | <Type>S</Type> |
||
9098 | <Comment>64.124.152.xx</Comment> |
||
9099 | <Link1></Link1> |
||
9100 | <Link2></Link2> |
||
9101 | </user-agent> |
||
9102 | <user-agent> |
||
9103 | <ID>id_g_m_644</ID> |
||
9104 | <String>lmspider (lmspider@scansoft.com)</String> |
||
9105 | <Description>lmspider from Scansoft (192.133.61.xx) - Web text collector</Description> |
||
9106 | <Type>R</Type> |
||
9107 | <Comment>see here</Comment> |
||
9108 | <Link1>http://www.kahunaburger.com/blog/archives/000117.html</Link1> |
||
9109 | <Link2></Link2> |
||
9110 | </user-agent> |
||
9111 | <user-agent> |
||
9112 | <ID>id_g_m_645</ID> |
||
9113 | <String>LNSpiderguy</String> |
||
9114 | <Description>Lexis-Nexis robot</Description> |
||
9115 | <Type>R</Type> |
||
9116 | <Comment></Comment> |
||
9117 | <Link1>http://www.lexis-nexis.com/</Link1> |
||
9118 | <Link2></Link2> |
||
9119 | </user-agent> |
||
9120 | <user-agent> |
||
9121 | <ID>id_g_m_300106_4</ID> |
||
9122 | <String>LocalBot/1.0 ( http://www.localbot.co.uk/)</String> |
||
9123 | <Description>LocalBot company information collector</Description> |
||
9124 | <Type>R</Type> |
||
9125 | <Comment></Comment> |
||
9126 | <Link1>http://www.localbot.co.uk/</Link1> |
||
9127 | <Link2></Link2> |
||
9128 | </user-agent> |
||
9129 | <user-agent> |
||
9130 | <ID>id_g_m_646</ID> |
||
9131 | <String>LocalcomBot/1.2.x ( http://www.local.com/bot.htm)</String> |
||
9132 | <Description>Local.com local search robot (216.52.252.xxx)</Description> |
||
9133 | <Type>R</Type> |
||
9134 | <Comment></Comment> |
||
9135 | <Link1>http://www.local.com/</Link1> |
||
9136 | <Link2></Link2> |
||
9137 | </user-agent> |
||
9138 | <user-agent> |
||
9139 | <ID>id_g_m_647</ID> |
||
9140 | <String>Lockstep Spider/1.0</String> |
||
9141 | <Description>Lockstep (website content protection tool) user agent</Description> |
||
9142 | <Type>R</Type> |
||
9143 | <Comment></Comment> |
||
9144 | <Link1>http://www.lockstep.com</Link1> |
||
9145 | <Link2></Link2> |
||
9146 | </user-agent> |
||
9147 | <user-agent> |
||
9148 | <ID>id_g_m_648</ID> |
||
9149 | <String>Look.com</String> |
||
9150 | <Description>GlobalQueue spider (64.40.105.xxx)</Description> |
||
9151 | <Type>R</Type> |
||
9152 | <Comment></Comment> |
||
9153 | <Link1>http://www.multi-mode.com/</Link1> |
||
9154 | <Link2></Link2> |
||
9155 | </user-agent> |
||
9156 | <user-agent> |
||
9157 | <ID>id_g_m_649</ID> |
||
9158 | <String>Lotus-Notes/4.5 ( Windows-NT )</String> |
||
9159 | <Description>Lotus Notes browser</Description> |
||
9160 | <Type>B</Type> |
||
9161 | <Comment></Comment> |
||
9162 | <Link1></Link1> |
||
9163 | <Link2></Link2> |
||
9164 | </user-agent> |
||
9165 | <user-agent> |
||
9166 | <ID>id_g_m_650</ID> |
||
9167 | <String>LotusDiscovery/x.0 (compatible; Mozilla 4.0; MSIE 4.01; Windows NT)</String> |
||
9168 | <Description>IBM Lotus Discovery Server</Description> |
||
9169 | <Type></Type> |
||
9170 | <Comment></Comment> |
||
9171 | <Link1>http://www-142.ibm.com/software/sw-lotus/products/product3.nsf/wdocs/644012e0434859b585256ec9006d37b8</Link1> |
||
9172 | <Link2></Link2> |
||
9173 | </user-agent> |
||
9174 | <user-agent> |
||
9175 | <ID>id_g_m_051207_1</ID> |
||
9176 | <String>Lovel as 1.0 ( +http://www.everatom.com)</String> |
||
9177 | <Description>Everatom.com song lyrics search</Description> |
||
9178 | <Type>R</Type> |
||
9179 | <Comment>80.91.191.2xx</Comment> |
||
9180 | <Link1>http://www.everatom.com</Link1> |
||
9181 | <Link2></Link2> |
||
9182 | </user-agent> |
||
9183 | <user-agent> |
||
9184 | <ID>id_g_m_100308_2</ID> |
||
9185 | <String>LTI/LemurProject Nutch Spider/Nutch-1.0-dev (lti crawler for CMU; http://www.lti.cs.cmu.edu; changkuk at cmu dot edu)</String> |
||
9186 | <Description>LTI - The Lemur Toolkit for Language Modeling and Information Retrieval via Yahoo</Description> |
||
9187 | <Type>R</Type> |
||
9188 | <Comment>68.180.139.12x</Comment> |
||
9189 | <Link1>http://www.lemurproject.org/</Link1> |
||
9190 | <Link2>http://www.yahoo.com/</Link2> |
||
9191 | </user-agent> |
||
9192 | <user-agent> |
||
9193 | <ID>id_g_m_050208_3</ID> |
||
9194 | <String>LTI/LemurProject Nutch Spider/Nutch-1.0-dev (Research spider using Nutch; http://www.lemurproject.org; mhoy@cs.cmu.edu)</String> |
||
9195 | <Description>LTI - The Lemur Toolkit for Language Modeling and Information Retrieval via Yahoo</Description> |
||
9196 | <Type>R</Type> |
||
9197 | <Comment>68.180.139.12x</Comment> |
||
9198 | <Link1>http://www.lemurproject.org/</Link1> |
||
9199 | <Link2>http://www.yahoo.com/</Link2> |
||
9200 | </user-agent> |
||
9201 | <user-agent> |
||
9202 | <ID>id_g_m_651</ID> |
||
9203 | <String>luchs.at URL checker</String> |
||
9204 | <Description>Luchs.at (Linux Wiki) link checking</Description> |
||
9205 | <Type>C</Type> |
||
9206 | <Comment></Comment> |
||
9207 | <Link1>http://web.luchs.at/information/linkchecker.php</Link1> |
||
9208 | <Link2></Link2> |
||
9209 | </user-agent> |
||
9210 | <user-agent> |
||
9211 | <ID>id_g_m_090106_1</ID> |
||
9212 | <String>Lunascape</String> |
||
9213 | <Description>Lunascape IE based browser (Japan)</Description> |
||
9214 | <Type>B</Type> |
||
9215 | <Comment>s. also Mozilla/4.0 (... Lunascape ...)</Comment> |
||
9216 | <Link1>http://www2.lunascape.jp/index.aspx</Link1> |
||
9217 | <Link2></Link2> |
||
9218 | </user-agent> |
||
9219 | <user-agent> |
||
9220 | <ID>id_g_m_652</ID> |
||
9221 | <String>lwp-trivial/1.32</String> |
||
9222 | <Description>Ultimate Search / Smartdesk (no website) robot</Description> |
||
9223 | <Type>R</Type> |
||
9224 | <Comment></Comment> |
||
9225 | <Link1></Link1> |
||
9226 | <Link2></Link2> |
||
9227 | </user-agent> |
||
9228 | <user-agent> |
||
9229 | <ID>id_g_m_653</ID> |
||
9230 | <String>lwp-trivial/1.34</String> |
||
9231 | <Description>Search4free robot</Description> |
||
9232 | <Type>R</Type> |
||
9233 | <Comment></Comment> |
||
9234 | <Link1>http://www.search4free.com</Link1> |
||
9235 | <Link2></Link2> |
||
9236 | </user-agent> |
||
9237 | <user-agent> |
||
9238 | <ID>id_g_m_654</ID> |
||
9239 | <String>lwp-trivial/1.34</String> |
||
9240 | <Description>Search4free robot</Description> |
||
9241 | <Type>R</Type> |
||
9242 | <Comment></Comment> |
||
9243 | <Link1>http://www.search4free.com</Link1> |
||
9244 | <Link2></Link2> |
||
9245 | </user-agent> |
||
9246 | <user-agent> |
||
9247 | <ID>id_g_m_656</ID> |
||
9248 | <String>lwp-trivial/1.35</String> |
||
9249 | <Description>Expert HTML online source viewer</Description> |
||
9250 | <Type>B</Type> |
||
9251 | <Comment></Comment> |
||
9252 | <Link1>http://www.expert-html.com/</Link1> |
||
9253 | <Link2></Link2> |
||
9254 | </user-agent> |
||
9255 | <user-agent> |
||
9256 | <ID>id_g_m_655</ID> |
||
9257 | <String>lwp-trivial/1.35</String> |
||
9258 | <Description>Expert HTML online source viewer</Description> |
||
9259 | <Type>B</Type> |
||
9260 | <Comment></Comment> |
||
9261 | <Link1>http://www.expert-html.com/</Link1> |
||
9262 | <Link2></Link2> |
||
9263 | </user-agent> |
||
9264 | <user-agent> |
||
9265 | <ID>id_g_m_657</ID> |
||
9266 | <String>LWP::Simple/5.22</String> |
||
9267 | <Description>Perl LWP:Collective module</Description> |
||
9268 | <Type>R</Type> |
||
9269 | <Comment></Comment> |
||
9270 | <Link1>http://www.thatrobotsite.com</Link1> |
||
9271 | <Link2></Link2> |
||
9272 | </user-agent> |
||
9273 | <user-agent> |
||
9274 | <ID>id_g_m_658</ID> |
||
9275 | <String>LWP::Simple/5.36</String> |
||
9276 | <Description>Perl LWP:Collective module</Description> |
||
9277 | <Type>R</Type> |
||
9278 | <Comment></Comment> |
||
9279 | <Link1>http://www.thatrobotsite.com</Link1> |
||
9280 | <Link2></Link2> |
||
9281 | </user-agent> |
||
9282 | <user-agent> |
||
9283 | <ID>id_g_m_659</ID> |
||
9284 | <String>LWP::Simple/5.48</String> |
||
9285 | <Description>Perl LWP:Collective module - Linkomatic robot</Description> |
||
9286 | <Type>R</Type> |
||
9287 | <Comment></Comment> |
||
9288 | <Link1>http://www.linkomatic.com/</Link1> |
||
9289 | <Link2>http://www.thatrobotsite.com</Link2> |
||
9290 | </user-agent> |
||
9291 | <user-agent> |
||
9292 | <ID>id_g_m_660</ID> |
||
9293 | <String>LWP::Simple/5.50</String> |
||
9294 | <Description>Perl LWP:Collective module - secure-netz.de link checking (in conjunction w. libwww-perl/5.50)</Description> |
||
9295 | <Type>R</Type> |
||
9296 | <Comment></Comment> |
||
9297 | <Link1>http://www.secure-netz.de</Link1> |
||
9298 | <Link2>http://www.thatrobotsite.com</Link2> |
||
9299 | </user-agent> |
||
9300 | <user-agent> |
||
9301 | <ID>id_g_m_661</ID> |
||
9302 | <String>LWP::Simple/5.51</String> |
||
9303 | <Description>Perl LWP:Collective module - Inktomi (62.253.64.x) robot</Description> |
||
9304 | <Type>R</Type> |
||
9305 | <Comment></Comment> |
||
9306 | <Link1>http://www.inktomi.com/</Link1> |
||
9307 | <Link2>http://www.thatrobotsite.com</Link2> |
||
9308 | </user-agent> |
||
9309 | <user-agent> |
||
9310 | <ID>id_g_m_662</ID> |
||
9311 | <String>LWP::Simple/5.53</String> |
||
9312 | <Description>Perl LWP:Collective module - Only.com </Description> |
||
9313 | <Type>R</Type> |
||
9314 | <Comment>in conjunction w. Spida/0.1</Comment> |
||
9315 | <Link1>http://www.only.com</Link1> |
||
9316 | <Link2>http://www.thatrobotsite.com</Link2> |
||
9317 | </user-agent> |
||
9318 | <user-agent> |
||
9319 | <ID>id_g_m_663</ID> |
||
9320 | <String>LWP::Simple/5.63</String> |
||
9321 | <Description>Perl LWP:Collective module</Description> |
||
9322 | <Type>R</Type> |
||
9323 | <Comment></Comment> |
||
9324 | <Link1>http://www.thatrobotsite.com</Link1> |
||
9325 | <Link2></Link2> |
||
9326 | </user-agent> |
||
9327 | <user-agent> |
||
9328 | <ID>id_g_m_291105_3</ID> |
||
9329 | <String>LWP::Simple/5.803</String> |
||
9330 | <Description>ThePlanet/jaja-jak-globusy.com Google Adsense refferer spam bot from 70.85.116.* / 70.84.128.xxx / 70.85.193.xxx</Description> |
||
9331 | <Type>S</Type> |
||
9332 | <Comment>appears also as Poirot - Mozilla/4.76 [en] (Win98; U) - Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)</Comment> |
||
9333 | <Link1>http://spamhuntress.com/wiki/Manila_Industries</Link1> |
||
9334 | <Link2></Link2> |
||
9335 | </user-agent> |
||
9336 | <user-agent> |
||
9337 | <ID>id_g_m_664</ID> |
||
9338 | <String>Lycos_Spider_(modspider)</String> |
||
9339 | <Description>Lycos spider</Description> |
||
9340 | <Type>R</Type> |
||
9341 | <Comment></Comment> |
||
9342 | <Link1>http://www.lycos.com</Link1> |
||
9343 | <Link2></Link2> |
||
9344 | </user-agent> |
||
9345 | <user-agent> |
||
9346 | <ID>id_g_m_665</ID> |
||
9347 | <String>Lycos_Spider_(T-Rex)</String> |
||
9348 | <Description>Lycos spider</Description> |
||
9349 | <Type>R</Type> |
||
9350 | <Comment></Comment> |
||
9351 | <Link1>http://www.lycos.com</Link1> |
||
9352 | <Link2></Link2> |
||
9353 | </user-agent> |
||
9354 | <user-agent> |
||
9355 | <ID>id_g_m_200308_2</ID> |
||
9356 | <String>Lynx/2-4-2 (Bobcat/0.5 [DOS] Jp Beta04)</String> |
||
9357 | <Description>Bobcat - Text and Lynx based DOS browser</Description> |
||
9358 | <Type>B</Type> |
||
9359 | <Comment></Comment> |
||
9360 | <Link1>http://www.fdisk.com/doslynx/bobcat.htm</Link1> |
||
9361 | <Link2></Link2> |
||
9362 | </user-agent> |
||
9363 | <user-agent> |
||
9364 | <ID>id_g_m_666</ID> |
||
9365 | <String>Lynx/2.6 libwww-FM/2.14</String> |
||
9366 | <Description>Lynx 2.x text mode browser</Description> |
||
9367 | <Type>B</Type> |
||
9368 | <Comment></Comment> |
||
9369 | <Link1>http://lynx.browser.org/</Link1> |
||
9370 | <Link2></Link2> |
||
9371 | </user-agent> |
||
9372 | <user-agent> |
||
9373 | <ID>id_g_m_180108_1</ID> |
||
9374 | <String>Lynx/2.8 (;http://seebot.org)</String> |
||
9375 | <Description>seebot.org online service - uses lynx browser for crawlers view of web pages</Description> |
||
9376 | <Type>B</Type> |
||
9377 | <Comment>208.113.176.x[xx]</Comment> |
||
9378 | <Link1>http://seebot.org/</Link1> |
||
9379 | <Link2></Link2> |
||
9380 | </user-agent> |
||
9381 | <user-agent> |
||
9382 | <ID>id_g_m_667</ID> |
||
9383 | <String>Lynx/2.8.3dev.9 libwww-FM/2.14 SSL-MM/1.4.1 OpenSSL/0.9.6</String> |
||
9384 | <Description>Lynx 2.x text mode browser</Description> |
||
9385 | <Type>B</Type> |
||
9386 | <Comment></Comment> |
||
9387 | <Link1>http://lynx.browser.org/</Link1> |
||
9388 | <Link2></Link2> |
||
9389 | </user-agent> |
||
9390 | <user-agent> |
||
9391 | <ID>id_g_m_668</ID> |
||
9392 | <String>Lynx/2.8.4rel.1 libwww-FM/2.14 SSL-MM/1.4.1 OpenSSL/0.9.6c (human-guided@lerly.net)</String> |
||
9393 | <Description>Lynx 2.x text mode browser used as robot via cogentco.com</Description> |
||
9394 | <Type>R</Type> |
||
9395 | <Comment></Comment> |
||
9396 | <Link1></Link1> |
||
9397 | <Link2></Link2> |
||
9398 | </user-agent> |
||
9399 | <user-agent> |
||
9400 | <ID>id_g_m_669</ID> |
||
9401 | <String>Mac Finder 1.0.xx</String> |
||
9402 | <Description>Some spam bot</Description> |
||
9403 | <Type>S</Type> |
||
9404 | <Comment></Comment> |
||
9405 | <Link1>http://www.kloth.net/internet/badbots.php</Link1> |
||
9406 | <Link2></Link2> |
||
9407 | </user-agent> |
||
9408 | <user-agent> |
||
9409 | <ID>id_g_m_670</ID> |
||
9410 | <String>Mackster( http://www.ukwizz.com )</String> |
||
9411 | <Description>UKWizz search robot</Description> |
||
9412 | <Type>R</Type> |
||
9413 | <Comment>s. also UKWizz/Nutch</Comment> |
||
9414 | <Link1>http://www.ukwizz.com</Link1> |
||
9415 | <Link2></Link2> |
||
9416 | </user-agent> |
||
9417 | <user-agent> |
||
9418 | <ID>id_g_m_671</ID> |
||
9419 | <String>Mag-Net</String> |
||
9420 | <Description>Wind.it client user-agent ?</Description> |
||
9421 | <Type></Type> |
||
9422 | <Comment></Comment> |
||
9423 | <Link1></Link1> |
||
9424 | <Link2></Link2> |
||
9425 | </user-agent> |
||
9426 | <user-agent> |
||
9427 | <ID>id_g_m_180606_3</ID> |
||
9428 | <String>MagicWML/1.0 (forcewml)</String> |
||
9429 | <Description>All Magic/Wap wml service for mobile devices</Description> |
||
9430 | <Type>P</Type> |
||
9431 | <Comment></Comment> |
||
9432 | <Link1>http://allmagic3.com/wap/</Link1> |
||
9433 | <Link2></Link2> |
||
9434 | </user-agent> |
||
9435 | <user-agent> |
||
9436 | <ID>id_g_m_061206_1</ID> |
||
9437 | <String>MagpieRSS/0.7x (+http://magpierss.sf.net)</String> |
||
9438 | <Description>Magpie RSS - PHP RSS Parser</Description> |
||
9439 | <Type>B</Type> |
||
9440 | <Comment></Comment> |
||
9441 | <Link1>http://magpierss.sourceforge.net/</Link1> |
||
9442 | <Link2></Link2> |
||
9443 | </user-agent> |
||
9444 | <user-agent> |
||
9445 | <ID>id_g_m_030308_1</ID> |
||
9446 | <String>Mahiti.Com/Mahiti Crawler-1.0 (Mahiti.Com; http://mahiti.com ; mahiti.com)</String> |
||
9447 | <Description>Mahiti.com India search crawler</Description> |
||
9448 | <Type>R</Type> |
||
9449 | <Comment>72.167.143.1x</Comment> |
||
9450 | <Link1>http://mahiti.com/</Link1> |
||
9451 | <Link2></Link2> |
||
9452 | </user-agent> |
||
9453 | <user-agent> |
||
9454 | <ID>id_g_m_020707_2</ID> |
||
9455 | <String>Mail.Ru/1.0</String> |
||
9456 | <Description>Mail.ru search</Description> |
||
9457 | <Type>R</Type> |
||
9458 | <Comment>194.186.55.2xx</Comment> |
||
9459 | <Link1>http://www.mail.ru/</Link1> |
||
9460 | <Link2></Link2> |
||
9461 | </user-agent> |
||
9462 | <user-agent> |
||
9463 | <ID>id_g_m_672</ID> |
||
9464 | <String>mailto:webcraft@bea.com</String> |
||
9465 | <Description>Unknown Bea robot</Description> |
||
9466 | <Type>R</Type> |
||
9467 | <Comment></Comment> |
||
9468 | <Link1>http://www.beasys.com</Link1> |
||
9469 | <Link2></Link2> |
||
9470 | </user-agent> |
||
9471 | <user-agent> |
||
9472 | <ID>id_g_m_673</ID> |
||
9473 | <String>mammoth/1.0 ( http://www.sli-systems.com/)</String> |
||
9474 | <Description>SLI Systems mammoth robot</Description> |
||
9475 | <Type>R</Type> |
||
9476 | <Comment>s. also Mozilla/5.0 (+http://www.sli-systems.com/) Mammoth/0.1</Comment> |
||
9477 | <Link1>http://www.sli-systems.com/</Link1> |
||
9478 | <Link2>http://www.tenspider.com/business-blog/more.php?id=A45_0_1_0_M</Link2> |
||
9479 | </user-agent> |
||
9480 | <user-agent> |
||
9481 | <ID>id_g_m_674</ID> |
||
9482 | <String>MantraAgent</String> |
||
9483 | <Description>Looksmart robot</Description> |
||
9484 | <Type>R</Type> |
||
9485 | <Comment></Comment> |
||
9486 | <Link1>http://www.looksmart.com</Link1> |
||
9487 | <Link2></Link2> |
||
9488 | </user-agent> |
||
9489 | <user-agent> |
||
9490 | <ID>id_g_m_675</ID> |
||
9491 | <String>MapoftheInternet.com ( http://MapoftheInternet.com)</String> |
||
9492 | <Description>Map of the Internet visual search engine index robot</Description> |
||
9493 | <Type>R</Type> |
||
9494 | <Comment></Comment> |
||
9495 | <Link1>http://MapoftheInternet.com</Link1> |
||
9496 | <Link2></Link2> |
||
9497 | </user-agent> |
||
9498 | <user-agent> |
||
9499 | <ID>id_g_m_676</ID> |
||
9500 | <String>Mariner/5.1b [de] (Win95; I ;Kolibri gncwebbot)</String> |
||
9501 | <Description>Kolibri.de robot</Description> |
||
9502 | <Type>R</Type> |
||
9503 | <Comment></Comment> |
||
9504 | <Link1>http://www.kolibri.de</Link1> |
||
9505 | <Link2></Link2> |
||
9506 | </user-agent> |
||
9507 | <user-agent> |
||
9508 | <ID>id_g_m_677</ID> |
||
9509 | <String>Marketwave Hit List</String> |
||
9510 | <Description>Pilot Hitlist web site analysis</Description> |
||
9511 | <Type>R</Type> |
||
9512 | <Comment></Comment> |
||
9513 | <Link1>http://www.marketwave.com/products_solutions/hitlist.html</Link1> |
||
9514 | <Link2></Link2> |
||
9515 | </user-agent> |
||
9516 | <user-agent> |
||
9517 | <ID>id_g_m_678</ID> |
||
9518 | <String>Martini</String> |
||
9519 | <Description>Looksmart directory page analysis</Description> |
||
9520 | <Type>R</Type> |
||
9521 | <Comment></Comment> |
||
9522 | <Link1>http://www.looksmart.com</Link1> |
||
9523 | <Link2></Link2> |
||
9524 | </user-agent> |
||
9525 | <user-agent> |
||
9526 | <ID>id_g_m_679</ID> |
||
9527 | <String>MARTINI</String> |
||
9528 | <Description>Looksmart directory page analysis</Description> |
||
9529 | <Type>R</Type> |
||
9530 | <Comment></Comment> |
||
9531 | <Link1>http://www.looksmart.com</Link1> |
||
9532 | <Link2></Link2> |
||
9533 | </user-agent> |
||
9534 | <user-agent> |
||
9535 | <ID>id_g_m_680</ID> |
||
9536 | <String>Marvin v0.3</String> |
||
9537 | <Description>Marvin Medhunt robot</Description> |
||
9538 | <Type>R</Type> |
||
9539 | <Comment></Comment> |
||
9540 | <Link1>http://www.hon.ch/MedHunt/Marvin.html</Link1> |
||
9541 | <Link2></Link2> |
||
9542 | </user-agent> |
||
9543 | <user-agent> |
||
9544 | <ID>id_g_m_270606_1</ID> |
||
9545 | <String>MaSagool/1.0 (MaSagool; http://sagool.jp/; info@sagool.jp)</String> |
||
9546 | <Description>Sagool search Japan robot</Description> |
||
9547 | <Type>R</Type> |
||
9548 | <Comment>124.32.246.xx</Comment> |
||
9549 | <Link1>http://sagool.jp/</Link1> |
||
9550 | <Link2></Link2> |
||
9551 | </user-agent> |
||
9552 | <user-agent> |
||
9553 | <ID>id_g_m_681</ID> |
||
9554 | <String>Mass Downloader 2.x</String> |
||
9555 | <Description>Mass Downloader download manager</Description> |
||
9556 | <Type>D</Type> |
||
9557 | <Comment></Comment> |
||
9558 | <Link1>http://www.metaproducts.com</Link1> |
||
9559 | <Link2></Link2> |
||
9560 | </user-agent> |
||
9561 | <user-agent> |
||
9562 | <ID>id_g_m_682</ID> |
||
9563 | <String>MasterSeek</String> |
||
9564 | <Description>Masterseek (Scandinavia) Beta business search ?</Description> |
||
9565 | <Type>R</Type> |
||
9566 | <Comment></Comment> |
||
9567 | <Link1>http://www.masterseek.com</Link1> |
||
9568 | <Link2></Link2> |
||
9569 | </user-agent> |
||
9570 | <user-agent> |
||
9571 | <ID>id_g_m_683</ID> |
||
9572 | <String>Mata Hari/2.00 </String> |
||
9573 | <Description>Lexibot (exMataHari) search software</Description> |
||
9574 | <Type>R</Type> |
||
9575 | <Comment></Comment> |
||
9576 | <Link1>http://www.lexibot.com</Link1> |
||
9577 | <Link2></Link2> |
||
9578 | </user-agent> |
||
9579 | <user-agent> |
||
9580 | <ID>id_g_m_684</ID> |
||
9581 | <String>Matrix S.p.A. - FAST Enterprise Crawler 6 (Unknown admin e-mail address)</String> |
||
9582 | <Description>Virgilio Italy robot (212.48.11.xxx) using Fast Enterprise Search</Description> |
||
9583 | <Type>R</Type> |
||
9584 | <Comment></Comment> |
||
9585 | <Link1>http://www.virgilio.it</Link1> |
||
9586 | <Link2></Link2> |
||
9587 | </user-agent> |
||
9588 | <user-agent> |
||
9589 | <ID>id_g_m_685</ID> |
||
9590 | <String>maxomobot/dev-20051201 (maxomo; http://67.102.134.34:4047/MAXOMO/MAXOMObot.html; maxomobot@maxomo.com)</String> |
||
9591 | <Description>Maxomo multimedia search robot</Description> |
||
9592 | <Type>R</Type> |
||
9593 | <Comment></Comment> |
||
9594 | <Link1>http://www.maxomo.com</Link1> |
||
9595 | <Link2></Link2> |
||
9596 | </user-agent> |
||
9597 | <user-agent> |
||
9598 | <ID>id_g_m_686</ID> |
||
9599 | <String>McBot/5.001 (windows; U; NT4.0; en-us)</String> |
||
9600 | <Description>Unknown robot from McAfee Austria (80.123.144.xx)</Description> |
||
9601 | <Type></Type> |
||
9602 | <Comment></Comment> |
||
9603 | <Link1></Link1> |
||
9604 | <Link2></Link2> |
||
9605 | </user-agent> |
||
9606 | <user-agent> |
||
9607 | <ID>id_g_m_290108_1</ID> |
||
9608 | <String>MDbot/1.0 (+http://www.megadownload.net/bot.html)</String> |
||
9609 | <Description>MegaDownload files search robot</Description> |
||
9610 | <Type>R</Type> |
||
9611 | <Comment>91.121.83.19x</Comment> |
||
9612 | <Link1>http://www.megadownload.net/</Link1> |
||
9613 | <Link2>http://www.megadownload.net/bot.html</Link2> |
||
9614 | </user-agent> |
||
9615 | <user-agent> |
||
9616 | <ID>id_g_m_170306_1</ID> |
||
9617 | <String>Media Player Classic</String> |
||
9618 | <Description>Substitute for Windows Media Player</Description> |
||
9619 | <Type>B</Type> |
||
9620 | <Comment></Comment> |
||
9621 | <Link1>http://sourceforge.net/projects/guliverkli/</Link1> |
||
9622 | <Link2></Link2> |
||
9623 | </user-agent> |
||
9624 | <user-agent> |
||
9625 | <ID>id_g_m_687</ID> |
||
9626 | <String>MediaCrawler-1.0 (Experimental)</String> |
||
9627 | <Description>Media Find crawler</Description> |
||
9628 | <Type>R</Type> |
||
9629 | <Comment></Comment> |
||
9630 | <Link1>http://www.mediacrawler.de</Link1> |
||
9631 | <Link2></Link2> |
||
9632 | </user-agent> |
||
9633 | <user-agent> |
||
9634 | <ID>id_g_m_688</ID> |
||
9635 | <String>Mediapartners-Google/2.1 ( http://www.googlebot.com/bot.html)</String> |
||
9636 | <Description>Google AdSense robot</Description> |
||
9637 | <Type>R</Type> |
||
9638 | <Comment></Comment> |
||
9639 | <Link1>http://www.google.com/ads/</Link1> |
||
9640 | <Link2></Link2> |
||
9641 | </user-agent> |
||
9642 | <user-agent> |
||
9643 | <ID>id_g_m_689</ID> |
||
9644 | <String>MediaSearch/0.1</String> |
||
9645 | <Description>WWW.fi Media Search</Description> |
||
9646 | <Type>R</Type> |
||
9647 | <Comment></Comment> |
||
9648 | <Link1>http://www.fi/haku/</Link1> |
||
9649 | <Link2></Link2> |
||
9650 | </user-agent> |
||
9651 | <user-agent> |
||
9652 | <ID>id_g_m_690</ID> |
||
9653 | <String>MegaSheep v1.0 (www.searchuk.com internet sheep)</String> |
||
9654 | <Description>Search UK robot</Description> |
||
9655 | <Type>R</Type> |
||
9656 | <Comment></Comment> |
||
9657 | <Link1>http://www.searchuk.com</Link1> |
||
9658 | <Link2></Link2> |
||
9659 | </user-agent> |
||
9660 | <user-agent> |
||
9661 | <ID>id_g_m_131107_1</ID> |
||
9662 | <String>Megite2.0 (http://www.megite.com)</String> |
||
9663 | <Description>Megite web2.0 RSS and news service software</Description> |
||
9664 | <Type>R</Type> |
||
9665 | <Comment></Comment> |
||
9666 | <Link1>http://www.megite.com/</Link1> |
||
9667 | <Link2></Link2> |
||
9668 | </user-agent> |
||
9669 | <user-agent> |
||
9670 | <ID>id_g_m_691</ID> |
||
9671 | <String>Mercator-1.x</String> |
||
9672 | <Description>Mercator crawler software (used by Altavista)</Description> |
||
9673 | <Type>R</Type> |
||
9674 | <Comment></Comment> |
||
9675 | <Link1>http://www.research.compaq.com</Link1> |
||
9676 | <Link2></Link2> |
||
9677 | </user-agent> |
||
9678 | <user-agent> |
||
9679 | <ID>id_g_m_692</ID> |
||
9680 | <String>Mercator-2.0</String> |
||
9681 | <Description>Mercator crawler software (used by Altavista)</Description> |
||
9682 | <Type>R</Type> |
||
9683 | <Comment></Comment> |
||
9684 | <Link1>http://www.research.compaq.com</Link1> |
||
9685 | <Link2></Link2> |
||
9686 | </user-agent> |
||
9687 | <user-agent> |
||
9688 | <ID>id_g_m_693</ID> |
||
9689 | <String>Mercator-Scrub-1.1</String> |
||
9690 | <Description>Mercator crawler software (used by Altavista)</Description> |
||
9691 | <Type>R</Type> |
||
9692 | <Comment></Comment> |
||
9693 | <Link1>http://www.research.compaq.com</Link1> |
||
9694 | <Link2></Link2> |
||
9695 | </user-agent> |
||
9696 | <user-agent> |
||
9697 | <ID>id_g_m_070207_1</ID> |
||
9698 | <String>Metaeuro Web Crawler/0.2 (MetaEuro Web Search Clustering Engine; http://www.metaeuro.com; crawler at metaeuro dot com)</String> |
||
9699 | <Description>MetaEuro.com Clustering Web Search Engine crawler</Description> |
||
9700 | <Type>R</Type> |
||
9701 | <Comment>83.97.31.1xx</Comment> |
||
9702 | <Link1>http://www.metaeuro.com/</Link1> |
||
9703 | <Link2></Link2> |
||
9704 | </user-agent> |
||
9705 | <user-agent> |
||
9706 | <ID>id_g_m_694</ID> |
||
9707 | <String>MetaGer-LinkChecker</String> |
||
9708 | <Description>MetaGer search robot (Germany)</Description> |
||
9709 | <Type>R</Type> |
||
9710 | <Comment>130.75.2.xx</Comment> |
||
9711 | <Link1>http://www.metager.de/</Link1> |
||
9712 | <Link2></Link2> |
||
9713 | </user-agent> |
||
9714 | <user-agent> |
||
9715 | <ID>id_g_m_270706_1</ID> |
||
9716 | <String>MetagerBot/0.8-dev (MetagerBot; http://metager.de; )</String> |
||
9717 | <Description>MetaGer search robot (Germany)</Description> |
||
9718 | <Type>R</Type> |
||
9719 | <Comment>130.75.2.xx</Comment> |
||
9720 | <Link1>http://www.metager.de/</Link1> |
||
9721 | <Link2></Link2> |
||
9722 | </user-agent> |
||
9723 | <user-agent> |
||
9724 | <ID>id_g_m_060307_1</ID> |
||
9725 | <String>MetaGer_PreChecker0.1</String> |
||
9726 | <Description>MetaGer search robot (Germany)</Description> |
||
9727 | <Type>R</Type> |
||
9728 | <Comment>130.75.2.xx</Comment> |
||
9729 | <Link1>http://www.metager.de/</Link1> |
||
9730 | <Link2></Link2> |
||
9731 | </user-agent> |
||
9732 | <user-agent> |
||
9733 | <ID>id_g_m_695</ID> |
||
9734 | <String>MetaProducts Download Express/1.x</String> |
||
9735 | <Description>Download Express download manager</Description> |
||
9736 | <Type>D</Type> |
||
9737 | <Comment></Comment> |
||
9738 | <Link1>http://www.metaproducts.com</Link1> |
||
9739 | <Link2></Link2> |
||
9740 | </user-agent> |
||
9741 | <user-agent> |
||
9742 | <ID>id_g_m_696</ID> |
||
9743 | <String>Metaspinner/0.01 (Metaspinner; http://www.meta-spinner.de/; support@meta-spinner.de/)</String> |
||
9744 | <Description>Metaspinner search robot - Germany</Description> |
||
9745 | <Type>R</Type> |
||
9746 | <Comment></Comment> |
||
9747 | <Link1>http://www.meta-spinner.de/</Link1> |
||
9748 | <Link2></Link2> |
||
9749 | </user-agent> |
||
9750 | <user-agent> |
||
9751 | <ID>id_g_m_300407_1</ID> |
||
9752 | <String>metatagsdir/0.7 (+http://metatagsdir.com/directory/)</String> |
||
9753 | <Description>Metatagsdir.com directory index spider</Description> |
||
9754 | <Type>R</Type> |
||
9755 | <Comment>206.196.111.2xx</Comment> |
||
9756 | <Link1>http://metatagsdir.com/directory/</Link1> |
||
9757 | <Link2></Link2> |
||
9758 | </user-agent> |
||
9759 | <user-agent> |
||
9760 | <ID>id_g_m_697</ID> |
||
9761 | <String>MFC Foundation Class Library 4.0</String> |
||
9762 | <Description>Microsoft Foundation Class Library - i.e. used for e-mail harvesting from 68.154.96.xx (bellsouth.net)</Description> |
||
9763 | <Type>S</Type> |
||
9764 | <Comment>appears also as Full Web Bot 0516B or Demo Bot Z 16b</Comment> |
||
9765 | <Link1></Link1> |
||
9766 | <Link2></Link2> |
||
9767 | </user-agent> |
||
9768 | <user-agent> |
||
9769 | <ID>id_g_m_698</ID> |
||
9770 | <String>MFC_Tear_Sample</String> |
||
9771 | <Description>Microsoft.com user agent</Description> |
||
9772 | <Type></Type> |
||
9773 | <Comment></Comment> |
||
9774 | <Link1></Link1> |
||
9775 | <Link2></Link2> |
||
9776 | </user-agent> |
||
9777 | <user-agent> |
||
9778 | <ID>id_g_m_699</ID> |
||
9779 | <String>MFHttpScan</String> |
||
9780 | <Description>Advanced Site Crawler web site ripper and extractor</Description> |
||
9781 | <Type>D</Type> |
||
9782 | <Comment></Comment> |
||
9783 | <Link1>http://www.innovative.go.ro/sitecrawler/index.htm</Link1> |
||
9784 | <Link2></Link2> |
||
9785 | </user-agent> |
||
9786 | <user-agent> |
||
9787 | <ID>id_g_m_700</ID> |
||
9788 | <String>MicroBaz</String> |
||
9789 | <Description>GigaBaz Brainbot (Germany) robot (213.139.152.xx)</Description> |
||
9790 | <Type>R</Type> |
||
9791 | <Comment> s. also - gigabaz/3.1x ...</Comment> |
||
9792 | <Link1>http://brainbot.com//site3</Link1> |
||
9793 | <Link2></Link2> |
||
9794 | </user-agent> |
||
9795 | <user-agent> |
||
9796 | <ID>id_g_m_701</ID> |
||
9797 | <String>Microsoft Data Access Internet Publishing Provider Cache Manager</String> |
||
9798 | <Description>MS Office 2000 acting as WebDAV client</Description> |
||
9799 | <Type>B P</Type> |
||
9800 | <Comment></Comment> |
||
9801 | <Link1></Link1> |
||
9802 | <Link2></Link2> |
||
9803 | </user-agent> |
||
9804 | <user-agent> |
||
9805 | <ID>id_g_m_702</ID> |
||
9806 | <String>Microsoft Data Access Internet Publishing Provider DAV</String> |
||
9807 | <Description>MS Office 2000 acting as WebDAV client</Description> |
||
9808 | <Type>B</Type> |
||
9809 | <Comment></Comment> |
||
9810 | <Link1></Link1> |
||
9811 | <Link2></Link2> |
||
9812 | </user-agent> |
||
9813 | <user-agent> |
||
9814 | <ID>id_g_m_704</ID> |
||
9815 | <String>Microsoft Data Access Internet Publishing Provider Protocol Discovery</String> |
||
9816 | <Description>Server probe for data access operations using MS Frontpage with OPTION header</Description> |
||
9817 | <Type>B C</Type> |
||
9818 | <Comment></Comment> |
||
9819 | <Link1></Link1> |
||
9820 | <Link2></Link2> |
||
9821 | </user-agent> |
||
9822 | <user-agent> |
||
9823 | <ID>id_g_m_703</ID> |
||
9824 | <String>Microsoft Data Access Internet Publishing Provider Protocol Discovery</String> |
||
9825 | <Description>MS Office 2000 acting as WebDAV client</Description> |
||
9826 | <Type>B C</Type> |
||
9827 | <Comment></Comment> |
||
9828 | <Link1></Link1> |
||
9829 | <Link2></Link2> |
||
9830 | </user-agent> |
||
9831 | <user-agent> |
||
9832 | <ID>id_g_m_190807_2</ID> |
||
9833 | <String>Microsoft Log Parser 2.2</String> |
||
9834 | <Description>Microsoft Log Parser text query tool</Description> |
||
9835 | <Type>D</Type> |
||
9836 | <Comment></Comment> |
||
9837 | <Link1>http://www.microsoft.com/technet/scriptcenter/tools/logparser/default.mspx</Link1> |
||
9838 | <Link2></Link2> |
||
9839 | </user-agent> |
||
9840 | <user-agent> |
||
9841 | <ID>id_g_m_180306_1</ID> |
||
9842 | <String>Microsoft Small Business Indexer</String> |
||
9843 | <Description>MS Small Business Server content indexer</Description> |
||
9844 | <Type>R</Type> |
||
9845 | <Comment>Indexing from Microsoft: 204.71.191.xx</Comment> |
||
9846 | <Link1>http://www.microsoft.com/windowsserver2003/sbs/default.mspx</Link1> |
||
9847 | <Link2></Link2> |
||
9848 | </user-agent> |
||
9849 | <user-agent> |
||
9850 | <ID>id_g_m_705</ID> |
||
9851 | <String>Microsoft URL Control - 6.00.8xxx</String> |
||
9852 | <Description>user agent looks for form-mail components (spam-bot)</Description> |
||
9853 | <Type>S</Type> |
||
9854 | <Comment></Comment> |
||
9855 | <Link1></Link1> |
||
9856 | <Link2></Link2> |
||
9857 | </user-agent> |
||
9858 | <user-agent> |
||
9859 | <ID>id_g_m_707</ID> |
||
9860 | <String>MicrosoftPrototypeCrawler (How's my crawling? mailto:newbiecrawler@hotmail.com)</String> |
||
9861 | <Description>Unknown robot from Microsoft.com (131.107.163.xx)</Description> |
||
9862 | <Type>R</Type> |
||
9863 | <Comment></Comment> |
||
9864 | <Link1></Link1> |
||
9865 | <Link2></Link2> |
||
9866 | </user-agent> |
||
9867 | <user-agent> |
||
9868 | <ID>id_g_m_706</ID> |
||
9869 | <String>Microsoft_Internet_Explorer_5.00.438 (fjones@isd.net)</String> |
||
9870 | <Description>Secure Computing SmartFilterWhere / Bess web filter (192.55.214.xx)</Description> |
||
9871 | <Type>P</Type> |
||
9872 | <Comment></Comment> |
||
9873 | <Link1>http://www.securecomputing.com/index.cfm?skey=22</Link1> |
||
9874 | <Link2></Link2> |
||
9875 | </user-agent> |
||
9876 | <user-agent> |
||
9877 | <ID>id_g_m_708</ID> |
||
9878 | <String>MIIxpc/4.2</String> |
||
9879 | <Description>xpc-mii.net HTTP server message</Description> |
||
9880 | <Type>P</Type> |
||
9881 | <Comment></Comment> |
||
9882 | <Link1></Link1> |
||
9883 | <Link2></Link2> |
||
9884 | </user-agent> |
||
9885 | <user-agent> |
||
9886 | <ID>id_g_m_130807_2</ID> |
||
9887 | <String>Mindjet MindManager</String> |
||
9888 | <Description>The Mindjet blog MindManager category</Description> |
||
9889 | <Type>D</Type> |
||
9890 | <Comment>80.229.1xx</Comment> |
||
9891 | <Link1>http://blog.mindjet.com/category/mindjet/mindmanager/</Link1> |
||
9892 | <Link2></Link2> |
||
9893 | </user-agent> |
||
9894 | <user-agent> |
||
9895 | <ID>id_g_m_709</ID> |
||
9896 | <String>minibot</String> |
||
9897 | <Description>unknown robot via Korea Telecom (211.218.xxx.xxx)</Description> |
||
9898 | <Type></Type> |
||
9899 | <Comment></Comment> |
||
9900 | <Link1></Link1> |
||
9901 | <Link2></Link2> |
||
9902 | </user-agent> |
||
9903 | <user-agent> |
||
9904 | <ID>id_g_m_110506_2</ID> |
||
9905 | <String>miniRank/1.6 (Website ranking; www.minirank.com; robot)</String> |
||
9906 | <Description>mini- Rank website popularity tool</Description> |
||
9907 | <Type>C</Type> |
||
9908 | <Comment>64.230.71.2xx</Comment> |
||
9909 | <Link1>http://www.minirank.com/</Link1> |
||
9910 | <Link2></Link2> |
||
9911 | </user-agent> |
||
9912 | <user-agent> |
||
9913 | <ID>id_g_m_710</ID> |
||
9914 | <String>MiracleAlphaTest</String> |
||
9915 | <Description>unknown robot via nec.co.jp Telecom (210.143.35.xx)</Description> |
||
9916 | <Type></Type> |
||
9917 | <Comment></Comment> |
||
9918 | <Link1></Link1> |
||
9919 | <Link2></Link2> |
||
9920 | </user-agent> |
||
9921 | <user-agent> |
||
9922 | <ID>id_g_m_711</ID> |
||
9923 | <String>Missauga Locate 1.0.0</String> |
||
9924 | <Description>Some spam bot</Description> |
||
9925 | <Type>S</Type> |
||
9926 | <Comment></Comment> |
||
9927 | <Link1>http://www.neilgunton.com/spambot_trap/appendix/</Link1> |
||
9928 | <Link2></Link2> |
||
9929 | </user-agent> |
||
9930 | <user-agent> |
||
9931 | <ID>id_g_m_712</ID> |
||
9932 | <String>Missigua Locator 1.9</String> |
||
9933 | <Description>Some spam bot</Description> |
||
9934 | <Type>S</Type> |
||
9935 | <Comment></Comment> |
||
9936 | <Link1>http://www.neilgunton.com/spambot_trap/appendix/</Link1> |
||
9937 | <Link2></Link2> |
||
9938 | </user-agent> |
||
9939 | <user-agent> |
||
9940 | <ID>id_g_m_713</ID> |
||
9941 | <String>Missouri College Browse</String> |
||
9942 | <Description>Some spam bot</Description> |
||
9943 | <Type>S</Type> |
||
9944 | <Comment></Comment> |
||
9945 | <Link1></Link1> |
||
9946 | <Link2></Link2> |
||
9947 | </user-agent> |
||
9948 | <user-agent> |
||
9949 | <ID>id_g_m_714</ID> |
||
9950 | <String>Mister Pix II 2.02a</String> |
||
9951 | <Description>Mister PiX picture finding software</Description> |
||
9952 | <Type>D R</Type> |
||
9953 | <Comment></Comment> |
||
9954 | <Link1>http://www.mister-pix.com/</Link1> |
||
9955 | <Link2></Link2> |
||
9956 | </user-agent> |
||
9957 | <user-agent> |
||
9958 | <ID>id_g_m_715</ID> |
||
9959 | <String>Mister PiX version.dll</String> |
||
9960 | <Description>Mister PiX picture finding software</Description> |
||
9961 | <Type>D R</Type> |
||
9962 | <Comment></Comment> |
||
9963 | <Link1>http://www.mister-pix.com/</Link1> |
||
9964 | <Link2></Link2> |
||
9965 | </user-agent> |
||
9966 | <user-agent> |
||
9967 | <ID>id_g_m_110206_3</ID> |
||
9968 | <String>Misterbot-Nutch/0.7.1 (Misterbot-Nutch; http://www.misterbot.fr; admin@misterbot.fr)</String> |
||
9969 | <Description>Misterbot search France robot</Description> |
||
9970 | <Type>R</Type> |
||
9971 | <Comment></Comment> |
||
9972 | <Link1>http://www.misterbot.fr/</Link1> |
||
9973 | <Link2></Link2> |
||
9974 | </user-agent> |
||
9975 | <user-agent> |
||
9976 | <ID>id_g_m_716</ID> |
||
9977 | <String>Miva (AlgoFeedback@miva.com)</String> |
||
9978 | <Description>Miva / ex Findwhat.com search robot (66.150.55.2xx)</Description> |
||
9979 | <Type>R</Type> |
||
9980 | <Comment></Comment> |
||
9981 | <Link1>http://www.miva.com/</Link1> |
||
9982 | <Link2></Link2> |
||
9983 | </user-agent> |
||
9984 | <user-agent> |
||
9985 | <ID>id_g_m_141105_2</ID> |
||
9986 | <String>Mizzu Labs 2.2</String> |
||
9987 | <Description>Some spam bot from Jasmine Internet - Bangkok (203.147.0.xx)</Description> |
||
9988 | <Type>S</Type> |
||
9989 | <Comment>s. link </Comment> |
||
9990 | <Link1>http://www.projecthoneypot.org/ip_inspector.php?iph=7bc2eae614063a45b0e1d0786dbe6a2e</Link1> |
||
9991 | <Link2></Link2> |
||
9992 | </user-agent> |
||
9993 | <user-agent> |
||
9994 | <ID>id_g_m_080706_3</ID> |
||
9995 | <String>MJ12bot/vx.x.x (http://majestic12.co.uk/bot.php?+)</String> |
||
9996 | <Description>Majestic-12 DSearch MJ12bot (Experimental distributed crawler)</Description> |
||
9997 | <Type>R</Type> |
||
9998 | <Comment></Comment> |
||
9999 | <Link1>http://www.majestic12.co.uk/projects/dsearch/</Link1> |
||
10000 | <Link2></Link2> |
||
10001 | </user-agent> |
||
10002 | <user-agent> |
||
10003 | <ID>id_g_m_717</ID> |
||
10004 | <String>MJ12bot/vx.x.x (http://www.majestic12.co.uk/projects/dsearch/mj12bot.php)</String> |
||
10005 | <Description>Majestic-12 DSearch MJ12bot (Experimental distributed crawler)</Description> |
||
10006 | <Type>R</Type> |
||
10007 | <Comment></Comment> |
||
10008 | <Link1>http://www.majestic12.co.uk/projects/dsearch/mj12bot.php</Link1> |
||
10009 | <Link2></Link2> |
||
10010 | </user-agent> |
||
10011 | <user-agent> |
||
10012 | <ID>id_g_m_200108_1</ID> |
||
10013 | <String>MJBot (SEO assessment)</String> |
||
10014 | <Description>MJB SEO Club MJBot</Description> |
||
10015 | <Type>R</Type> |
||
10016 | <Comment>217.8.248.19x</Comment> |
||
10017 | <Link1>http://www.mjbdata.com/information/</Link1> |
||
10018 | <Link2></Link2> |
||
10019 | </user-agent> |
||
10020 | <user-agent> |
||
10021 | <ID>id_g_m_030308_2</ID> |
||
10022 | <String>MLBot (www.metadatalabs.com)</String> |
||
10023 | <Description>MLBot - metadata labs web crawler for building a media index (beta)</Description> |
||
10024 | <Type>R</Type> |
||
10025 | <Comment></Comment> |
||
10026 | <Link1>http://www.metadatalabs.com/</Link1> |
||
10027 | <Link2></Link2> |
||
10028 | </user-agent> |
||
10029 | <user-agent> |
||
10030 | <ID>id_g_m_718</ID> |
||
10031 | <String>MnogoSearch/3.2.xx</String> |
||
10032 | <Description>mnoGoSearch (ex UdmSearch) software robot</Description> |
||
10033 | <Type>R</Type> |
||
10034 | <Comment></Comment> |
||
10035 | <Link1>http://mnogosearch.org/</Link1> |
||
10036 | <Link2></Link2> |
||
10037 | </user-agent> |
||
10038 | <user-agent> |
||
10039 | <ID>id_g_m_260306_3</ID> |
||
10040 | <String>Mo College 1.9</String> |
||
10041 | <Description>Unknown bad bot - maybe guestbook spamming or email harvesting</Description> |
||
10042 | <Type>S</Type> |
||
10043 | <Comment>see link:</Comment> |
||
10044 | <Link1>http://www.kloth.net/internet/badbots.php</Link1> |
||
10045 | <Link2></Link2> |
||
10046 | </user-agent> |
||
10047 | <user-agent> |
||
10048 | <ID>id_g_m_719</ID> |
||
10049 | <String>moget/x.x (moget@goo.ne.jp)</String> |
||
10050 | <Description>Goo Japan / Inktomi robot (210.173.179.xx)</Description> |
||
10051 | <Type>R</Type> |
||
10052 | <Comment>s. also ichiro</Comment> |
||
10053 | <Link1>http://www.goo.ne.jp</Link1> |
||
10054 | <Link2></Link2> |
||
10055 | </user-agent> |
||
10056 | <user-agent> |
||
10057 | <ID>id_g_m_720</ID> |
||
10058 | <String>mogimogi/1.0</String> |
||
10059 | <Description>Goo Japan / Inktomi robot (210.173.179.xx)</Description> |
||
10060 | <Type>R</Type> |
||
10061 | <Comment>s. also ichiro</Comment> |
||
10062 | <Link1>http://www.goo.ne.jp</Link1> |
||
10063 | <Link2></Link2> |
||
10064 | </user-agent> |
||
10065 | <user-agent> |
||
10066 | <ID>id_g_m_721</ID> |
||
10067 | <String>moiNAG 0.02</String> |
||
10068 | <Description>moiNag - net.art generator</Description> |
||
10069 | <Type>R D</Type> |
||
10070 | <Comment></Comment> |
||
10071 | <Link1>http://soundwarez.org/generator/moiNAG/</Link1> |
||
10072 | <Link2></Link2> |
||
10073 | </user-agent> |
||
10074 | <user-agent> |
||
10075 | <ID>id_g_m_722</ID> |
||
10076 | <String>MojeekBot/0.x (archi; http://www.mojeek.com/bot.html)</String> |
||
10077 | <Description>Mojeek Search Preview robot (217.155.205.xx)</Description> |
||
10078 | <Type>R</Type> |
||
10079 | <Comment>s.also Mozilla/5.0 (compatible; MojeekBot/2.0 ...</Comment> |
||
10080 | <Link1>http://www.mojeek.com</Link1> |
||
10081 | <Link2></Link2> |
||
10082 | </user-agent> |
||
10083 | <user-agent> |
||
10084 | <ID>id_g_m_150407_1</ID> |
||
10085 | <String>monkeyagent</String> |
||
10086 | <Description>Greasemonkey Firefox extension</Description> |
||
10087 | <Type>D</Type> |
||
10088 | <Comment></Comment> |
||
10089 | <Link1>http://www.greasespot.net/</Link1> |
||
10090 | <Link2>http://diveintogreasemonkey.org/install/what-is-greasemonkey.html</Link2> |
||
10091 | </user-agent> |
||
10092 | <user-agent> |
||
10093 | <ID>id_g_m_090106_2</ID> |
||
10094 | <String>MoonBrowser (version 0.41 Beta4)</String> |
||
10095 | <Description>Moonbrowser - IE based browser (Japan)</Description> |
||
10096 | <Type>B</Type> |
||
10097 | <Comment></Comment> |
||
10098 | <Link1>http://www.geocities.co.jp/SiliconValley-Cupertino/8986/</Link1> |
||
10099 | <Link2></Link2> |
||
10100 | </user-agent> |
||
10101 | <user-agent> |
||
10102 | <ID>id_g_m_010307_2</ID> |
||
10103 | <String>Moreoverbot/x.00 (+http://www.moreover.com)</String> |
||
10104 | <Description>Moreover / FeedDirect RSS feed robot</Description> |
||
10105 | <Type>C</Type> |
||
10106 | <Comment>72.13.32.x</Comment> |
||
10107 | <Link1>http://w.moreover.com/</Link1> |
||
10108 | <Link2>http://www.feeddirect.com/</Link2> |
||
10109 | </user-agent> |
||
10110 | <user-agent> |
||
10111 | <ID>id_g_m_723</ID> |
||
10112 | <String>Morris - Mixcat Crawler ( http://mixcat.com)</String> |
||
10113 | <Description>MixCat robot s. also Felix</Description> |
||
10114 | <Type>R</Type> |
||
10115 | <Comment></Comment> |
||
10116 | <Link1>http://mixcat.com</Link1> |
||
10117 | <Link2></Link2> |
||
10118 | </user-agent> |
||
10119 | <user-agent> |
||
10120 | <ID>id_g_m_100206_2</ID> |
||
10121 | <String>Motoricerca-Robots.txt-Checker/1.0 (http://tool.motoricerca.info/robots-checker.phtml)</String> |
||
10122 | <Description>Robots.txt online checker</Description> |
||
10123 | <Type>C</Type> |
||
10124 | <Comment></Comment> |
||
10125 | <Link1>http://tool.motoricerca.info/robots-checker.phtml</Link1> |
||
10126 | <Link2></Link2> |
||
10127 | </user-agent> |
||
10128 | <user-agent> |
||
10129 | <ID>id_g_m_240108_1</ID> |
||
10130 | <String>Motorola-V3m Obigo</String> |
||
10131 | <Description>Obigo WAP browser for mobiles on Motorola V3</Description> |
||
10132 | <Type>B</Type> |
||
10133 | <Comment></Comment> |
||
10134 | <Link1>http://www.obigo.com/</Link1> |
||
10135 | <Link2>http://en.wikipedia.org/wiki/Obigo_Browser</Link2> |
||
10136 | </user-agent> |
||
10137 | <user-agent> |
||
10138 | <ID>id_g_m_724</ID> |
||
10139 | <String>Mouse-House/7.4 (spider_monkey spider info at www.mobrien.com/sm.shtml)</String> |
||
10140 | <Description>MPRM Group Ltd. Spider Monkey robot</Description> |
||
10141 | <Type>R</Type> |
||
10142 | <Comment></Comment> |
||
10143 | <Link1>http://www.spidermonkey.ca/sm.shtml</Link1> |
||
10144 | <Link2></Link2> |
||
10145 | </user-agent> |
||
10146 | <user-agent> |
||
10147 | <ID>id_g_m_725</ID> |
||
10148 | <String>MovableType/x.x</String> |
||
10149 | <Description>Movable Type web-based personal publishing system</Description> |
||
10150 | <Type>B</Type> |
||
10151 | <Comment></Comment> |
||
10152 | <Link1>http://www.movabletype.org</Link1> |
||
10153 | <Link2></Link2> |
||
10154 | </user-agent> |
||
10155 | <user-agent> |
||
10156 | <ID>id_g_m_726</ID> |
||
10157 | <String>mozDex/0.xx-dev (mozDex; http://www.mozdex.com/en/bot.html; spider@mozdex.com)</String> |
||
10158 | <Description>Mozdex Open search engine spider (65.98.100.2xx)</Description> |
||
10159 | <Type>R</Type> |
||
10160 | <Comment></Comment> |
||
10161 | <Link1>http://www.mozdex.com/</Link1> |
||
10162 | <Link2></Link2> |
||
10163 | </user-agent> |
||
10164 | <user-agent> |
||
10165 | <ID>id_g_m_727</ID> |
||
10166 | <String>Mozi!</String> |
||
10167 | <Description>Bell Nexxia / Sympatico Canada user robot & spoofed referer from diff. IPs</Description> |
||
10168 | <Type></Type> |
||
10169 | <Comment></Comment> |
||
10170 | <Link1></Link1> |
||
10171 | <Link2></Link2> |
||
10172 | </user-agent> |
||
10173 | <user-agent> |
||
10174 | <ID>id_moz_728</ID> |
||
10175 | <String>Mozilla</String> |
||
10176 | <Description>Unknown robots from diff. IPs</Description> |
||
10177 | <Type></Type> |
||
10178 | <Comment></Comment> |
||
10179 | <Link1></Link1> |
||
10180 | <Link2></Link2> |
||
10181 | </user-agent> |
||
10182 | <user-agent> |
||
10183 | <ID>id_moz_100109_3</ID> |
||
10184 | <String>Mozilla (libwhisker/2.4)</String> |
||
10185 | <Description>libwhisker - HTTP client and utility - Perl library</Description> |
||
10186 | <Type></Type> |
||
10187 | <Comment></Comment> |
||
10188 | <Link1>http://www.wiretrip.net/rfp/lw.asp</Link1> |
||
10189 | <Link2></Link2> |
||
10190 | </user-agent> |
||
10191 | <user-agent> |
||
10192 | <ID>id_moz_729</ID> |
||
10193 | <String>Mozilla (Mozilla@somewhere.com)</String> |
||
10194 | <Description>http://www.somewhere.com robot</Description> |
||
10195 | <Type>R</Type> |
||
10196 | <Comment></Comment> |
||
10197 | <Link1>http://www.somewhere.com</Link1> |
||
10198 | <Link2></Link2> |
||
10199 | </user-agent> |
||
10200 | <user-agent> |
||
10201 | <ID>id_moz_041007_1</ID> |
||
10202 | <String>Mozilla 4.0(compatible; BotSeer/1.0; +http://botseer.ist.psu.edu)</String> |
||
10203 | <Description>BotSeer search engine for robots.txt</Description> |
||
10204 | <Type>R</Type> |
||
10205 | <Comment>130.203.154.2xx</Comment> |
||
10206 | <Link1>http://botseer.ist.psu.edu/</Link1> |
||
10207 | <Link2>http://botseer.ist.psu.edu/about.html</Link2> |
||
10208 | </user-agent> |
||
10209 | <user-agent> |
||
10210 | <ID>id_moz_731</ID> |
||
10211 | <String>Mozilla/1.1 (compatible; MSPIE 2.0; Windows CE)</String> |
||
10212 | <Description>PDA Pocket IE 2.x Windows CE</Description> |
||
10213 | <Type>B</Type> |
||
10214 | <Comment></Comment> |
||
10215 | <Link1></Link1> |
||
10216 | <Link2></Link2> |
||
10217 | </user-agent> |
||
10218 | <user-agent> |
||
10219 | <ID>id_moz_732</ID> |
||
10220 | <String>Mozilla/1.10 [en] (Compatible; RISC OS 3.70; Oregano 1.10)</String> |
||
10221 | <Description>Oregano browser for RISC OS</Description> |
||
10222 | <Type>B</Type> |
||
10223 | <Comment></Comment> |
||
10224 | <Link1>http://www.crashnet.org.uk</Link1> |
||
10225 | <Link2></Link2> |
||
10226 | </user-agent> |
||
10227 | <user-agent> |
||
10228 | <ID>id_moz_730</ID> |
||
10229 | <String>Mozilla/1.22 (compatible; MSIE 2.0d; Windows NT)</String> |
||
10230 | <Description>IE 2.x WinNT</Description> |
||
10231 | <Type>B</Type> |
||
10232 | <Comment></Comment> |
||
10233 | <Link1></Link1> |
||
10234 | <Link2></Link2> |
||
10235 | </user-agent> |
||
10236 | <user-agent> |
||
10237 | <ID>id_moz_733</ID> |
||
10238 | <String>Mozilla/1.22 (compatible; MSIE 5.01; PalmOS 3.0) EudoraWeb 2</String> |
||
10239 | <Description>EudoraWeb 2.0 browser (Eudora Internet Suite) for PalmOS</Description> |
||
10240 | <Type>B</Type> |
||
10241 | <Comment></Comment> |
||
10242 | <Link1>http://www.eudora.com/products/unsupported/internetsuite/</Link1> |
||
10243 | <Link2></Link2> |
||
10244 | </user-agent> |
||
10245 | <user-agent> |
||
10246 | <ID>id_moz_1552</ID> |
||
10247 | <String>Mozilla/2.0</String> |
||
10248 | <Description>Dummy user agent - i.e. used by Namo Web Editor</Description> |
||
10249 | <Type>B</Type> |
||
10250 | <Comment></Comment> |
||
10251 | <Link1>http://www.namo.com/</Link1> |
||
10252 | <Link2></Link2> |
||
10253 | </user-agent> |
||
10254 | <user-agent> |
||
10255 | <ID>id_moz_734</ID> |
||
10256 | <String>Mozilla/2.0 (compatible; AOL 3.0; Mac_PowerPC)</String> |
||
10257 | <Description>AOL Mac</Description> |
||
10258 | <Type>B</Type> |
||
10259 | <Comment></Comment> |
||
10260 | <Link1></Link1> |
||
10261 | <Link2></Link2> |
||
10262 | </user-agent> |
||
10263 | <user-agent> |
||
10264 | <ID>id_moz_735</ID> |
||
10265 | <String>Mozilla/2.0 (Compatible; AOL-IWENG 3.0; Win16)</String> |
||
10266 | <Description>AOL Win 3.x</Description> |
||
10267 | <Type>B</Type> |
||
10268 | <Comment></Comment> |
||
10269 | <Link1></Link1> |
||
10270 | <Link2></Link2> |
||
10271 | </user-agent> |
||
10272 | <user-agent> |
||
10273 | <ID>id_moz_736</ID> |
||
10274 | <String>Mozilla/2.0 (compatible; Ask Jeeves)</String> |
||
10275 | <Description>Ask Jeeves /Teoma robot</Description> |
||
10276 | <Type>R</Type> |
||
10277 | <Comment> 65.214.45.[x]xx</Comment> |
||
10278 | <Link1>http://sp.ask.com</Link1> |
||
10279 | <Link2></Link2> |
||
10280 | </user-agent> |
||
10281 | <user-agent> |
||
10282 | <ID>id_moz_040707_2</ID> |
||
10283 | <String>Mozilla/2.0 (compatible; Ask Jeeves/Teoma)</String> |
||
10284 | <Description>Ask Jeeves /Teoma robot</Description> |
||
10285 | <Type>R</Type> |
||
10286 | <Comment>65.214.45.[x]xx</Comment> |
||
10287 | <Link1>http://sp.ask.com</Link1> |
||
10288 | <Link2></Link2> |
||
10289 | </user-agent> |
||
10290 | <user-agent> |
||
10291 | <ID>id_moz_160506_3</ID> |
||
10292 | <String>Mozilla/2.0 (compatible; Ask Jeeves/Teoma; http://about.ask.com/en/docs/about/webmasters.shtml) </String> |
||
10293 | <Description>Ask Jeeves /Teoma robot</Description> |
||
10294 | <Type>R</Type> |
||
10295 | <Comment> 65.214.45.[x]xx</Comment> |
||
10296 | <Link1>http://sp.ask.com</Link1> |
||
10297 | <Link2></Link2> |
||
10298 | </user-agent> |
||
10299 | <user-agent> |
||
10300 | <ID>id_moz_737</ID> |
||
10301 | <String>Mozilla/2.0 (compatible; Ask Jeeves/Teoma; http://sp.ask.com/docs/about/tech_crawling.html)</String> |
||
10302 | <Description>Ask Jeeves /Teoma robot</Description> |
||
10303 | <Type>R</Type> |
||
10304 | <Comment> 65.214.45.[x]xx</Comment> |
||
10305 | <Link1>http://sp.ask.com</Link1> |
||
10306 | <Link2></Link2> |
||
10307 | </user-agent> |
||
10308 | <user-agent> |
||
10309 | <ID>id_moz_738</ID> |
||
10310 | <String>Mozilla/2.0 (compatible; EZResult -- Internet Search Engine)</String> |
||
10311 | <Description>Direct Hit Robot</Description> |
||
10312 | <Type>R</Type> |
||
10313 | <Comment></Comment> |
||
10314 | <Link1>http://www.directhit.com</Link1> |
||
10315 | <Link2></Link2> |
||
10316 | </user-agent> |
||
10317 | <user-agent> |
||
10318 | <ID>id_moz_739</ID> |
||
10319 | <String>Mozilla/2.0 (compatible; MS FrontPage x.0)</String> |
||
10320 | <Description>MS Frontpage x.x web editor</Description> |
||
10321 | <Type>B</Type> |
||
10322 | <Comment></Comment> |
||
10323 | <Link1></Link1> |
||
10324 | <Link2></Link2> |
||
10325 | </user-agent> |
||
10326 | <user-agent> |
||
10327 | <ID>id_moz_740</ID> |
||
10328 | <String>Mozilla/2.0 (compatible; MSIE 2.1; Mac_PowerPC)</String> |
||
10329 | <Description>IE 2.x Mac Power PC</Description> |
||
10330 | <Type>B</Type> |
||
10331 | <Comment></Comment> |
||
10332 | <Link1></Link1> |
||
10333 | <Link2></Link2> |
||
10334 | </user-agent> |
||
10335 | <user-agent> |
||
10336 | <ID>id_moz_743</ID> |
||
10337 | <String>Mozilla/2.0 (compatible; MSIE 3.02; Update a; AK; Windows NT)</String> |
||
10338 | <Description>IE 3.x WinNT</Description> |
||
10339 | <Type>B</Type> |
||
10340 | <Comment></Comment> |
||
10341 | <Link1></Link1> |
||
10342 | <Link2></Link2> |
||
10343 | </user-agent> |
||
10344 | <user-agent> |
||
10345 | <ID>id_moz_744</ID> |
||
10346 | <String>Mozilla/2.0 (compatible; MSIE 3.02; Update a; AOL 3.0; Windows 95)</String> |
||
10347 | <Description>IE 3.x AOL Win95</Description> |
||
10348 | <Type>B</Type> |
||
10349 | <Comment></Comment> |
||
10350 | <Link1></Link1> |
||
10351 | <Link2></Link2> |
||
10352 | </user-agent> |
||
10353 | <user-agent> |
||
10354 | <ID>id_moz_741</ID> |
||
10355 | <String>Mozilla/2.0 (compatible; MSIE 3.0; AK; Windows 95)</String> |
||
10356 | <Description>IE 3.x Win95</Description> |
||
10357 | <Type>B</Type> |
||
10358 | <Comment></Comment> |
||
10359 | <Link1></Link1> |
||
10360 | <Link2></Link2> |
||
10361 | </user-agent> |
||
10362 | <user-agent> |
||
10363 | <ID>id_moz_742</ID> |
||
10364 | <String>Mozilla/2.0 (compatible; MSIE 3.0; Windows 3.1)</String> |
||
10365 | <Description>IE 3.x Win 3.1</Description> |
||
10366 | <Type>B</Type> |
||
10367 | <Comment></Comment> |
||
10368 | <Link1></Link1> |
||
10369 | <Link2></Link2> |
||
10370 | </user-agent> |
||
10371 | <user-agent> |
||
10372 | <ID>id_moz_745</ID> |
||
10373 | <String>Mozilla/2.0 (compatible; MSIE 3.0B; Win32)</String> |
||
10374 | <Description>IE 3.x WinXP</Description> |
||
10375 | <Type>B</Type> |
||
10376 | <Comment></Comment> |
||
10377 | <Link1></Link1> |
||
10378 | <Link2></Link2> |
||
10379 | </user-agent> |
||
10380 | <user-agent> |
||
10381 | <ID>id_moz_746</ID> |
||
10382 | <String>Mozilla/2.0 (compatible; NEWT ActiveX; Win32)</String> |
||
10383 | <Description>Borland Delphi .OCX component used by WebCollector email harverster</Description> |
||
10384 | <Type>S</Type> |
||
10385 | <Comment></Comment> |
||
10386 | <Link1></Link1> |
||
10387 | <Link2></Link2> |
||
10388 | </user-agent> |
||
10389 | <user-agent> |
||
10390 | <ID>id_moz_747</ID> |
||
10391 | <String>Mozilla/2.0 (compatible; T-H-U-N-D-E-R-S-T-O-N-E)</String> |
||
10392 | <Description>Thunderstone's Webinator Web indexing program</Description> |
||
10393 | <Type>R</Type> |
||
10394 | <Comment></Comment> |
||
10395 | <Link1>http://www.thunderstone.com/texis/site/pages/Products.html</Link1> |
||
10396 | <Link2></Link2> |
||
10397 | </user-agent> |
||
10398 | <user-agent> |
||
10399 | <ID>id_moz_748</ID> |
||
10400 | <String>Mozilla/2.0 compatible; Check&Get 1.1x (Windows 98)</String> |
||
10401 | <Description>Check&Get bookmark and link checking tool</Description> |
||
10402 | <Type>C</Type> |
||
10403 | <Comment></Comment> |
||
10404 | <Link1>http://www.activeurls.com</Link1> |
||
10405 | <Link2></Link2> |
||
10406 | </user-agent> |
||
10407 | <user-agent> |
||
10408 | <ID>id_moz_749</ID> |
||
10409 | <String>Mozilla/2.01 (Win16; I)</String> |
||
10410 | <Description>Netscape 2.x Win3.x International</Description> |
||
10411 | <Type>B</Type> |
||
10412 | <Comment></Comment> |
||
10413 | <Link1></Link1> |
||
10414 | <Link2></Link2> |
||
10415 | </user-agent> |
||
10416 | <user-agent> |
||
10417 | <ID>id_moz_750</ID> |
||
10418 | <String>Mozilla/2.02Gold (Win95; I)</String> |
||
10419 | <Description>Netscape 2.x Gold Win95</Description> |
||
10420 | <Type>B</Type> |
||
10421 | <Comment></Comment> |
||
10422 | <Link1></Link1> |
||
10423 | <Link2></Link2> |
||
10424 | </user-agent> |
||
10425 | <user-agent> |
||
10426 | <ID>id_moz_771</ID> |
||
10427 | <String>Mozilla/3.0 (compatible)</String> |
||
10428 | <Description>Faked user agent for diff. purposes i.e.: - some download manager - E-mail harvesting</Description> |
||
10429 | <Type>S D</Type> |
||
10430 | <Comment></Comment> |
||
10431 | <Link1></Link1> |
||
10432 | <Link2></Link2> |
||
10433 | </user-agent> |
||
10434 | <user-agent> |
||
10435 | <ID>id_moz_751</ID> |
||
10436 | <String>Mozilla/3.0 (compatible; AvantGo 3.2)</String> |
||
10437 | <Description>AvantGo PDA browser</Description> |
||
10438 | <Type>B</Type> |
||
10439 | <Comment></Comment> |
||
10440 | <Link1>http://avantgo.com/products/solutions/sfa.html</Link1> |
||
10441 | <Link2></Link2> |
||
10442 | </user-agent> |
||
10443 | <user-agent> |
||
10444 | <ID>id_moz_752</ID> |
||
10445 | <String>Mozilla/3.0 (compatible; Fluffy the spider; http://www.searchhippo.com/; info@searchhippo.com)</String> |
||
10446 | <Description>Searchhippo robot</Description> |
||
10447 | <Type>R</Type> |
||
10448 | <Comment></Comment> |
||
10449 | <Link1>http://www.searchhippo.com</Link1> |
||
10450 | <Link2></Link2> |
||
10451 | </user-agent> |
||
10452 | <user-agent> |
||
10453 | <ID>id_moz_753</ID> |
||
10454 | <String>Mozilla/3.0 (compatible; HP Web PrintSmart 04b0 1.0.1.34)</String> |
||
10455 | <Description>HP Web PrintSmart (discontinued) - web page printing software</Description> |
||
10456 | <Type>B D</Type> |
||
10457 | <Comment></Comment> |
||
10458 | <Link1></Link1> |
||
10459 | <Link2></Link2> |
||
10460 | </user-agent> |
||
10461 | <user-agent> |
||
10462 | <ID>id_moz_754</ID> |
||
10463 | <String>Mozilla/3.0 (compatible; Indy Library)</String> |
||
10464 | <Description>Internet Direct Library for Borland (often used as e-mail address collector and mass mailing tool)</Description> |
||
10465 | <Type>S</Type> |
||
10466 | <Comment></Comment> |
||
10467 | <Link1>http://forge.novell.com/modules/xfmod/project/?indy-net</Link1> |
||
10468 | <Link2>http://www.indyproject.org/</Link2> |
||
10469 | </user-agent> |
||
10470 | <user-agent> |
||
10471 | <ID>id_moz_755</ID> |
||
10472 | <String>Mozilla/3.0 (compatible; Linkman)</String> |
||
10473 | <Description>Outertechs Linkman bookmark tool</Description> |
||
10474 | <Type>C</Type> |
||
10475 | <Comment></Comment> |
||
10476 | <Link1>http://www.outertech.com</Link1> |
||
10477 | <Link2></Link2> |
||
10478 | </user-agent> |
||
10479 | <user-agent> |
||
10480 | <ID>id_moz_757</ID> |
||
10481 | <String>Mozilla/3.0 (compatible; MuscatFerret/1.5.4; claude@euroferret.com)</String> |
||
10482 | <Description>Euroferret robot</Description> |
||
10483 | <Type>R</Type> |
||
10484 | <Comment></Comment> |
||
10485 | <Link1>http://www.euroferret.com</Link1> |
||
10486 | <Link2></Link2> |
||
10487 | </user-agent> |
||
10488 | <user-agent> |
||
10489 | <ID>id_moz_756</ID> |
||
10490 | <String>Mozilla/3.0 (compatible; MuscatFerret/1.5; olly@muscat.co.uk)</String> |
||
10491 | <Description>Euroferret robot</Description> |
||
10492 | <Type>R</Type> |
||
10493 | <Comment></Comment> |
||
10494 | <Link1>http://www.euroferret.com</Link1> |
||
10495 | <Link2></Link2> |
||
10496 | </user-agent> |
||
10497 | <user-agent> |
||
10498 | <ID>id_moz_758</ID> |
||
10499 | <String>Mozilla/3.0 (compatible; MuscatFerret/1.6.x; claude@euroferret.com)</String> |
||
10500 | <Description>Euroferret robot</Description> |
||
10501 | <Type>R</Type> |
||
10502 | <Comment></Comment> |
||
10503 | <Link1>http://www.euroferret.com</Link1> |
||
10504 | <Link2></Link2> |
||
10505 | </user-agent> |
||
10506 | <user-agent> |
||
10507 | <ID>id_moz_759</ID> |
||
10508 | <String>Mozilla/3.0 (compatible; netart generator/1.0; libwww-perl/5.64)</String> |
||
10509 | <Description>Netart Generator - script generated random websites</Description> |
||
10510 | <Type>R D</Type> |
||
10511 | <Comment></Comment> |
||
10512 | <Link1>http://www.obn.org/generator/</Link1> |
||
10513 | <Link2></Link2> |
||
10514 | </user-agent> |
||
10515 | <user-agent> |
||
10516 | <ID>id_moz_760</ID> |
||
10517 | <String>Mozilla/3.0 (compatible; NetPositive/2.2)</String> |
||
10518 | <Description>NetPositive BEOS browser</Description> |
||
10519 | <Type>B</Type> |
||
10520 | <Comment></Comment> |
||
10521 | <Link1>http://www.tunetrackersystems.com/bedocs/documentation/User's%20Guide/03_network/Network07_NetPositive.html</Link1> |
||
10522 | <Link2></Link2> |
||
10523 | </user-agent> |
||
10524 | <user-agent> |
||
10525 | <ID>id_moz_761</ID> |
||
10526 | <String>Mozilla/3.0 (compatible; Opera/3.0; Windows 3.1) v3.1</String> |
||
10527 | <Description>Opera 3.x Win3.x</Description> |
||
10528 | <Type>B</Type> |
||
10529 | <Comment></Comment> |
||
10530 | <Link1></Link1> |
||
10531 | <Link2></Link2> |
||
10532 | </user-agent> |
||
10533 | <user-agent> |
||
10534 | <ID>id_moz_762</ID> |
||
10535 | <String>Mozilla/3.0 (compatible; Opera/3.0; Windows 95/NT4) 3.2</String> |
||
10536 | <Description>Opera 3.x Win95/NT</Description> |
||
10537 | <Type>B</Type> |
||
10538 | <Comment></Comment> |
||
10539 | <Link1></Link1> |
||
10540 | <Link2></Link2> |
||
10541 | </user-agent> |
||
10542 | <user-agent> |
||
10543 | <ID>id_moz_763</ID> |
||
10544 | <String>Mozilla/3.0 (compatible; PerMan Surfer 3.0; Win95)</String> |
||
10545 | <Description>Perman Surfer bookmark tool</Description> |
||
10546 | <Type>C</Type> |
||
10547 | <Comment></Comment> |
||
10548 | <Link1>http://www.bug.co.jp/nami-nori/</Link1> |
||
10549 | <Link2></Link2> |
||
10550 | </user-agent> |
||
10551 | <user-agent> |
||
10552 | <ID>id_moz_764</ID> |
||
10553 | <String>Mozilla/3.0 (compatible; REL Software Web Link Validator 2.x)</String> |
||
10554 | <Description>Web Link Validator link validation software</Description> |
||
10555 | <Type>C</Type> |
||
10556 | <Comment></Comment> |
||
10557 | <Link1>http://www.relsoftware.com</Link1> |
||
10558 | <Link2></Link2> |
||
10559 | </user-agent> |
||
10560 | <user-agent> |
||
10561 | <ID>id_moz_765</ID> |
||
10562 | <String>Mozilla/3.0 (compatible; scan4mail (advanced version) http://www.peterspages.net/?scan4mail)</String> |
||
10563 | <Description>Scan4Mail online mail extraction service</Description> |
||
10564 | <Type>S</Type> |
||
10565 | <Comment></Comment> |
||
10566 | <Link1>http://www.peterspages.net</Link1> |
||
10567 | <Link2></Link2> |
||
10568 | </user-agent> |
||
10569 | <user-agent> |
||
10570 | <ID>id_moz_220606_2</ID> |
||
10571 | <String>Mozilla/3.0 (compatible; ScollSpider; http://www.webwobot.com)</String> |
||
10572 | <Description>WebWobot UK search engine robot (82.43.129.2xx)</Description> |
||
10573 | <Type>R</Type> |
||
10574 | <Comment>s. also ScollSpider</Comment> |
||
10575 | <Link1>http://www.webwobot.com/</Link1> |
||
10576 | <Link2></Link2> |
||
10577 | </user-agent> |
||
10578 | <user-agent> |
||
10579 | <ID>id_moz_766</ID> |
||
10580 | <String>Mozilla/3.0 (compatible; Web Link Validator 2.x)Web Link Validator http://www.relsoftware.com/ link validation software</String> |
||
10581 | <Description>Web Link Validator link validation software</Description> |
||
10582 | <Type>C</Type> |
||
10583 | <Comment></Comment> |
||
10584 | <Link1>http://www.relsoftware.com</Link1> |
||
10585 | <Link2></Link2> |
||
10586 | </user-agent> |
||
10587 | <user-agent> |
||
10588 | <ID>id_moz_767</ID> |
||
10589 | <String>Mozilla/3.0 (compatible; WebCapture x.x; Auto; Windows)</String> |
||
10590 | <Description>Xelios Web Capture (now Wysigot) website downloading tool (Discontinued)</Description> |
||
10591 | <Type>D</Type> |
||
10592 | <Comment></Comment> |
||
10593 | <Link1>http://www.xelios.com/</Link1> |
||
10594 | <Link2>http://www.wysigot.com/int/about.html</Link2> |
||
10595 | </user-agent> |
||
10596 | <user-agent> |
||
10597 | <ID>id_moz_768</ID> |
||
10598 | <String>Mozilla/3.0 (compatible; Webinator-DEV01.home.iprospect.com/2.56)</String> |
||
10599 | <Description>Iprospect search engine positioning using Thunderstone's Webinator</Description> |
||
10600 | <Type>R</Type> |
||
10601 | <Comment></Comment> |
||
10602 | <Link1>http://www.iprospect.com</Link1> |
||
10603 | <Link2>http://www.thunderstone.com/texis/site/pages/Products.html</Link2> |
||
10604 | </user-agent> |
||
10605 | <user-agent> |
||
10606 | <ID>id_moz_769</ID> |
||
10607 | <String>Mozilla/3.0 (compatible; Webinator-indexer.cyberalert.com/2.56)</String> |
||
10608 | <Description>CyberAlert's Media Monitor using Thunderstone's Webinator</Description> |
||
10609 | <Type>R</Type> |
||
10610 | <Comment></Comment> |
||
10611 | <Link1>http://www.cyberalert.com</Link1> |
||
10612 | <Link2>http://www.thunderstone.com/texis/site/pages/Products.html</Link2> |
||
10613 | </user-agent> |
||
10614 | <user-agent> |
||
10615 | <ID>id_moz_770</ID> |
||
10616 | <String>Mozilla/3.0 (Compatible;Viking/1.8)</String> |
||
10617 | <Description>Viking server user/client</Description> |
||
10618 | <Type>P</Type> |
||
10619 | <Comment></Comment> |
||
10620 | <Link1>http://www.robtex.com</Link1> |
||
10621 | <Link2></Link2> |
||
10622 | </user-agent> |
||
10623 | <user-agent> |
||
10624 | <ID>id_moz_772</ID> |
||
10625 | <String>Mozilla/3.0 (DreamPassport/3.0)</String> |
||
10626 | <Description>One of DC-Sakuras download manager user-agent names</Description> |
||
10627 | <Type>D</Type> |
||
10628 | <Comment></Comment> |
||
10629 | <Link1>http://www.dc-sakura.com</Link1> |
||
10630 | <Link2></Link2> |
||
10631 | </user-agent> |
||
10632 | <user-agent> |
||
10633 | <ID>id_moz_773</ID> |
||
10634 | <String>Mozilla/3.0 (INGRID/3.0 MT; webcrawler@NOSPAMexperimental.net; http://aanmelden.ilse.nl/?aanmeld_mode=webhints)</String> |
||
10635 | <Description>Ilse Netherlands robot (62.69.178.xx)</Description> |
||
10636 | <Type>R</Type> |
||
10637 | <Comment>s. also - INGRID/3.0 .. / IlseBot/1.0 ..</Comment> |
||
10638 | <Link1>http://www.ilse.nl/</Link1> |
||
10639 | <Link2></Link2> |
||
10640 | </user-agent> |
||
10641 | <user-agent> |
||
10642 | <ID>id_moz_774</ID> |
||
10643 | <String>Mozilla/3.0 (Liberate DTV 1.1)</String> |
||
10644 | <Description>Liberate DTV server suite / TV-emulator</Description> |
||
10645 | <Type>B P</Type> |
||
10646 | <Comment></Comment> |
||
10647 | <Link1>http://www.liberate.com</Link1> |
||
10648 | <Link2></Link2> |
||
10649 | </user-agent> |
||
10650 | <user-agent> |
||
10651 | <ID>id_moz_775</ID> |
||
10652 | <String>Mozilla/3.0 (Planetweb/2.100 JS SSL US; Dreamcast US)</String> |
||
10653 | <Description>Planetweb 2.1 Browser (discontinued) for Dreamcast</Description> |
||
10654 | <Type>B</Type> |
||
10655 | <Comment></Comment> |
||
10656 | <Link1>http://www.planetweb.com</Link1> |
||
10657 | <Link2></Link2> |
||
10658 | </user-agent> |
||
10659 | <user-agent> |
||
10660 | <ID>id_moz_776</ID> |
||
10661 | <String>Mozilla/3.0 (Slurp.so/Goo; slurp@inktomi.com; http://www.inktomi.com/slurp.html)</String> |
||
10662 | <Description>http://www.goo.ne.jp /Inktomi robot</Description> |
||
10663 | <Type>R</Type> |
||
10664 | <Comment></Comment> |
||
10665 | <Link1>http://www.goo.ne.jp</Link1> |
||
10666 | <Link2></Link2> |
||
10667 | </user-agent> |
||
10668 | <user-agent> |
||
10669 | <ID>id_moz_777</ID> |
||
10670 | <String>Mozilla/3.0 (Slurp/cat; slurp@inktomi.com; http://www.inktomi.com/slurp.html)</String> |
||
10671 | <Description>Inktomi (Hotbot-Lycos-NBCi) robot - 72.30.61.xx(x)</Description> |
||
10672 | <Type>R</Type> |
||
10673 | <Comment>s. also Slurpy Verifier ...</Comment> |
||
10674 | <Link1>http://www.inktomi.com/</Link1> |
||
10675 | <Link2></Link2> |
||
10676 | </user-agent> |
||
10677 | <user-agent> |
||
10678 | <ID>id_moz_778</ID> |
||
10679 | <String>Mozilla/3.0 (Slurp/si; slurp@inktomi.com; http://www.inktomi.com/slurp.html)</String> |
||
10680 | <Description>Inktomi (Hotbot-Lycos-NBCi) robot - 72.30.61.xx(x)</Description> |
||
10681 | <Type>R</Type> |
||
10682 | <Comment>s. also Slurpy Verifier ...</Comment> |
||
10683 | <Link1>http://www.inktomi.com/</Link1> |
||
10684 | <Link2></Link2> |
||
10685 | </user-agent> |
||
10686 | <user-agent> |
||
10687 | <ID>id_moz_779</ID> |
||
10688 | <String>Mozilla/3.0 (Vagabondo/1.1 MT; webcrawler@NOSPAMwise-guys.nl; http://webagent.wise-guys.nl/)</String> |
||
10689 | <Description>WiseGuys robot Netherland - 82.94.216.2</Description> |
||
10690 | <Type>R</Type> |
||
10691 | <Comment>s. also Vagabondo</Comment> |
||
10692 | <Link1>http://www.wise-guys.nl/Contact/index.php?botselected=webagents&lang=uk</Link1> |
||
10693 | <Link2></Link2> |
||
10694 | </user-agent> |
||
10695 | <user-agent> |
||
10696 | <ID>id_moz_780</ID> |
||
10697 | <String>Mozilla/3.0 (Vagabondo/1.x MT; webagent@wise-guys.nl; http://webagent.wise-guys.nl/)</String> |
||
10698 | <Description>WiseGuys robot Netherland - 82.94.216.2</Description> |
||
10699 | <Type>R</Type> |
||
10700 | <Comment>s. also Vagabondo</Comment> |
||
10701 | <Link1>http://www.wise-guys.nl/Contact/index.php?botselected=webagents&lang=uk</Link1> |
||
10702 | <Link2></Link2> |
||
10703 | </user-agent> |
||
10704 | <user-agent> |
||
10705 | <ID>id_moz_781</ID> |
||
10706 | <String>Mozilla/3.0 (Vagabondo/2.0 MT; webcrawler@NOSPAMexperimental.net; http://aanmelden.ilse.nl/?aanmeld_mode=webhints)</String> |
||
10707 | <Description>Ilse Netherlands robot</Description> |
||
10708 | <Type>R</Type> |
||
10709 | <Comment></Comment> |
||
10710 | <Link1>http://www.ilse.nl</Link1> |
||
10711 | <Link2></Link2> |
||
10712 | </user-agent> |
||
10713 | <user-agent> |
||
10714 | <ID>id_moz_782</ID> |
||
10715 | <String>Mozilla/3.0 (Vagabondo/2.0 MT; webcrawler@NOSPAMwise-guys.nl; http://webagent.wise-guys.nl/)</String> |
||
10716 | <Description>WiseGuys robot Netherland - 82.94.216.2</Description> |
||
10717 | <Type>R</Type> |
||
10718 | <Comment>s. also Vagabondo</Comment> |
||
10719 | <Link1>http://www.wise-guys.nl/Contact/index.php?botselected=webagents&lang=uk</Link1> |
||
10720 | <Link2></Link2> |
||
10721 | </user-agent> |
||
10722 | <user-agent> |
||
10723 | <ID>id_moz_783</ID> |
||
10724 | <String>Mozilla/3.0 (Win16; I)</String> |
||
10725 | <Description>Netscape 3.x Win3.x</Description> |
||
10726 | <Type>B</Type> |
||
10727 | <Comment></Comment> |
||
10728 | <Link1></Link1> |
||
10729 | <Link2></Link2> |
||
10730 | </user-agent> |
||
10731 | <user-agent> |
||
10732 | <ID>id_moz_784</ID> |
||
10733 | <String>Mozilla/3.0 (Win95; I)</String> |
||
10734 | <Description>Netscape 3.x Win95</Description> |
||
10735 | <Type>B</Type> |
||
10736 | <Comment></Comment> |
||
10737 | <Link1></Link1> |
||
10738 | <Link2></Link2> |
||
10739 | </user-agent> |
||
10740 | <user-agent> |
||
10741 | <ID>id_moz_785</ID> |
||
10742 | <String>Mozilla/3.0 (WinNT; I)</String> |
||
10743 | <Description>Netscape 3.x WinNT</Description> |
||
10744 | <Type>B</Type> |
||
10745 | <Comment></Comment> |
||
10746 | <Link1></Link1> |
||
10747 | <Link2></Link2> |
||
10748 | </user-agent> |
||
10749 | <user-agent> |
||
10750 | <ID>id_moz_786</ID> |
||
10751 | <String>Mozilla/3.0 (WorldGate Gazelle 3.5.1 build 11; FreeBSD2.2.8-STABLE)</String> |
||
10752 | <Description>Netscape 3.x FreeBSD</Description> |
||
10753 | <Type>B</Type> |
||
10754 | <Comment></Comment> |
||
10755 | <Link1></Link1> |
||
10756 | <Link2></Link2> |
||
10757 | </user-agent> |
||
10758 | <user-agent> |
||
10759 | <ID>id_moz_787</ID> |
||
10760 | <String>Mozilla/3.0 (X11; I; OSF1 V4.0 alpha)</String> |
||
10761 | <Description>Netscape 3.x OSF1 V4.0 alpha </Description> |
||
10762 | <Type>B</Type> |
||
10763 | <Comment></Comment> |
||
10764 | <Link1></Link1> |
||
10765 | <Link2></Link2> |
||
10766 | </user-agent> |
||
10767 | <user-agent> |
||
10768 | <ID>id_moz_788</ID> |
||
10769 | <String>Mozilla/3.0 NAVIO_AOLTV (11; 13; Philips; PH200; 1; R2.0C36_AOL.0110OPTIK; R2.0.0139d_OPTIK)</String> |
||
10770 | <Description>AOL Web TV</Description> |
||
10771 | <Type>B</Type> |
||
10772 | <Comment></Comment> |
||
10773 | <Link1></Link1> |
||
10774 | <Link2></Link2> |
||
10775 | </user-agent> |
||
10776 | <user-agent> |
||
10777 | <ID>id_moz_789</ID> |
||
10778 | <String>Mozilla/3.0 WebTV/1.2 (compatible; MSIE 2.0)</String> |
||
10779 | <Description>WebTV</Description> |
||
10780 | <Type>B</Type> |
||
10781 | <Comment></Comment> |
||
10782 | <Link1></Link1> |
||
10783 | <Link2></Link2> |
||
10784 | </user-agent> |
||
10785 | <user-agent> |
||
10786 | <ID>id_moz_790</ID> |
||
10787 | <String>Mozilla/3.01 (compatible; AmigaVoyager/2.95; AmigaOS/MC680x0)</String> |
||
10788 | <Description>Amiga Voyager Browser Amiga</Description> |
||
10789 | <Type>B</Type> |
||
10790 | <Comment></Comment> |
||
10791 | <Link1></Link1> |
||
10792 | <Link2></Link2> |
||
10793 | </user-agent> |
||
10794 | <user-agent> |
||
10795 | <ID>id_moz_791</ID> |
||
10796 | <String>Mozilla/3.01 (Compatible; Links2Go Similarity Engine)</String> |
||
10797 | <Description>Links2Go robot</Description> |
||
10798 | <Type>R</Type> |
||
10799 | <Comment></Comment> |
||
10800 | <Link1>http://www.links2go.com</Link1> |
||
10801 | <Link2></Link2> |
||
10802 | </user-agent> |
||
10803 | <user-agent> |
||
10804 | <ID>id_moz_792</ID> |
||
10805 | <String>Mozilla/3.01 (compatible; Netbox/3.5 R92; Linux 2.2)</String> |
||
10806 | <Description>Netgem Netbox cable modem TV Box Linux</Description> |
||
10807 | <Type>B</Type> |
||
10808 | <Comment></Comment> |
||
10809 | <Link1>http://www.netgem.com</Link1> |
||
10810 | <Link2></Link2> |
||
10811 | </user-agent> |
||
10812 | <user-agent> |
||
10813 | <ID>id_moz_793</ID> |
||
10814 | <String>Mozilla/3.01-C-MACOS8 (Macintosh; I; PPC)</String> |
||
10815 | <Description>Netscape 3.x Mac</Description> |
||
10816 | <Type>B</Type> |
||
10817 | <Comment></Comment> |
||
10818 | <Link1></Link1> |
||
10819 | <Link2></Link2> |
||
10820 | </user-agent> |
||
10821 | <user-agent> |
||
10822 | <ID>id_moz_794</ID> |
||
10823 | <String>Mozilla/3.01Gold (X11; I; Linux 2.0.32 i486)</String> |
||
10824 | <Description>Netscape 3.x Linux</Description> |
||
10825 | <Type>B</Type> |
||
10826 | <Comment></Comment> |
||
10827 | <Link1></Link1> |
||
10828 | <Link2></Link2> |
||
10829 | </user-agent> |
||
10830 | <user-agent> |
||
10831 | <ID>id_moz_795</ID> |
||
10832 | <String>Mozilla/3.01Gold (X11; I; SunOS 5.5.1 sun4m)</String> |
||
10833 | <Description>Netscape 3.x SunOS</Description> |
||
10834 | <Type>B</Type> |
||
10835 | <Comment></Comment> |
||
10836 | <Link1></Link1> |
||
10837 | <Link2></Link2> |
||
10838 | </user-agent> |
||
10839 | <user-agent> |
||
10840 | <ID>id_moz_796</ID> |
||
10841 | <String>Mozilla/3.01SGoldC-SGI (X11; I; IRIX 6.3 IP32)</String> |
||
10842 | <Description>Netscape 3.x Irix</Description> |
||
10843 | <Type>B</Type> |
||
10844 | <Comment></Comment> |
||
10845 | <Link1></Link1> |
||
10846 | <Link2></Link2> |
||
10847 | </user-agent> |
||
10848 | <user-agent> |
||
10849 | <ID>id_moz_797</ID> |
||
10850 | <String>Mozilla/3.04 (compatible; ANTFresco/2.13; RISC OS 4.02)</String> |
||
10851 | <Description>ANT Fresco Browser Risc OS</Description> |
||
10852 | <Type>B</Type> |
||
10853 | <Comment></Comment> |
||
10854 | <Link1>http://www.antlimited.com</Link1> |
||
10855 | <Link2></Link2> |
||
10856 | </user-agent> |
||
10857 | <user-agent> |
||
10858 | <ID>id_moz_798</ID> |
||
10859 | <String>Mozilla/3.04 (compatible; NCBrowser/2.35; ANTFresco/2.17; RISC OS-NC 5.13 Laz1UK1309)</String> |
||
10860 | <Description>NCBrowser ANT Fresco Browser Risc OS</Description> |
||
10861 | <Type>B</Type> |
||
10862 | <Comment></Comment> |
||
10863 | <Link1>http://www.antlimited.com</Link1> |
||
10864 | <Link2></Link2> |
||
10865 | </user-agent> |
||
10866 | <user-agent> |
||
10867 | <ID>id_moz_281106_1</ID> |
||
10868 | <String>Mozilla/3.04 (compatible;QNX Voyager 2.03B ;Photon)</String> |
||
10869 | <Description>QNX OS Voyager embedded browser</Description> |
||
10870 | <Type>B</Type> |
||
10871 | <Comment></Comment> |
||
10872 | <Link1>http://www.qnx.com/products/browsers/</Link1> |
||
10873 | <Link2></Link2> |
||
10874 | </user-agent> |
||
10875 | <user-agent> |
||
10876 | <ID>id_moz_799</ID> |
||
10877 | <String>Mozilla/3.x (I-Opener 1.1; Netpliance)</String> |
||
10878 | <Description>I-Opener (was www.netpliance.com/) web PC</Description> |
||
10879 | <Type>B</Type> |
||
10880 | <Comment></Comment> |
||
10881 | <Link1></Link1> |
||
10882 | <Link2></Link2> |
||
10883 | </user-agent> |
||
10884 | <user-agent> |
||
10885 | <ID>id_moz_100406_3</ID> |
||
10886 | <String>Mozilla/4.0</String> |
||
10887 | <Description>Yahoo Mindset: Intent-driven Search (66.228.182.1xx)</Description> |
||
10888 | <Type>R</Type> |
||
10889 | <Comment>s. also Yahoo! Mindset</Comment> |
||
10890 | <Link1>http://mindset.research.yahoo.com/</Link1> |
||
10891 | <Link2></Link2> |
||
10892 | </user-agent> |
||
10893 | <user-agent> |
||
10894 | <ID>id_moz_800</ID> |
||
10895 | <String>Mozilla/4.0 (agadine3.0) www.agada.de</String> |
||
10896 | <Description>Agada search (Germany) robot</Description> |
||
10897 | <Type>R</Type> |
||
10898 | <Comment>s. also agadine/1.x.x</Comment> |
||
10899 | <Link1>http://www.agada.de</Link1> |
||
10900 | <Link2></Link2> |
||
10901 | </user-agent> |
||
10902 | <user-agent> |
||
10903 | <ID>id_moz_290406_1</ID> |
||
10904 | <String>Mozilla/4.0 (Compatible); URLBase 6</String> |
||
10905 | <Description>URLBase 6 bookmark manager</Description> |
||
10906 | <Type>C</Type> |
||
10907 | <Comment>s. also URLBase/6.x</Comment> |
||
10908 | <Link1>http://www.terriadev.com/products/urlbase/</Link1> |
||
10909 | <Link2></Link2> |
||
10910 | </user-agent> |
||
10911 | <user-agent> |
||
10912 | <ID>id_moz_895</ID> |
||
10913 | <String>Mozilla/4.0 (compatible: AstraSpider V.2.1 : astrafind.com)</String> |
||
10914 | <Description>Astrafind! adult search robot (66.98.252.xx)</Description> |
||
10915 | <Type>R</Type> |
||
10916 | <Comment></Comment> |
||
10917 | <Link1>http://www.astrafind.com</Link1> |
||
10918 | <Link2></Link2> |
||
10919 | </user-agent> |
||
10920 | <user-agent> |
||
10921 | <ID>id_moz_021205_1</ID> |
||
10922 | <String>Mozilla/4.0 (compatible; Vagabondo/2.2; webcrawler at wise-guys dot nl; http://webagent.wise-guys.nl/)</String> |
||
10923 | <Description>WiseGuys robot Netherland - 82.94.216.2</Description> |
||
10924 | <Type>R</Type> |
||
10925 | <Comment>s.also - Mozilla/3.0 (Vagabondo... - Vagabondo..</Comment> |
||
10926 | <Link1>http://www.wise-guys.nl/Contact/index.php?botselected=webagents&lang=uk</Link1> |
||
10927 | <Link2></Link2> |
||
10928 | </user-agent> |
||
10929 | <user-agent> |
||
10930 | <ID>id_moz_240906_1</ID> |
||
10931 | <String>Mozilla/4.0 (compatible; Vagabondo/4.0Beta; webcrawler at wise-guys dot nl; http://webagent.wise-guys.nl/)</String> |
||
10932 | <Description>WiseGuys robot Netherland - 82.94.216.2</Description> |
||
10933 | <Type>R</Type> |
||
10934 | <Comment>s.also - Mozilla/3.0 (Vagabondo... - Vagabondo..</Comment> |
||
10935 | <Link1>http://www.wise-guys.nl/Contact/index.php?botselected=webagents&lang=uk</Link1> |
||
10936 | <Link2></Link2> |
||
10937 | </user-agent> |
||
10938 | <user-agent> |
||
10939 | <ID>id_moz_100208_1</ID> |
||
10940 | <String>Mozilla/4.0 (compatible; <a href=http://www.reget.com>ReGet Deluxe 5.1</a>; Windows NT 5.1)</String> |
||
10941 | <Description>ReGet Deluxe! download manager</Description> |
||
10942 | <Type>D</Type> |
||
10943 | <Comment></Comment> |
||
10944 | <Link1>http://deluxe.reget.com/en/</Link1> |
||
10945 | <Link2></Link2> |
||
10946 | </user-agent> |
||
10947 | <user-agent> |
||
10948 | <ID>id_moz_801</ID> |
||
10949 | <String>Mozilla/4.0 (compatible; Advanced Email Extractor v2.xx)</String> |
||
10950 | <Description>Advanced Email Extractor e-mail collector (spam bot)</Description> |
||
10951 | <Type>S</Type> |
||
10952 | <Comment></Comment> |
||
10953 | <Link1>http://www.mailutilities.com</Link1> |
||
10954 | <Link2></Link2> |
||
10955 | </user-agent> |
||
10956 | <user-agent> |
||
10957 | <ID>id_moz_802</ID> |
||
10958 | <String>Mozilla/4.0 (compatible; Arachmo)</String> |
||
10959 | <Description>Arachmo Spider - web site file extraction tool</Description> |
||
10960 | <Type>D</Type> |
||
10961 | <Comment></Comment> |
||
10962 | <Link1>http://bbbearchan.hp.infoseek.co.jp/</Link1> |
||
10963 | <Link2></Link2> |
||
10964 | </user-agent> |
||
10965 | <user-agent> |
||
10966 | <ID>id_moz_804</ID> |
||
10967 | <String>Mozilla/4.0 (compatible; BorderManager 3.0)</String> |
||
10968 | <Description>Novell Border Manager security suite</Description> |
||
10969 | <Type>P</Type> |
||
10970 | <Comment></Comment> |
||
10971 | <Link1></Link1> |
||
10972 | <Link2></Link2> |
||
10973 | </user-agent> |
||
10974 | <user-agent> |
||
10975 | <ID>id_moz_090807_3</ID> |
||
10976 | <String>Mozilla/4.0 (compatible; BOTW Spider; +http://botw.org)</String> |
||
10977 | <Description>Best of the Web directory link checking</Description> |
||
10978 | <Type>C</Type> |
||
10979 | <Comment>209.11.177.1xx</Comment> |
||
10980 | <Link1>http://botw.org/</Link1> |
||
10981 | <Link2></Link2> |
||
10982 | </user-agent> |
||
10983 | <user-agent> |
||
10984 | <ID>id_moz_803</ID> |
||
10985 | <String>Mozilla/4.0 (compatible; B_L_I_T_Z_B_O_T)</String> |
||
10986 | <Description>Blitzsuche Germany robot</Description> |
||
10987 | <Type>R</Type> |
||
10988 | <Comment>s. BlitzBOT@tricus.net</Comment> |
||
10989 | <Link1>http://blitzsuche.rp-online.de/</Link1> |
||
10990 | <Link2></Link2> |
||
10991 | </user-agent> |
||
10992 | <user-agent> |
||
10993 | <ID>id_moz_805</ID> |
||
10994 | <String>Mozilla/4.0 (compatible; Cerberian Drtrs Version-3.2-Build-0)</String> |
||
10995 | <Description>Content Control from Blue Coat</Description> |
||
10996 | <Type>P</Type> |
||
10997 | <Comment></Comment> |
||
10998 | <Link1>http://www.cerberian.com</Link1> |
||
10999 | <Link2></Link2> |
||
11000 | </user-agent> |
||
11001 | <user-agent> |
||
11002 | <ID>id_moz_080706_1</ID> |
||
11003 | <String>Mozilla/4.0 (compatible; Check&Get 3.0; Windows NT)</String> |
||
11004 | <Description>Check&Get bookmark manager, web change monitor and archiver</Description> |
||
11005 | <Type>C</Type> |
||
11006 | <Comment></Comment> |
||
11007 | <Link1>http://activeurls.com/en/</Link1> |
||
11008 | <Link2></Link2> |
||
11009 | </user-agent> |
||
11010 | <user-agent> |
||
11011 | <ID>id_moz_806</ID> |
||
11012 | <String>Mozilla/4.0 (compatible; ChristCrawler.com ChristCrawler@ChristCENTRAL.com)</String> |
||
11013 | <Description>Christcentral.com Christcrawler (was www.christcrawler.com)</Description> |
||
11014 | <Type>R</Type> |
||
11015 | <Comment>s.also ChristCRAWLER</Comment> |
||
11016 | <Link1></Link1> |
||
11017 | <Link2></Link2> |
||
11018 | </user-agent> |
||
11019 | <user-agent> |
||
11020 | <ID>id_moz_301105_4</ID> |
||
11021 | <String>Mozilla/4.0 (compatible; crawlx, crawler@trd.overture.com)</String> |
||
11022 | <Description>Yahoo Search Marketing crawler (68.142.211.1xx)</Description> |
||
11023 | <Type>R</Type> |
||
11024 | <Comment></Comment> |
||
11025 | <Link1>http://www.content.overture.com/d/</Link1> |
||
11026 | <Link2></Link2> |
||
11027 | </user-agent> |
||
11028 | <user-agent> |
||
11029 | <ID>id_moz_011207_1</ID> |
||
11030 | <String>Mozilla/4.0 (compatible; DAUMOA-video; +http://ws.daum.net/aboutkr.html)</String> |
||
11031 | <Description>DAUMOA - Daum search Korea robot (211.115.109.xxx)</Description> |
||
11032 | <Type>R</Type> |
||
11033 | <Comment>s. also RaBot</Comment> |
||
11034 | <Link1>http://www.daum.net/</Link1> |
||
11035 | <Link2>http://ws.daum.net/abouten.html</Link2> |
||
11036 | </user-agent> |
||
11037 | <user-agent> |
||
11038 | <ID>id_moz_131206_1</ID> |
||
11039 | <String>Mozilla/4.0 (compatible; DepSpid/5.0x; +http://about.depspid.net)</String> |
||
11040 | <Description>DepSpid distributed web crawler for link dependencies</Description> |
||
11041 | <Type>C</Type> |
||
11042 | <Comment></Comment> |
||
11043 | <Link1>http://depspid.net/</Link1> |
||
11044 | <Link2>http://about.depspid.net/</Link2> |
||
11045 | </user-agent> |
||
11046 | <user-agent> |
||
11047 | <ID>id_moz_807</ID> |
||
11048 | <String>Mozilla/4.0 (compatible; DnloadMage 1.0)</String> |
||
11049 | <Description>Download Mage download manager</Description> |
||
11050 | <Type>D</Type> |
||
11051 | <Comment></Comment> |
||
11052 | <Link1>http://www.dlmage.com</Link1> |
||
11053 | <Link2></Link2> |
||
11054 | </user-agent> |
||
11055 | <user-agent> |
||
11056 | <ID>id_moz_808</ID> |
||
11057 | <String>Mozilla/4.0 (compatible; FastCrawler3 support-fastcrawler3@fast.no)</String> |
||
11058 | <Description>Fast/Alltheweb crawler</Description> |
||
11059 | <Type>R</Type> |
||
11060 | <Comment></Comment> |
||
11061 | <Link1>http://www.alltheweb.com</Link1> |
||
11062 | <Link2></Link2> |
||
11063 | </user-agent> |
||
11064 | <user-agent> |
||
11065 | <ID>id_moz_809</ID> |
||
11066 | <String>Mozilla/4.0 (compatible; FDSE robot)</String> |
||
11067 | <Description>Fluid Dynamics Search Engine (FDSE) robot used by Abadoor.de</Description> |
||
11068 | <Type>R</Type> |
||
11069 | <Comment></Comment> |
||
11070 | <Link1>http://www.xav.com/scripts/search/</Link1> |
||
11071 | <Link2>http://www.abadoor.de/</Link2> |
||
11072 | </user-agent> |
||
11073 | <user-agent> |
||
11074 | <ID>id_moz_161105_2</ID> |
||
11075 | <String>Mozilla/4.0 (compatible; GPU p2p crawler http://gpu.sourceforge.net/search_engine.php)</String> |
||
11076 | <Description>GPU Distributed Search Engine crawler</Description> |
||
11077 | <Type>R</Type> |
||
11078 | <Comment></Comment> |
||
11079 | <Link1>http://gpu.sourceforge.net/search_engine.php</Link1> |
||
11080 | <Link2></Link2> |
||
11081 | </user-agent> |
||
11082 | <user-agent> |
||
11083 | <ID>id_moz_810</ID> |
||
11084 | <String>Mozilla/4.0 (compatible; grub-client-0.2.x; Crawl your stuff with http://grub.org)</String> |
||
11085 | <Description>Grub open source crawler</Description> |
||
11086 | <Type>R</Type> |
||
11087 | <Comment></Comment> |
||
11088 | <Link1>http://www.grub.org</Link1> |
||
11089 | <Link2></Link2> |
||
11090 | </user-agent> |
||
11091 | <user-agent> |
||
11092 | <ID>id_moz_811</ID> |
||
11093 | <String>Mozilla/4.0 (compatible; grub-client-0.3.x; Crawl your own stuff with http://grub.org)</String> |
||
11094 | <Description>Grub open source crawler</Description> |
||
11095 | <Type>R</Type> |
||
11096 | <Comment></Comment> |
||
11097 | <Link1>http://www.grub.org</Link1> |
||
11098 | <Link2></Link2> |
||
11099 | </user-agent> |
||
11100 | <user-agent> |
||
11101 | <ID>id_moz_812</ID> |
||
11102 | <String>Mozilla/4.0 (compatible; grub-client-2.x)</String> |
||
11103 | <Description>Grub open source crawler used by Looksmart ( 64.241.242.xx)</Description> |
||
11104 | <Type>R</Type> |
||
11105 | <Comment></Comment> |
||
11106 | <Link1>http://www.grub.org</Link1> |
||
11107 | <Link2></Link2> |
||
11108 | </user-agent> |
||
11109 | <user-agent> |
||
11110 | <ID>id_moz_261205_2</ID> |
||
11111 | <String>Mozilla/4.0 (compatible; ibisBrowser)</String> |
||
11112 | <Description>ibisBrowser Japanese mobile browser</Description> |
||
11113 | <Type>B</Type> |
||
11114 | <Comment></Comment> |
||
11115 | <Link1>http://www.ibis.ne.jp/products/ibisBrowser/index.html</Link1> |
||
11116 | <Link2></Link2> |
||
11117 | </user-agent> |
||
11118 | <user-agent> |
||
11119 | <ID>id_moz_813</ID> |
||
11120 | <String>Mozilla/4.0 (compatible; ICS 1.2.xxx)</String> |
||
11121 | <Description>Novell iChain Cool Solutions caching</Description> |
||
11122 | <Type>P</Type> |
||
11123 | <Comment></Comment> |
||
11124 | <Link1>http://www.novell.com</Link1> |
||
11125 | <Link2></Link2> |
||
11126 | </user-agent> |
||
11127 | <user-agent> |
||
11128 | <ID>id_moz_220206_1</ID> |
||
11129 | <String>Mozilla/4.0 (compatible; IE-Favorites-Check-0.5)</String> |
||
11130 | <Description>IE Favorites Check - Bookmark manager</Description> |
||
11131 | <Type>C</Type> |
||
11132 | <Comment></Comment> |
||
11133 | <Link1>http://secure.sintraweb.net/public/soft/iefc/</Link1> |
||
11134 | <Link2></Link2> |
||
11135 | </user-agent> |
||
11136 | <user-agent> |
||
11137 | <ID>id_moz_814</ID> |
||
11138 | <String>Mozilla/4.0 (compatible; Iplexx Spider/1.0 http://www.iplexx.at)</String> |
||
11139 | <Description>Iplexx Austria (webhosting company) logfile spamming bot</Description> |
||
11140 | <Type>S</Type> |
||
11141 | <Comment></Comment> |
||
11142 | <Link1>http://www.iplexx.at</Link1> |
||
11143 | <Link2></Link2> |
||
11144 | </user-agent> |
||
11145 | <user-agent> |
||
11146 | <ID>id_moz_020208_1</ID> |
||
11147 | <String>Mozilla/4.0 (compatible; KeepNI web site monitor)</String> |
||
11148 | <Description>KeepNi Monitors - Web site monitoring / link checking tool</Description> |
||
11149 | <Type>C</Type> |
||
11150 | <Comment></Comment> |
||
11151 | <Link1>http://www.keepni.com/</Link1> |
||
11152 | <Link2></Link2> |
||
11153 | </user-agent> |
||
11154 | <user-agent> |
||
11155 | <ID>id_moz_815</ID> |
||
11156 | <String>Mozilla/4.0 (compatible; Link Utility; http://net-promoter.com)</String> |
||
11157 | <Description>NetPromoter Link Utility link checking tool</Description> |
||
11158 | <Type>C</Type> |
||
11159 | <Comment>s. also - Mozilla/4.0 (compatible; NetPromoter Spider ...</Comment> |
||
11160 | <Link1>http://www.net-promoter.com/</Link1> |
||
11161 | <Link2></Link2> |
||
11162 | </user-agent> |
||
11163 | <user-agent> |
||
11164 | <ID>id_moz_816</ID> |
||
11165 | <String>Mozilla/4.0 (compatible; Lotus-Notes/5.0; Windows-NT)</String> |
||
11166 | <Description>Lotus Notes 5.0 browser</Description> |
||
11167 | <Type>B</Type> |
||
11168 | <Comment></Comment> |
||
11169 | <Link1>http://www-10.lotus.com/ldd/whatisnotes#Release%205.0%3A%20Web%20integration%20by%20d</Link1> |
||
11170 | <Link2></Link2> |
||
11171 | </user-agent> |
||
11172 | <user-agent> |
||
11173 | <ID>id_moz_819</ID> |
||
11174 | <String>Mozilla/4.0 (compatible; MSIE 4.01; AOL 4.0; Windows 98)</String> |
||
11175 | <Description>IE 4.x AOL Win98</Description> |
||
11176 | <Type>B</Type> |
||
11177 | <Comment></Comment> |
||
11178 | <Link1></Link1> |
||
11179 | <Link2></Link2> |
||
11180 | </user-agent> |
||
11181 | <user-agent> |
||
11182 | <ID>id_moz_820</ID> |
||
11183 | <String>Mozilla/4.0 (compatible; MSIE 4.01; Mac_PowerPC)</String> |
||
11184 | <Description>IE 4.x Mac Power PC</Description> |
||
11185 | <Type>B</Type> |
||
11186 | <Comment></Comment> |
||
11187 | <Link1></Link1> |
||
11188 | <Link2></Link2> |
||
11189 | </user-agent> |
||
11190 | <user-agent> |
||
11191 | <ID>id_moz_821</ID> |
||
11192 | <String>Mozilla/4.0 (compatible; MSIE 4.01; MSIECrawler; Windows 95)</String> |
||
11193 | <Description>Internet Explorer 4.0 URL check</Description> |
||
11194 | <Type>B C</Type> |
||
11195 | <Comment></Comment> |
||
11196 | <Link1></Link1> |
||
11197 | <Link2></Link2> |
||
11198 | </user-agent> |
||
11199 | <user-agent> |
||
11200 | <ID>id_moz_090506_1</ID> |
||
11201 | <String>Mozilla/4.0 (compatible; MSIE 4.01; Vonna.com b o t)</String> |
||
11202 | <Description>Vonna search robot</Description> |
||
11203 | <Type>R</Type> |
||
11204 | <Comment></Comment> |
||
11205 | <Link1>http://www.vonna.com/</Link1> |
||
11206 | <Link2></Link2> |
||
11207 | </user-agent> |
||
11208 | <user-agent> |
||
11209 | <ID>id_moz_822</ID> |
||
11210 | <String>Mozilla/4.0 (compatible; MSIE 4.01; Windows 95)</String> |
||
11211 | <Description>IE 4.x Win95</Description> |
||
11212 | <Type>B</Type> |
||
11213 | <Comment></Comment> |
||
11214 | <Link1></Link1> |
||
11215 | <Link2></Link2> |
||
11216 | </user-agent> |
||
11217 | <user-agent> |
||
11218 | <ID>id_moz_823</ID> |
||
11219 | <String>Mozilla/4.0 (compatible; MSIE 4.01; Windows CE; MSN Companion 2.0; 800x600; Compaq)</String> |
||
11220 | <Description>IE PDA Browser Windows CE</Description> |
||
11221 | <Type>B</Type> |
||
11222 | <Comment></Comment> |
||
11223 | <Link1></Link1> |
||
11224 | <Link2></Link2> |
||
11225 | </user-agent> |
||
11226 | <user-agent> |
||
11227 | <ID>id_moz_100109_4</ID> |
||
11228 | <String>Mozilla/4.0 (compatible; MSIE 4.01; Windows CE; PPC; 240x320; SPV M700; OpVer 19.123.2.733) OrangeBot-Mobile 2008.0 (mobilesearch.support@orange-ftgroup.com)</String> |
||
11229 | <Description>Orange France robot for mobiles</Description> |
||
11230 | <Type>R</Type> |
||
11231 | <Comment>81.52.143.xx</Comment> |
||
11232 | <Link1>http://www.orange.com/en_EN/</Link1> |
||
11233 | <Link2></Link2> |
||
11234 | </user-agent> |
||
11235 | <user-agent> |
||
11236 | <ID>id_moz_010308_2</ID> |
||
11237 | <String>Mozilla/4.0 (compatible; MSIE 4.01; Windows CE; PPS; 240x320)</String> |
||
11238 | <Description>IE for Windows CE on a PocketPC (HP iPAQ)</Description> |
||
11239 | <Type>B</Type> |
||
11240 | <Comment></Comment> |
||
11241 | <Link1>http://www.hp.com/</Link1> |
||
11242 | <Link2></Link2> |
||
11243 | </user-agent> |
||
11244 | <user-agent> |
||
11245 | <ID>id_moz_824</ID> |
||
11246 | <String>Mozilla/4.0 (compatible; MSIE 4.01; Windows NT Windows CE)</String> |
||
11247 | <Description>IE PDA Browser Windows CE</Description> |
||
11248 | <Type>B</Type> |
||
11249 | <Comment></Comment> |
||
11250 | <Link1></Link1> |
||
11251 | <Link2></Link2> |
||
11252 | </user-agent> |
||
11253 | <user-agent> |
||
11254 | <ID>id_moz_826</ID> |
||
11255 | <String>Mozilla/4.0 (compatible; MSIE 4.01; Windows NT)</String> |
||
11256 | <Description>IE 4.x WinNT</Description> |
||
11257 | <Type>B</Type> |
||
11258 | <Comment></Comment> |
||
11259 | <Link1></Link1> |
||
11260 | <Link2></Link2> |
||
11261 | </user-agent> |
||
11262 | <user-agent> |
||
11263 | <ID>id_moz_825</ID> |
||
11264 | <String>Mozilla/4.0 (compatible; MSIE 4.01; Windows NT; MS Search 4.0 Robot) Microsoft</String> |
||
11265 | <Description>diff. IPs / services i.e.: - Microsoft server information robot (see link) - Okanagan Internet Junction web filter (robot)</Description> |
||
11266 | <Type></Type> |
||
11267 | <Comment></Comment> |
||
11268 | <Link1>http://www.webmasterworld.com/forum11/841.htm</Link1> |
||
11269 | <Link2>http://www.junction.net/</Link2> |
||
11270 | </user-agent> |
||
11271 | <user-agent> |
||
11272 | <ID>id_moz_010406_3</ID> |
||
11273 | <String>Mozilla/4.0 (compatible; MSIE 4.0; Windows NT; Site Server 3.0 Robot) ACR</String> |
||
11274 | <Description>Unknown robot from American College of Radiology (ACR) running MS Site Server</Description> |
||
11275 | <Type>R C</Type> |
||
11276 | <Comment>208.236.180.xx</Comment> |
||
11277 | <Link1>http://www.acr.org/s_acr/index.asp</Link1> |
||
11278 | <Link2>http://www.microsoft.com/commerceserver/default.mspx</Link2> |
||
11279 | </user-agent> |
||
11280 | <user-agent> |
||
11281 | <ID>id_moz_817</ID> |
||
11282 | <String>Mozilla/4.0 (compatible; MSIE 4.0; Windows NT; Site Server 3.0 Robot) Indonesia Interactive</String> |
||
11283 | <Description>Indonesia Interactive Web-portal robot on MS Site Server</Description> |
||
11284 | <Type>R</Type> |
||
11285 | <Comment></Comment> |
||
11286 | <Link1>http://www.i-2.co.id/</Link1> |
||
11287 | <Link2>http://www.microsoft.com/commerceserver/default.mspx</Link2> |
||
11288 | </user-agent> |
||
11289 | <user-agent> |
||
11290 | <ID>id_moz_818</ID> |
||
11291 | <String>Mozilla/4.0 (compatible; MSIE 4.0; Windows NT; Site Server 3.0 Robot) WebQuest Designs</String> |
||
11292 | <Description>Webquestdesigns hosting</Description> |
||
11293 | <Type></Type> |
||
11294 | <Comment></Comment> |
||
11295 | <Link1>http://www.webquestdesigns.com</Link1> |
||
11296 | <Link2></Link2> |
||
11297 | </user-agent> |
||
11298 | <user-agent> |
||
11299 | <ID>id_moz_841</ID> |
||
11300 | <String>Mozilla/4.0 (compatible; MSIE 5.01; Windows 95) via <B>Avirt Gateway Server</B> v4.0</String> |
||
11301 | <Description>Avirt Gateway proxy server</Description> |
||
11302 | <Type>P</Type> |
||
11303 | <Comment></Comment> |
||
11304 | <Link1>http://www.avirt.com/products/gateway.html</Link1> |
||
11305 | <Link2></Link2> |
||
11306 | </user-agent> |
||
11307 | <user-agent> |
||
11308 | <ID>id_moz_843</ID> |
||
11309 | <String>Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0) (samualt9@bigfoot.com)</String> |
||
11310 | <Description>Metacarta.com (66.28.xx.xxx) robot</Description> |
||
11311 | <Type>R</Type> |
||
11312 | <Comment>s. Larbin....</Comment> |
||
11313 | <Link1>http://www.metacarta.com/</Link1> |
||
11314 | <Link2></Link2> |
||
11315 | </user-agent> |
||
11316 | <user-agent> |
||
11317 | <ID>id_moz_842</ID> |
||
11318 | <String>Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0; NetCaptor 6.5.0RC1)</String> |
||
11319 | <Description>NetCaptor IE browser addon</Description> |
||
11320 | <Type>B</Type> |
||
11321 | <Comment></Comment> |
||
11322 | <Link1>http://www.netcaptor.com</Link1> |
||
11323 | <Link2></Link2> |
||
11324 | </user-agent> |
||
11325 | <user-agent> |
||
11326 | <ID>id_moz_827</ID> |
||
11327 | <String>Mozilla/4.0 (compatible; MSIE 5.0; AOL 5.0; Windows 95; DigExt; Gateway2000; sureseeker.com)</String> |
||
11328 | <Description>IE 5.x AOL Win95 Sureseeker search plugin</Description> |
||
11329 | <Type>B</Type> |
||
11330 | <Comment></Comment> |
||
11331 | <Link1>http://www.sureseeker.com</Link1> |
||
11332 | <Link2></Link2> |
||
11333 | </user-agent> |
||
11334 | <user-agent> |
||
11335 | <ID>id_moz_828</ID> |
||
11336 | <String>Mozilla/4.0 (compatible; MSIE 5.0; Mac_PowerPC; AtHome021)</String> |
||
11337 | <Description>IE 5.x Mac PowerPC AtHome user</Description> |
||
11338 | <Type>B</Type> |
||
11339 | <Comment></Comment> |
||
11340 | <Link1></Link1> |
||
11341 | <Link2></Link2> |
||
11342 | </user-agent> |
||
11343 | <user-agent> |
||
11344 | <ID>id_moz_829</ID> |
||
11345 | <String>Mozilla/4.0 (compatible; MSIE 5.0; NetNose-Crawler 2.0; A New Search Experience: http://www.netnose.com)</String> |
||
11346 | <Description>www.netnose.com crawler</Description> |
||
11347 | <Type>R</Type> |
||
11348 | <Comment>parked domain</Comment> |
||
11349 | <Link1>http://www.netnose.com/</Link1> |
||
11350 | <Link2></Link2> |
||
11351 | </user-agent> |
||
11352 | <user-agent> |
||
11353 | <ID>id_moz_830</ID> |
||
11354 | <String>Mozilla/4.0 (compatible; MSIE 5.0; Win32) via proxy gateway CERN-HTTPD/3.0 libwww/2.17</String> |
||
11355 | <Description>WinXP via CERN httpd proxy server </Description> |
||
11356 | <Type>P</Type> |
||
11357 | <Comment></Comment> |
||
11358 | <Link1>http://www.w3.org</Link1> |
||
11359 | <Link2></Link2> |
||
11360 | </user-agent> |
||
11361 | <user-agent> |
||
11362 | <ID>id_moz_831</ID> |
||
11363 | <String>Mozilla/4.0 (compatible; MSIE 5.0; Windows 95) TrueRobot; 1.5</String> |
||
11364 | <Description>Echo.com robot</Description> |
||
11365 | <Type>R</Type> |
||
11366 | <Comment></Comment> |
||
11367 | <Link1>http://www.echo.com</Link1> |
||
11368 | <Link2></Link2> |
||
11369 | </user-agent> |
||
11370 | <user-agent> |
||
11371 | <ID>id_moz_832</ID> |
||
11372 | <String>Mozilla/4.0 (compatible; MSIE 5.0; Windows 95) VoilaBot BETA 1.2 (http://www.voila.com/)</String> |
||
11373 | <Description>Voila.fr robot</Description> |
||
11374 | <Type>R</Type> |
||
11375 | <Comment></Comment> |
||
11376 | <Link1>http://www.voila.fr</Link1> |
||
11377 | <Link2></Link2> |
||
11378 | </user-agent> |
||
11379 | <user-agent> |
||
11380 | <ID>id_moz_833</ID> |
||
11381 | <String>Mozilla/4.0 (compatible; MSIE 5.0; Windows 95) VoilaBot; 1.6</String> |
||
11382 | <Description>Voila.fr robot</Description> |
||
11383 | <Type>R</Type> |
||
11384 | <Comment></Comment> |
||
11385 | <Link1>http://www.voila.fr</Link1> |
||
11386 | <Link2></Link2> |
||
11387 | </user-agent> |
||
11388 | <user-agent> |
||
11389 | <ID>id_moz_835</ID> |
||
11390 | <String>Mozilla/4.0 (compatible; MSIE 5.0; Windows ME) Opera 5.11 [en]</String> |
||
11391 | <Description>WinME Opera 5.x</Description> |
||
11392 | <Type>B</Type> |
||
11393 | <Comment></Comment> |
||
11394 | <Link1></Link1> |
||
11395 | <Link2></Link2> |
||
11396 | </user-agent> |
||
11397 | <user-agent> |
||
11398 | <ID>id_moz_834</ID> |
||
11399 | <String>Mozilla/4.0 (compatible; MSIE 5.0; Windows ME; Link Checker 2.x.xx http://www.kyosoft.com)</String> |
||
11400 | <Description>Kyosoft's Link Checker</Description> |
||
11401 | <Type>C</Type> |
||
11402 | <Comment></Comment> |
||
11403 | <Link1>http://www.kyosoft.com</Link1> |
||
11404 | <Link2></Link2> |
||
11405 | </user-agent> |
||
11406 | <user-agent> |
||
11407 | <ID>id_moz_836</ID> |
||
11408 | <String>Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt; DTS Agent</String> |
||
11409 | <Description>Beijing Express Email Address Extractor via DHCP Data Transport Services (DTS)</Description> |
||
11410 | <Type>S</Type> |
||
11411 | <Comment>site is closed</Comment> |
||
11412 | <Link1>http://www.zstools.com</Link1> |
||
11413 | <Link2>http://esupport.ca.com/index.html?/public/dto_transportit/infodocs/dto1013.asp</Link2> |
||
11414 | </user-agent> |
||
11415 | <user-agent> |
||
11416 | <ID>id_moz_837</ID> |
||
11417 | <String>Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; Girafabot; girafabot at girafa dot com; http://www.girafa.com)</String> |
||
11418 | <Description>Girafa (browser plug-in) robot</Description> |
||
11419 | <Type>B R</Type> |
||
11420 | <Comment></Comment> |
||
11421 | <Link1>http://www.girafa.com</Link1> |
||
11422 | <Link2></Link2> |
||
11423 | </user-agent> |
||
11424 | <user-agent> |
||
11425 | <ID>id_moz_838</ID> |
||
11426 | <String>Mozilla/4.0 (compatible; MSIE 5.0; www.galaxy.com; www.psychedelix.com)</String> |
||
11427 | <Description>Galaxy robot (63.121.41.xxx) </Description> |
||
11428 | <Type>R</Type> |
||
11429 | <Comment>s. also GalaxyBot..</Comment> |
||
11430 | <Link1>http://www.galaxy.com/</Link1> |
||
11431 | <Link2></Link2> |
||
11432 | </user-agent> |
||
11433 | <user-agent> |
||
11434 | <ID>id_moz_839</ID> |
||
11435 | <String>Mozilla/4.0 (compatible; MSIE 5.0; www.galaxy.com; www.psychedelix.com/; http://www.galaxy.com/info/crawler.html)</String> |
||
11436 | <Description>Galaxy robot (63.121.41.xxx)</Description> |
||
11437 | <Type>R</Type> |
||
11438 | <Comment>s. also GalaxyBot..</Comment> |
||
11439 | <Link1>http://www.galaxy.com/</Link1> |
||
11440 | <Link2></Link2> |
||
11441 | </user-agent> |
||
11442 | <user-agent> |
||
11443 | <ID>id_moz_840</ID> |
||
11444 | <String>Mozilla/4.0 (compatible; MSIE 5.0; YANDEX)</String> |
||
11445 | <Description>Yandex Search Russia link checking (213.180.206.2xx)</Description> |
||
11446 | <Type>R</Type> |
||
11447 | <Comment>s. also Yandex/1...</Comment> |
||
11448 | <Link1>http://www.yandex.ru</Link1> |
||
11449 | <Link2></Link2> |
||
11450 | </user-agent> |
||
11451 | <user-agent> |
||
11452 | <ID>id_moz_844</ID> |
||
11453 | <String>Mozilla/4.0 (compatible; MSIE 5.5; AOL 4.0; Windows 98; GoBeez (www.gobeez.com))</String> |
||
11454 | <Description>Gobeez starting page plugin</Description> |
||
11455 | <Type>C</Type> |
||
11456 | <Comment>site is offline</Comment> |
||
11457 | <Link1>http://www.gobeez.com/</Link1> |
||
11458 | <Link2></Link2> |
||
11459 | </user-agent> |
||
11460 | <user-agent> |
||
11461 | <ID>id_moz_845</ID> |
||
11462 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows 95; Transmission Segment; Hotbar 2.0)</String> |
||
11463 | <Description>IE 5.5 Win95 Hotbar plug-in</Description> |
||
11464 | <Type></Type> |
||
11465 | <Comment></Comment> |
||
11466 | <Link1>http://hotbar.com/install/firstvisit.asp</Link1> |
||
11467 | <Link2></Link2> |
||
11468 | </user-agent> |
||
11469 | <user-agent> |
||
11470 | <ID>id_moz_846</ID> |
||
11471 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; Crazy Browser 1.x.x)</String> |
||
11472 | <Description>Crazy Browser - IE based tabbed Browser</Description> |
||
11473 | <Type>B</Type> |
||
11474 | <Comment></Comment> |
||
11475 | <Link1>http://www.crazybrowser.com</Link1> |
||
11476 | <Link2></Link2> |
||
11477 | </user-agent> |
||
11478 | <user-agent> |
||
11479 | <ID>id_moz_847</ID> |
||
11480 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; KITV4.7 Wanadoo)</String> |
||
11481 | <Description>Wanadoo Internet services</Description> |
||
11482 | <Type>B</Type> |
||
11483 | <Comment></Comment> |
||
11484 | <Link1></Link1> |
||
11485 | <Link2></Link2> |
||
11486 | </user-agent> |
||
11487 | <user-agent> |
||
11488 | <ID>id_moz_848</ID> |
||
11489 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; SAFEXPLORER TL)</String> |
||
11490 | <Description>Safexplorer (safexplorer.com - site is offline) kids browser</Description> |
||
11491 | <Type>B</Type> |
||
11492 | <Comment></Comment> |
||
11493 | <Link1></Link1> |
||
11494 | <Link2></Link2> |
||
11495 | </user-agent> |
||
11496 | <user-agent> |
||
11497 | <ID>id_moz_849</ID> |
||
11498 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; SYMPA; Katiesoft 7; SimulBrowse 3.0)</String> |
||
11499 | <Description>Katiesoft Scroll (ex www.katiesoft.com now discarded) & SimulBrowse (ex www.simulbrowse.com now dead) IE browser plugins</Description> |
||
11500 | <Type>B</Type> |
||
11501 | <Comment></Comment> |
||
11502 | <Link1></Link1> |
||
11503 | <Link2></Link2> |
||
11504 | </user-agent> |
||
11505 | <user-agent> |
||
11506 | <ID>id_moz_850</ID> |
||
11507 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; Win 9x 4.90; BTinternet V8.1)</String> |
||
11508 | <Description>Windows ME BTOpenworld Internet services</Description> |
||
11509 | <Type>B</Type> |
||
11510 | <Comment></Comment> |
||
11511 | <Link1></Link1> |
||
11512 | <Link2></Link2> |
||
11513 | </user-agent> |
||
11514 | <user-agent> |
||
11515 | <ID>id_moz_851</ID> |
||
11516 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; Win 9x 4.90; MSIECrawler)</String> |
||
11517 | <Description>Windows ME Internet Explorer URL check</Description> |
||
11518 | <Type>B C</Type> |
||
11519 | <Comment></Comment> |
||
11520 | <Link1></Link1> |
||
11521 | <Link2></Link2> |
||
11522 | </user-agent> |
||
11523 | <user-agent> |
||
11524 | <ID>id_moz_852</ID> |
||
11525 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 4.0; obot)</String> |
||
11526 | <Description>Cobion Germany Brand Protection Services robot</Description> |
||
11527 | <Type>R</Type> |
||
11528 | <Comment></Comment> |
||
11529 | <Link1>http://www.cobion.com</Link1> |
||
11530 | <Link2></Link2> |
||
11531 | </user-agent> |
||
11532 | <user-agent> |
||
11533 | <ID>id_moz_853</ID> |
||
11534 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 4.0; QXW03018)</String> |
||
11535 | <Description>Cobion Germany Brand Protection Services robot</Description> |
||
11536 | <Type>R</Type> |
||
11537 | <Comment></Comment> |
||
11538 | <Link1>http://www.cobion.com</Link1> |
||
11539 | <Link2></Link2> |
||
11540 | </user-agent> |
||
11541 | <user-agent> |
||
11542 | <ID>id_moz_858</ID> |
||
11543 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0) Active Cache Request</String> |
||
11544 | <Description>IE 5.5 Win2000 / user agent</Description> |
||
11545 | <Type>B</Type> |
||
11546 | <Comment></Comment> |
||
11547 | <Link1></Link1> |
||
11548 | <Link2></Link2> |
||
11549 | </user-agent> |
||
11550 | <user-agent> |
||
11551 | <ID>id_moz_859</ID> |
||
11552 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0) Fetch API Request</String> |
||
11553 | <Description>Maybe: - MS Internet Security & Acceleration Server (ISA) cache refreshing request (see link) or - IE 5.5 Win2000 probably with some (website) API request component (see 2nd link) - suspected as email-harvester / site scanning tool (see http://www.byte.com/documents/s=493/byt20010208s0001/index.htm</Description> |
||
11554 | <Type>P S ?</Type> |
||
11555 | <Comment></Comment> |
||
11556 | <Link1>http://groups.google.com/groups?hl=en&lr=&ie=UTF-8&safe=off&threadm=uGoenyodBHA.1472%40tkmsftngp07&rnum=1&prev=/groups%3Fq%3DFetch%2BAPI%26hl%3Den%26lr%3D%26ie%3DUTF-8%26safe%3Doff%26selm%3DuGoenyodBHA.1472%2540tkmsftngp07%26rnum%3D1</Link1> |
||
11557 | <Link2>http://groups.google.de/groups?q=%22fetch+api+request%22&hl=de&lr=&ie=UTF-8&oe=UTF-8&selm=3CAD577B.C29BA3B2%40execpc.com&rnum=2</Link2> |
||
11558 | </user-agent> |
||
11559 | <user-agent> |
||
11560 | <ID>id_moz_854</ID> |
||
11561 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0; .NET CLR 1.0.3705)</String> |
||
11562 | <Description>IE 5.5 Win2000 with MS.NET SDK</Description> |
||
11563 | <Type>B</Type> |
||
11564 | <Comment></Comment> |
||
11565 | <Link1></Link1> |
||
11566 | <Link2></Link2> |
||
11567 | </user-agent> |
||
11568 | <user-agent> |
||
11569 | <ID>id_moz_855</ID> |
||
11570 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0; AIRF)</String> |
||
11571 | <Description>IE 5.5 Win2000 / user agent w. AI RoboForm (AIRF) password manager</Description> |
||
11572 | <Type>B</Type> |
||
11573 | <Comment></Comment> |
||
11574 | <Link1>http://www.roboform.com</Link1> |
||
11575 | <Link2></Link2> |
||
11576 | </user-agent> |
||
11577 | <user-agent> |
||
11578 | <ID>id_moz_856</ID> |
||
11579 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0; AspTear 1.5)</String> |
||
11580 | <Description>AspTear URL fetching program component / Download32.com spider</Description> |
||
11581 | <Type>R D</Type> |
||
11582 | <Comment></Comment> |
||
11583 | <Link1>http://www.alphasierrapapa.com/IisDev/Components/AspTear/</Link1> |
||
11584 | <Link2>http://www.download32.com</Link2> |
||
11585 | </user-agent> |
||
11586 | <user-agent> |
||
11587 | <ID>id_moz_857</ID> |
||
11588 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0; N_o_k_i_a)</String> |
||
11589 | <Description>Nokia.com network</Description> |
||
11590 | <Type>B</Type> |
||
11591 | <Comment></Comment> |
||
11592 | <Link1></Link1> |
||
11593 | <Link2></Link2> |
||
11594 | </user-agent> |
||
11595 | <user-agent> |
||
11596 | <ID>id_moz_051102_1</ID> |
||
11597 | <String>Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0; T312461) RPT-HTTPClient/0.3-3E</String> |
||
11598 | <Description>Unknown Object Sciences Corp. robot using the HTTPClient</Description> |
||
11599 | <Type></Type> |
||
11600 | <Comment></Comment> |
||
11601 | <Link1>http://www.objectsciences.com</Link1> |
||
11602 | <Link2>http://www.innovation.ch/java/HTTPClient/</Link2> |
||
11603 | </user-agent> |
||
11604 | <user-agent> |
||
11605 | <ID>id_moz_060406_2</ID> |
||
11606 | <String>Mozilla/4.0 (compatible; MSIE 6.0 compatible; Asterias Crawler v4; +http://www.singingfish.com/help/spider.html; webmaster@singingfish.com); SpiderThread Revision: 3.10</String> |
||
11607 | <Description>Singingfish media spider (64.12.186.2xx) via AOL search</Description> |
||
11608 | <Type>R</Type> |
||
11609 | <Comment>s. also asterias/2.0</Comment> |
||
11610 | <Link1>http://search.singingfish.com/sfw/home.jsp</Link1> |
||
11611 | <Link2></Link2> |
||
11612 | </user-agent> |
||
11613 | <user-agent> |
||
11614 | <ID>id_moz_200108_2</ID> |
||
11615 | <String>Mozilla/4.0 (compatible; MSIE 6.0; AOL 9.0; Windows 98; .NET CLR 1.1.4322; MEGAUPLOAD 2.0)</String> |
||
11616 | <Description>Megaupload Mega Manager - Download manager toolbar for IE</Description> |
||
11617 | <Type>D</Type> |
||
11618 | <Comment></Comment> |
||
11619 | <Link1>http://www.megaupload.com/manager/de/</Link1> |
||
11620 | <Link2></Link2> |
||
11621 | </user-agent> |
||
11622 | <user-agent> |
||
11623 | <ID>id_moz_010106_1</ID> |
||
11624 | <String>Mozilla/4.0 (compatible; MSIE 6.0; AOL 9.0; Windows NT 5.1; SV1; HbTools 4.7.2)</String> |
||
11625 | <Description>Hotbar IE graphical skin</Description> |
||
11626 | <Type>B</Type> |
||
11627 | <Comment>Adware / Spyware component</Comment> |
||
11628 | <Link1>http://hotbar.com/Installation/Browsing/WhatIs/Hotbar.htm</Link1> |
||
11629 | <Link2></Link2> |
||
11630 | </user-agent> |
||
11631 | <user-agent> |
||
11632 | <ID>id_moz_860</ID> |
||
11633 | <String>Mozilla/4.0 (compatible; MSIE 6.0; MSIE 5.5; Windows NT 5.1) Skampy/0.9.x [en]</String> |
||
11634 | <Description>Skaffe.com directory link checker</Description> |
||
11635 | <Type>R</Type> |
||
11636 | <Comment>s. also Skampy</Comment> |
||
11637 | <Link1>http://www.skaffe.com</Link1> |
||
11638 | <Link2></Link2> |
||
11639 | </user-agent> |
||
11640 | <user-agent> |
||
11641 | <ID>id_moz_100606_1</ID> |
||
11642 | <String>Mozilla/4.0 (compatible; MSIE 6.0; TargetSeek/1.0; +http://www.targetgroups.net/TargetSeek.html)</String> |
||
11643 | <Description>TargetSeek Crawler concerning electronics industry product announcements</Description> |
||
11644 | <Type>R</Type> |
||
11645 | <Comment>71.161.205.2xx</Comment> |
||
11646 | <Link1>http://www.targetgroups.net/TargetSeek.html</Link1> |
||
11647 | <Link2></Link2> |
||
11648 | </user-agent> |
||
11649 | <user-agent> |
||
11650 | <ID>id_moz_861</ID> |
||
11651 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Win32) WebWasher 3.0</String> |
||
11652 | <Description>IE 6.0 WebWasher ad filter</Description> |
||
11653 | <Type>B P</Type> |
||
11654 | <Comment></Comment> |
||
11655 | <Link1>http://www.webwasher.com</Link1> |
||
11656 | <Link2></Link2> |
||
11657 | </user-agent> |
||
11658 | <user-agent> |
||
11659 | <ID>id_moz_864</ID> |
||
11660 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows 98) REL Software Web Link Validator 2.x)</String> |
||
11661 | <Description>Web Link Validator link validation software</Description> |
||
11662 | <Type>C</Type> |
||
11663 | <Comment></Comment> |
||
11664 | <Link1>http://www.relsoftware.com</Link1> |
||
11665 | <Link2></Link2> |
||
11666 | </user-agent> |
||
11667 | <user-agent> |
||
11668 | <ID>id_moz_865</ID> |
||
11669 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows 98) Web Link Validator 2.x)</String> |
||
11670 | <Description>Web Link Validator link validation software</Description> |
||
11671 | <Type>C</Type> |
||
11672 | <Comment></Comment> |
||
11673 | <Link1>http://www.relsoftware.com</Link1> |
||
11674 | <Link2></Link2> |
||
11675 | </user-agent> |
||
11676 | <user-agent> |
||
11677 | <ID>id_moz_862</ID> |
||
11678 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows 98; Net M@nager V3.02 - www.vinn.com.au)</String> |
||
11679 | <Description>IE 6.0 Netmanager IE add-on</Description> |
||
11680 | <Type>B</Type> |
||
11681 | <Comment></Comment> |
||
11682 | <Link1>http://www.vinn.com.au</Link1> |
||
11683 | <Link2></Link2> |
||
11684 | </user-agent> |
||
11685 | <user-agent> |
||
11686 | <ID>id_moz_290306_1</ID> |
||
11687 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows 98; support@illumit.com; http://www.illumit.com/Products/weblight/)</String> |
||
11688 | <Description>WebLight web analyzer & link checker</Description> |
||
11689 | <Type>C</Type> |
||
11690 | <Comment>s. also WebLight/4.x.x ...</Comment> |
||
11691 | <Link1>http://www.illumit.com/Products/weblight/</Link1> |
||
11692 | <Link2></Link2> |
||
11693 | </user-agent> |
||
11694 | <user-agent> |
||
11695 | <ID>id_moz_863</ID> |
||
11696 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows 98; Win 9x 4.90; http://www.Abolimba.de)</String> |
||
11697 | <Description>Abolimba Multibrowser - IE based browser</Description> |
||
11698 | <Type>C</Type> |
||
11699 | <Comment></Comment> |
||
11700 | <Link1>http://www.autag.com</Link1> |
||
11701 | <Link2></Link2> |
||
11702 | </user-agent> |
||
11703 | <user-agent> |
||
11704 | <ID>id_moz_866</ID> |
||
11705 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; .NET CLR 1.1.4322; Lunascape 2.1.3)</String> |
||
11706 | <Description>Lunascape IE based browser (Japan)</Description> |
||
11707 | <Type>B</Type> |
||
11708 | <Comment>s. also Lunascape</Comment> |
||
11709 | <Link1>http://www2.lunascape.jp/index.aspx</Link1> |
||
11710 | <Link2></Link2> |
||
11711 | </user-agent> |
||
11712 | <user-agent> |
||
11713 | <ID>id_moz_290708_4</ID> |
||
11714 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; Google Wireless Transcoder;)</String> |
||
11715 | <Description>Google wireless transcoder (GWT) proxy for rewriting websites for mobiles</Description> |
||
11716 | <Type>P</Type> |
||
11717 | <Comment>209.85.136.xxx</Comment> |
||
11718 | <Link1>http://www.google.com/gwt/n</Link1> |
||
11719 | <Link2></Link2> |
||
11720 | </user-agent> |
||
11721 | <user-agent> |
||
11722 | <ID>id_moz_150906_1</ID> |
||
11723 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; ODP entries t_st; http://tuezilla.de/t_st-odp-entries-agent.html)</String> |
||
11724 | <Description>Tüzilla (Germany) - ODP link checking using Robozilla</Description> |
||
11725 | <Type>R</Type> |
||
11726 | <Comment>81.169.154.xx</Comment> |
||
11727 | <Link1>http://tuezilla.de</Link1> |
||
11728 | <Link2>http://dmoz.org/profiles/robozilla.html</Link2> |
||
11729 | </user-agent> |
||
11730 | <user-agent> |
||
11731 | <ID>id_moz_867</ID> |
||
11732 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; ODP links test; http://tuezilla.de/test-odp-links-agent.html)</String> |
||
11733 | <Description>Tüzilla (Germany) - ODP link checking using Robozilla</Description> |
||
11734 | <Type>R</Type> |
||
11735 | <Comment>81.169.154.xx</Comment> |
||
11736 | <Link1>http://tuezilla.de</Link1> |
||
11737 | <Link2>http://dmoz.org/profiles/robozilla.html</Link2> |
||
11738 | </user-agent> |
||
11739 | <user-agent> |
||
11740 | <ID>id_moz_080606_1</ID> |
||
11741 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; ZoomSpider.net bot; .NET CLR 1.1.4322)</String> |
||
11742 | <Description>ZoomSpider.Net indexing robot for several directorys</Description> |
||
11743 | <Type>R</Type> |
||
11744 | <Comment>70.94.232.2xx</Comment> |
||
11745 | <Link1>http://www.zoomspider.net/</Link1> |
||
11746 | <Link2></Link2> |
||
11747 | </user-agent> |
||
11748 | <user-agent> |
||
11749 | <ID>id_moz_882</ID> |
||
11750 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1) (dns_admin@c-a-s-h.com)</String> |
||
11751 | <Description>unknown robot from 64.246.44.xx</Description> |
||
11752 | <Type></Type> |
||
11753 | <Comment></Comment> |
||
11754 | <Link1></Link1> |
||
11755 | <Link2></Link2> |
||
11756 | </user-agent> |
||
11757 | <user-agent> |
||
11758 | <ID>id_moz_280408_1</ID> |
||
11759 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Covac UPPS Cathan 1.2.5;)</String> |
||
11760 | <Description>Covac Software UPPS (Universal PHP Proxy Server) - free public proxy server</Description> |
||
11761 | <Type>P</Type> |
||
11762 | <Comment></Comment> |
||
11763 | <Link1>http://www.covac-software.com/proxy/</Link1> |
||
11764 | <Link2></Link2> |
||
11765 | </user-agent> |
||
11766 | <user-agent> |
||
11767 | <ID>id_moz_160406_1</ID> |
||
11768 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Crayon Crawler; snprtz|T04056566514940; (R1 1.5))</String> |
||
11769 | <Description>GetNetWise Crayon Crawler web filter</Description> |
||
11770 | <Type>P</Type> |
||
11771 | <Comment></Comment> |
||
11772 | <Link1>http://kids.getnetwise.org/tools/tool_info.php?tool_id=931919301.7202</Link1> |
||
11773 | <Link2></Link2> |
||
11774 | </user-agent> |
||
11775 | <user-agent> |
||
11776 | <ID>id_moz_868</ID> |
||
11777 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Deepnet Explorer)</String> |
||
11778 | <Description>Deepnet Explorer - IE based browser</Description> |
||
11779 | <Type>B</Type> |
||
11780 | <Comment></Comment> |
||
11781 | <Link1>http://deepnetexplorer.com/</Link1> |
||
11782 | <Link2></Link2> |
||
11783 | </user-agent> |
||
11784 | <user-agent> |
||
11785 | <ID>id_moz_869</ID> |
||
11786 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; heritrix/1.3.0 http://www.cs.washington.edu/research/networking/websys/)</String> |
||
11787 | <Description>Heritrix Internet Archive's open-source web project used by Analysis Projects at UW</Description> |
||
11788 | <Type>R</Type> |
||
11789 | <Comment></Comment> |
||
11790 | <Link1>http://crawler.archive.org/</Link1> |
||
11791 | <Link2>http://www.cs.washington.edu/research/networking/websys/</Link2> |
||
11792 | </user-agent> |
||
11793 | <user-agent> |
||
11794 | <ID>id_moz_870</ID> |
||
11795 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Hotbar 3.0)</String> |
||
11796 | <Description>IE 6x WinXP Hotbar plug-in</Description> |
||
11797 | <Type>B</Type> |
||
11798 | <Comment></Comment> |
||
11799 | <Link1>http://hotbar.com/install/firstvisit.asp</Link1> |
||
11800 | <Link2></Link2> |
||
11801 | </user-agent> |
||
11802 | <user-agent> |
||
11803 | <ID>id_moz_871</ID> |
||
11804 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; iOpus-I-M)</String> |
||
11805 | <Description>IE 6x WinXP iOpus Internet Macros - Internet-based macro recorder </Description> |
||
11806 | <Type>B</Type> |
||
11807 | <Comment></Comment> |
||
11808 | <Link1>http://www.iopus.com</Link1> |
||
11809 | <Link2></Link2> |
||
11810 | </user-agent> |
||
11811 | <user-agent> |
||
11812 | <ID>id_moz_872</ID> |
||
11813 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; iRider 2.21.1108; FDM)</String> |
||
11814 | <Description>iRider - IE based browser / Free Download Manager (FDM)</Description> |
||
11815 | <Type>D</Type> |
||
11816 | <Comment></Comment> |
||
11817 | <Link1>http://www.irider.com/irider/index.htm</Link1> |
||
11818 | <Link2>http://www.freedownloadmanager.org/</Link2> |
||
11819 | </user-agent> |
||
11820 | <user-agent> |
||
11821 | <ID>id_moz_873</ID> |
||
11822 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; KKman3.0)</String> |
||
11823 | <Description>KKman http://www.kkman.com/ - Japanese IE based browser</Description> |
||
11824 | <Type>B</Type> |
||
11825 | <Comment></Comment> |
||
11826 | <Link1>http://www.kkman.com</Link1> |
||
11827 | <Link2></Link2> |
||
11828 | </user-agent> |
||
11829 | <user-agent> |
||
11830 | <ID>id_moz_874</ID> |
||
11831 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; MathPlayer2.0)</String> |
||
11832 | <Description>IE 6x WinXP MathPlayer mathematical notation plugin </Description> |
||
11833 | <Type>B</Type> |
||
11834 | <Comment></Comment> |
||
11835 | <Link1>http://www.mathtype.com/en/products/mathplayer/</Link1> |
||
11836 | <Link2></Link2> |
||
11837 | </user-agent> |
||
11838 | <user-agent> |
||
11839 | <ID>id_moz_875</ID> |
||
11840 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Maxthon) </String> |
||
11841 | <Description>Maxton (ex MyIE2) - IE based browser</Description> |
||
11842 | <Type>B</Type> |
||
11843 | <Comment></Comment> |
||
11844 | <Link1>http://www.maxthon.com</Link1> |
||
11845 | <Link2></Link2> |
||
11846 | </user-agent> |
||
11847 | <user-agent> |
||
11848 | <ID>id_moz_876</ID> |
||
11849 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; PeoplePal 3.0; MSIECrawler)</String> |
||
11850 | <Description>IE 6x WinXP peoplepc online PeoplePal IE toolbar</Description> |
||
11851 | <Type>B</Type> |
||
11852 | <Comment></Comment> |
||
11853 | <Link1>http://home.vfw-online.com/peoplepal/default.asp</Link1> |
||
11854 | <Link2></Link2> |
||
11855 | </user-agent> |
||
11856 | <user-agent> |
||
11857 | <ID>id_moz_877</ID> |
||
11858 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Q312461; IOpener Release 1.1.04)</String> |
||
11859 | <Description>IE 6x WinXP / I-Opener (was www.netpliance.com/) web PC</Description> |
||
11860 | <Type>B</Type> |
||
11861 | <Comment></Comment> |
||
11862 | <Link1></Link1> |
||
11863 | <Link2></Link2> |
||
11864 | </user-agent> |
||
11865 | <user-agent> |
||
11866 | <ID>id_moz_050307_1</ID> |
||
11867 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; QihooBot 1.0 qihoobot@qihoo.net)</String> |
||
11868 | <Description>Qihoo search (China) robot</Description> |
||
11869 | <Type>R</Type> |
||
11870 | <Comment>220.181.34.1xx</Comment> |
||
11871 | <Link1>http://www.qihoo.com/</Link1> |
||
11872 | <Link2></Link2> |
||
11873 | </user-agent> |
||
11874 | <user-agent> |
||
11875 | <ID>id_moz_070306_1</ID> |
||
11876 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SIMBAR Enabled; InfoPath.1)</String> |
||
11877 | <Description>SimBar IE toolbar for accessing The Sims sites / Infopath IE form & spreadsheet plugin</Description> |
||
11878 | <Type>B</Type> |
||
11879 | <Comment></Comment> |
||
11880 | <Link1>http://www.simstools.com/simbar.php</Link1> |
||
11881 | <Link2>http://office.microsoft.com/en-us/fx010857921033.aspx</Link2> |
||
11882 | </user-agent> |
||
11883 | <user-agent> |
||
11884 | <ID>id_moz_878</ID> |
||
11885 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; StumbleUpon.com 1.760; .NET CLR 1.1.4322)</String> |
||
11886 | <Description>IE 6x WinXP Stumble Upon IE toolbar</Description> |
||
11887 | <Type>B</Type> |
||
11888 | <Comment></Comment> |
||
11889 | <Link1>http://www.stumbleupon.com</Link1> |
||
11890 | <Link2></Link2> |
||
11891 | </user-agent> |
||
11892 | <user-agent> |
||
11893 | <ID>id_moz_150807_1</ID> |
||
11894 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Embedded Web Browser from: http://bsalsa.com/; MSIECrawler)</String> |
||
11895 | <Description>Balsa Productions embedded web browser package for Borland Delphi</Description> |
||
11896 | <Type>B</Type> |
||
11897 | <Comment></Comment> |
||
11898 | <Link1>http://bsalsa.com/product.html</Link1> |
||
11899 | <Link2></Link2> |
||
11900 | </user-agent> |
||
11901 | <user-agent> |
||
11902 | <ID>id_moz_030807_2</ID> |
||
11903 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; http://www.changedetection.com/bot.html )</String> |
||
11904 | <Description>ChangeDetection robot for web page monitoring</Description> |
||
11905 | <Type>C</Type> |
||
11906 | <Comment>68.166.223.x</Comment> |
||
11907 | <Link1>http://www.changedetection.com/</Link1> |
||
11908 | <Link2>http://www.changedetection.com/bot.html</Link2> |
||
11909 | </user-agent> |
||
11910 | <user-agent> |
||
11911 | <ID>id_moz_879</ID> |
||
11912 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322)</String> |
||
11913 | <Description>IE 6x WinXP also used by WebSite Pro HTML editor</Description> |
||
11914 | <Type>B</Type> |
||
11915 | <Comment></Comment> |
||
11916 | <Link1>http://www.gtpcc.org/gtpcc/websitepro.htm</Link1> |
||
11917 | <Link2></Link2> |
||
11918 | </user-agent> |
||
11919 | <user-agent> |
||
11920 | <ID>id_moz_880</ID> |
||
11921 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; DX-Browser 5.0.0.0)</String> |
||
11922 | <Description>DX-Browser - German IE based browser</Description> |
||
11923 | <Type>B</Type> |
||
11924 | <Comment>was http://www.dx-soft.net/ (expired)</Comment> |
||
11925 | <Link1>http://www.zdnet.de/downloads/prg/t/p/deDCTP-wc.html</Link1> |
||
11926 | <Link2></Link2> |
||
11927 | </user-agent> |
||
11928 | <user-agent> |
||
11929 | <ID>id_moz_271006_1</ID> |
||
11930 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; FunWebProducts; ezPeer+ v1.0 Beta (0.4.1.98); ezPeer+ v1.0 (0.5.0.00); .NET CLR 1.1.4322; MSIECrawler)</String> |
||
11931 | <Description>ezPeer+ P2P IE addon</Description> |
||
11932 | <Type>B</Type> |
||
11933 | <Comment></Comment> |
||
11934 | <Link1>http://web.ezpeer.com/</Link1> |
||
11935 | <Link2></Link2> |
||
11936 | </user-agent> |
||
11937 | <user-agent> |
||
11938 | <ID>id_moz_881</ID> |
||
11939 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; IBP; .NET CLR 1.1.4322)</String> |
||
11940 | <Description>Axandra IBP website promotion software ?</Description> |
||
11941 | <Type>C B</Type> |
||
11942 | <Comment></Comment> |
||
11943 | <Link1>http://www.axandra-web-site-promotion-software-tool.com/index.htm</Link1> |
||
11944 | <Link2></Link2> |
||
11945 | </user-agent> |
||
11946 | <user-agent> |
||
11947 | <ID>id_moz_290606_3</ID> |
||
11948 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; MRA 4.3 (build 01218))</String> |
||
11949 | <Description>MRA = Mail.ru Agent - Instant Messenger / VoIP</Description> |
||
11950 | <Type>B</Type> |
||
11951 | <Comment></Comment> |
||
11952 | <Link1>http://agent.mail.ru/</Link1> |
||
11953 | <Link2></Link2> |
||
11954 | </user-agent> |
||
11955 | <user-agent> |
||
11956 | <ID>id_moz_883</ID> |
||
11957 | <String>Mozilla/4.0 (compatible; MSIE 6.0; Windows NT; MS Search 4.0 Robot)</String> |
||
11958 | <Description>MSN Search robot (207.46.89.xx)</Description> |
||
11959 | <Type>R</Type> |
||
11960 | <Comment>s. also: - MSNBOT</Comment> |
||
11961 | <Link1></Link1> |
||
11962 | <Link2></Link2> |
||
11963 | </user-agent> |
||
11964 | <user-agent> |
||
11965 | <ID>id_moz_170207_3</ID> |
||
11966 | <String>Mozilla/4.0 (compatible; MSIE 7.0; Win32) Link Commander 4.0</String> |
||
11967 | <Description>Link Commander bookmark manager</Description> |
||
11968 | <Type>C</Type> |
||
11969 | <Comment></Comment> |
||
11970 | <Link1>http://www.resortlabs.com/bookmark-manager/linkcommander.php</Link1> |
||
11971 | <Link2></Link2> |
||
11972 | </user-agent> |
||
11973 | <user-agent> |
||
11974 | <ID>id_moz_170706_2</ID> |
||
11975 | <String>Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; bgft)</String> |
||
11976 | <Description>IE 7.0 - WinXP</Description> |
||
11977 | <Type>B</Type> |
||
11978 | <Comment></Comment> |
||
11979 | <Link1>http://www.microsoft.com/windows/ie/default.mspx</Link1> |
||
11980 | <Link2></Link2> |
||
11981 | </user-agent> |
||
11982 | <user-agent> |
||
11983 | <ID>id_moz_080209_1</ID> |
||
11984 | <String>Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; GTB5; User-agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; http://bsalsa.com) ; .NET CLR 2.0.50727)</String> |
||
11985 | <Description>GTB = Google Toolbar Internet Explorer add-on</Description> |
||
11986 | <Type>B</Type> |
||
11987 | <Comment></Comment> |
||
11988 | <Link1>http://toolbar.google.com/T4/index.html</Link1> |
||
11989 | <Link2></Link2> |
||
11990 | </user-agent> |
||
11991 | <user-agent> |
||
11992 | <ID>id_moz_080209_2</ID> |
||
11993 | <String>Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; Tablet PC 2.0)</String> |
||
11994 | <Description>MSIE 7.0 *and* Trident token used by Internet Explorer 8 in compatibility view mode</Description> |
||
11995 | <Type>B</Type> |
||
11996 | <Comment></Comment> |
||
11997 | <Link1>http://blogs.msdn.com/ie/archive/2009/01/09/the-internet-explorer-8-user-agent-string-updated-edition.aspx</Link1> |
||
11998 | <Link2></Link2> |
||
11999 | </user-agent> |
||
12000 | <user-agent> |
||
12001 | <ID>id_moz_080209_3</ID> |
||
12002 | <String>Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 1.1.4322; .NET CLR 3.0.04506.30; .NET CLR 3.0.04506.648)</String> |
||
12003 | <Description>Internet Explorer 8</Description> |
||
12004 | <Type>B</Type> |
||
12005 | <Comment></Comment> |
||
12006 | <Link1>http://www.microsoft.com/windows/internet-explorer/beta/default.aspx</Link1> |
||
12007 | <Link2></Link2> |
||
12008 | </user-agent> |
||
12009 | <user-agent> |
||
12010 | <ID>id_moz_150408_4</ID> |
||
12011 | <String>Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0)</String> |
||
12012 | <Description>IE 8.0 (beta) on Win Vista</Description> |
||
12013 | <Type>B</Type> |
||
12014 | <Comment></Comment> |
||
12015 | <Link1>http://www.microsoft.com/windows/products/winfamily/ie/ie8/default.mspx</Link1> |
||
12016 | <Link2></Link2> |
||
12017 | </user-agent> |
||
12018 | <user-agent> |
||
12019 | <ID>id_moz_030110_1</ID> |
||
12020 | <String>Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; Orange 8.0; GTB6.3; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; Embedded Web Browser from: http://bsalsa.com/; SLCC1; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30618; OfficeLiveConnector.1.3; OfficeLivePatch.1.3)</String> |
||
12021 | <Description>Bsalsa embedded browser</Description> |
||
12022 | <Type>B</Type> |
||
12023 | <Comment></Comment> |
||
12024 | <Link1>http://bsalsa.com/</Link1> |
||
12025 | <Link2></Link2> |
||
12026 | </user-agent> |
||
12027 | <user-agent> |
||
12028 | <ID>id_moz_010108_4</ID> |
||
12029 | <String>Mozilla/4.0 (compatible; MSIE enviable; DAUMOA 2.0; DAUM Web Robot; Daum Communications Corp., Korea; +http://ws.daum.net/aboutkr.html)</String> |
||
12030 | <Description>DAUMOA - Daum search Korea robot (211.115.109.xxx)</Description> |
||
12031 | <Type>R</Type> |
||
12032 | <Comment>s. also RaBot</Comment> |
||
12033 | <Link1>http://www.daum.net/</Link1> |
||
12034 | <Link2>http://ws.daum.net/abouten.html</Link2> |
||
12035 | </user-agent> |
||
12036 | <user-agent> |
||
12037 | <ID>id_moz_311206_1</ID> |
||
12038 | <String>Mozilla/4.0 (compatible; MSIE is not me; DAUMOA/1.0.1; DAUM Web Robot; Daum Communications Corp., Korea)</String> |
||
12039 | <Description>DAUMOA - Daum search Korea robot (211.115.109.xxx)</Description> |
||
12040 | <Type>R</Type> |
||
12041 | <Comment>s. also RaBot</Comment> |
||
12042 | <Link1>http://www.daum.net/</Link1> |
||
12043 | <Link2></Link2> |
||
12044 | </user-agent> |
||
12045 | <user-agent> |
||
12046 | <ID>id_moz_281106_2</ID> |
||
12047 | <String>Mozilla/4.0 (compatible; NaverBot/1.0; http://help.naver.com/delete_main.asp)</String> |
||
12048 | <Description>Naver Search Korea Naverbot</Description> |
||
12049 | <Type>R</Type> |
||
12050 | <Comment></Comment> |
||
12051 | <Link1>http://www.naver.com/</Link1> |
||
12052 | <Link2></Link2> |
||
12053 | </user-agent> |
||
12054 | <user-agent> |
||
12055 | <ID>id_moz_884</ID> |
||
12056 | <String>Mozilla/4.0 (compatible; Netcraft Web Server Survey)</String> |
||
12057 | <Description>Netcraft webserver info</Description> |
||
12058 | <Type>R C</Type> |
||
12059 | <Comment></Comment> |
||
12060 | <Link1>http://www.netcraft.com</Link1> |
||
12061 | <Link2></Link2> |
||
12062 | </user-agent> |
||
12063 | <user-agent> |
||
12064 | <ID>id_moz_885</ID> |
||
12065 | <String>Mozilla/4.0 (compatible; NetPromoter Spider;http://www.net-promoter.com/)</String> |
||
12066 | <Description>NetPromoter Link Utility link checking tool </Description> |
||
12067 | <Type>C</Type> |
||
12068 | <Comment>s. also - Mozilla/4.0 (compatible; Link Utility ...</Comment> |
||
12069 | <Link1>http://www.net-promoter.com/</Link1> |
||
12070 | <Link2></Link2> |
||
12071 | </user-agent> |
||
12072 | <user-agent> |
||
12073 | <ID>id_moz_886</ID> |
||
12074 | <String>Mozilla/4.0 (compatible; Opera/3.0; Windows 4.10) 3.51 [en]</String> |
||
12075 | <Description>Opera 3.x WinNT</Description> |
||
12076 | <Type>B</Type> |
||
12077 | <Comment></Comment> |
||
12078 | <Link1></Link1> |
||
12079 | <Link2></Link2> |
||
12080 | </user-agent> |
||
12081 | <user-agent> |
||
12082 | <ID>id_moz_887</ID> |
||
12083 | <String>Mozilla/4.0 (compatible; Powermarks/3.5; Windows 95/98/2000/NT)</String> |
||
12084 | <Description>Powermarks bookmark manager</Description> |
||
12085 | <Type>C</Type> |
||
12086 | <Comment></Comment> |
||
12087 | <Link1>http://www.kaylon.com</Link1> |
||
12088 | <Link2></Link2> |
||
12089 | </user-agent> |
||
12090 | <user-agent> |
||
12091 | <ID>id_moz_230607_1</ID> |
||
12092 | <String>Mozilla/4.0 (compatible; RSS Popper)</String> |
||
12093 | <Description>RSS Popper - MS Outlook RSS reader plugin</Description> |
||
12094 | <Type>B</Type> |
||
12095 | <Comment></Comment> |
||
12096 | <Link1>http://rsspopper.unknown/2004/10/home.html</Link1> |
||
12097 | <Link2></Link2> |
||
12098 | </user-agent> |
||
12099 | <user-agent> |
||
12100 | <ID>id_moz_888</ID> |
||
12101 | <String>Mozilla/4.0 (compatible; SiteKiosk 4.0; MSIE 5.0; Windows 98; SiteCoach 1.0)</String> |
||
12102 | <Description>SiteKiosk public terminal browser</Description> |
||
12103 | <Type>B</Type> |
||
12104 | <Comment></Comment> |
||
12105 | <Link1>http://www.sitekiosk.com</Link1> |
||
12106 | <Link2></Link2> |
||
12107 | </user-agent> |
||
12108 | <user-agent> |
||
12109 | <ID>id_moz_889</ID> |
||
12110 | <String>Mozilla/4.0 (compatible; SpeedySpider; www.entireweb.com)</String> |
||
12111 | <Description>Entireweb Search Speedyspider (62.13.25.xxx)</Description> |
||
12112 | <Type>R</Type> |
||
12113 | <Comment>s. also Worldlight</Comment> |
||
12114 | <Link1>http://www.entireweb.com</Link1> |
||
12115 | <Link2></Link2> |
||
12116 | </user-agent> |
||
12117 | <user-agent> |
||
12118 | <ID>id_moz_890</ID> |
||
12119 | <String>Mozilla/4.0 (compatible; SPENG)</String> |
||
12120 | <Description>SiteProbe - website status checking</Description> |
||
12121 | <Type>R C</Type> |
||
12122 | <Comment></Comment> |
||
12123 | <Link1>http://www.siteprobe.com</Link1> |
||
12124 | <Link2></Link2> |
||
12125 | </user-agent> |
||
12126 | <user-agent> |
||
12127 | <ID>id_moz_891</ID> |
||
12128 | <String>Mozilla/4.0 (compatible; SuperCleaner 2.xx; Windows 98)</String> |
||
12129 | <Description>Super Cleaner privacy tool (bookmark checking)</Description> |
||
12130 | <Type>C</Type> |
||
12131 | <Comment></Comment> |
||
12132 | <Link1>http://www.southbaypc.com/SuperCleaner/</Link1> |
||
12133 | <Link2></Link2> |
||
12134 | </user-agent> |
||
12135 | <user-agent> |
||
12136 | <ID>id_moz_020406_1</ID> |
||
12137 | <String>Mozilla/4.0 (compatible; Synapse)</String> |
||
12138 | <Description>Synapse - Apache web service for processing XML documents</Description> |
||
12139 | <Type>P</Type> |
||
12140 | <Comment></Comment> |
||
12141 | <Link1>http://wiki.apache.org/incubator/SynapseProposal</Link1> |
||
12142 | <Link2></Link2> |
||
12143 | </user-agent> |
||
12144 | <user-agent> |
||
12145 | <ID>id_moz_150207_1</ID> |
||
12146 | <String>Mozilla/4.0 (compatible; WebCapture 3.0; Windows)</String> |
||
12147 | <Description>Web2PDF - Adobe Acrobat plugin for site traversal and other services for the Web Capture feature</Description> |
||
12148 | <Type>D</Type> |
||
12149 | <Comment></Comment> |
||
12150 | <Link1></Link1> |
||
12151 | <Link2></Link2> |
||
12152 | </user-agent> |
||
12153 | <user-agent> |
||
12154 | <ID>id_moz_892</ID> |
||
12155 | <String>Mozilla/4.0 (compatible; Win32; WinHttp.WinHttpRequest.5)</String> |
||
12156 | <Description>Windows HTTP Services (WinHTTP / XML-parser)</Description> |
||
12157 | <Type></Type> |
||
12158 | <Comment></Comment> |
||
12159 | <Link1></Link1> |
||
12160 | <Link2></Link2> |
||
12161 | </user-agent> |
||
12162 | <user-agent> |
||
12163 | <ID>id_moz_170108_1</ID> |
||
12164 | <String>Mozilla/4.0 (compatible; WSN Links)</String> |
||
12165 | <Description>WSN Links PHP directory software</Description> |
||
12166 | <Type>C</Type> |
||
12167 | <Comment></Comment> |
||
12168 | <Link1>http://scripts.webmastersite.net/wsnlinks/</Link1> |
||
12169 | <Link2></Link2> |
||
12170 | </user-agent> |
||
12171 | <user-agent> |
||
12172 | <ID>id_moz_111205_6</ID> |
||
12173 | <String>Mozilla/4.0 (compatible; www.euro-directory.com; urlchecker1.0)</String> |
||
12174 | <Description>Euro Directory (German / Austrian) directory link checking</Description> |
||
12175 | <Type>R C</Type> |
||
12176 | <Comment></Comment> |
||
12177 | <Link1>http://www.euro-directory.com/</Link1> |
||
12178 | <Link2></Link2> |
||
12179 | </user-agent> |
||
12180 | <user-agent> |
||
12181 | <ID>id_moz_893</ID> |
||
12182 | <String>Mozilla/4.0 (compatible; www.galaxy.com)</String> |
||
12183 | <Description>Galaxy robot</Description> |
||
12184 | <Type>R</Type> |
||
12185 | <Comment></Comment> |
||
12186 | <Link1>http://www.galaxy.com</Link1> |
||
12187 | <Link2></Link2> |
||
12188 | </user-agent> |
||
12189 | <user-agent> |
||
12190 | <ID>id_moz_894</ID> |
||
12191 | <String>Mozilla/4.0 (compatible; www.linkguard.com Linkguard Online 1.0; Windows NT)</String> |
||
12192 | <Description>Linkguard.com link validation (service is offline)</Description> |
||
12193 | <Type>C</Type> |
||
12194 | <Comment></Comment> |
||
12195 | <Link1></Link1> |
||
12196 | <Link2></Link2> |
||
12197 | </user-agent> |
||
12198 | <user-agent> |
||
12199 | <ID>id_moz_240106_1</ID> |
||
12200 | <String>Mozilla/4.0 (compatible; Y!J; for robot study; keyoshid)</String> |
||
12201 | <Description>Yahoo Search Japan robot (203.141.52.)</Description> |
||
12202 | <Type>R</Type> |
||
12203 | <Comment>s. also Y!J-BSC/1.0...</Comment> |
||
12204 | <Link1>http://www.yahoo.co.jp/</Link1> |
||
12205 | <Link2></Link2> |
||
12206 | </user-agent> |
||
12207 | <user-agent> |
||
12208 | <ID>id_moz_170706_1</ID> |
||
12209 | <String>Mozilla/4.0 (compatible; Yahoo Japan; for robot study; kasugiya)</String> |
||
12210 | <Description>Yahoo Japan robot (202.93.76.xx)</Description> |
||
12211 | <Type>R</Type> |
||
12212 | <Comment></Comment> |
||
12213 | <Link1>http://www.yahoo.co.jp/</Link1> |
||
12214 | <Link2></Link2> |
||
12215 | </user-agent> |
||
12216 | <user-agent> |
||
12217 | <ID>id_moz_210207_1</ID> |
||
12218 | <String>Mozilla/4.0 (compatible;MSIE 6.0; Windows NT 5.0; H010818)</String> |
||
12219 | <Description>Faked IE id string used by DeepTrawl link checking tool</Description> |
||
12220 | <Type>C</Type> |
||
12221 | <Comment></Comment> |
||
12222 | <Link1>http://deeptrawl.com/</Link1> |
||
12223 | <Link2></Link2> |
||
12224 | </user-agent> |
||
12225 | <user-agent> |
||
12226 | <ID>id_moz_896</ID> |
||
12227 | <String>Mozilla/4.0 (fantomBrowser)</String> |
||
12228 | <Description>spoofed referer by Fantomaster (Multiblocker) anonymity products</Description> |
||
12229 | <Type>P</Type> |
||
12230 | <Comment></Comment> |
||
12231 | <Link1>http://fantomaster.com</Link1> |
||
12232 | <Link2>http://multiblocker.com/home.html</Link2> |
||
12233 | </user-agent> |
||
12234 | <user-agent> |
||
12235 | <ID>id_moz_897</ID> |
||
12236 | <String>Mozilla/4.0 (fantomCrew Browser)</String> |
||
12237 | <Description>spoofed referer by Fantomaster (Multiblocker) anonymity products</Description> |
||
12238 | <Type>P</Type> |
||
12239 | <Comment></Comment> |
||
12240 | <Link1>http://fantomaster.com</Link1> |
||
12241 | <Link2>http://multiblocker.com/home.html</Link2> |
||
12242 | </user-agent> |
||
12243 | <user-agent> |
||
12244 | <ID>id_moz_898</ID> |
||
12245 | <String>Mozilla/4.0 (hhjhj@yahoo.com)</String> |
||
12246 | <Description>unknown robot from - 64.57.223.40 - 66.28.233.xxx (cogentco.com)</Description> |
||
12247 | <Type></Type> |
||
12248 | <Comment></Comment> |
||
12249 | <Link1></Link1> |
||
12250 | <Link2></Link2> |
||
12251 | </user-agent> |
||
12252 | <user-agent> |
||
12253 | <ID>id_moz_899</ID> |
||
12254 | <String>Mozilla/4.0 (JemmaTheTourist;http://www.activtourist.com)</String> |
||
12255 | <Description>Activtourist Jemma spider</Description> |
||
12256 | <Type>R</Type> |
||
12257 | <Comment></Comment> |
||
12258 | <Link1>http://www.activtourist.com</Link1> |
||
12259 | <Link2></Link2> |
||
12260 | </user-agent> |
||
12261 | <user-agent> |
||
12262 | <ID>id_moz_900</ID> |
||
12263 | <String>Mozilla/4.0 (MobilePhone PM-8200/US/1.0) NetFront/3.x MMP/2.0</String> |
||
12264 | <Description>NetFront (v3.x) for Pocket PC (here on Sanyo PM-8200 cell phone)</Description> |
||
12265 | <Type>B</Type> |
||
12266 | <Comment></Comment> |
||
12267 | <Link1>http://nfppc.access.co.jp/english/</Link1> |
||
12268 | <Link2></Link2> |
||
12269 | </user-agent> |
||
12270 | <user-agent> |
||
12271 | <ID>id_moz_901</ID> |
||
12272 | <String>Mozilla/4.0 (MobilePhone SCP-5500/US/1.0) NetFront/3.0 MMP/2.0 (compatible; Googlebot/2.1; http://www.google.com/bot.html)</String> |
||
12273 | <Description>Google robot from 66.249.66.xxx </Description> |
||
12274 | <Type>R</Type> |
||
12275 | <Comment>s. also: - Googlebot - Mozilla/5.0 (compatible; Googlebot/2.1...</Comment> |
||
12276 | <Link1>http://www.google.com</Link1> |
||
12277 | <Link2></Link2> |
||
12278 | </user-agent> |
||
12279 | <user-agent> |
||
12280 | <ID>id_moz_902</ID> |
||
12281 | <String>Mozilla/4.0 (MobilePhone SCP-5500/US/1.0) NetFront/3.0 MMP/2.0 FAKE (compatible; Googlebot/2.1; http://www.google.com/bot.html)</String> |
||
12282 | <Description>Google robot from 66.249.66.xxx </Description> |
||
12283 | <Type>R</Type> |
||
12284 | <Comment>s. also: - Googlebot - Mozilla/5.0 (compatible; Googlebot/2.1...</Comment> |
||
12285 | <Link1>http://www.google.com</Link1> |
||
12286 | <Link2></Link2> |
||
12287 | </user-agent> |
||
12288 | <user-agent> |
||
12289 | <ID>id_moz_081106_1</ID> |
||
12290 | <String>Mozilla/4.0 (Mozilla; http://www.mozilla.org/docs/en/bot.html; master@mozilla.com)</String> |
||
12291 | <Description>Unknown robot from Mozilla.org</Description> |
||
12292 | <Type>R</Type> |
||
12293 | <Comment>63.209.222.xx</Comment> |
||
12294 | <Link1>http://www.mozilla.org/</Link1> |
||
12295 | <Link2></Link2> |
||
12296 | </user-agent> |
||
12297 | <user-agent> |
||
12298 | <ID>id_moz_903</ID> |
||
12299 | <String>Mozilla/4.0 (Sleek Spider/1.2)</String> |
||
12300 | <Description>ASI - Any Search Info robot</Description> |
||
12301 | <Type>R</Type> |
||
12302 | <Comment></Comment> |
||
12303 | <Link1>http://search-info.com/</Link1> |
||
12304 | <Link2></Link2> |
||
12305 | </user-agent> |
||
12306 | <user-agent> |
||
12307 | <ID>id_moz_170406_1</ID> |
||
12308 | <String>Mozilla/4.0 compatible FurlBot/Furl Search 2.0 (FurlBot; http://www.furl.net; wn.furlbot@looksmart.net)</String> |
||
12309 | <Description>Furl (Looksmart) online bookmark tool robot</Description> |
||
12310 | <Type>R</Type> |
||
12311 | <Comment>64.242.88.xx</Comment> |
||
12312 | <Link1>http://www.furl.net/</Link1> |
||
12313 | <Link2></Link2> |
||
12314 | </user-agent> |
||
12315 | <user-agent> |
||
12316 | <ID>id_moz_905</ID> |
||
12317 | <String>Mozilla/4.0 compatible ZyBorg/1.0 (wn.zyborg@looksmart.net; http://www.WISEnutbot.com)</String> |
||
12318 | <Description>Wisenut robot</Description> |
||
12319 | <Type>R</Type> |
||
12320 | <Comment></Comment> |
||
12321 | <Link1>http://www.wisenut.com/</Link1> |
||
12322 | <Link2></Link2> |
||
12323 | </user-agent> |
||
12324 | <user-agent> |
||
12325 | <ID>id_moz_906</ID> |
||
12326 | <String>Mozilla/4.0 compatible ZyBorg/1.0 (ZyBorg@WISEnutbot.com; http://www.WISEnutbot.com)</String> |
||
12327 | <Description>Wisenut robot</Description> |
||
12328 | <Type>R</Type> |
||
12329 | <Comment></Comment> |
||
12330 | <Link1>http://www.wisenut.com/</Link1> |
||
12331 | <Link2></Link2> |
||
12332 | </user-agent> |
||
12333 | <user-agent> |
||
12334 | <ID>id_moz_907</ID> |
||
12335 | <String>Mozilla/4.0 compatible ZyBorg/1.0 Dead Link Checker (wn.zyborg@looksmart.net; http://www.WISEnutbot.com)</String> |
||
12336 | <Description>Wisenut robot</Description> |
||
12337 | <Type>R</Type> |
||
12338 | <Comment></Comment> |
||
12339 | <Link1>http://www.wisenut.com/</Link1> |
||
12340 | <Link2></Link2> |
||
12341 | </user-agent> |
||
12342 | <user-agent> |
||
12343 | <ID>id_moz_908</ID> |
||
12344 | <String>Mozilla/4.0 compatible ZyBorg/1.0 for Homepage (ZyBorg@WISEnutbot.com; http://www.WISEnutbot.com)</String> |
||
12345 | <Description>Wisenut robot</Description> |
||
12346 | <Type>R</Type> |
||
12347 | <Comment></Comment> |
||
12348 | <Link1>http://www.wisenut.com/</Link1> |
||
12349 | <Link2></Link2> |
||
12350 | </user-agent> |
||
12351 | <user-agent> |
||
12352 | <ID>id_moz_909</ID> |
||
12353 | <String>Mozilla/4.0 efp@gmx.net</String> |
||
12354 | <Description>Unknown robot from 66.230.140.xx (argon.oxeo.com) maybe an e-mail collector</Description> |
||
12355 | <Type>S</Type> |
||
12356 | <Comment>see also LARBIN-EXPERIMENTAL</Comment> |
||
12357 | <Link1></Link1> |
||
12358 | <Link2></Link2> |
||
12359 | </user-agent> |
||
12360 | <user-agent> |
||
12361 | <ID>id_moz_910</ID> |
||
12362 | <String>Mozilla/4.0 WebTV/2.6 (compatible; MSIE 4.0)</String> |
||
12363 | <Description>WebTV</Description> |
||
12364 | <Type>B</Type> |
||
12365 | <Comment></Comment> |
||
12366 | <Link1></Link1> |
||
12367 | <Link2></Link2> |
||
12368 | </user-agent> |
||
12369 | <user-agent> |
||
12370 | <ID>id_moz_904</ID> |
||
12371 | <String>Mozilla/4.0 [en] (Ask Jeeves Corporate Spider)</String> |
||
12372 | <Description>Ask / Ask Jeeves robot</Description> |
||
12373 | <Type>R</Type> |
||
12374 | <Comment></Comment> |
||
12375 | <Link1>http://www.Ask.com</Link1> |
||
12376 | <Link2></Link2> |
||
12377 | </user-agent> |
||
12378 | <user-agent> |
||
12379 | <ID>id_moz_913</ID> |
||
12380 | <String>Mozilla/4.0(compatible; Zealbot 1.0)</String> |
||
12381 | <Description>LookSmart spider</Description> |
||
12382 | <Type>R</Type> |
||
12383 | <Comment></Comment> |
||
12384 | <Link1>http://www.looksmart.com</Link1> |
||
12385 | <Link2></Link2> |
||
12386 | </user-agent> |
||
12387 | <user-agent> |
||
12388 | <ID>id_moz_290807_1</ID> |
||
12389 | <String>Mozilla/4.01 (compatible; NORAD National Defence Network)</String> |
||
12390 | <Description>HideMe - Web based anonymous proxy server service</Description> |
||
12391 | <Type>P</Type> |
||
12392 | <Comment></Comment> |
||
12393 | <Link1>http://www.hideme.biz/</Link1> |
||
12394 | <Link2>http://www.cnn.com/TECH/computing/9901/25/hacktracts.idg/index.html</Link2> |
||
12395 | </user-agent> |
||
12396 | <user-agent> |
||
12397 | <ID>id_moz_914</ID> |
||
12398 | <String>Mozilla/4.01 [en](Win95;I)</String> |
||
12399 | <Description>Some download manager spoofing Netscape 4.01</Description> |
||
12400 | <Type>D</Type> |
||
12401 | <Comment></Comment> |
||
12402 | <Link1></Link1> |
||
12403 | <Link2></Link2> |
||
12404 | </user-agent> |
||
12405 | <user-agent> |
||
12406 | <ID>id_moz_915</ID> |
||
12407 | <String>Mozilla/4.02 [en] (X11; I; SunOS 5.6 sun4u)</String> |
||
12408 | <Description>Netscape 4.x SunOS 5.6</Description> |
||
12409 | <Type>B</Type> |
||
12410 | <Comment></Comment> |
||
12411 | <Link1></Link1> |
||
12412 | <Link2></Link2> |
||
12413 | </user-agent> |
||
12414 | <user-agent> |
||
12415 | <ID>id_moz_161105_3</ID> |
||
12416 | <String>Mozilla/4.04 (compatible; Dulance bot; +http://www.dulance.com/bot.jsp)</String> |
||
12417 | <Description>Dulance Bot - Dulance automated price comparison engine</Description> |
||
12418 | <Type>R</Type> |
||
12419 | <Comment></Comment> |
||
12420 | <Link1>http://www.dulance.com/</Link1> |
||
12421 | <Link2></Link2> |
||
12422 | </user-agent> |
||
12423 | <user-agent> |
||
12424 | <ID>id_moz_916</ID> |
||
12425 | <String>Mozilla/4.04 [en] (X11; I; HP-UX B.10.20 9000/712)</String> |
||
12426 | <Description>Netscape 4.x HP-Unix</Description> |
||
12427 | <Type>B</Type> |
||
12428 | <Comment></Comment> |
||
12429 | <Link1></Link1> |
||
12430 | <Link2></Link2> |
||
12431 | </user-agent> |
||
12432 | <user-agent> |
||
12433 | <ID>id_moz_917</ID> |
||
12434 | <String>Mozilla/4.04 [en] (X11; I; IRIX 5.3 IP22)</String> |
||
12435 | <Description>Netscape 4.x IRIX</Description> |
||
12436 | <Type>B</Type> |
||
12437 | <Comment></Comment> |
||
12438 | <Link1></Link1> |
||
12439 | <Link2></Link2> |
||
12440 | </user-agent> |
||
12441 | <user-agent> |
||
12442 | <ID>id_moz_918</ID> |
||
12443 | <String>Mozilla/4.05 (Macintosh; I; 68K Nav)</String> |
||
12444 | <Description>Netscape 4.x Macintosh 68k</Description> |
||
12445 | <Type>B</Type> |
||
12446 | <Comment></Comment> |
||
12447 | <Link1></Link1> |
||
12448 | <Link2></Link2> |
||
12449 | </user-agent> |
||
12450 | <user-agent> |
||
12451 | <ID>id_moz_919</ID> |
||
12452 | <String>Mozilla/4.05 (Macintosh; I; PPC Nav)</String> |
||
12453 | <Description>Netscape 4.x Macintosh PowerPC</Description> |
||
12454 | <Type>B</Type> |
||
12455 | <Comment></Comment> |
||
12456 | <Link1></Link1> |
||
12457 | <Link2></Link2> |
||
12458 | </user-agent> |
||
12459 | <user-agent> |
||
12460 | <ID>id_moz_920</ID> |
||
12461 | <String>Mozilla/4.05 [en] (X11; I; SunOS 4.1.4 sun4m)</String> |
||
12462 | <Description>Netscape 4.x SunOS 4.1.4</Description> |
||
12463 | <Type>B</Type> |
||
12464 | <Comment></Comment> |
||
12465 | <Link1></Link1> |
||
12466 | <Link2></Link2> |
||
12467 | </user-agent> |
||
12468 | <user-agent> |
||
12469 | <ID>id_moz_921</ID> |
||
12470 | <String>Mozilla/4.08 [en] (Win98; U ;Nav)</String> |
||
12471 | <Description>Version 4.08 [en]-98306</Description> |
||
12472 | <Type>Someone copied the help function in the referrer field ?</Type> |
||
12473 | <Comment></Comment> |
||
12474 | <Link1></Link1> |
||
12475 | <Link2></Link2> |
||
12476 | </user-agent> |
||
12477 | <user-agent> |
||
12478 | <ID>id_moz_922</ID> |
||
12479 | <String>Mozilla/4.08 [en] (WinNT; U)</String> |
||
12480 | <Description>Netscape 4.x WinNT</Description> |
||
12481 | <Type>B</Type> |
||
12482 | <Comment></Comment> |
||
12483 | <Link1></Link1> |
||
12484 | <Link2></Link2> |
||
12485 | </user-agent> |
||
12486 | <user-agent> |
||
12487 | <ID>id_moz_911</ID> |
||
12488 | <String>Mozilla/4.0_(compatible;_MSIE_5.0;_Windows_95)_TrueRobot/1.4 libwww/5.2.8</String> |
||
12489 | <Description>Echo.com robot</Description> |
||
12490 | <Type>R</Type> |
||
12491 | <Comment></Comment> |
||
12492 | <Link1>http://www.echo.com</Link1> |
||
12493 | <Link2></Link2> |
||
12494 | </user-agent> |
||
12495 | <user-agent> |
||
12496 | <ID>id_moz_912</ID> |
||
12497 | <String>Mozilla/4.0_(compatible;_MSIE_5.0;_Windows_95)_VoilaBot/1.6 libwww/5.3.2</String> |
||
12498 | <Description>Voila.fr robot</Description> |
||
12499 | <Type>R</Type> |
||
12500 | <Comment></Comment> |
||
12501 | <Link1>http://www.voila.fr</Link1> |
||
12502 | <Link2></Link2> |
||
12503 | </user-agent> |
||
12504 | <user-agent> |
||
12505 | <ID>id_moz_923</ID> |
||
12506 | <String>Mozilla/4.5 (compatible; HTTrack 3.0x; Windows 98)</String> |
||
12507 | <Description>HTTrack Offline Browser</Description> |
||
12508 | <Type>B D</Type> |
||
12509 | <Comment></Comment> |
||
12510 | <Link1>http://www.httrack.com/</Link1> |
||
12511 | <Link2></Link2> |
||
12512 | </user-agent> |
||
12513 | <user-agent> |
||
12514 | <ID>id_moz_924</ID> |
||
12515 | <String>Mozilla/4.5 (compatible; iCab 2.5.3; Macintosh; I; PPC)</String> |
||
12516 | <Description>iCab MAC Web browser MAC Power PC</Description> |
||
12517 | <Type>B</Type> |
||
12518 | <Comment></Comment> |
||
12519 | <Link1>http://www.icab.de</Link1> |
||
12520 | <Link2></Link2> |
||
12521 | </user-agent> |
||
12522 | <user-agent> |
||
12523 | <ID>id_moz_925</ID> |
||
12524 | <String>Mozilla/4.5 (compatible; OmniWeb/4.0.5; Mac_PowerPC)</String> |
||
12525 | <Description>OmniWeb 4.x.x Mac browser</Description> |
||
12526 | <Type>B</Type> |
||
12527 | <Comment></Comment> |
||
12528 | <Link1>http://www.omnigroup.com</Link1> |
||
12529 | <Link2></Link2> |
||
12530 | </user-agent> |
||
12531 | <user-agent> |
||
12532 | <ID>id_moz_926</ID> |
||
12533 | <String>Mozilla/4.5 (compatible; OmniWeb/4.1-beta-1; Mac_PowerPC)</String> |
||
12534 | <Description>OmniWeb 4.x.x Mac browser</Description> |
||
12535 | <Type>B</Type> |
||
12536 | <Comment></Comment> |
||
12537 | <Link1>http://www.omnigroup.com</Link1> |
||
12538 | <Link2></Link2> |
||
12539 | </user-agent> |
||
12540 | <user-agent> |
||
12541 | <ID>id_moz_928</ID> |
||
12542 | <String>Mozilla/4.5 RPT-HTTPClient/0.3-2</String> |
||
12543 | <Description>different IPs using the HTTPClient library (mostly link checking)</Description> |
||
12544 | <Type>C R</Type> |
||
12545 | <Comment></Comment> |
||
12546 | <Link1>http://www.innovation.ch</Link1> |
||
12547 | <Link2></Link2> |
||
12548 | </user-agent> |
||
12549 | <user-agent> |
||
12550 | <ID>id_moz_927</ID> |
||
12551 | <String>Mozilla/4.5 [en]C-CCK-MCD {RuralNet} (Win98; I)</String> |
||
12552 | <Description>RuralNet Internet Services</Description> |
||
12553 | <Type>B</Type> |
||
12554 | <Comment></Comment> |
||
12555 | <Link1>http://www.ruralnet.net.au</Link1> |
||
12556 | <Link2></Link2> |
||
12557 | </user-agent> |
||
12558 | <user-agent> |
||
12559 | <ID>id_moz_929</ID> |
||
12560 | <String>Mozilla/4.5b1 [en] (X11; I; Linux 2.0.35 i586)</String> |
||
12561 | <Description>Netscape 4.x Linux</Description> |
||
12562 | <Type>B</Type> |
||
12563 | <Comment></Comment> |
||
12564 | <Link1></Link1> |
||
12565 | <Link2></Link2> |
||
12566 | </user-agent> |
||
12567 | <user-agent> |
||
12568 | <ID>id_moz_301105_3</ID> |
||
12569 | <String>Mozilla/4.6 [en] (http://www.cnet.com/)</String> |
||
12570 | <Description>Cnet robot for Search.com (216.239.114.xx)</Description> |
||
12571 | <Type>R</Type> |
||
12572 | <Comment></Comment> |
||
12573 | <Link1>http://www.search.com/</Link1> |
||
12574 | <Link2>http://www.cnet.com/</Link2> |
||
12575 | </user-agent> |
||
12576 | <user-agent> |
||
12577 | <ID>id_moz_930</ID> |
||
12578 | <String>Mozilla/4.61 [de] (OS/2; I)</String> |
||
12579 | <Description>Netscape 4.x OS/2</Description> |
||
12580 | <Type>B</Type> |
||
12581 | <Comment></Comment> |
||
12582 | <Link1></Link1> |
||
12583 | <Link2></Link2> |
||
12584 | </user-agent> |
||
12585 | <user-agent> |
||
12586 | <ID>id_moz_931</ID> |
||
12587 | <String>Mozilla/4.61 [en] (X11; U; ) - BrowseX (2.0.0 Windows)</String> |
||
12588 | <Description>BrowseX cross-platform browser</Description> |
||
12589 | <Type>B</Type> |
||
12590 | <Comment></Comment> |
||
12591 | <Link1>http://browsex.com/</Link1> |
||
12592 | <Link2></Link2> |
||
12593 | </user-agent> |
||
12594 | <user-agent> |
||
12595 | <ID>id_moz_932</ID> |
||
12596 | <String>Mozilla/4.7</String> |
||
12597 | <Description>Nameprotect (12.148.196.128 - 12.148.196.255) snoopbot</Description> |
||
12598 | <Type>R</Type> |
||
12599 | <Comment></Comment> |
||
12600 | <Link1>http://www.nameprotect.com</Link1> |
||
12601 | <Link2></Link2> |
||
12602 | </user-agent> |
||
12603 | <user-agent> |
||
12604 | <ID>id_moz_933</ID> |
||
12605 | <String>Mozilla/4.7 (compatible; http://eidetica.com/spider)</String> |
||
12606 | <Description>Eidetica earch and text mining spider</Description> |
||
12607 | <Type>R</Type> |
||
12608 | <Comment></Comment> |
||
12609 | <Link1>http://eidetica.com/</Link1> |
||
12610 | <Link2></Link2> |
||
12611 | </user-agent> |
||
12612 | <user-agent> |
||
12613 | <ID>id_moz_934</ID> |
||
12614 | <String>Mozilla/4.7 (compatible; Intelliseek; http://www.intelliseek.com)</String> |
||
12615 | <Description>Intelliseek (64.158.138.xx) robot</Description> |
||
12616 | <Type>R</Type> |
||
12617 | <Comment></Comment> |
||
12618 | <Link1>http://www.intelliseek.com</Link1> |
||
12619 | <Link2></Link2> |
||
12620 | </user-agent> |
||
12621 | <user-agent> |
||
12622 | <ID>id_moz_935</ID> |
||
12623 | <String>Mozilla/4.7 (compatible; OffByOne; Windows 98) Webster Pro V3.2</String> |
||
12624 | <Description>OffByOne Browser</Description> |
||
12625 | <Type>B</Type> |
||
12626 | <Comment></Comment> |
||
12627 | <Link1>http://www.offbyone.com</Link1> |
||
12628 | <Link2></Link2> |
||
12629 | </user-agent> |
||
12630 | <user-agent> |
||
12631 | <ID>id_moz_937</ID> |
||
12632 | <String>Mozilla/4.7 (compatible; Whizbang)</String> |
||
12633 | <Description>WhizBang! Labs information extraction robot</Description> |
||
12634 | <Type>R</Type> |
||
12635 | <Comment>closed since May 2002</Comment> |
||
12636 | <Link1>http://www.whizbang.com</Link1> |
||
12637 | <Link2></Link2> |
||
12638 | </user-agent> |
||
12639 | <user-agent> |
||
12640 | <ID>id_moz_936</ID> |
||
12641 | <String>Mozilla/4.7 (compatible; WhizBang; http://www.whizbang.com/crawler)</String> |
||
12642 | <Description>WhizBang! Labs information extraction robot</Description> |
||
12643 | <Type>R</Type> |
||
12644 | <Comment>closed since May 2002</Comment> |
||
12645 | <Link1>http://www.whizbang.com</Link1> |
||
12646 | <Link2></Link2> |
||
12647 | </user-agent> |
||
12648 | <user-agent> |
||
12649 | <ID>id_moz_938</ID> |
||
12650 | <String>Mozilla/4.7 [en](BecomeBot@exava.com)</String> |
||
12651 | <Description>BecomeBot - Becomecom shopping search (64.124.85.xx(x))</Description> |
||
12652 | <Type>R</Type> |
||
12653 | <Comment>64.124.85.[x]xx</Comment> |
||
12654 | <Link1>http://www.become.com</Link1> |
||
12655 | <Link2></Link2> |
||
12656 | </user-agent> |
||
12657 | <user-agent> |
||
12658 | <ID>id_moz_939</ID> |
||
12659 | <String>Mozilla/4.7 [en](Exabot@exava.com)</String> |
||
12660 | <Description>Exabot - exava shopping search (64.124.85.xx(x))</Description> |
||
12661 | <Type>R</Type> |
||
12662 | <Comment></Comment> |
||
12663 | <Link1>http://www.exava.com</Link1> |
||
12664 | <Link2></Link2> |
||
12665 | </user-agent> |
||
12666 | <user-agent> |
||
12667 | <ID>id_moz_940</ID> |
||
12668 | <String>Mozilla/4.7 [en]C-CCK-MCD {Yahoo;YIP052400} (Win95; I)</String> |
||
12669 | <Description>unknown</Description> |
||
12670 | <Type></Type> |
||
12671 | <Comment></Comment> |
||
12672 | <Link1></Link1> |
||
12673 | <Link2></Link2> |
||
12674 | </user-agent> |
||
12675 | <user-agent> |
||
12676 | <ID>id_moz_941</ID> |
||
12677 | <String>Mozilla/4.72 [en] (BACS http://www.ba.be)</String> |
||
12678 | <Description>http://www.ba.be robot</Description> |
||
12679 | <Type>R</Type> |
||
12680 | <Comment></Comment> |
||
12681 | <Link1>http://www.ba.be</Link1> |
||
12682 | <Link2></Link2> |
||
12683 | </user-agent> |
||
12684 | <user-agent> |
||
12685 | <ID>id_moz_942</ID> |
||
12686 | <String>Mozilla/4.72C-CCK-MCD Caldera Systems OpenLinux [en] (X11; U; Linux 2.2.14 i686)</String> |
||
12687 | <Description>Netscpape 4.7x Caldera Open Linux Pentium III</Description> |
||
12688 | <Type>B</Type> |
||
12689 | <Comment></Comment> |
||
12690 | <Link1></Link1> |
||
12691 | <Link2></Link2> |
||
12692 | </user-agent> |
||
12693 | <user-agent> |
||
12694 | <ID>id_moz_943</ID> |
||
12695 | <String>Mozilla/4.75C-ja [ja] (X11; U; OSF1 V5.1 alpha)</String> |
||
12696 | <Description>Netscape 4.7x Japan OSF1 alpha</Description> |
||
12697 | <Type>B</Type> |
||
12698 | <Comment></Comment> |
||
12699 | <Link1></Link1> |
||
12700 | <Link2></Link2> |
||
12701 | </user-agent> |
||
12702 | <user-agent> |
||
12703 | <ID>id_moz_944</ID> |
||
12704 | <String>Mozilla/4.76 (Windows 98; U) Opera 5.12 [en]</String> |
||
12705 | <Description>Opera 5.x Win 98</Description> |
||
12706 | <Type>B</Type> |
||
12707 | <Comment></Comment> |
||
12708 | <Link1></Link1> |
||
12709 | <Link2></Link2> |
||
12710 | </user-agent> |
||
12711 | <user-agent> |
||
12712 | <ID>id_moz_945</ID> |
||
12713 | <String>Mozilla/4.76 [en] (X11; U; FreeBSD 4.4-STABLE i386)</String> |
||
12714 | <Description>Netscape 4.7x FreeBSD</Description> |
||
12715 | <Type>B</Type> |
||
12716 | <Comment></Comment> |
||
12717 | <Link1></Link1> |
||
12718 | <Link2></Link2> |
||
12719 | </user-agent> |
||
12720 | <user-agent> |
||
12721 | <ID>id_moz_946</ID> |
||
12722 | <String>Mozilla/4.76 [en] (X11; U; SunOS 5.7 sun4u)</String> |
||
12723 | <Description>Netscape 4.7x SunOS</Description> |
||
12724 | <Type>B</Type> |
||
12725 | <Comment></Comment> |
||
12726 | <Link1></Link1> |
||
12727 | <Link2></Link2> |
||
12728 | </user-agent> |
||
12729 | <user-agent> |
||
12730 | <ID>id_moz_947</ID> |
||
12731 | <String>Mozilla/4.77C-SGI [en] (X11; U; IRIX 6.5 IP32)</String> |
||
12732 | <Description>IRIX 6.5</Description> |
||
12733 | <Type>B</Type> |
||
12734 | <Comment></Comment> |
||
12735 | <Link1></Link1> |
||
12736 | <Link2></Link2> |
||
12737 | </user-agent> |
||
12738 | <user-agent> |
||
12739 | <ID>id_moz_948</ID> |
||
12740 | <String>Mozilla/5.0</String> |
||
12741 | <Description>GigaMedia / NTT DoCoMo robot</Description> |
||
12742 | <Type>R</Type> |
||
12743 | <Comment></Comment> |
||
12744 | <Link1>http://ir.giga.net.tw/products.htm</Link1> |
||
12745 | <Link2></Link2> |
||
12746 | </user-agent> |
||
12747 | <user-agent> |
||
12748 | <ID>id_moz_040707_3</ID> |
||
12749 | <String>Mozilla/5.0 (+http://www.eurekster.com/mammoth) Mammoth/0.1</String> |
||
12750 | <Description>Eurekster Swicki community search using SLI-Systems site search engine Mammoth</Description> |
||
12751 | <Type>R</Type> |
||
12752 | <Comment>64.106.253.1xx</Comment> |
||
12753 | <Link1>http://www.eurekster.com/</Link1> |
||
12754 | <Link2>http://www.sli-systems.com/</Link2> |
||
12755 | </user-agent> |
||
12756 | <user-agent> |
||
12757 | <ID>id_moz_240306_2</ID> |
||
12758 | <String>Mozilla/5.0 (+http://www.sli-systems.com/) Mammoth/0.1</String> |
||
12759 | <Description>SLI Systems mammoth robot</Description> |
||
12760 | <Type>R</Type> |
||
12761 | <Comment>s. also mammoth/1.0 ...</Comment> |
||
12762 | <Link1>http://www.sli-systems.com/</Link1> |
||
12763 | <Link2>http://www.tenspider.com/business-blog/more.php?id=A45_0_1_0_M</Link2> |
||
12764 | </user-agent> |
||
12765 | <user-agent> |
||
12766 | <ID>id_moz_949</ID> |
||
12767 | <String>Mozilla/5.0 (Clustered-Search-Bot/1.0; support@clush.com; http://www.clush.com/)</String> |
||
12768 | <Description>Clush search robot</Description> |
||
12769 | <Type>R</Type> |
||
12770 | <Comment></Comment> |
||
12771 | <Link1>http://www.clush.com</Link1> |
||
12772 | <Link2></Link2> |
||
12773 | </user-agent> |
||
12774 | <user-agent> |
||
12775 | <ID>id_moz_020807_1</ID> |
||
12776 | <String>Mozilla/5.0 (compatible) GM RSS Panel X</String> |
||
12777 | <Description>Greasemonkey RSS panel Firefox plugin</Description> |
||
12778 | <Type>B</Type> |
||
12779 | <Comment></Comment> |
||
12780 | <Link1>http://www.xs4all.nl/~jlpoutre/BoT/Javascript/RSSpanel/</Link1> |
||
12781 | <Link2></Link2> |
||
12782 | </user-agent> |
||
12783 | <user-agent> |
||
12784 | <ID>id_moz_140209_3</ID> |
||
12785 | <String>Mozilla/5.0 (compatible; +http://www.evri.com/evrinid)</String> |
||
12786 | <Description>Evri search robot</Description> |
||
12787 | <Type>R</Type> |
||
12788 | <Comment>216.168.43.1xx</Comment> |
||
12789 | <Link1>http://www.evri.com/</Link1> |
||
12790 | <Link2></Link2> |
||
12791 | </user-agent> |
||
12792 | <user-agent> |
||
12793 | <ID>id_new_250310_1</ID> |
||
12794 | <String>Mozilla/5.0 (compatible; 008/0.83; http://www.80legs.com/spider.html;) Gecko/2008032620</String> |
||
12795 | <Description>008 distributed crawler for 80legs</Description> |
||
12796 | <Type>R</Type> |
||
12797 | <Comment></Comment> |
||
12798 | <Link1>http://www.80legs.com/spider.html</Link1> |
||
12799 | <Link2></Link2> |
||
12800 | </user-agent> |
||
12801 | <user-agent> |
||
12802 | <ID>id_moz_140209_4</ID> |
||
12803 | <String>Mozilla/5.0 (compatible; Abonti/0.8 - http://www.abonti.com)</String> |
||
12804 | <Description>Abonti WebSearch beta robot</Description> |
||
12805 | <Type>R</Type> |
||
12806 | <Comment>77.233.225.11x</Comment> |
||
12807 | <Link1>http://www.abonti.com/</Link1> |
||
12808 | <Link2></Link2> |
||
12809 | </user-agent> |
||
12810 | <user-agent> |
||
12811 | <ID>id_moz_030110_4</ID> |
||
12812 | <String>Mozilla/5.0 (compatible; aiHitBot/1.0; +http://www.aihit.com/)</String> |
||
12813 | <Description>HitCompanies Aihit crawler</Description> |
||
12814 | <Type>R</Type> |
||
12815 | <Comment>195.128.18.xx</Comment> |
||
12816 | <Link1>http://hitcompanies.aihit.com/search.htm</Link1> |
||
12817 | <Link2></Link2> |
||
12818 | </user-agent> |
||
12819 | <user-agent> |
||
12820 | <ID>id_moz_300406_1</ID> |
||
12821 | <String>Mozilla/5.0 (compatible; AnsearchBot/1.x; +http://www.ansearch.com.au/)</String> |
||
12822 | <Description>Ansearch Australian search robot</Description> |
||
12823 | <Type>R</Type> |
||
12824 | <Comment>203.206.162.x</Comment> |
||
12825 | <Link1>http://www.ansearch.com.au/</Link1> |
||
12826 | <Link2></Link2> |
||
12827 | </user-agent> |
||
12828 | <user-agent> |
||
12829 | <ID>id_moz_011107_1</ID> |
||
12830 | <String>Mozilla/5.0 (compatible; archive.org_bot/1.10.0 +http://www.loc.gov/minerva/crawl.html)</String> |
||
12831 | <Description>The Library of Congress Minerva crawler</Description> |
||
12832 | <Type>R</Type> |
||
12833 | <Comment>207.241.232.1xx</Comment> |
||
12834 | <Link1>http://www.loc.gov/minerva/crawl.html</Link1> |
||
12835 | <Link2></Link2> |
||
12836 | </user-agent> |
||
12837 | <user-agent> |
||
12838 | <ID>id_moz_230607_2</ID> |
||
12839 | <String>Mozilla/5.0 (compatible; archive.org_bot/1.13.1x http://crawler.archive.org)</String> |
||
12840 | <Description>Heritrix - The Internet Archive's open-source crawler (207.241.225.2xx)</Description> |
||
12841 | <Type>R</Type> |
||
12842 | <Comment>s.also - InternetArchive/0.8-dev - Mozilla/5.0 (compatible;archive.org_bot/...</Comment> |
||
12843 | <Link1>http://www.archive.org/</Link1> |
||
12844 | <Link2></Link2> |
||
12845 | </user-agent> |
||
12846 | <user-agent> |
||
12847 | <ID>id_moz_141105_1</ID> |
||
12848 | <String>Mozilla/5.0 (compatible; archive.org_bot/1.5.0-200506132127 http://crawler.archive.org) Hurricane Katrina</String> |
||
12849 | <Description>Heritrix - The Internet Archive's open-source crawler</Description> |
||
12850 | <Type>R</Type> |
||
12851 | <Comment>s. also - InternetArchive/0.8-dev... - mozilla/5.0 (compatible; heritrix/...</Comment> |
||
12852 | <Link1>http://www.archive.org/</Link1> |
||
12853 | <Link2></Link2> |
||
12854 | </user-agent> |
||
12855 | <user-agent> |
||
12856 | <ID>id_moz_150207_2</ID> |
||
12857 | <String>Mozilla/5.0 (compatible; Ask Jeeves/Teoma; http://about.ask.com/en/docs/about/webmasters.shtml)</String> |
||
12858 | <Description>Ask Jeeves /Teoma robot</Description> |
||
12859 | <Type>R</Type> |
||
12860 | <Comment> 65.214.45.[x]xx</Comment> |
||
12861 | <Link1>http://sp.ask.com</Link1> |
||
12862 | <Link2></Link2> |
||
12863 | </user-agent> |
||
12864 | <user-agent> |
||
12865 | <ID>id_moz_291205_2</ID> |
||
12866 | <String>Mozilla/5.0 (compatible; BanBots/2.0b; Fetch; +http://www.banbots.com)</String> |
||
12867 | <Description>Project BanBots Perl script robot</Description> |
||
12868 | <Type>C</Type> |
||
12869 | <Comment>s. also BanBots/1.2...</Comment> |
||
12870 | <Link1>http://www.banbots.com/</Link1> |
||
12871 | <Link2></Link2> |
||
12872 | </user-agent> |
||
12873 | <user-agent> |
||
12874 | <ID>id_moz_950</ID> |
||
12875 | <String>Mozilla/5.0 (compatible; BecomeBot/1.23; http://www.become.com/webmasters.html)</String> |
||
12876 | <Description>BecomeBot - Become.com shopping search (64.124.85.xx(x))</Description> |
||
12877 | <Type>R</Type> |
||
12878 | <Comment>64.124.85.[x]xx</Comment> |
||
12879 | <Link1>http://www.become.com</Link1> |
||
12880 | <Link2></Link2> |
||
12881 | </user-agent> |
||
12882 | <user-agent> |
||
12883 | <ID>id_moz_951</ID> |
||
12884 | <String>Mozilla/5.0 (compatible; BecomeBot/1.xx; MSIE 6.0 compatible; http://www.become.com/webmasters.html)</String> |
||
12885 | <Description>BecomeBot - Become.com shopping search (64.124.85.xx(x))</Description> |
||
12886 | <Type>R</Type> |
||
12887 | <Comment>64.124.85.[x]xx</Comment> |
||
12888 | <Link1>http://www.become.com</Link1> |
||
12889 | <Link2></Link2> |
||
12890 | </user-agent> |
||
12891 | <user-agent> |
||
12892 | <ID>id_moz_952</ID> |
||
12893 | <String>Mozilla/5.0 (compatible; BecomeBot/2.0beta; http://www.become.com/webmasters.html)</String> |
||
12894 | <Description>BecomeBot - Become.com shopping search (64.124.85.xx(x))</Description> |
||
12895 | <Type>R</Type> |
||
12896 | <Comment>64.124.85.[x]xx</Comment> |
||
12897 | <Link1>http://www.become.com</Link1> |
||
12898 | <Link2></Link2> |
||
12899 | </user-agent> |
||
12900 | <user-agent> |
||
12901 | <ID>id_moz_953</ID> |
||
12902 | <String>Mozilla/5.0 (compatible; BecomeBot/2.x; MSIE 6.0 compatible; http://www.become.com/site_owners.html)</String> |
||
12903 | <Description>BecomeBot - Become.com shopping search (64.124.85.xx(x))</Description> |
||
12904 | <Type>R</Type> |
||
12905 | <Comment>64.124.85.[x]xx</Comment> |
||
12906 | <Link1>http://www.become.com</Link1> |
||
12907 | <Link2></Link2> |
||
12908 | </user-agent> |
||
12909 | <user-agent> |
||
12910 | <ID>id_moz_090506_2</ID> |
||
12911 | <String>Mozilla/5.0 (compatible; BecomeJPBot/2.3; MSIE 6.0 compatible; +http://www.become.co.jp/site_owners.html)</String> |
||
12912 | <Description>BecomeBot - Become.com shopping search (64.124.85.xx(x))</Description> |
||
12913 | <Type>R</Type> |
||
12914 | <Comment>64.124.85.[x]xx</Comment> |
||
12915 | <Link1>http://www.become.com</Link1> |
||
12916 | <Link2></Link2> |
||
12917 | </user-agent> |
||
12918 | <user-agent> |
||
12919 | <ID>id_moz_020907_1</ID> |
||
12920 | <String>Mozilla/5.0 (compatible; BlogRefsBot/0.1; http://www.blogrefs.com/about/bloggers)</String> |
||
12921 | <Description>BlogRefsBot.com blog robot</Description> |
||
12922 | <Type>R</Type> |
||
12923 | <Comment>69.90.42.xx</Comment> |
||
12924 | <Link1>http://www.blogrefs.com/</Link1> |
||
12925 | <Link2>http://www.blogrefs.com/about/bloggers</Link2> |
||
12926 | </user-agent> |
||
12927 | <user-agent> |
||
12928 | <ID>id_moz_171107_1</ID> |
||
12929 | <String>Mozilla/5.0 (compatible; Bot; +http://pressemitteilung.ws/spamfilter</String> |
||
12930 | <Description>Pressemitteilungen Webservice RSS / news crawler (Germany)</Description> |
||
12931 | <Type>R</Type> |
||
12932 | <Comment>87.164.242.1xx</Comment> |
||
12933 | <Link1>http://pressemitteilung.ws/</Link1> |
||
12934 | <Link2></Link2> |
||
12935 | </user-agent> |
||
12936 | <user-agent> |
||
12937 | <ID>id_moz_031206_1</ID> |
||
12938 | <String>Mozilla/5.0 (compatible; BuzzRankingBot/1.0; +http://www.buzzrankingbot.com/)</String> |
||
12939 | <Description>BuzzRanking internet content analysis</Description> |
||
12940 | <Type>R</Type> |
||
12941 | <Comment>213.251.187.1xx</Comment> |
||
12942 | <Link1>http://www.buzzrankingbot.com/</Link1> |
||
12943 | <Link2></Link2> |
||
12944 | </user-agent> |
||
12945 | <user-agent> |
||
12946 | <ID>id_moz_310506_1</ID> |
||
12947 | <String>Mozilla/5.0 (compatible; Charlotte/1.0b; charlotte@betaspider.com)</String> |
||
12948 | <Description>Charlotte indexing spider for Searchme / Wikiseek</Description> |
||
12949 | <Type>R</Type> |
||
12950 | <Comment>209.249.86.x</Comment> |
||
12951 | <Link1>http://www.searchme.com/</Link1> |
||
12952 | <Link2>http://www.wikiseek.com/</Link2> |
||
12953 | </user-agent> |
||
12954 | <user-agent> |
||
12955 | <ID>id_moz_080307_1</ID> |
||
12956 | <String>Mozilla/5.0 (compatible; Charlotte/1.0b; http://www.searchme.com/support/)</String> |
||
12957 | <Description>Charlotte indexing spider for Searchme / Wikiseek</Description> |
||
12958 | <Type>R</Type> |
||
12959 | <Comment>209.249.86.x</Comment> |
||
12960 | <Link1>http://www.searchme.com/</Link1> |
||
12961 | <Link2>http://www.wikiseek.com/</Link2> |
||
12962 | </user-agent> |
||
12963 | <user-agent> |
||
12964 | <ID>id_moz_220106_1</ID> |
||
12965 | <String>Mozilla/5.0 (compatible; Crawling jpeg; http://www.yama.info.waseda.ac.jp)</String> |
||
12966 | <Description>Unknown graphics crawler or downloading agent from Yamana Laboratory - Waseda Univerity Japan (133.9.238.xx)</Description> |
||
12967 | <Type>R</Type> |
||
12968 | <Comment>doesn't read robots.txt</Comment> |
||
12969 | <Link1>http://www.yama.info.waseda.ac.jp/eng/index.html</Link1> |
||
12970 | <Link2></Link2> |
||
12971 | </user-agent> |
||
12972 | <user-agent> |
||
12973 | <ID>id_moz_954</ID> |
||
12974 | <String>Mozilla/5.0 (compatible; Custo 3 (Netwu.com); Windows NT 5.1)</String> |
||
12975 | <Description>Custo web site spidering tool (link checking)</Description> |
||
12976 | <Type>C</Type> |
||
12977 | <Comment>s. also - Custo x.x (www.netwu.com)</Comment> |
||
12978 | <Link1>http://www.netwu.com</Link1> |
||
12979 | <Link2></Link2> |
||
12980 | </user-agent> |
||
12981 | <user-agent> |
||
12982 | <ID>id_moz_071207_1</ID> |
||
12983 | <String>Mozilla/5.0 (compatible; de/1.13.2 +http://www.de.com)</String> |
||
12984 | <Description>De.com German travel related search via Amazon Web Services</Description> |
||
12985 | <Type>R</Type> |
||
12986 | <Comment>67.202.29.xx</Comment> |
||
12987 | <Link1>http://www.de.com/start.php?homepage=true</Link1> |
||
12988 | <Link2>http://www.amazon.com/gp/browse.html?node=3435361</Link2> |
||
12989 | </user-agent> |
||
12990 | <user-agent> |
||
12991 | <ID>id_moz_170109_1</ID> |
||
12992 | <String>Mozilla/5.0 (compatible; Diffbot/0.1; +http://www.diffbot.com)</String> |
||
12993 | <Description>Diffbot beta - RSS and news feed crawler</Description> |
||
12994 | <Type>R</Type> |
||
12995 | <Comment>64.71.190.13x</Comment> |
||
12996 | <Link1>http://www.diffbot.com/</Link1> |
||
12997 | <Link2></Link2> |
||
12998 | </user-agent> |
||
12999 | <user-agent> |
||
13000 | <ID>id_moz_030207_1</ID> |
||
13001 | <String>Mozilla/5.0 (compatible; DNS-Digger-Explorer/1.0; +http://www.dnsdigger.com)</String> |
||
13002 | <Description>DNS-Digger - DNS server neighbourhood search</Description> |
||
13003 | <Type>R</Type> |
||
13004 | <Comment>212.214.165.2xx</Comment> |
||
13005 | <Link1>http://www.dnsdigger.com/</Link1> |
||
13006 | <Link2></Link2> |
||
13007 | </user-agent> |
||
13008 | <user-agent> |
||
13009 | <ID>id_moz_100606_2</ID> |
||
13010 | <String>Mozilla/5.0 (compatible; DNS-Digger/1.0; +http://www.dnsdigger.com)</String> |
||
13011 | <Description>DNS-Digger - DNS server neighbourhood search</Description> |
||
13012 | <Type>R</Type> |
||
13013 | <Comment>212.214.165.2xx</Comment> |
||
13014 | <Link1>http://www.dnsdigger.com/</Link1> |
||
13015 | <Link2></Link2> |
||
13016 | </user-agent> |
||
13017 | <user-agent> |
||
13018 | <ID>id_moz_020506_1</ID> |
||
13019 | <String>Mozilla/5.0 (compatible; EARTHCOM.info/2.01; http://www.earthcom.info)</String> |
||
13020 | <Description>Earthcom (Czech Republic) search robot (194.108.39.xx)</Description> |
||
13021 | <Type>R</Type> |
||
13022 | <Comment>s. also EARTHCOM ..</Comment> |
||
13023 | <Link1>http://www.earthcom.info</Link1> |
||
13024 | <Link2></Link2> |
||
13025 | </user-agent> |
||
13026 | <user-agent> |
||
13027 | <ID>id_moz_190807_3</ID> |
||
13028 | <String>Mozilla/5.0 (compatible; EARTHCOM/2.2; +http://enter4u.eu)</String> |
||
13029 | <Description>enter4u / Earthcom.info search (Czech Republic)</Description> |
||
13030 | <Type>R</Type> |
||
13031 | <Comment></Comment> |
||
13032 | <Link1>http://enter4u.eu/</Link1> |
||
13033 | <Link2>http://www.earthcom.info</Link2> |
||
13034 | </user-agent> |
||
13035 | <user-agent> |
||
13036 | <ID>id_moz_050107_1</ID> |
||
13037 | <String>Mozilla/5.0 (compatible; egothor/8.0g; +http://ego.ms.mff.cuni.cz/)</String> |
||
13038 | <Description>Prague Faculty of Mathematics and Physics using Egothor open source crawler</Description> |
||
13039 | <Type>P</Type> |
||
13040 | <Comment>195.113.20.125</Comment> |
||
13041 | <Link1>http://ego.ms.mff.cuni.cz/</Link1> |
||
13042 | <Link2>http://www.egothor.org/</Link2> |
||
13043 | </user-agent> |
||
13044 | <user-agent> |
||
13045 | <ID>id_moz_310507_1</ID> |
||
13046 | <String>Mozilla/5.0 (compatible; Exabot Test/3.0; +http://www.exabot.com/go/robot)</String> |
||
13047 | <Description>Exalead (France) search robot (193.47.80.xx)</Description> |
||
13048 | <Type>R</Type> |
||
13049 | <Comment>s. Harvest-NG/1.0.2 and Exalead NG...</Comment> |
||
13050 | <Link1>http://www.exabot.com/</Link1> |
||
13051 | <Link2></Link2> |
||
13052 | </user-agent> |
||
13053 | <user-agent> |
||
13054 | <ID>id_moz_221207_1</ID> |
||
13055 | <String>Mozilla/5.0 (compatible; FatBot 2.0; http://www.thefind.com/main/CrawlerFAQs.fhtml)</String> |
||
13056 | <Description>TheFind.com - Shopping search robot</Description> |
||
13057 | <Type>R</Type> |
||
13058 | <Comment>64.124.148.xx[x]</Comment> |
||
13059 | <Link1>http://www.thefind.com/</Link1> |
||
13060 | <Link2></Link2> |
||
13061 | </user-agent> |
||
13062 | <user-agent> |
||
13063 | <ID>id_moz_170109_2</ID> |
||
13064 | <String>Mozilla/5.0 (compatible; Galbot/1.0; +http://www.galbot.com/bot.html)</String> |
||
13065 | <Description>Galbot tagging robot (beta) - Denmark</Description> |
||
13066 | <Type>R</Type> |
||
13067 | <Comment></Comment> |
||
13068 | <Link1>http://www.galbot.com/</Link1> |
||
13069 | <Link2></Link2> |
||
13070 | </user-agent> |
||
13071 | <user-agent> |
||
13072 | <ID>id_moz_955</ID> |
||
13073 | <String>mozilla/5.0 (compatible; genevabot http://www.healthdash.com)</String> |
||
13074 | <Description>Geneva Single-Site Search Engine used by Healthdash health search</Description> |
||
13075 | <Type>R</Type> |
||
13076 | <Comment></Comment> |
||
13077 | <Link1>http://www.healthdash.com</Link1> |
||
13078 | <Link2></Link2> |
||
13079 | </user-agent> |
||
13080 | <user-agent> |
||
13081 | <ID>id_moz_170207_4</ID> |
||
13082 | <String>Mozilla/5.0 (compatible; Google Desktop) Paros/3.2.12</String> |
||
13083 | <Description>Paros - a Java based HTTP/HTTPS proxy</Description> |
||
13084 | <Type>P</Type> |
||
13085 | <Comment></Comment> |
||
13086 | <Link1>http://sourceforge.net/projects/paros</Link1> |
||
13087 | <Link2></Link2> |
||
13088 | </user-agent> |
||
13089 | <user-agent> |
||
13090 | <ID>id_moz_956</ID> |
||
13091 | <String>Mozilla/5.0 (compatible; Googlebot/2.1; http://www.google.com/bot.html)</String> |
||
13092 | <Description>Google robot</Description> |
||
13093 | <Type>R</Type> |
||
13094 | <Comment>s. also: - Googlebot - Mozilla/4.0 (MobilePhone SCP ...</Comment> |
||
13095 | <Link1>http://www.google.com</Link1> |
||
13096 | <Link2></Link2> |
||
13097 | </user-agent> |
||
13098 | <user-agent> |
||
13099 | <ID>id_moz_957</ID> |
||
13100 | <String>mozilla/5.0 (compatible; heritrix/1.0.4 http://innovationblog.com)</String> |
||
13101 | <Description>Unknown robot using Heritrix</Description> |
||
13102 | <Type>R</Type> |
||
13103 | <Comment></Comment> |
||
13104 | <Link1>http://innovationblog.com</Link1> |
||
13105 | <Link2>http://crawler.archive.org/</Link2> |
||
13106 | </user-agent> |
||
13107 | <user-agent> |
||
13108 | <ID>id_moz_280207_1</ID> |
||
13109 | <String>Mozilla/5.0 (compatible; heritrix/1.10.2 +http://i.stanford.edu/)</String> |
||
13110 | <Description>The Stanford University InfoLab robot using Heritrix</Description> |
||
13111 | <Type>R</Type> |
||
13112 | <Comment>171.67.73.1x</Comment> |
||
13113 | <Link1>http://i.stanford.edu/</Link1> |
||
13114 | <Link2>http://www.archive.org/</Link2> |
||
13115 | </user-agent> |
||
13116 | <user-agent> |
||
13117 | <ID>id_moz_280108_2</ID> |
||
13118 | <String>Mozilla/5.0 (compatible; heritrix/1.12.1 +http://newstin.com/)</String> |
||
13119 | <Description>Newstin news feed search using Heritrix</Description> |
||
13120 | <Type>R</Type> |
||
13121 | <Comment>195.39.35.1xx</Comment> |
||
13122 | <Link1>http://www.newstin.com/</Link1> |
||
13123 | <Link2></Link2> |
||
13124 | </user-agent> |
||
13125 | <user-agent> |
||
13126 | <ID>id_moz_210807_1</ID> |
||
13127 | <String>Mozilla/5.0 (compatible; heritrix/1.12.1 +http://www.page-store.com)</String> |
||
13128 | <Description>Page-store.com vertical search via Amazon Web Services</Description> |
||
13129 | <Type>R</Type> |
||
13130 | <Comment>72.44.62.1xx</Comment> |
||
13131 | <Link1>http://www.page-store.com/</Link1> |
||
13132 | <Link2>http://www.amazonaws.com/</Link2> |
||
13133 | </user-agent> |
||
13134 | <user-agent> |
||
13135 | <ID>id_moz_230108_1</ID> |
||
13136 | <String>Mozilla/5.0 (compatible; heritrix/1.12.1 +http://www.page-store.com) [email:paul@page-store.com]</String> |
||
13137 | <Description>Page-store.com vertical search via Amazon Web Services</Description> |
||
13138 | <Type>R</Type> |
||
13139 | <Comment>72.44.62.1xx</Comment> |
||
13140 | <Link1>http://www.page-store.com/</Link1> |
||
13141 | <Link2>http://www.amazonaws.com/</Link2> |
||
13142 | </user-agent> |
||
13143 | <user-agent> |
||
13144 | <ID>id_moz_958</ID> |
||
13145 | <String>mozilla/5.0 (compatible; heritrix/1.3.0 http://archive.crawler.org)</String> |
||
13146 | <Description>Heritrix Internet Archive's open-source web project </Description> |
||
13147 | <Type>R</Type> |
||
13148 | <Comment></Comment> |
||
13149 | <Link1>http://archive.crawler.org</Link1> |
||
13150 | <Link2></Link2> |
||
13151 | </user-agent> |
||
13152 | <user-agent> |
||
13153 | <ID>id_moz_270106_2</ID> |
||
13154 | <String>Mozilla/5.0 (compatible; heritrix/1.4.0 +http://www.chepi.net)</String> |
||
13155 | <Description>Chepi Beta search Spain (194.116.240.1xx) using Heritrix</Description> |
||
13156 | <Type>R</Type> |
||
13157 | <Comment></Comment> |
||
13158 | <Link1>http://www.chepi.net/</Link1> |
||
13159 | <Link2>http://lucene.apache.org</Link2> |
||
13160 | </user-agent> |
||
13161 | <user-agent> |
||
13162 | <ID>id_moz_959</ID> |
||
13163 | <String>Mozilla/5.0 (compatible; heritrix/1.4t http://www.truveo.com/)</String> |
||
13164 | <Description>Truveo data mining robot using Heritrix</Description> |
||
13165 | <Type>R</Type> |
||
13166 | <Comment></Comment> |
||
13167 | <Link1>http://www.truveo.com/home/</Link1> |
||
13168 | <Link2>http://crawler.archive.org/</Link2> |
||
13169 | </user-agent> |
||
13170 | <user-agent> |
||
13171 | <ID>id_moz_960</ID> |
||
13172 | <String>Mozilla/5.0 (compatible; heritrix/1.5.0 http://www.l3s.de/~kohlschuetter/projects/crawling/)</String> |
||
13173 | <Description>L3S WebCrawling Project (Germany) using Heritrix</Description> |
||
13174 | <Type>R</Type> |
||
13175 | <Comment></Comment> |
||
13176 | <Link1>http://www.l3s.de/~kohlschuetter/projects/crawling/</Link1> |
||
13177 | <Link2>http://crawler.archive.org/</Link2> |
||
13178 | </user-agent> |
||
13179 | <user-agent> |
||
13180 | <ID>id_moz_961</ID> |
||
13181 | <String>Mozilla/5.0 (compatible; heritrix/1.5.0-200506231921 http://pandora.nla.gov.au/crawl.html)</String> |
||
13182 | <Description>Pandora Internet Archive crawler (Australia) using Heritrix</Description> |
||
13183 | <Type>R</Type> |
||
13184 | <Comment></Comment> |
||
13185 | <Link1>http://pandora.nla.gov.au</Link1> |
||
13186 | <Link2>http://crawler.archive.org/</Link2> |
||
13187 | </user-agent> |
||
13188 | <user-agent> |
||
13189 | <ID>id_moz_250706_3</ID> |
||
13190 | <String>Mozilla/5.0 (compatible; heritrix/1.6.0 http://www.worio.com/)</String> |
||
13191 | <Description>WORIO (beta) search for computer scientists and programmers using Heritrix open-source crawler</Description> |
||
13192 | <Type>R</Type> |
||
13193 | <Comment>137.82.84.xx</Comment> |
||
13194 | <Link1>http://www.worio.com/</Link1> |
||
13195 | <Link2>http://www.archive.org/</Link2> |
||
13196 | </user-agent> |
||
13197 | <user-agent> |
||
13198 | <ID>id_moz_190607_1</ID> |
||
13199 | <String>Mozilla/5.0 (compatible; heritrix/1.7.0 +http://www.greaterera.com/)</String> |
||
13200 | <Description>greatarea.com website collection project using Heritrix</Description> |
||
13201 | <Type>R</Type> |
||
13202 | <Comment>63.209.222.</Comment> |
||
13203 | <Link1>http://www.greaterera.com/</Link1> |
||
13204 | <Link2></Link2> |
||
13205 | </user-agent> |
||
13206 | <user-agent> |
||
13207 | <ID>id_moz_230307_1</ID> |
||
13208 | <String>Mozilla/5.0 (compatible; Heritrix/1.8.0 http://www.hanzoarchives.com)</String> |
||
13209 | <Description>hanzo:web social web archiving service</Description> |
||
13210 | <Type>D</Type> |
||
13211 | <Comment>216.182.238.</Comment> |
||
13212 | <Link1>http://www.hanzoweb.com/</Link1> |
||
13213 | <Link2></Link2> |
||
13214 | </user-agent> |
||
13215 | <user-agent> |
||
13216 | <ID>id_moz_151106_1</ID> |
||
13217 | <String>Mozilla/5.0 (compatible; heritrix/1.x.x +http://www.accelobot.com)</String> |
||
13218 | <Description>Accelobot - Accelovation Market Discovery software robot</Description> |
||
13219 | <Type>R</Type> |
||
13220 | <Comment>72.20.99.xx</Comment> |
||
13221 | <Link1>http://www.accelobot.com/</Link1> |
||
13222 | <Link2>http://www.accelovation.com/solutions.html</Link2> |
||
13223 | </user-agent> |
||
13224 | <user-agent> |
||
13225 | <ID>id_moz_030208_1</ID> |
||
13226 | <String>Mozilla/5.0 (compatible; heritrix/2.0.0-RC1 +http://www.aol.com)</String> |
||
13227 | <Description>Unknown AOL robot using Heritrix</Description> |
||
13228 | <Type>R</Type> |
||
13229 | <Comment>64.236.128.x</Comment> |
||
13230 | <Link1>http://www.aol.com/</Link1> |
||
13231 | <Link2></Link2> |
||
13232 | </user-agent> |
||
13233 | <user-agent> |
||
13234 | <ID>id_moz_051207_2</ID> |
||
13235 | <String>Mozilla/5.0 (compatible; Hermit Search. Com; +http://www.hermitsearch.com)</String> |
||
13236 | <Description>Hermits Search.com - Products and service search robot</Description> |
||
13237 | <Type>R</Type> |
||
13238 | <Comment>72.55.165.11x</Comment> |
||
13239 | <Link1>http://www.hermitsearch.com/</Link1> |
||
13240 | <Link2></Link2> |
||
13241 | </user-agent> |
||
13242 | <user-agent> |
||
13243 | <ID>id_moz_161006_2</ID> |
||
13244 | <String>Mozilla/5.0 (compatible; http://www.IsMySiteUp.Net/bot/ )</String> |
||
13245 | <Description>IsMySiteUp? - Online website monitoring service</Description> |
||
13246 | <Type>C</Type> |
||
13247 | <Comment>142.179.247.xx</Comment> |
||
13248 | <Link1>http://www.ismysiteup.net/</Link1> |
||
13249 | <Link2></Link2> |
||
13250 | </user-agent> |
||
13251 | <user-agent> |
||
13252 | <ID>id_moz_101106_2</ID> |
||
13253 | <String>Mozilla/5.0 (compatible; http://www.UptimeAuditor.com/bot/ )</String> |
||
13254 | <Description>UptimeAuditor - real time web monitoring</Description> |
||
13255 | <Type>C</Type> |
||
13256 | <Comment>142.179.247.xx</Comment> |
||
13257 | <Link1>http://www.uptimeauditor.com/</Link1> |
||
13258 | <Link2></Link2> |
||
13259 | </user-agent> |
||
13260 | <user-agent> |
||
13261 | <ID>id_moz_180508_1</ID> |
||
13262 | <String>Mozilla/5.0 (compatible; HyperixScoop/1.3; +http://www.hyperix.com)</String> |
||
13263 | <Description>Hyperix vertical search crawler</Description> |
||
13264 | <Type>R</Type> |
||
13265 | <Comment>64.40.113.[x]xx</Comment> |
||
13266 | <Link1>http://www.hyperix.com/</Link1> |
||
13267 | <Link2></Link2> |
||
13268 | </user-agent> |
||
13269 | <user-agent> |
||
13270 | <ID>id_moz_070406_1</ID> |
||
13271 | <String>Mozilla/5.0 (compatible; iaskspider/1.0; MSIE 6.0)</String> |
||
13272 | <Description>Unknown robot (reads robots.txt) from chinatelecom (219.142.78.xx)</Description> |
||
13273 | <Type></Type> |
||
13274 | <Comment>Not from iask.com.cn - s. also iaskspider</Comment> |
||
13275 | <Link1></Link1> |
||
13276 | <Link2></Link2> |
||
13277 | </user-agent> |
||
13278 | <user-agent> |
||
13279 | <ID>id_moz_280607_1</ID> |
||
13280 | <String>Mozilla/5.0 (compatible; IDBot/1.0; +http://www.id-search.org/bot.html)</String> |
||
13281 | <Description>ID-Search.org - Russian search project</Description> |
||
13282 | <Type>R</Type> |
||
13283 | <Comment>67.159.44.2xx</Comment> |
||
13284 | <Link1>http://id-search.org/bot.html</Link1> |
||
13285 | <Link2></Link2> |
||
13286 | </user-agent> |
||
13287 | <user-agent> |
||
13288 | <ID>id_moz_962</ID> |
||
13289 | <String>Mozilla/5.0 (compatible; InterseekWeb/3.x)</String> |
||
13290 | <Description>Najdi.si (Slovenia) search using Interseek/Web Interseek/API Search Engine</Description> |
||
13291 | <Type>R</Type> |
||
13292 | <Comment></Comment> |
||
13293 | <Link1>http://www.najdi.si/pomoc/eng/index.jsp</Link1> |
||
13294 | <Link2></Link2> |
||
13295 | </user-agent> |
||
13296 | <user-agent> |
||
13297 | <ID>id_moz_130807_4</ID> |
||
13298 | <String>Mozilla/5.0 (compatible; Jim +http://www.hanzoarchives.com)</String> |
||
13299 | <Description>hanzo:web social web archiving service</Description> |
||
13300 | <Type>D</Type> |
||
13301 | <Comment>216.182.238.</Comment> |
||
13302 | <Link1>http://www.hanzoweb.com/</Link1> |
||
13303 | <Link2></Link2> |
||
13304 | </user-agent> |
||
13305 | <user-agent> |
||
13306 | <ID>id_moz_963</ID> |
||
13307 | <String>Mozilla/5.0 (compatible; Konqueror/2.0.1; X11); Supports MD5-Digest; Supports gzip encoding</String> |
||
13308 | <Description>Konqueror 2.0.x X11</Description> |
||
13309 | <Type>B</Type> |
||
13310 | <Comment></Comment> |
||
13311 | <Link1>http://www.konqueror.org/</Link1> |
||
13312 | <Link2></Link2> |
||
13313 | </user-agent> |
||
13314 | <user-agent> |
||
13315 | <ID>id_moz_964</ID> |
||
13316 | <String>Mozilla/5.0 (compatible; Konqueror/2.1.1; X11)</String> |
||
13317 | <Description>Konqueror 2.1.x X11</Description> |
||
13318 | <Type>B</Type> |
||
13319 | <Comment></Comment> |
||
13320 | <Link1>http://www.konqueror.org/</Link1> |
||
13321 | <Link2></Link2> |
||
13322 | </user-agent> |
||
13323 | <user-agent> |
||
13324 | <ID>id_moz_966</ID> |
||
13325 | <String>Mozilla/5.0 (compatible; Konqueror/2.2.2)</String> |
||
13326 | <Description>Konqueror 2.2.x</Description> |
||
13327 | <Type>B</Type> |
||
13328 | <Comment></Comment> |
||
13329 | <Link1>http://www.konqueror.org/</Link1> |
||
13330 | <Link2></Link2> |
||
13331 | </user-agent> |
||
13332 | <user-agent> |
||
13333 | <ID>id_moz_965</ID> |
||
13334 | <String>Mozilla/5.0 (compatible; Konqueror/2.2.2; Linux 2.4.14-xfs; X11; i686)</String> |
||
13335 | <Description>Konqueror 2.2.x Linux</Description> |
||
13336 | <Type>B</Type> |
||
13337 | <Comment></Comment> |
||
13338 | <Link1>http://www.konqueror.org/</Link1> |
||
13339 | <Link2></Link2> |
||
13340 | </user-agent> |
||
13341 | <user-agent> |
||
13342 | <ID>id_moz_050108_2</ID> |
||
13343 | <String>Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Exabot-Thumbnails)</String> |
||
13344 | <Description>Exalead (France) search robot (193.47.80.xx)</Description> |
||
13345 | <Type>R</Type> |
||
13346 | <Comment>s. Harvest-NG/1.0.2 and Exalead NG...</Comment> |
||
13347 | <Link1>http://www.exabot.com/</Link1> |
||
13348 | <Link2></Link2> |
||
13349 | </user-agent> |
||
13350 | <user-agent> |
||
13351 | <ID>id_moz_967</ID> |
||
13352 | <String>Mozilla/5.0 (compatible; LemSpider 0.1)</String> |
||
13353 | <Description>Lemur Consulting LemIR spider</Description> |
||
13354 | <Type>R</Type> |
||
13355 | <Comment></Comment> |
||
13356 | <Link1>http://www.lemurconsulting.com</Link1> |
||
13357 | <Link2></Link2> |
||
13358 | </user-agent> |
||
13359 | <user-agent> |
||
13360 | <ID>id_moz_968</ID> |
||
13361 | <String>Mozilla/5.0 (compatible; LinksManager.com_bot http://linksmanager.com/linkchecker.html)</String> |
||
13362 | <Description>Linksmanager.com online link checking service</Description> |
||
13363 | <Type>C</Type> |
||
13364 | <Comment>s.also LinksManager.com</Comment> |
||
13365 | <Link1>http://www.linksmanager.com</Link1> |
||
13366 | <Link2></Link2> |
||
13367 | </user-agent> |
||
13368 | <user-agent> |
||
13369 | <ID>id_moz_140408_2</ID> |
||
13370 | <String>Mozilla/5.0 (compatible; LinkStash Bookmark Manager; http://www.xrayz.co.uk/)</String> |
||
13371 | <Description>LinkStash Bookmark Manager</Description> |
||
13372 | <Type>C</Type> |
||
13373 | <Comment></Comment> |
||
13374 | <Link1>http://www.xrayz.co.uk/</Link1> |
||
13375 | <Link2></Link2> |
||
13376 | </user-agent> |
||
13377 | <user-agent> |
||
13378 | <ID>id_moz_060706_2</ID> |
||
13379 | <String>Mozilla/5.0 (compatible; MojeekBot/2.0; http://www.mojeek.com/bot.html)</String> |
||
13380 | <Description>Mojeek Search Preview robot (217.155.205.xx)</Description> |
||
13381 | <Type>R</Type> |
||
13382 | <Comment>s. also MojeekBot/0.x</Comment> |
||
13383 | <Link1>http://www.mojeek.com</Link1> |
||
13384 | <Link2></Link2> |
||
13385 | </user-agent> |
||
13386 | <user-agent> |
||
13387 | <ID>id_moz_290107_1</ID> |
||
13388 | <String>Mozilla/5.0 (compatible; MOSBookmarks/v2.6-Plus; Link Checker)</String> |
||
13389 | <Description>Joomla!/Mambo component - MosBookmarks (bot) link checking</Description> |
||
13390 | <Type>C</Type> |
||
13391 | <Comment></Comment> |
||
13392 | <Link1>http://www.tegdesign.ch/</Link1> |
||
13393 | <Link2></Link2> |
||
13394 | </user-agent> |
||
13395 | <user-agent> |
||
13396 | <ID>id_moz_091007_1</ID> |
||
13397 | <String>Mozilla/5.0 (compatible; MSIE 6.0; Podtech Network; crawler_admin@podtech.net)</String> |
||
13398 | <Description>PodTech entertainment and video network crawler</Description> |
||
13399 | <Type>R</Type> |
||
13400 | <Comment>71.134.235.xx</Comment> |
||
13401 | <Link1>http://www.podtech.net/home/</Link1> |
||
13402 | <Link2></Link2> |
||
13403 | </user-agent> |
||
13404 | <user-agent> |
||
13405 | <ID>id_moz_969</ID> |
||
13406 | <String>Mozilla/5.0 (compatible; OnetSzukaj/5.0; http://szukaj.onet.pl)</String> |
||
13407 | <Description>onet.pl Szukaj (Search) robot (213.180.128.1xx)</Description> |
||
13408 | <Type>R</Type> |
||
13409 | <Comment>s. also - Onet.pl SA</Comment> |
||
13410 | <Link1>http://szukaj.onet.pl</Link1> |
||
13411 | <Link2></Link2> |
||
13412 | </user-agent> |
||
13413 | <user-agent> |
||
13414 | <ID>id_moz_181207_1</ID> |
||
13415 | <String>Mozilla/5.0 (compatible; PagestackerBot; http://www.pagestacker.com)</String> |
||
13416 | <Description>Pagestacker online bookmark service</Description> |
||
13417 | <Type>C</Type> |
||
13418 | <Comment>70.85.129.12x</Comment> |
||
13419 | <Link1>http://www.pagestacker.com/</Link1> |
||
13420 | <Link2></Link2> |
||
13421 | </user-agent> |
||
13422 | <user-agent> |
||
13423 | <ID>id_moz_020307_1</ID> |
||
13424 | <String>Mozilla/5.0 (compatible; PalmeraBot; http://www.links24h.com/help/palmera) Version 0.001</String> |
||
13425 | <Description>PalmeraBot - Links24h.com search engine robot</Description> |
||
13426 | <Type>R</Type> |
||
13427 | <Comment>80.59.111.2xx</Comment> |
||
13428 | <Link1>http://www.links24h.com/</Link1> |
||
13429 | <Link2>http://www.links24h.com/help/palmera/</Link2> |
||
13430 | </user-agent> |
||
13431 | <user-agent> |
||
13432 | <ID>id_moz_130806_1</ID> |
||
13433 | <String>Mozilla/5.0 (compatible; PEAR HTTP_Request class; http://feed.moo.jp/)</String> |
||
13434 | <Description>FeedMo feed search (Japan) using Pear HTTP</Description> |
||
13435 | <Type>C ?</Type> |
||
13436 | <Comment>210.188.205.2xx</Comment> |
||
13437 | <Link1>http://feed.moo.jp/</Link1> |
||
13438 | <Link2>http://pear.php.net/</Link2> |
||
13439 | </user-agent> |
||
13440 | <user-agent> |
||
13441 | <ID>id_moz_190607_2</ID> |
||
13442 | <String>Mozilla/5.0 (compatible; Phonifier; +http://www.phonifier.com)</String> |
||
13443 | <Description>PHONifier mobile access to web content</Description> |
||
13444 | <Type>D B</Type> |
||
13445 | <Comment></Comment> |
||
13446 | <Link1>http://www.phonifier.com/</Link1> |
||
13447 | <Link2></Link2> |
||
13448 | </user-agent> |
||
13449 | <user-agent> |
||
13450 | <ID>id_moz_240208_2</ID> |
||
13451 | <String>Mozilla/5.0 (compatible; pmoz.info ODP link checker; +http://pmoz.info/doc/botinfo.htm)</String> |
||
13452 | <Description>pmoz.info ODP link checking bot</Description> |
||
13453 | <Type>C</Type> |
||
13454 | <Comment>74.208.25.118 / 216.15.74.85</Comment> |
||
13455 | <Link1>http://pmoz.info/doc/botinfo.htm</Link1> |
||
13456 | <Link2>http://www.dmoz.org/</Link2> |
||
13457 | </user-agent> |
||
13458 | <user-agent> |
||
13459 | <ID>id_moz_970</ID> |
||
13460 | <String>Mozilla/5.0 (compatible; pogodak.ba/3.x)</String> |
||
13461 | <Description>Pogodak search (Slovenia) robot via Interseek</Description> |
||
13462 | <Type>R</Type> |
||
13463 | <Comment>89.143.229.1xx</Comment> |
||
13464 | <Link1>http://www.pogodak.hr</Link1> |
||
13465 | <Link2>http://www.interseek.com/</Link2> |
||
13466 | </user-agent> |
||
13467 | <user-agent> |
||
13468 | <ID>id_moz_100408_2</ID> |
||
13469 | <String>Mozilla/5.0 (compatible; Pogodak.hr/3.1)</String> |
||
13470 | <Description>Pogodak search (Slovenia) robot via Interseek</Description> |
||
13471 | <Type>R</Type> |
||
13472 | <Comment>89.143.229.1xx</Comment> |
||
13473 | <Link1>http://www.pogodak.hr</Link1> |
||
13474 | <Link2>http://www.interseek.com/</Link2> |
||
13475 | </user-agent> |
||
13476 | <user-agent> |
||
13477 | <ID>id_moz_101107_1</ID> |
||
13478 | <String>Mozilla/5.0 (compatible; Proximic crawler; +http://www.proximic.com/en/about-us/contact-us.html)</String> |
||
13479 | <Description>Proximic Publisher Widget - RSS and news content generator</Description> |
||
13480 | <Type>C</Type> |
||
13481 | <Comment></Comment> |
||
13482 | <Link1>http://www.proximic.com/</Link1> |
||
13483 | <Link2></Link2> |
||
13484 | </user-agent> |
||
13485 | <user-agent> |
||
13486 | <ID>id_moz_230907_1</ID> |
||
13487 | <String>Mozilla/5.0 (compatible; PWeBot/3.1; http://www.programacionweb.net/robot.php)</String> |
||
13488 | <Description>ProgramacionWeb.net PWeBot crawler (Argentina)</Description> |
||
13489 | <Type>R</Type> |
||
13490 | <Comment>62.149.236.2xx</Comment> |
||
13491 | <Link1>http://www.programacionweb.net/robot-en.php</Link1> |
||
13492 | <Link2>http://www.programacionweb.net/</Link2> |
||
13493 | </user-agent> |
||
13494 | <user-agent> |
||
13495 | <ID>id_moz_130507_1</ID> |
||
13496 | <String>Mozilla/5.0 (compatible; Quantcastbot/1.0; www.quantcast.com)</String> |
||
13497 | <Description>Quantcast - Open Internet Ratings Service</Description> |
||
13498 | <Type>R</Type> |
||
13499 | <Comment></Comment> |
||
13500 | <Link1>http://www.quantcast.com/</Link1> |
||
13501 | <Link2></Link2> |
||
13502 | </user-agent> |
||
13503 | <user-agent> |
||
13504 | <ID>id_moz_190706_1</ID> |
||
13505 | <String>Mozilla/5.0 (compatible; robtexbot/1.0; http://www.robtex.com/ )</String> |
||
13506 | <Description>robtex - Multi-RBL check and AS-numbercheck</Description> |
||
13507 | <Type>C</Type> |
||
13508 | <Comment></Comment> |
||
13509 | <Link1>http://www.robtex.com/</Link1> |
||
13510 | <Link2></Link2> |
||
13511 | </user-agent> |
||
13512 | <user-agent> |
||
13513 | <ID>id_moz_050408_1</ID> |
||
13514 | <String>Mozilla/5.0 (compatible; ScoutJet; +http://www.scoutjet.com/)</String> |
||
13515 | <Description>ScoutJet (Blekko) search web crawler</Description> |
||
13516 | <Type>R</Type> |
||
13517 | <Comment></Comment> |
||
13518 | <Link1>http://www.scoutjet.com/</Link1> |
||
13519 | <Link2></Link2> |
||
13520 | </user-agent> |
||
13521 | <user-agent> |
||
13522 | <ID>id_moz_300106_3</ID> |
||
13523 | <String>Mozilla/5.0 (compatible; Scrubby/2.2; http://www.scrubtheweb.com/)</String> |
||
13524 | <Description>Scrub the web robot (66.93.156.xx)</Description> |
||
13525 | <Type>R</Type> |
||
13526 | <Comment>s.also Scrubby/2.x </Comment> |
||
13527 | <Link1>http://www.scrubtheweb.com/</Link1> |
||
13528 | <Link2></Link2> |
||
13529 | </user-agent> |
||
13530 | <user-agent> |
||
13531 | <ID>id_moz_031107_4</ID> |
||
13532 | <String>Mozilla/5.0 (compatible; ShunixBot/1.x.x +http://www.shunix.com/robot.htm)</String> |
||
13533 | <Description>Shunixbot (France) beta / test semantic web indexing robot</Description> |
||
13534 | <Type>R</Type> |
||
13535 | <Comment></Comment> |
||
13536 | <Link1>http://www.shunix.com/</Link1> |
||
13537 | <Link2></Link2> |
||
13538 | </user-agent> |
||
13539 | <user-agent> |
||
13540 | <ID>id_moz_971</ID> |
||
13541 | <String>Mozilla/5.0 (compatible; ShunixBot/1.x; http://www.shunix.com/bot.htm)</String> |
||
13542 | <Description>Shunixbot (France) beta / test semantic web indexing robot</Description> |
||
13543 | <Type>R</Type> |
||
13544 | <Comment></Comment> |
||
13545 | <Link1>http://www.shunix.com/</Link1> |
||
13546 | <Link2></Link2> |
||
13547 | </user-agent> |
||
13548 | <user-agent> |
||
13549 | <ID>id_moz_280607_2</ID> |
||
13550 | <String>Mozilla/5.0 (compatible; SkreemRBot +http://skreemr.com)</String> |
||
13551 | <Description>Skreemr - Audio search engine</Description> |
||
13552 | <Type>R</Type> |
||
13553 | <Comment>64.15.69.x</Comment> |
||
13554 | <Link1>http://skreemr.com/</Link1> |
||
13555 | <Link2></Link2> |
||
13556 | </user-agent> |
||
13557 | <user-agent> |
||
13558 | <ID>id_moz_070207_2</ID> |
||
13559 | <String>Mozilla/5.0 (compatible; SnapPreviewBot; en-US; rv:1.8.0.9) Gecko/20061206 Firefox/1.5.0.9</String> |
||
13560 | <Description>Snap Firefox Search Plugin</Description> |
||
13561 | <Type>B</Type> |
||
13562 | <Comment></Comment> |
||
13563 | <Link1>http://www.snap.com/about/spa1A.php</Link1> |
||
13564 | <Link2></Link2> |
||
13565 | </user-agent> |
||
13566 | <user-agent> |
||
13567 | <ID>id_moz_972</ID> |
||
13568 | <String>Mozilla/5.0 (compatible; SpurlBot/0.2) </String> |
||
13569 | <Description>Spurl.net bookmark service & search engine (84.40.30.xxx)</Description> |
||
13570 | <Type>R C</Type> |
||
13571 | <Comment></Comment> |
||
13572 | <Link1>http://www.spurl.net</Link1> |
||
13573 | <Link2></Link2> |
||
13574 | </user-agent> |
||
13575 | <user-agent> |
||
13576 | <ID>id_moz_190108_1</ID> |
||
13577 | <String>Mozilla/5.0 (compatible; SummizeBot +http://www.summize.com)</String> |
||
13578 | <Description>Summize - Opinion and review search robot</Description> |
||
13579 | <Type>R</Type> |
||
13580 | <Comment>208.79.17.x[x]</Comment> |
||
13581 | <Link1>http://www.summize.com/</Link1> |
||
13582 | <Link2></Link2> |
||
13583 | </user-agent> |
||
13584 | <user-agent> |
||
13585 | <ID>id_moz_973</ID> |
||
13586 | <String>Mozilla/5.0 (compatible; SYCLIKControl/LinkChecker;)</String> |
||
13587 | <Description>Syclik Control web content management system</Description> |
||
13588 | <Type>R C</Type> |
||
13589 | <Comment></Comment> |
||
13590 | <Link1>http://www.syclik.com</Link1> |
||
13591 | <Link2></Link2> |
||
13592 | </user-agent> |
||
13593 | <user-agent> |
||
13594 | <ID>id_moz_070607_1</ID> |
||
13595 | <String>Mozilla/5.0 (compatible; Synoobot/0.9; http://www.synoo.com/search/bot.html)</String> |
||
13596 | <Description>Synoo web directory robot</Description> |
||
13597 | <Type>R</Type> |
||
13598 | <Comment>212.12.114.2xx</Comment> |
||
13599 | <Link1>http://www.synoo.com/search/bot.html</Link1> |
||
13600 | <Link2></Link2> |
||
13601 | </user-agent> |
||
13602 | <user-agent> |
||
13603 | <ID>id_moz_261105_1</ID> |
||
13604 | <String>Mozilla/5.0 (compatible; Theophrastus/x.x; http://users.cs.cf.ac.uk/N.A.Smith/theophrastus.php)</String> |
||
13605 | <Description>Theophrastus Internet Spider for a basic search engine project</Description> |
||
13606 | <Type>R</Type> |
||
13607 | <Comment></Comment> |
||
13608 | <Link1>http://users.cs.cf.ac.uk/N.A.Smith/theophrastus.php</Link1> |
||
13609 | <Link2></Link2> |
||
13610 | </user-agent> |
||
13611 | <user-agent> |
||
13612 | <ID>id_moz_030207_2</ID> |
||
13613 | <String>Mozilla/5.0 (compatible; TridentSpider/3.1)</String> |
||
13614 | <Description>Interseek - Java search engine technology used for Pogodak search</Description> |
||
13615 | <Type>R</Type> |
||
13616 | <Comment>213.253.92.x</Comment> |
||
13617 | <Link1>http://www.interseek.com/</Link1> |
||
13618 | <Link2>http://www.pogodak.com/</Link2> |
||
13619 | </user-agent> |
||
13620 | <user-agent> |
||
13621 | <ID>id_moz_974</ID> |
||
13622 | <String>Mozilla/5.0 (compatible; Vagabondo/2.1; webcrawler at wise-guys dot nl; http://webagent.wise-guys.nl/)</String> |
||
13623 | <Description>WiseGuys robot</Description> |
||
13624 | <Type>R</Type> |
||
13625 | <Comment>s.also - Mozilla/3.0 (Vagabondo... - Vagabondo..</Comment> |
||
13626 | <Link1>http://www.wise-guys.nl/Contact/index.php?botselected=webagents&lang=uk</Link1> |
||
13627 | <Link2></Link2> |
||
13628 | </user-agent> |
||
13629 | <user-agent> |
||
13630 | <ID>id_moz_280209_4</ID> |
||
13631 | <String>Mozilla/5.0 (compatible; Webduniabot/1.0; +http://search.webdunia.com/bot.aspx)</String> |
||
13632 | <Description>Webdunia search (India) robot</Description> |
||
13633 | <Type>R</Type> |
||
13634 | <Comment></Comment> |
||
13635 | <Link1>http://www.webdunia.com/</Link1> |
||
13636 | <Link2></Link2> |
||
13637 | </user-agent> |
||
13638 | <user-agent> |
||
13639 | <ID>id_moz_151205_1</ID> |
||
13640 | <String>Mozilla/5.0 (compatible; Windows NT 5.0; phpwebbrainBot/0.1 - http://www.monsterli.ch/phpwebbrain/)</String> |
||
13641 | <Description>phpwebbrain online bookmark service (Germany)</Description> |
||
13642 | <Type>C</Type> |
||
13643 | <Comment></Comment> |
||
13644 | <Link1>http://www.monsterli.ch/phpwebbrain/</Link1> |
||
13645 | <Link2></Link2> |
||
13646 | </user-agent> |
||
13647 | <user-agent> |
||
13648 | <ID>id_moz_150307_1</ID> |
||
13649 | <String>Mozilla/5.0 (compatible; worio bot heritrix/1.10.0 +http://worio.com)</String> |
||
13650 | <Description>WORIO (beta) search for computer scientists and programmers using Heritrix open-source crawler</Description> |
||
13651 | <Type>R</Type> |
||
13652 | <Comment>137.82.84.xx</Comment> |
||
13653 | <Link1>http://www.worio.com/</Link1> |
||
13654 | <Link2>http://www.archive.org/</Link2> |
||
13655 | </user-agent> |
||
13656 | <user-agent> |
||
13657 | <ID>id_moz_221008_1</ID> |
||
13658 | <String>Mozilla/5.0 (compatible; WoW Lemmings Kathune/2.0;http://www.wowlemmings.com/kathune.html)</String> |
||
13659 | <Description>Kathune spider for World of Warcraft guild data. Used to power WoW Lemmings</Description> |
||
13660 | <Type>R</Type> |
||
13661 | <Comment>76.12.83.24x</Comment> |
||
13662 | <Link1>http://www.wowlemmings.com/kathune.html</Link1> |
||
13663 | <Link2>http://www.wowlemmings.com/</Link2> |
||
13664 | </user-agent> |
||
13665 | <user-agent> |
||
13666 | <ID>id_moz_260407_1</ID> |
||
13667 | <String>Mozilla/5.0 (compatible; XTbot/1.0v; +http://www.externaltest.com)</String> |
||
13668 | <Description>eXternalTest - Server and online services monitoring</Description> |
||
13669 | <Type>C</Type> |
||
13670 | <Comment></Comment> |
||
13671 | <Link1>http://www.externaltest.com/</Link1> |
||
13672 | <Link2></Link2> |
||
13673 | </user-agent> |
||
13674 | <user-agent> |
||
13675 | <ID>id_moz_290606_2</ID> |
||
13676 | <String>Mozilla/5.0 (compatible; Yahoo! DE Slurp; http://help.yahoo.com/help/us/ysearch/slurp)</String> |
||
13677 | <Description>Yahoo / Inktomi search robot</Description> |
||
13678 | <Type>R</Type> |
||
13679 | <Comment>66.196.77.1xx / 72.30.98.2xx</Comment> |
||
13680 | <Link1></Link1> |
||
13681 | <Link2></Link2> |
||
13682 | </user-agent> |
||
13683 | <user-agent> |
||
13684 | <ID>id_moz_181105_1</ID> |
||
13685 | <String>Mozilla/5.0 (compatible; Yahoo! Slurp China; http://misc.yahoo.com.cn/help.html)</String> |
||
13686 | <Description>Inktomi robot (202.160.180.xxx) for Yahoo China</Description> |
||
13687 | <Type>R</Type> |
||
13688 | <Comment></Comment> |
||
13689 | <Link1>http://www.yahoo.com.cn/</Link1> |
||
13690 | <Link2>http://www.inktomi.com/</Link2> |
||
13691 | </user-agent> |
||
13692 | <user-agent> |
||
13693 | <ID>id_moz_975</ID> |
||
13694 | <String>Mozilla/5.0 (compatible; Yahoo! Slurp; http://help.yahoo.com/help/us/ysearch/slurp)</String> |
||
13695 | <Description>Inktomi robot for Yahoo (via 66.196.xx.xxx)</Description> |
||
13696 | <Type>R</Type> |
||
13697 | <Comment></Comment> |
||
13698 | <Link1>http://www.inktomi.com</Link1> |
||
13699 | <Link2></Link2> |
||
13700 | </user-agent> |
||
13701 | <user-agent> |
||
13702 | <ID>id_moz_061208_2</ID> |
||
13703 | <String>Mozilla/5.0 (compatible; YesupBot/1.0; +http://www.yesup.net/bot.html)</String> |
||
13704 | <Description>Yesup Seo - Toronto SEO Service</Description> |
||
13705 | <Type>C</Type> |
||
13706 | <Comment>66.48.78.1xx</Comment> |
||
13707 | <Link1>http://yesupseo.com/</Link1> |
||
13708 | <Link2></Link2> |
||
13709 | </user-agent> |
||
13710 | <user-agent> |
||
13711 | <ID>id_moz_250107_1</ID> |
||
13712 | <String>Mozilla/5.0 (compatible; Yoono; http://www.yoono.com/)</String> |
||
13713 | <Description>Yoono - community based search (193.110.140.xxx / 194.0.179.[x]xx)</Description> |
||
13714 | <Type>R</Type> |
||
13715 | <Comment>s. also yoono/1.0 web-crawler - yoofind/yoofind ..</Comment> |
||
13716 | <Link1>http://www.yoono.com/</Link1> |
||
13717 | <Link2></Link2> |
||
13718 | </user-agent> |
||
13719 | <user-agent> |
||
13720 | <ID>id_moz_061208_3</ID> |
||
13721 | <String>Mozilla/5.0 (compatible; YoudaoBot/1.0; http://www.youdao.com/help/webmaster/spider/; )</String> |
||
13722 | <Description>Youdao search (China) robot</Description> |
||
13723 | <Type>R</Type> |
||
13724 | <Comment>202.108.7.1xx</Comment> |
||
13725 | <Link1>http://www.youdao.com/</Link1> |
||
13726 | <Link2></Link2> |
||
13727 | </user-agent> |
||
13728 | <user-agent> |
||
13729 | <ID>id_moz_050807_1</ID> |
||
13730 | <String>Mozilla/5.0 (compatible; Zenbot/1.3; +http://zen.co.za/webmasters/)</String> |
||
13731 | <Description>Zenbot robot for the Southern African Zen search service</Description> |
||
13732 | <Type>R</Type> |
||
13733 | <Comment>196.46.116.x[x] / 196.23.180.x[x]</Comment> |
||
13734 | <Link1>http://zen.co.za/</Link1> |
||
13735 | <Link2>http://zen.co.za/webmasters/</Link2> |
||
13736 | </user-agent> |
||
13737 | <user-agent> |
||
13738 | <ID>id_moz_110408_1</ID> |
||
13739 | <String>Mozilla/5.0 (compatible; zermelo +http://www.powerset.com) [email:paul@page-store.com,crawl@powerset.com]</String> |
||
13740 | <Description>Powerset Natural Language Search crawler (under development) using Heritrix via Amazon Web Services</Description> |
||
13741 | <Type>R</Type> |
||
13742 | <Comment>67.202.34.xxx</Comment> |
||
13743 | <Link1>http://www.powerset.com/</Link1> |
||
13744 | <Link2>http://www.amazon.com/gp/browse.html?node=3435361</Link2> |
||
13745 | </user-agent> |
||
13746 | <user-agent> |
||
13747 | <ID>id_moz_030606_1</ID> |
||
13748 | <String>Mozilla/5.0 (compatible;archive.org_bot/1.7.1; collectionId=316; Archive-It; +http://www.archive-it.org)</String> |
||
13749 | <Description>Heritrix - The Internet Archive's open-source crawler (207.241.225.2xx)</Description> |
||
13750 | <Type>R</Type> |
||
13751 | <Comment>s.also - InternetArchive/0.8-dev - archive.org_bot</Comment> |
||
13752 | <Link1>http://www.archive.org/</Link1> |
||
13753 | <Link2></Link2> |
||
13754 | </user-agent> |
||
13755 | <user-agent> |
||
13756 | <ID>id_moz_180906_2</ID> |
||
13757 | <String>Mozilla/5.0 (compatible;archive.org_bot/heritrix-1.9.0-200608171144 +http://pandora.nla.gov.au/crawl.html)</String> |
||
13758 | <Description>Wayback Machine Internet Archive crawler</Description> |
||
13759 | <Type>R</Type> |
||
13760 | <Comment>207.241.233.2xx</Comment> |
||
13761 | <Link1>http://www.archive.org/index.php</Link1> |
||
13762 | <Link2></Link2> |
||
13763 | </user-agent> |
||
13764 | <user-agent> |
||
13765 | <ID>id_moz_180107_1</ID> |
||
13766 | <String>Mozilla/5.0 (compatible;FindITAnswersbot/1.0;+http://search.it-influentials.com/bot.htm)</String> |
||
13767 | <Description>FindITAnswers - Search engine for software developers</Description> |
||
13768 | <Type>B</Type> |
||
13769 | <Comment>74.93.15.249</Comment> |
||
13770 | <Link1>http://www.finditanswers.com/</Link1> |
||
13771 | <Link2></Link2> |
||
13772 | </user-agent> |
||
13773 | <user-agent> |
||
13774 | <ID>id_moz_170906_2</ID> |
||
13775 | <String>Mozilla/5.0 (compatible;MAINSEEK_BOT)</String> |
||
13776 | <Description>Mainseek search (Poland) robot</Description> |
||
13777 | <Type>R</Type> |
||
13778 | <Comment>80.190.213.xx</Comment> |
||
13779 | <Link1>http://www.mainseek.com/</Link1> |
||
13780 | <Link2></Link2> |
||
13781 | </user-agent> |
||
13782 | <user-agent> |
||
13783 | <ID>id_moz_290708_1</ID> |
||
13784 | <String>Mozilla/5.0 (Gecko/20070310 Mozshot/0.0.20070628; http://mozshot.nemui.org/)</String> |
||
13785 | <Description>MozShot - Technical demo to take screenshot of any URL</Description> |
||
13786 | <Type>B</Type> |
||
13787 | <Comment></Comment> |
||
13788 | <Link1>http://mozshot.nemui.org/</Link1> |
||
13789 | <Link2></Link2> |
||
13790 | </user-agent> |
||
13791 | <user-agent> |
||
13792 | <ID>id_moz_150408_2</ID> |
||
13793 | <String>Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.4; en-US; rv:1.9b5) Gecko/2008032619 Firefox/3.0b5</String> |
||
13794 | <Description>Mozilla Firefox 3.0 beta (Gran Paradiso) for MacOS</Description> |
||
13795 | <Type>B</Type> |
||
13796 | <Comment></Comment> |
||
13797 | <Link1>http://developer.mozilla.org/en/docs/Firefox_3_for_developers</Link1> |
||
13798 | <Link2></Link2> |
||
13799 | </user-agent> |
||
13800 | <user-agent> |
||
13801 | <ID>id_moz_976</ID> |
||
13802 | <String>Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.0.1) Gecko/20021219 Chimera/0.6 </String> |
||
13803 | <Description>Chimera browser (Mozilla/Gecko engine) - now Camino Mac PowerPC</Description> |
||
13804 | <Type>B</Type> |
||
13805 | <Comment></Comment> |
||
13806 | <Link1>http://www.mozilla.org</Link1> |
||
13807 | <Link2></Link2> |
||
13808 | </user-agent> |
||
13809 | <user-agent> |
||
13810 | <ID>id_moz_977</ID> |
||
13811 | <String>Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.0.1) Gecko/20030306 Camino/0.7</String> |
||
13812 | <Description>Camino browser (Mozilla/Gecko engine) - ex Chimera Mac PowerPC</Description> |
||
13813 | <Type>B</Type> |
||
13814 | <Comment></Comment> |
||
13815 | <Link1>http://www.mozilla.org</Link1> |
||
13816 | <Link2></Link2> |
||
13817 | </user-agent> |
||
13818 | <user-agent> |
||
13819 | <ID>id_moz_978</ID> |
||
13820 | <String>Mozilla/5.0 (Macintosh; U; PPC Mac OS X; en-US) AppleWebKit/xx (KHTML like Gecko) OmniWeb/v5xx.xx</String> |
||
13821 | <Description>OmniWeb 5.x.x Mac OS X browser</Description> |
||
13822 | <Type>B</Type> |
||
13823 | <Comment></Comment> |
||
13824 | <Link1>http://www.omnigroup.com</Link1> |
||
13825 | <Link2></Link2> |
||
13826 | </user-agent> |
||
13827 | <user-agent> |
||
13828 | <ID>id_moz_979</ID> |
||
13829 | <String>Mozilla/5.0 (Macintosh; U; PPC Mac OS X; en-us) AppleWebKit/xxx.x (KHTML like Gecko) Safari/12x.x</String> |
||
13830 | <Description>Safari 1.2x browser (Mozilla/Gecko engine) MAC OS X</Description> |
||
13831 | <Type>B</Type> |
||
13832 | <Comment></Comment> |
||
13833 | <Link1>http://www.apple.com</Link1> |
||
13834 | <Link2></Link2> |
||
13835 | </user-agent> |
||
13836 | <user-agent> |
||
13837 | <ID>id_moz_980</ID> |
||
13838 | <String>Mozilla/5.0 (Macintosh; U; PPC; en-US; rv:0.9.2) Gecko/20010726 Netscape6/6.1</String> |
||
13839 | <Description>Netscape 6.x Mac PowerPC</Description> |
||
13840 | <Type>B</Type> |
||
13841 | <Comment></Comment> |
||
13842 | <Link1></Link1> |
||
13843 | <Link2></Link2> |
||
13844 | </user-agent> |
||
13845 | <user-agent> |
||
13846 | <ID>id_moz_981</ID> |
||
13847 | <String>Mozilla/5.0 (research@mediatrec.com)</String> |
||
13848 | <Description>unknown robot from gw.ocg-corp.com</Description> |
||
13849 | <Type></Type> |
||
13850 | <Comment></Comment> |
||
13851 | <Link1></Link1> |
||
13852 | <Link2></Link2> |
||
13853 | </user-agent> |
||
13854 | <user-agent> |
||
13855 | <ID>id_moz_260806_1</ID> |
||
13856 | <String>Mozilla/5.0 (Sage)</String> |
||
13857 | <Description>Sage - RSS and Atom feed reader extension for Mozilla Firefox</Description> |
||
13858 | <Type>B</Type> |
||
13859 | <Comment></Comment> |
||
13860 | <Link1>http://sage.mozdev.org/</Link1> |
||
13861 | <Link2></Link2> |
||
13862 | </user-agent> |
||
13863 | <user-agent> |
||
13864 | <ID>id_moz_982</ID> |
||
13865 | <String>Mozilla/5.0 (Slurp/cat; slurp@inktomi.com; http://www.inktomi.com/slurp.html)</String> |
||
13866 | <Description>Inktomi (Hotbot-Lycos - NBCi etc.) robot</Description> |
||
13867 | <Type>R</Type> |
||
13868 | <Comment></Comment> |
||
13869 | <Link1>http://www.inktomi.com</Link1> |
||
13870 | <Link2></Link2> |
||
13871 | </user-agent> |
||
13872 | <user-agent> |
||
13873 | <ID>id_moz_983</ID> |
||
13874 | <String>Mozilla/5.0 (Slurp/si; slurp@inktomi.com; http://www.inktomi.com/slurp.html)</String> |
||
13875 | <Description>Inktomi (Hotbot-Lycos - NBCi etc.) robot</Description> |
||
13876 | <Type>R</Type> |
||
13877 | <Comment></Comment> |
||
13878 | <Link1>http://www.inktomi.com</Link1> |
||
13879 | <Link2></Link2> |
||
13880 | </user-agent> |
||
13881 | <user-agent> |
||
13882 | <ID>id_moz_984</ID> |
||
13883 | <String>Mozilla/5.0 (SunOS 5.8 sun4u; U) Opera 5.0 [en]</String> |
||
13884 | <Description>Opera 5.x SunOS</Description> |
||
13885 | <Type>B</Type> |
||
13886 | <Comment></Comment> |
||
13887 | <Link1></Link1> |
||
13888 | <Link2></Link2> |
||
13889 | </user-agent> |
||
13890 | <user-agent> |
||
13891 | <ID>id_moz_020507_1</ID> |
||
13892 | <String>Mozilla/5.0 (Twiceler-0.9 http://www.cuill.com/twiceler/robot.html)</String> |
||
13893 | <Description>Twiceler experimental web crawler</Description> |
||
13894 | <Type>R</Type> |
||
13895 | <Comment>64.62.136.xxx</Comment> |
||
13896 | <Link1>http://www.cuill.com/</Link1> |
||
13897 | <Link2></Link2> |
||
13898 | </user-agent> |
||
13899 | <user-agent> |
||
13900 | <ID>id_moz_070106_2</ID> |
||
13901 | <String>Mozilla/5.0 (Version: xxxx Type:xx)</String> |
||
13902 | <Description>Some spambot from Romania (82.208.139.1xx & 86.123.65.xx) - Maybe email harvesting</Description> |
||
13903 | <Type>S</Type> |
||
13904 | <Comment>UA sometimes have random letters like: vkfjkgo...</Comment> |
||
13905 | <Link1></Link1> |
||
13906 | <Link2></Link2> |
||
13907 | </user-agent> |
||
13908 | <user-agent> |
||
13909 | <ID>id_moz_985</ID> |
||
13910 | <String>Mozilla/5.0 (wgao@genieknows.com)</String> |
||
13911 | <Description>GenieKnows.com search robot (64.5.245.xx / 64.5.220.xxx)</Description> |
||
13912 | <Type>R</Type> |
||
13913 | <Comment></Comment> |
||
13914 | <Link1>http://www.genieknows.com/</Link1> |
||
13915 | <Link2></Link2> |
||
13916 | </user-agent> |
||
13917 | <user-agent> |
||
13918 | <ID>id_moz_986</ID> |
||
13919 | <String>Mozilla/5.0 (Windows; U; Win98; en-US; rv:0.9.2) Gecko/20010726 Netscape6/6.1</String> |
||
13920 | <Description>Netscape 6.x Win98</Description> |
||
13921 | <Type>B</Type> |
||
13922 | <Comment></Comment> |
||
13923 | <Link1></Link1> |
||
13924 | <Link2></Link2> |
||
13925 | </user-agent> |
||
13926 | <user-agent> |
||
13927 | <ID>id_moz_987</ID> |
||
13928 | <String>Mozilla/5.0 (Windows; U; Win98; en-US; rv:x.xx) Gecko/20030423 Firebird Browser/0.6</String> |
||
13929 | <Description>Firebird browser (Mozilla/Gecko engine) - ex Phoenix Win98</Description> |
||
13930 | <Type>B</Type> |
||
13931 | <Comment></Comment> |
||
13932 | <Link1>http://www.mozilla.org</Link1> |
||
13933 | <Link2></Link2> |
||
13934 | </user-agent> |
||
13935 | <user-agent> |
||
13936 | <ID>id_moz_988</ID> |
||
13937 | <String>Mozilla/5.0 (Windows; U; Win9x; en; Stable) Gecko/20020911 Beonex/0.8.1-stable</String> |
||
13938 | <Description>Beonex Communicator browser (Mozilla/Gecko engine)</Description> |
||
13939 | <Type>B</Type> |
||
13940 | <Comment></Comment> |
||
13941 | <Link1>http://www.beonex.com</Link1> |
||
13942 | <Link2></Link2> |
||
13943 | </user-agent> |
||
13944 | <user-agent> |
||
13945 | <ID>id_moz_111205_1</ID> |
||
13946 | <String>Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.7.7) NimbleCrawler 1.11 obeys UserAgent NimbleCrawler For problems contact: crawler_at_dataalchemy.com</String> |
||
13947 | <Description>Healthline health related search robot (72.5.115.xx)</Description> |
||
13948 | <Type>R</Type> |
||
13949 | <Comment></Comment> |
||
13950 | <Link1>http://www.healthline.com/</Link1> |
||
13951 | <Link2></Link2> |
||
13952 | </user-agent> |
||
13953 | <user-agent> |
||
13954 | <ID>id_moz_171008_2</ID> |
||
13955 | <String>Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/0.2.153.1 Safari/525.19</String> |
||
13956 | <Description>Google Chrome browser based on WebKit (Safari)</Description> |
||
13957 | <Type>B</Type> |
||
13958 | <Comment></Comment> |
||
13959 | <Link1>http://www.google.com/chrome</Link1> |
||
13960 | <Link2></Link2> |
||
13961 | </user-agent> |
||
13962 | <user-agent> |
||
13963 | <ID>id_moz_170207_1</ID> |
||
13964 | <String>Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.0.5) Gecko/20060731 Firefox/1.5.0.5 Flock/0.7.4.1</String> |
||
13965 | <Description>Flock web browser built on Mozilla technologies</Description> |
||
13966 | <Type>B</Type> |
||
13967 | <Comment></Comment> |
||
13968 | <Link1>http://www.flock.com/</Link1> |
||
13969 | <Link2></Link2> |
||
13970 | </user-agent> |
||
13971 | <user-agent> |
||
13972 | <ID>id_moz_190108_3</ID> |
||
13973 | <String>Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.4/Megaupload x.0</String> |
||
13974 | <Description>Megaupload Mega Manager - Download manager plugin for Firefox</Description> |
||
13975 | <Type>D</Type> |
||
13976 | <Comment></Comment> |
||
13977 | <Link1>http://www.megaupload.com/manager/de/</Link1> |
||
13978 | <Link2></Link2> |
||
13979 | </user-agent> |
||
13980 | <user-agent> |
||
13981 | <ID>id_moz_171008_1</ID> |
||
13982 | <String>Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.1) Gecko/2008092215 Firefox/3.0.1 Orca/1.1 beta 3</String> |
||
13983 | <Description>Orca browser - based on Gecko</Description> |
||
13984 | <Type>B</Type> |
||
13985 | <Comment></Comment> |
||
13986 | <Link1>http://www.orcabrowser.com</Link1> |
||
13987 | <Link2></Link2> |
||
13988 | </user-agent> |
||
13989 | <user-agent> |
||
13990 | <ID>id_moz_989</ID> |
||
13991 | <String>Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:x.x.x) Gecko/20041107 Firefox/x.x</String> |
||
13992 | <Description>Firefox browser (Mozilla/Gecko engine) - ex Firebird WinXP</Description> |
||
13993 | <Type>B</Type> |
||
13994 | <Comment></Comment> |
||
13995 | <Link1>http://www.mozilla.org</Link1> |
||
13996 | <Link2></Link2> |
||
13997 | </user-agent> |
||
13998 | <user-agent> |
||
13999 | <ID>id_moz_990</ID> |
||
14000 | <String>Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:x.xx) Gecko/20030504 Mozilla Firebird/0.6</String> |
||
14001 | <Description>Firebird browser (Mozilla/Gecko engine) - ex Phoenix WinXP</Description> |
||
14002 | <Type>B</Type> |
||
14003 | <Comment></Comment> |
||
14004 | <Link1>http://www.mozilla.org</Link1> |
||
14005 | <Link2></Link2> |
||
14006 | </user-agent> |
||
14007 | <user-agent> |
||
14008 | <ID>id_moz_991</ID> |
||
14009 | <String>Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:x.xxx) Gecko/20041027 Mnenhy/0.6.0.104</String> |
||
14010 | <Description>Mnenhy - enhanced mail & news Mozilla based browser</Description> |
||
14011 | <Type>B</Type> |
||
14012 | <Comment></Comment> |
||
14013 | <Link1>http://mnenhy.mozdev.org/index-de.html</Link1> |
||
14014 | <Link2></Link2> |
||
14015 | </user-agent> |
||
14016 | <user-agent> |
||
14017 | <ID>id_moz_060508_2</ID> |
||
14018 | <String>Mozilla/5.0 (Windows; U; Windows NT 5.1; fr; rv:1.8.1) VoilaBot BETA 1.2 (support.voilabot@orange-ftgroup.com)</String> |
||
14019 | <Description>Voila.fr robot</Description> |
||
14020 | <Type>R</Type> |
||
14021 | <Comment></Comment> |
||
14022 | <Link1>http://www.voila.fr</Link1> |
||
14023 | <Link2></Link2> |
||
14024 | </user-agent> |
||
14025 | <user-agent> |
||
14026 | <ID>id_moz_080608_2</ID> |
||
14027 | <String>Mozilla/5.0 (Windows; U; Windows NT 5.1; fr; rv:1.8.1) VoilaBot BETA 1.2 (support.voilabot@orange-ftgroup.com)</String> |
||
14028 | <Description>Voila.fr robot</Description> |
||
14029 | <Type>R</Type> |
||
14030 | <Comment></Comment> |
||
14031 | <Link1>http://www.voila.fr</Link1> |
||
14032 | <Link2></Link2> |
||
14033 | </user-agent> |
||
14034 | <user-agent> |
||
14035 | <ID>id_moz_150408_3</ID> |
||
14036 | <String>Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9b5) Gecko/2008032620 Firefox/3.0b5</String> |
||
14037 | <Description>Mozilla Firefox 3.0 beta (Gran Paradiso) for Win</Description> |
||
14038 | <Type>B</Type> |
||
14039 | <Comment></Comment> |
||
14040 | <Link1>http://developer.mozilla.org/en/docs/Firefox_3_for_developers</Link1> |
||
14041 | <Link2></Link2> |
||
14042 | </user-agent> |
||
14043 | <user-agent> |
||
14044 | <ID>id_moz_300407_2</ID> |
||
14045 | <String>Mozilla/5.0 (Windows; U;XMPP Tiscali Communicator v.10.0.1; Windows NT 5.1; it; rv:1.8.1.3) Gecko/20070309 Firefox/2.0.0.3</String> |
||
14046 | <Description>Tiscali Communicator - Online services suite</Description> |
||
14047 | <Type>B</Type> |
||
14048 | <Comment></Comment> |
||
14049 | <Link1>http://im.tiscali.com/index.html</Link1> |
||
14050 | <Link2></Link2> |
||
14051 | </user-agent> |
||
14052 | <user-agent> |
||
14053 | <ID>id_moz_300106_1</ID> |
||
14054 | <String>Mozilla/5.0 (Windows;) NimbleCrawler 1.12 obeys UserAgent NimbleCrawler For problems contact: crawler@health</String> |
||
14055 | <Description>Healthline health related search robot (72.5.115.xx)</Description> |
||
14056 | <Type>R</Type> |
||
14057 | <Comment></Comment> |
||
14058 | <Link1>http://www.healthline.com/</Link1> |
||
14059 | <Link2></Link2> |
||
14060 | </user-agent> |
||
14061 | <user-agent> |
||
14062 | <ID>id_moz_161205_2</ID> |
||
14063 | <String>Mozilla/5.0 (Windows;) NimbleCrawler 1.12 obeys UserAgent NimbleCrawler For problems contact: crawler@healthline.com</String> |
||
14064 | <Description>Healthline health related search robot (72.5.115.xx)</Description> |
||
14065 | <Type>R</Type> |
||
14066 | <Comment></Comment> |
||
14067 | <Link1>http://www.healthline.com/</Link1> |
||
14068 | <Link2></Link2> |
||
14069 | </user-agent> |
||
14070 | <user-agent> |
||
14071 | <ID>id_moz_090807_2</ID> |
||
14072 | <String>Mozilla/5.0 (X11; Linux i686; U;rv: 1.7.13) Gecko/20070322 Kazehakase/0.4.4.1</String> |
||
14073 | <Description>Kazehakase - Gecko based browser (Japan)</Description> |
||
14074 | <Type>B</Type> |
||
14075 | <Comment></Comment> |
||
14076 | <Link1>http://kazehakase.sourceforge.jp/</Link1> |
||
14077 | <Link2></Link2> |
||
14078 | </user-agent> |
||
14079 | <user-agent> |
||
14080 | <ID>id_moz_992</ID> |
||
14081 | <String>Mozilla/5.0 (X11; U; Linux 2.4.2-2 i586; en-US; m18) Gecko/20010131 Netscape6/6.01</String> |
||
14082 | <Description>Netscape 6.x Linux</Description> |
||
14083 | <Type>B</Type> |
||
14084 | <Comment></Comment> |
||
14085 | <Link1></Link1> |
||
14086 | <Link2></Link2> |
||
14087 | </user-agent> |
||
14088 | <user-agent> |
||
14089 | <ID>id_moz_160306_1</ID> |
||
14090 | <String>Mozilla/5.0 (X11; U; Linux i686; de-AT; rv:1.8.0.2) Gecko/20060309 SeaMonkey/1.0</String> |
||
14091 | <Description>SeaMonkey browser suite (ex Mozilla) on Linux</Description> |
||
14092 | <Type>B</Type> |
||
14093 | <Comment></Comment> |
||
14094 | <Link1>http://www.mozilla.org/projects/seamonkey/</Link1> |
||
14095 | <Link2></Link2> |
||
14096 | </user-agent> |
||
14097 | <user-agent> |
||
14098 | <ID>id_moz_993</ID> |
||
14099 | <String>Mozilla/5.0 (X11; U; Linux i686; en-GB; rv:1.7.6) Gecko/20050405 Epiphany/1.6.1 (Ubuntu) (Ubuntu package 1.0.2)</String> |
||
14100 | <Description>Epiphany (Mozilla/Gecko engine) browser Linux</Description> |
||
14101 | <Type>B</Type> |
||
14102 | <Comment></Comment> |
||
14103 | <Link1>http://www.gnome.org/projects/epiphany/</Link1> |
||
14104 | <Link2></Link2> |
||
14105 | </user-agent> |
||
14106 | <user-agent> |
||
14107 | <ID>id_moz_994</ID> |
||
14108 | <String>Mozilla/5.0 (X11; U; Linux i686; en-US; Nautilus/1.0Final) Gecko/20020408</String> |
||
14109 | <Description>Nautilus (developed by Eazel.com) 1.x Browser Linux</Description> |
||
14110 | <Type>B</Type> |
||
14111 | <Comment></Comment> |
||
14112 | <Link1>http://swin05.dyndns.biz/Doc/Docrh7.03us/DocRH7.3us/sunsite.mff.cuni.cz/pub/redhat/linux/7.3/fr/doc/RH-DOCS/rhl-gsg-en-7.3/s1-browsers-nautilus.html</Link1> |
||
14113 | <Link2></Link2> |
||
14114 | </user-agent> |
||
14115 | <user-agent> |
||
14116 | <ID>id_moz_995</ID> |
||
14117 | <String>Mozilla/5.0 (X11; U; Linux i686; en-US; rv:0.9.3) Gecko/20010801</String> |
||
14118 | <Description>Mozilla (Gecko) 0.9x browser Linux</Description> |
||
14119 | <Type>B</Type> |
||
14120 | <Comment></Comment> |
||
14121 | <Link1></Link1> |
||
14122 | <Link2></Link2> |
||
14123 | </user-agent> |
||
14124 | <user-agent> |
||
14125 | <ID>id_moz_030110_5</ID> |
||
14126 | <String>Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2.1; aggregator:Spinn3r (Spinn3r 3.1); http://spinn3r.com/robot) Gecko/20021130</String> |
||
14127 | <Description>Spinn3r social network crawler</Description> |
||
14128 | <Type>R</Type> |
||
14129 | <Comment>64.34.195.1xx</Comment> |
||
14130 | <Link1>http://spinn3r.com/</Link1> |
||
14131 | <Link2></Link2> |
||
14132 | </user-agent> |
||
14133 | <user-agent> |
||
14134 | <ID>id_moz_996</ID> |
||
14135 | <String>Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2b) Gecko/20021007 Phoenix/0.3</String> |
||
14136 | <Description>Phoenix 0.3 browser (Mozilla/Gecko engine) - now Firebird Linux</Description> |
||
14137 | <Type>B</Type> |
||
14138 | <Comment></Comment> |
||
14139 | <Link1>http://www.firebirdsql.org/</Link1> |
||
14140 | <Link2></Link2> |
||
14141 | </user-agent> |
||
14142 | <user-agent> |
||
14143 | <ID>id_moz_997</ID> |
||
14144 | <String>Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.6) Gecko/20040413 Epiphany/1.2.1</String> |
||
14145 | <Description>Epiphany (Mozilla/Gecko engine) browser Linux</Description> |
||
14146 | <Type>B</Type> |
||
14147 | <Comment></Comment> |
||
14148 | <Link1>http://www.gnome.org/projects/epiphany/</Link1> |
||
14149 | <Link2></Link2> |
||
14150 | </user-agent> |
||
14151 | <user-agent> |
||
14152 | <ID>id_moz_190107_1</ID> |
||
14153 | <String>Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.7) Gecko/20060909 Firefox/1.5.0.7 SnapPreviewBot</String> |
||
14154 | <Description>Snap Firefox Search Plugin</Description> |
||
14155 | <Type>B</Type> |
||
14156 | <Comment></Comment> |
||
14157 | <Link1>http://www.snap.com/about/spa1A.php</Link1> |
||
14158 | <Link2></Link2> |
||
14159 | </user-agent> |
||
14160 | <user-agent> |
||
14161 | <ID>id_moz_240107_2</ID> |
||
14162 | <String>Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.1) Gecko/20061129 BonEcho/2.0</String> |
||
14163 | <Description>Bon Echo Alpha - developer preview of future Firefox browser</Description> |
||
14164 | <Type>B</Type> |
||
14165 | <Comment></Comment> |
||
14166 | <Link1>http://www.mozilla.org/projects/bonecho/releases/2.0a1.html</Link1> |
||
14167 | <Link2></Link2> |
||
14168 | </user-agent> |
||
14169 | <user-agent> |
||
14170 | <ID>id_moz_240207_2</ID> |
||
14171 | <String>Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.1.1) Gecko/20061205 Iceweasel/2.0.0.1 (Debian-2.0.0.1+dfsg-2)</String> |
||
14172 | <Description>IceWeasel - the GNU version of the Firefox browser</Description> |
||
14173 | <Type>B</Type> |
||
14174 | <Comment></Comment> |
||
14175 | <Link1>http://www.gnu.org/software/gnuzilla/</Link1> |
||
14176 | <Link2></Link2> |
||
14177 | </user-agent> |
||
14178 | <user-agent> |
||
14179 | <ID>id_moz_150408_1</ID> |
||
14180 | <String>Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9a8) Gecko/2007100619 GranParadiso/3.0a8</String> |
||
14181 | <Description>Mozilla Firefox 3.0 beta (Gran Paradiso) for Linux</Description> |
||
14182 | <Type>B</Type> |
||
14183 | <Comment></Comment> |
||
14184 | <Link1>http://developer.mozilla.org/en/docs/Firefox_3_for_developers</Link1> |
||
14185 | <Link2></Link2> |
||
14186 | </user-agent> |
||
14187 | <user-agent> |
||
14188 | <ID>id_moz_999</ID> |
||
14189 | <String>Mozilla/5.0 Galeon/1.0.2 (X11; Linux i686; U;) Gecko/20011224</String> |
||
14190 | <Description>Galeon 1.x Browser Linux</Description> |
||
14191 | <Type>B</Type> |
||
14192 | <Comment></Comment> |
||
14193 | <Link1>http://galeon.sourceforge.net/</Link1> |
||
14194 | <Link2></Link2> |
||
14195 | </user-agent> |
||
14196 | <user-agent> |
||
14197 | <ID>id_moz_1000</ID> |
||
14198 | <String>Mozilla/5.0 gURLChecker/0.x.x (Linux)</String> |
||
14199 | <Description>gURLChecker - GNOME link checking tool</Description> |
||
14200 | <Type>C</Type> |
||
14201 | <Comment></Comment> |
||
14202 | <Link1>http://www.nongnu.org</Link1> |
||
14203 | <Link2></Link2> |
||
14204 | </user-agent> |
||
14205 | <user-agent> |
||
14206 | <ID>id_moz_1001</ID> |
||
14207 | <String>Mozilla/5.0 URL-Spider</String> |
||
14208 | <Description>URL Spider - used by usww.net</Description> |
||
14209 | <Type>R</Type> |
||
14210 | <Comment></Comment> |
||
14211 | <Link1>http://www.url-spider.com/</Link1> |
||
14212 | <Link2></Link2> |
||
14213 | </user-agent> |
||
14214 | <user-agent> |
||
14215 | <ID>id_moz_1002</ID> |
||
14216 | <String>Mozilla/5.0 usww.com-Spider-for-w8.net</String> |
||
14217 | <Description>W8net spider</Description> |
||
14218 | <Type>R</Type> |
||
14219 | <Comment></Comment> |
||
14220 | <Link1>http://www.usww.com</Link1> |
||
14221 | <Link2></Link2> |
||
14222 | </user-agent> |
||
14223 | <user-agent> |
||
14224 | <ID>id_moz_1003</ID> |
||
14225 | <String>Mozilla/5.0 wgao@genieknows.com</String> |
||
14226 | <Description>GenieKnows.com search robot (64.5.245.xx / 64.5.220.xxx)</Description> |
||
14227 | <Type>R</Type> |
||
14228 | <Comment></Comment> |
||
14229 | <Link1>http://www.genieknows.com</Link1> |
||
14230 | <Link2></Link2> |
||
14231 | </user-agent> |
||
14232 | <user-agent> |
||
14233 | <ID>id_moz_111205_7</ID> |
||
14234 | <String>Mozilla/5.0 whoiam [http://www.axxus.de/]</String> |
||
14235 | <Description>axxus.de German business directory</Description> |
||
14236 | <Type>R C</Type> |
||
14237 | <Comment></Comment> |
||
14238 | <Link1>http://www.axxus.de/</Link1> |
||
14239 | <Link2></Link2> |
||
14240 | </user-agent> |
||
14241 | <user-agent> |
||
14242 | <ID>id_moz_998</ID> |
||
14243 | <String>Mozilla/5.0 [en] (compatible; Gulper Web Bot 0.2.4 www.ecsl.cs.sunysb.edu/~maxim/cgi-bin/Link/GulperBot)</String> |
||
14244 | <Description>Yuntis : Collaborative Web Resource Categorization and Ranking Project robot</Description> |
||
14245 | <Type>R</Type> |
||
14246 | <Comment></Comment> |
||
14247 | <Link1>http://www.ecsl.cs.sunysb.edu/yuntis/</Link1> |
||
14248 | <Link2></Link2> |
||
14249 | </user-agent> |
||
14250 | <user-agent> |
||
14251 | <ID>id_g_m_190606_1</ID> |
||
14252 | <String>MQbot metaquerier.cs.uiuc.edu/crawler</String> |
||
14253 | <Description>MetaExplorer project's MetaQuerier robot</Description> |
||
14254 | <Type>R</Type> |
||
14255 | <Comment>192.17.11.xx</Comment> |
||
14256 | <Link1>http://metaquerier.cs.uiuc.edu/</Link1> |
||
14257 | <Link2></Link2> |
||
14258 | </user-agent> |
||
14259 | <user-agent> |
||
14260 | <ID>id_g_m_251006_1</ID> |
||
14261 | <String>MQBOT/Nutch-0.9-dev (MQBOT Nutch Crawler; http://falcon.cs.uiuc.edu; mqbot@cs.uiuc.edu)</String> |
||
14262 | <Description>MetaExplorer project's MetaQuerier robot</Description> |
||
14263 | <Type>R</Type> |
||
14264 | <Comment>192.17.11.xx</Comment> |
||
14265 | <Link1>http://metaquerier.cs.uiuc.edu/</Link1> |
||
14266 | <Link2></Link2> |
||
14267 | </user-agent> |
||
14268 | <user-agent> |
||
14269 | <ID>id_g_m_1004</ID> |
||
14270 | <String>MSFrontPage/4.0</String> |
||
14271 | <Description>MS Frontpage 4.x</Description> |
||
14272 | <Type>B</Type> |
||
14273 | <Comment></Comment> |
||
14274 | <Link1></Link1> |
||
14275 | <Link2></Link2> |
||
14276 | </user-agent> |
||
14277 | <user-agent> |
||
14278 | <ID>id_g_m_1005</ID> |
||
14279 | <String>MSIE 4.0 (Win95)</String> |
||
14280 | <Description>Some faked UA - maybe for a download manager</Description> |
||
14281 | <Type>D</Type> |
||
14282 | <Comment></Comment> |
||
14283 | <Link1></Link1> |
||
14284 | <Link2></Link2> |
||
14285 | </user-agent> |
||
14286 | <user-agent> |
||
14287 | <ID>id_g_m_1006</ID> |
||
14288 | <String>MSIE-5.13 (larbin@unspecified.mail)</String> |
||
14289 | <Description>unknown robot from gw.ocg-corp.com (209.126.176.x)</Description> |
||
14290 | <Type></Type> |
||
14291 | <Comment>see also: - Opera/6.01 (larbin@.....) - WinampMPEG/2.00 larbin@....</Comment> |
||
14292 | <Link1></Link1> |
||
14293 | <Link2></Link2> |
||
14294 | </user-agent> |
||
14295 | <user-agent> |
||
14296 | <ID>id_g_m_190506_1</ID> |
||
14297 | <String>msnbot-media/1.0 (+http://search.msn.com/msnbot.htm)</String> |
||
14298 | <Description>MSN media search robot</Description> |
||
14299 | <Type>R</Type> |
||
14300 | <Comment>65.55.235.1xx</Comment> |
||
14301 | <Link1>http://search.msn.com</Link1> |
||
14302 | <Link2></Link2> |
||
14303 | </user-agent> |
||
14304 | <user-agent> |
||
14305 | <ID>id_g_m_290806_1</ID> |
||
14306 | <String>msnbot-Products/1.0 (+http://search.msn.com/msnbot.htm)</String> |
||
14307 | <Description>Windows Live product search (Beta) robot</Description> |
||
14308 | <Type>R</Type> |
||
14309 | <Comment>207.68.157.xxx</Comment> |
||
14310 | <Link1>http://products.live.com</Link1> |
||
14311 | <Link2>http://productsearch.spaces.live.com/</Link2> |
||
14312 | </user-agent> |
||
14313 | <user-agent> |
||
14314 | <ID>id_g_m_1007</ID> |
||
14315 | <String>MSNBOT/0.xx (http://search.msn.com/msnbot.htm)</String> |
||
14316 | <Description>MSN Search robot - 131.107.xxx.xxx 204.95.96.xxx - 204.95.111.xxx 207.46.xxx.xxx</Description> |
||
14317 | <Type>R</Type> |
||
14318 | <Comment>s. also Mozilla/4.0 (compatible; MSIE 6.0; Windows NT; MS Search...</Comment> |
||
14319 | <Link1>http://search.msn.com</Link1> |
||
14320 | <Link2></Link2> |
||
14321 | </user-agent> |
||
14322 | <user-agent> |
||
14323 | <ID>id_g_m_1008</ID> |
||
14324 | <String>msnbot/x.xx ( http://search.msn.com/msnbot.htm)</String> |
||
14325 | <Description>MSN Search robot - 131.107.xxx.xxx 204.95.96.xxx - 204.95.111.xxx 207.46.xxx.xxx</Description> |
||
14326 | <Type>R</Type> |
||
14327 | <Comment>s. also Mozilla/4.0 (compatible; MSIE 6.0; Windows NT; MS Search...</Comment> |
||
14328 | <Link1>http://search.msn.com</Link1> |
||
14329 | <Link2></Link2> |
||
14330 | </user-agent> |
||
14331 | <user-agent> |
||
14332 | <ID>id_g_m_190108_2</ID> |
||
14333 | <String>MSNBOT_Mobile MSMOBOT Mozilla/2.0 (compatible; MSIE 4.02; Windows CE; Default)</String> |
||
14334 | <Description>Microsoft search for mobiles</Description> |
||
14335 | <Type>R</Type> |
||
14336 | <Comment>65.55.241.2xx</Comment> |
||
14337 | <Link1>http://livesearchmobile.com/?mid=1011</Link1> |
||
14338 | <Link2></Link2> |
||
14339 | </user-agent> |
||
14340 | <user-agent> |
||
14341 | <ID>id_g_m_1009</ID> |
||
14342 | <String>MSNPTC/1.0</String> |
||
14343 | <Description>MSN Search robot - 131.107.xxx.xxx 204.95.96.xxx - 204.95.111.xxx 207.46.xxx.xxx</Description> |
||
14344 | <Type>R</Type> |
||
14345 | <Comment>s. also Mozilla/4.0 (compatible; MSIE 6.0; Windows NT; MS Search...</Comment> |
||
14346 | <Link1>http://search.msn.com</Link1> |
||
14347 | <Link2></Link2> |
||
14348 | </user-agent> |
||
14349 | <user-agent> |
||
14350 | <ID>id_g_m_1010</ID> |
||
14351 | <String>MSProxy/2.0</String> |
||
14352 | <Description>Microsoft proxy server</Description> |
||
14353 | <Type>P</Type> |
||
14354 | <Comment></Comment> |
||
14355 | <Link1>http://www.microsoft.com/isaserver/evaluation/previousversions/default.mspx</Link1> |
||
14356 | <Link2></Link2> |
||
14357 | </user-agent> |
||
14358 | <user-agent> |
||
14359 | <ID>id_g_m_181205_3</ID> |
||
14360 | <String>MSRBOT</String> |
||
14361 | <Description>MacEdition CodeBitch link checking</Description> |
||
14362 | <Type>C</Type> |
||
14363 | <Comment></Comment> |
||
14364 | <Link1>http://www.macedition.com/cb/cb_20030310.php</Link1> |
||
14365 | <Link2></Link2> |
||
14366 | </user-agent> |
||
14367 | <user-agent> |
||
14368 | <ID>id_g_m_270407_1</ID> |
||
14369 | <String>MSRBOT (http://research.microsoft.com/research/sv/msrbot)</String> |
||
14370 | <Description>Microsoft MSRBot</Description> |
||
14371 | <Type>R</Type> |
||
14372 | <Comment></Comment> |
||
14373 | <Link1>http://research.microsoft.com/research/sv/msrbot/</Link1> |
||
14374 | <Link2></Link2> |
||
14375 | </user-agent> |
||
14376 | <user-agent> |
||
14377 | <ID>id_g_m_070406_3</ID> |
||
14378 | <String>Mulder, VCR-1.0</String> |
||
14379 | <Description>StreamBox VCR user agent</Description> |
||
14380 | <Type>D</Type> |
||
14381 | <Comment></Comment> |
||
14382 | <Link1>http://all-streaming-media.com/streaming-media-faq/faq-streambox-vcr-download-problems.htm</Link1> |
||
14383 | <Link2></Link2> |
||
14384 | </user-agent> |
||
14385 | <user-agent> |
||
14386 | <ID>id_g_m_1011</ID> |
||
14387 | <String>multiBlocker browser</String> |
||
14388 | <Description>Multiblocker (Fantomaster) anonymity software user</Description> |
||
14389 | <Type>P</Type> |
||
14390 | <Comment></Comment> |
||
14391 | <Link1>http://multiblocker.com/home.html</Link1> |
||
14392 | <Link2>http://fantomaster.com</Link2> |
||
14393 | </user-agent> |
||
14394 | <user-agent> |
||
14395 | <ID>id_g_m_030807_1</ID> |
||
14396 | <String>multicrawler ( http://sw.deri.org/2006/04/multicrawler/robots.html)</String> |
||
14397 | <Description>MultiCrawler for DERI Galway's Semantic Web Search Engine cluster</Description> |
||
14398 | <Type>R</Type> |
||
14399 | <Comment>140.203.154.1xx</Comment> |
||
14400 | <Link1>http://sw.deri.org/2006/04/multicrawler/robots.html</Link1> |
||
14401 | <Link2>http://sw.deri.ie/</Link2> |
||
14402 | </user-agent> |
||
14403 | <user-agent> |
||
14404 | <ID>id_g_m_1012</ID> |
||
14405 | <String>MultiText/0.1</String> |
||
14406 | <Description>Virginia Tech Digital Library Research Laboratory robot</Description> |
||
14407 | <Type>R</Type> |
||
14408 | <Comment></Comment> |
||
14409 | <Link1>http://www.dlib.vt.edu</Link1> |
||
14410 | <Link2></Link2> |
||
14411 | </user-agent> |
||
14412 | <user-agent> |
||
14413 | <ID>id_g_m_1013</ID> |
||
14414 | <String>MusicWalker2.0 ( http://www.somusical.com)</String> |
||
14415 | <Description>SoMusical! musical directory link checking</Description> |
||
14416 | <Type>R</Type> |
||
14417 | <Comment></Comment> |
||
14418 | <Link1>http://www.somusical.com</Link1> |
||
14419 | <Link2></Link2> |
||
14420 | </user-agent> |
||
14421 | <user-agent> |
||
14422 | <ID>id_g_m_270306_1</ID> |
||
14423 | <String>MVAClient</String> |
||
14424 | <Description>Unknown bad bot from diff. Taiwanese IPs</Description> |
||
14425 | <Type>S</Type> |
||
14426 | <Comment>see this blog:</Comment> |
||
14427 | <Link1>http://www.tenspider.com/business-blog/weblog.php</Link1> |
||
14428 | <Link2></Link2> |
||
14429 | </user-agent> |
||
14430 | <user-agent> |
||
14431 | <ID>id_g_m_241105_1</ID> |
||
14432 | <String>My WinHTTP Connection</String> |
||
14433 | <Description>Windows HTTP Services (WinHTTP)</Description> |
||
14434 | <Type></Type> |
||
14435 | <Comment></Comment> |
||
14436 | <Link1>http://msdn.microsoft.com/library/?url=/library/en-us/winhttp/http/about_winhttp.asp</Link1> |
||
14437 | <Link2></Link2> |
||
14438 | </user-agent> |
||
14439 | <user-agent> |
||
14440 | <ID>id_g_m_1014</ID> |
||
14441 | <String>myDaemon</String> |
||
14442 | <Description>unknown user robot (24.124.34.42)</Description> |
||
14443 | <Type></Type> |
||
14444 | <Comment></Comment> |
||
14445 | <Link1></Link1> |
||
14446 | <Link2></Link2> |
||
14447 | </user-agent> |
||
14448 | <user-agent> |
||
14449 | <ID>id_g_m_1015</ID> |
||
14450 | <String>MyGetRight/1.0.0</String> |
||
14451 | <Description>GetRight download manager</Description> |
||
14452 | <Type>D</Type> |
||
14453 | <Comment></Comment> |
||
14454 | <Link1>http://www.getright.com</Link1> |
||
14455 | <Link2></Link2> |
||
14456 | </user-agent> |
||
14457 | <user-agent> |
||
14458 | <ID>id_g_m_1016</ID> |
||
14459 | <String>MyGetRight/1.0b</String> |
||
14460 | <Description>GetRight download manager</Description> |
||
14461 | <Type>D</Type> |
||
14462 | <Comment></Comment> |
||
14463 | <Link1>http://www.getright.com</Link1> |
||
14464 | <Link2></Link2> |
||
14465 | </user-agent> |
||
14466 | <user-agent> |
||
14467 | <ID>id_g_m_1017</ID> |
||
14468 | <String>Mylinea.com Crawler 2.0</String> |
||
14469 | <Description>Mylinea France web catalogue crawler</Description> |
||
14470 | <Type>R</Type> |
||
14471 | <Comment></Comment> |
||
14472 | <Link1>http://www.mylinea.com</Link1> |
||
14473 | <Link2></Link2> |
||
14474 | </user-agent> |
||
14475 | <user-agent> |
||
14476 | <ID>id_g_m_040906_1</ID> |
||
14477 | <String>mylinkcheck/1.02</String> |
||
14478 | <Description>VDOG - SEO webdirecory (Germany) link checking</Description> |
||
14479 | <Type>C</Type> |
||
14480 | <Comment></Comment> |
||
14481 | <Link1>http://www.vdog.de/</Link1> |
||
14482 | <Link2></Link2> |
||
14483 | </user-agent> |
||
14484 | <user-agent> |
||
14485 | <ID>id_n_s_1018</ID> |
||
14486 | <String>Naamah 1.0.1/Blogbot (http://blogbot.de/)</String> |
||
14487 | <Description>Blogbot (Germany) robot</Description> |
||
14488 | <Type>R</Type> |
||
14489 | <Comment></Comment> |
||
14490 | <Link1>http://blogbot.de/</Link1> |
||
14491 | <Link2></Link2> |
||
14492 | </user-agent> |
||
14493 | <user-agent> |
||
14494 | <ID>id_n_s_1019</ID> |
||
14495 | <String>Naamah 1.0a/Blogbot (http://blogbot.de/)</String> |
||
14496 | <Description>Blogbot (Germany) robot</Description> |
||
14497 | <Type>R</Type> |
||
14498 | <Comment></Comment> |
||
14499 | <Link1>http://blogbot.de/</Link1> |
||
14500 | <Link2></Link2> |
||
14501 | </user-agent> |
||
14502 | <user-agent> |
||
14503 | <ID>id_n_s_1021</ID> |
||
14504 | <String>NABOT/5.0</String> |
||
14505 | <Description>Naver Japan / Korea robot </Description> |
||
14506 | <Type>R</Type> |
||
14507 | <Comment>s.also Python-urllib/1.15 - dloader(NaverRobot)/1.0 & Cowbot</Comment> |
||
14508 | <Link1>http://www.naver.co.jp/</Link1> |
||
14509 | <Link2></Link2> |
||
14510 | </user-agent> |
||
14511 | <user-agent> |
||
14512 | <ID>id_n_s_1020</ID> |
||
14513 | <String>nabot_1.0</String> |
||
14514 | <Description>Naver Japan / Korea robot </Description> |
||
14515 | <Type>R</Type> |
||
14516 | <Comment>s.also Python-urllib/1.15 - dloader(NaverRobot)/1.0 & Cowbot</Comment> |
||
14517 | <Link1>http://www.naver.co.jp/</Link1> |
||
14518 | <Link2></Link2> |
||
14519 | </user-agent> |
||
14520 | <user-agent> |
||
14521 | <ID>id_n_s_180408_4</ID> |
||
14522 | <String>NameOfAgent (CMS Spider)</String> |
||
14523 | <Description>Badbot searching for Wordpress wp-login.php</Description> |
||
14524 | <Type>S</Type> |
||
14525 | <Comment></Comment> |
||
14526 | <Link1></Link1> |
||
14527 | <Link2></Link2> |
||
14528 | </user-agent> |
||
14529 | <user-agent> |
||
14530 | <ID>id_n_s_071205_1</ID> |
||
14531 | <String>naoFavicon4IE/1.xx</String> |
||
14532 | <Description>naoFavicon4IE</Description> |
||
14533 | <Type>D</Type> |
||
14534 | <Comment></Comment> |
||
14535 | <Link1>http://nao4u.com/software/naoFavicon4IE/</Link1> |
||
14536 | <Link2></Link2> |
||
14537 | </user-agent> |
||
14538 | <user-agent> |
||
14539 | <ID>id_n_s_140506_2</ID> |
||
14540 | <String>NASA Search 1.0</String> |
||
14541 | <Description>Unknown spambot / harvester from diff. IPs</Description> |
||
14542 | <Type>S</Type> |
||
14543 | <Comment></Comment> |
||
14544 | <Link1>http://www.projecthoneypot.org/ip_inspector.php?iph=978231e229521680d11cb93f32de0fa1</Link1> |
||
14545 | <Link2></Link2> |
||
14546 | </user-agent> |
||
14547 | <user-agent> |
||
14548 | <ID>id_n_s_1022</ID> |
||
14549 | <String>NationalDirectory-WebSpider/1.3</String> |
||
14550 | <Description>Nationaldirectory spider</Description> |
||
14551 | <Type>R</Type> |
||
14552 | <Comment></Comment> |
||
14553 | <Link1>http://www.nationaldirectory.com/</Link1> |
||
14554 | <Link2></Link2> |
||
14555 | </user-agent> |
||
14556 | <user-agent> |
||
14557 | <ID>id_n_s_1023</ID> |
||
14558 | <String>NationalDirectoryAddURL/1.0</String> |
||
14559 | <Description>Nationaldirectory spider</Description> |
||
14560 | <Type>R</Type> |
||
14561 | <Comment></Comment> |
||
14562 | <Link1>http://www.nationaldirectory.com/</Link1> |
||
14563 | <Link2></Link2> |
||
14564 | </user-agent> |
||
14565 | <user-agent> |
||
14566 | <ID>id_n_s_1025</ID> |
||
14567 | <String>NaverBot-1.0 (NHN Corp. / +82-2-3011-1954 / nhnbot@naver.com)</String> |
||
14568 | <Description>Naver Japan / Korea robot</Description> |
||
14569 | <Type>R</Type> |
||
14570 | <Comment>s. also Python-urllib/1.15- nabot- cowbot & dloader</Comment> |
||
14571 | <Link1>http://www.naver.co.jp/</Link1> |
||
14572 | <Link2></Link2> |
||
14573 | </user-agent> |
||
14574 | <user-agent> |
||
14575 | <ID>id_n_s_1024</ID> |
||
14576 | <String>NaverBot_dloader/1.5</String> |
||
14577 | <Description>Naver Japan / Korea robot</Description> |
||
14578 | <Type>R</Type> |
||
14579 | <Comment>s. also Python-urllib/1.15 - nabot - cowbot & dloader</Comment> |
||
14580 | <Link1>http://www.naver.co.jp/</Link1> |
||
14581 | <Link2></Link2> |
||
14582 | </user-agent> |
||
14583 | <user-agent> |
||
14584 | <ID>id_n_s_181205_1</ID> |
||
14585 | <String>NavissoBot</String> |
||
14586 | <Description>Navisso closed beta robot (69.41.162.1xx)</Description> |
||
14587 | <Type>R</Type> |
||
14588 | <Comment></Comment> |
||
14589 | <Link1>http://navisso.com/</Link1> |
||
14590 | <Link2></Link2> |
||
14591 | </user-agent> |
||
14592 | <user-agent> |
||
14593 | <ID>id_n_s_181205_2</ID> |
||
14594 | <String>NavissoBot/1.7 (+http://navisso.com/)</String> |
||
14595 | <Description>Navisso closed beta robot (69.41.162.1xx)</Description> |
||
14596 | <Type>R</Type> |
||
14597 | <Comment></Comment> |
||
14598 | <Link1>http://navisso.com/</Link1> |
||
14599 | <Link2></Link2> |
||
14600 | </user-agent> |
||
14601 | <user-agent> |
||
14602 | <ID>id_n_s_1026</ID> |
||
14603 | <String>NCSA Beta 1 (http://vias.ncsa.uiuc.edu/viasarchivinginformation.html)</String> |
||
14604 | <Description>Vias Information Archival robot</Description> |
||
14605 | <Type>R</Type> |
||
14606 | <Comment></Comment> |
||
14607 | <Link1>http://vias.ncsa.uiuc.edu/</Link1> |
||
14608 | <Link2></Link2> |
||
14609 | </user-agent> |
||
14610 | <user-agent> |
||
14611 | <ID>id_n_s_250507_1</ID> |
||
14612 | <String>Nebullabot/2.2 (http://bot.nebulla.info)</String> |
||
14613 | <Description>Nebulla.info distributed crawler (Germany)</Description> |
||
14614 | <Type>R</Type> |
||
14615 | <Comment>81.169.180.2xx</Comment> |
||
14616 | <Link1>http://www.nebulla.info/</Link1> |
||
14617 | <Link2>http://bot.nebulla.info/</Link2> |
||
14618 | </user-agent> |
||
14619 | <user-agent> |
||
14620 | <ID>id_n_s_1027</ID> |
||
14621 | <String>NEC Research Agent -- compuman at research.nj.nec.com</String> |
||
14622 | <Description>NEC Researchindex robot - now CiteSeer.IST scientific document index</Description> |
||
14623 | <Type>R</Type> |
||
14624 | <Comment></Comment> |
||
14625 | <Link1>http://citeseer.ist.psu.edu/</Link1> |
||
14626 | <Link2></Link2> |
||
14627 | </user-agent> |
||
14628 | <user-agent> |
||
14629 | <ID>id_n_s_1028</ID> |
||
14630 | <String>NEC-Hayek/1.0</String> |
||
14631 | <Description>rcn.com user agent ? NEC Researchindex robot ?</Description> |
||
14632 | <Type></Type> |
||
14633 | <Comment>s. NEC Research Agent</Comment> |
||
14634 | <Link1></Link1> |
||
14635 | <Link2></Link2> |
||
14636 | </user-agent> |
||
14637 | <user-agent> |
||
14638 | <ID>id_n_s_291108_4</ID> |
||
14639 | <String>Net-Seekr Bot/Net-Seekr Bot V1 (http://www.net-seekr.com)</String> |
||
14640 | <Description>Net Seekr search robot</Description> |
||
14641 | <Type>R</Type> |
||
14642 | <Comment>78.129.201.19x</Comment> |
||
14643 | <Link1>http://www.net-seekr.com/</Link1> |
||
14644 | <Link2></Link2> |
||
14645 | </user-agent> |
||
14646 | <user-agent> |
||
14647 | <ID>id_n_s_1029</ID> |
||
14648 | <String>NetAnts/1.2x</String> |
||
14649 | <Description>NetAnts download manager</Description> |
||
14650 | <Type>D</Type> |
||
14651 | <Comment></Comment> |
||
14652 | <Link1>http://www.netants.com/en/index.html</Link1> |
||
14653 | <Link2></Link2> |
||
14654 | </user-agent> |
||
14655 | <user-agent> |
||
14656 | <ID>id_n_s_1030</ID> |
||
14657 | <String>NETCOMplete/x.xx</String> |
||
14658 | <Description>NetComplete IE browser package</Description> |
||
14659 | <Type>B</Type> |
||
14660 | <Comment></Comment> |
||
14661 | <Link1>http://www.netcom.net.uk/</Link1> |
||
14662 | <Link2></Link2> |
||
14663 | </user-agent> |
||
14664 | <user-agent> |
||
14665 | <ID>id_n_s_010807_2</ID> |
||
14666 | <String>NetinfoBot/1.0 (http://netinfo.bg/netinfobot.html)</String> |
||
14667 | <Description>Netinfo.bg search (Bulgaria) robot</Description> |
||
14668 | <Type>R</Type> |
||
14669 | <Comment>194.153.145.x[xx]</Comment> |
||
14670 | <Link1>http://netinfo.bg/</Link1> |
||
14671 | <Link2></Link2> |
||
14672 | </user-agent> |
||
14673 | <user-agent> |
||
14674 | <ID>id_n_s_1031</ID> |
||
14675 | <String>NetLookout/2.24</String> |
||
14676 | <Description>Netlookout internet notifier</Description> |
||
14677 | <Type>R</Type> |
||
14678 | <Comment>site is offline</Comment> |
||
14679 | <Link1>http://www.frugalsoft.com</Link1> |
||
14680 | <Link2></Link2> |
||
14681 | </user-agent> |
||
14682 | <user-agent> |
||
14683 | <ID>id_n_s_230406_3</ID> |
||
14684 | <String>Netluchs/0.8-dev ( ; http://www.netluchs.de/; ___don't___spam_me_@netluchs.de)</String> |
||
14685 | <Description>Netluchs (Germany) search (193.164.8.xx)</Description> |
||
14686 | <Type>R</Type> |
||
14687 | <Comment>Same IP-range as Metager search - powered by Nutch</Comment> |
||
14688 | <Link1>http://www.netluchs.de/</Link1> |
||
14689 | <Link2></Link2> |
||
14690 | </user-agent> |
||
14691 | <user-agent> |
||
14692 | <ID>id_n_s_1032</ID> |
||
14693 | <String>NetMechanic Vx.0</String> |
||
14694 | <Description>NetMechanic link checker</Description> |
||
14695 | <Type>C</Type> |
||
14696 | <Comment></Comment> |
||
14697 | <Link1>http://www.netmechanic.com/</Link1> |
||
14698 | <Link2></Link2> |
||
14699 | </user-agent> |
||
14700 | <user-agent> |
||
14701 | <ID>id_n_s_030906_1</ID> |
||
14702 | <String>NetNewsWire/2.x (Mac OS X; http://ranchero.com/netnewswire/)</String> |
||
14703 | <Description>NewsGator NetNewsWire - Mac RSS feed reader</Description> |
||
14704 | <Type>B</Type> |
||
14705 | <Comment></Comment> |
||
14706 | <Link1>http://www.newsgator.com/NGOLProduct.aspx?ProdID=NetNewsWire</Link1> |
||
14707 | <Link2></Link2> |
||
14708 | </user-agent> |
||
14709 | <user-agent> |
||
14710 | <ID>id_n_s_1033</ID> |
||
14711 | <String>NetNoseCrawler/v1.0</String> |
||
14712 | <Description>unknown InCom (216.0.107.xx) robot</Description> |
||
14713 | <Type>R</Type> |
||
14714 | <Comment></Comment> |
||
14715 | <Link1>http://www.incom.net/</Link1> |
||
14716 | <Link2></Link2> |
||
14717 | </user-agent> |
||
14718 | <user-agent> |
||
14719 | <ID>id_n_s_1034</ID> |
||
14720 | <String>Netprospector JavaCrawler</String> |
||
14721 | <Description>Netprospector metasearch software</Description> |
||
14722 | <Type>R</Type> |
||
14723 | <Comment></Comment> |
||
14724 | <Link1>http://www.actaddons.com/products/netprospector.asp</Link1> |
||
14725 | <Link2></Link2> |
||
14726 | </user-agent> |
||
14727 | <user-agent> |
||
14728 | <ID>id_n_s_1035</ID> |
||
14729 | <String>NetPumper/x.xx</String> |
||
14730 | <Description>Netpumper download manager</Description> |
||
14731 | <Type>D</Type> |
||
14732 | <Comment></Comment> |
||
14733 | <Link1>http://www.netpumper.com/</Link1> |
||
14734 | <Link2></Link2> |
||
14735 | </user-agent> |
||
14736 | <user-agent> |
||
14737 | <ID>id_n_s_1036</ID> |
||
14738 | <String>NetResearchServer(http://www.look.com)</String> |
||
14739 | <Description>Look.com robot (209.87.232.x)</Description> |
||
14740 | <Type>R</Type> |
||
14741 | <Comment></Comment> |
||
14742 | <Link1>http://www.look.com/</Link1> |
||
14743 | <Link2></Link2> |
||
14744 | </user-agent> |
||
14745 | <user-agent> |
||
14746 | <ID>id_n_s_1037</ID> |
||
14747 | <String>NetResearchServer/x.x(loopimprovements.com/robot.html)</String> |
||
14748 | <Description>IncyWincy search engine using DMOZ database</Description> |
||
14749 | <Type>R</Type> |
||
14750 | <Comment></Comment> |
||
14751 | <Link1>http://www.loopimprovements.com/</Link1> |
||
14752 | <Link2></Link2> |
||
14753 | </user-agent> |
||
14754 | <user-agent> |
||
14755 | <ID>id_n_s_140209_5</ID> |
||
14756 | <String>NetSeer/Nutch-0.9 (NetSeer Crawler; http://www.netseer.com; crawler@netseer.com)</String> |
||
14757 | <Description>NetSeer search (beta) crawler via Amazon Web Services - see also Teemer</Description> |
||
14758 | <Type>R</Type> |
||
14759 | <Comment>67.202.26.1xx</Comment> |
||
14760 | <Link1>http://www.netseer.com/</Link1> |
||
14761 | <Link2>http://www.amazon.com/gp/browse.html?node=3435361</Link2> |
||
14762 | </user-agent> |
||
14763 | <user-agent> |
||
14764 | <ID>id_n_s_150906_2</ID> |
||
14765 | <String>NetSprint -- 2.0</String> |
||
14766 | <Description>Wirtualna Polska / Netsprint search (Poland) robot</Description> |
||
14767 | <Type>R</Type> |
||
14768 | <Comment>212.77.102.1xx</Comment> |
||
14769 | <Link1>http://www.wp.pl/</Link1> |
||
14770 | <Link2>http://www.netsprint.pl/serwis/</Link2> |
||
14771 | </user-agent> |
||
14772 | <user-agent> |
||
14773 | <ID>id_n_s_190306_1</ID> |
||
14774 | <String>NetWhatCrawler/0.06-dev (NetWhatCrawler from NetWhat.com; http://www.netwhat.com; support@netwhat.com)</String> |
||
14775 | <Description>NetWhat Search crawler (69.9.167.1xx)</Description> |
||
14776 | <Type>R</Type> |
||
14777 | <Comment></Comment> |
||
14778 | <Link1>http://www.netwhat.com/</Link1> |
||
14779 | <Link2></Link2> |
||
14780 | </user-agent> |
||
14781 | <user-agent> |
||
14782 | <ID>id_n_s_1038</ID> |
||
14783 | <String>NetZippy</String> |
||
14784 | <Description>Netzippy robot</Description> |
||
14785 | <Type>R</Type> |
||
14786 | <Comment>site is closed</Comment> |
||
14787 | <Link1>http://www.netzippy.com/</Link1> |
||
14788 | <Link2></Link2> |
||
14789 | </user-agent> |
||
14790 | <user-agent> |
||
14791 | <ID>id_n_s_1039</ID> |
||
14792 | <String>NeuralBot/0.2</String> |
||
14793 | <Description>unknown</Description> |
||
14794 | <Type></Type> |
||
14795 | <Comment></Comment> |
||
14796 | <Link1></Link1> |
||
14797 | <Link2></Link2> |
||
14798 | </user-agent> |
||
14799 | <user-agent> |
||
14800 | <ID>id_n_s_1040</ID> |
||
14801 | <String>newsearchengine (ThisUser@unspecified.mail)</String> |
||
14802 | <Description>Unknown (12.238.4.xxx) attbi.com client robot</Description> |
||
14803 | <Type></Type> |
||
14804 | <Comment></Comment> |
||
14805 | <Link1></Link1> |
||
14806 | <Link2></Link2> |
||
14807 | </user-agent> |
||
14808 | <user-agent> |
||
14809 | <ID>id_n_s_250707_3</ID> |
||
14810 | <String>NewsGator FetchLinks extension/0.2.0 (http://graemef.com)</String> |
||
14811 | <Description>FetchLinks plugin for NewsGator RSS reader</Description> |
||
14812 | <Type>B</Type> |
||
14813 | <Comment></Comment> |
||
14814 | <Link1>http://graemef.com/project/fetchlinks</Link1> |
||
14815 | <Link2></Link2> |
||
14816 | </user-agent> |
||
14817 | <user-agent> |
||
14818 | <ID>id_n_s_250707_4</ID> |
||
14819 | <String>NewsGatorOnline/2.0 (http://www.newsgator.com; 1 subscribers)</String> |
||
14820 | <Description>NewsGator online RSS reader</Description> |
||
14821 | <Type>B</Type> |
||
14822 | <Comment>64.78.155.1xx</Comment> |
||
14823 | <Link1>http://www.newsgator.com/</Link1> |
||
14824 | <Link2></Link2> |
||
14825 | </user-agent> |
||
14826 | <user-agent> |
||
14827 | <ID>id_n_s_1041</ID> |
||
14828 | <String>NextGenSearchBot 1 (for information visit http://www.eliyon.com/NextGenSearchBot)</String> |
||
14829 | <Description>Eliyon Crawler for Business People Search</Description> |
||
14830 | <Type>R</Type> |
||
14831 | <Comment></Comment> |
||
14832 | <Link1>http://www.eliyon.com/NextGenSearchBot</Link1> |
||
14833 | <Link2></Link2> |
||
14834 | </user-agent> |
||
14835 | <user-agent> |
||
14836 | <ID>id_n_s_1042</ID> |
||
14837 | <String>NextopiaBOT (+http://www.nextopia.com) distributed crawler client beta v0.x</String> |
||
14838 | <Description>Nextopia crawler</Description> |
||
14839 | <Type>R</Type> |
||
14840 | <Comment></Comment> |
||
14841 | <Link1>http://www.nextopia.com/</Link1> |
||
14842 | <Link2></Link2> |
||
14843 | </user-agent> |
||
14844 | <user-agent> |
||
14845 | <ID>id_n_s_060906_1</ID> |
||
14846 | <String>NG-Search/0.90 (NG-SearchBot; http://www.ng-search.com; )</String> |
||
14847 | <Description>find your keywords - semantic search (Germany) robot</Description> |
||
14848 | <Type>R</Type> |
||
14849 | <Comment>84.56.87.1xx</Comment> |
||
14850 | <Link1>http://www.ng-search.com/</Link1> |
||
14851 | <Link2></Link2> |
||
14852 | </user-agent> |
||
14853 | <user-agent> |
||
14854 | <ID>id_n_s_1043</ID> |
||
14855 | <String>NG/1.0</String> |
||
14856 | <Description>Exalead (France) search robot (193.47.80.xx)</Description> |
||
14857 | <Type>R</Type> |
||
14858 | <Comment>s. Harvest-NG/1.0.2 and Exalead NG...</Comment> |
||
14859 | <Link1>http://www.exabot.com/</Link1> |
||
14860 | <Link2></Link2> |
||
14861 | </user-agent> |
||
14862 | <user-agent> |
||
14863 | <ID>id_n_s_050406_3</ID> |
||
14864 | <String>NG/4.0.1229</String> |
||
14865 | <Description>Exalead Websearch image crawler (193.47.80.xx)</Description> |
||
14866 | <Type>R</Type> |
||
14867 | <Comment>s. also Exabot-Images/1.0</Comment> |
||
14868 | <Link1>http://www.exalead.com/search</Link1> |
||
14869 | <Link2></Link2> |
||
14870 | </user-agent> |
||
14871 | <user-agent> |
||
14872 | <ID>id_n_s_071106_1</ID> |
||
14873 | <String>nicebot</String> |
||
14874 | <Description>Unknown UA from PlanetLab distributed network</Description> |
||
14875 | <Type></Type> |
||
14876 | <Comment>128.8.126.xx</Comment> |
||
14877 | <Link1>http://planetlab2.cs.umd.edu/</Link1> |
||
14878 | <Link2></Link2> |
||
14879 | </user-agent> |
||
14880 | <user-agent> |
||
14881 | <ID>id_n_s_1044</ID> |
||
14882 | <String>NICO/1.0</String> |
||
14883 | <Description>NicoZone childsafe search robot </Description> |
||
14884 | <Type>R P</Type> |
||
14885 | <Comment>-site is offline-</Comment> |
||
14886 | <Link1>http://www.nicozone.net/</Link1> |
||
14887 | <Link2></Link2> |
||
14888 | </user-agent> |
||
14889 | <user-agent> |
||
14890 | <ID>id_n_s_291007_2</ID> |
||
14891 | <String>Nikita the Spider (http://NikitaTheSpider.com/)</String> |
||
14892 | <Description>Nikita the Spider - Online HTML validation , link checking</Description> |
||
14893 | <Type>C</Type> |
||
14894 | <Comment>69.61.23.11x</Comment> |
||
14895 | <Link1>http://nikitathespider.com/</Link1> |
||
14896 | <Link2></Link2> |
||
14897 | </user-agent> |
||
14898 | <user-agent> |
||
14899 | <ID>id_n_s_1045</ID> |
||
14900 | <String>NITLE Blog Spider/0.01</String> |
||
14901 | <Description>Experimental LSI (?) robot from 140.233.69.xx (Middlebury.edu)</Description> |
||
14902 | <Type>R</Type> |
||
14903 | <Comment></Comment> |
||
14904 | <Link1>http://javelina.cet.middlebury.edu/lsa/out/lsa_intro.htm</Link1> |
||
14905 | <Link2></Link2> |
||
14906 | </user-agent> |
||
14907 | <user-agent> |
||
14908 | <ID>id_n_s_1046</ID> |
||
14909 | <String>Nitro Downloader 1.x (www.klsofttools.com)</String> |
||
14910 | <Description>Download manager</Description> |
||
14911 | <Type>D</Type> |
||
14912 | <Comment></Comment> |
||
14913 | <Link1>http://www.klsofttools.com</Link1> |
||
14914 | <Link2></Link2> |
||
14915 | </user-agent> |
||
14916 | <user-agent> |
||
14917 | <ID>id_n_s_1047</ID> |
||
14918 | <String>Noago Spider</String> |
||
14919 | <Description>Noago spider</Description> |
||
14920 | <Type>R</Type> |
||
14921 | <Comment></Comment> |
||
14922 | <Link1>http://www.noago.com/</Link1> |
||
14923 | <Link2></Link2> |
||
14924 | </user-agent> |
||
14925 | <user-agent> |
||
14926 | <ID>id_n_s_1048</ID> |
||
14927 | <String>Nocilla/1.0</String> |
||
14928 | <Description>telefonica.es user robot</Description> |
||
14929 | <Type></Type> |
||
14930 | <Comment></Comment> |
||
14931 | <Link1></Link1> |
||
14932 | <Link2></Link2> |
||
14933 | </user-agent> |
||
14934 | <user-agent> |
||
14935 | <ID>id_n_s_1049</ID> |
||
14936 | <String>Nokia-WAPToolkit/1.2 googlebot(at)googlebot.com</String> |
||
14937 | <Description>Google WAP robot</Description> |
||
14938 | <Type>R</Type> |
||
14939 | <Comment></Comment> |
||
14940 | <Link1>http://www.google.com/</Link1> |
||
14941 | <Link2></Link2> |
||
14942 | </user-agent> |
||
14943 | <user-agent> |
||
14944 | <ID>id_n_s_290708_3</ID> |
||
14945 | <String>Nokia6300/2.0 (05.50) Profile/MIDP-2.0 Configuration/CLDC-1.1 (botmobi http://find.mobi/bot.html abuse@mtld.mobi)</String> |
||
14946 | <Description>Botmobi crawler for Find.mobi mobile search</Description> |
||
14947 | <Type>C</Type> |
||
14948 | <Comment></Comment> |
||
14949 | <Link1>http://find.mobi/bot.html</Link1> |
||
14950 | <Link2>http://find.mobi/</Link2> |
||
14951 | </user-agent> |
||
14952 | <user-agent> |
||
14953 | <ID>id_n_s_200108_3</ID> |
||
14954 | <String>Nokia6610/1.0 (3.09) Profile/MIDP-1.0 Configuration/CLDC-1.0 (compatible;YahooSeeker/M1A1-R2D2; http://help.yahoo.com/help/us/ysearch/crawling/crawling-01.html)</String> |
||
14955 | <Description>YahooSeeker/M1A1-R2D2 - Yahoo mobile web crawling robot</Description> |
||
14956 | <Type>R</Type> |
||
14957 | <Comment>68.180.2xx.[x]xx</Comment> |
||
14958 | <Link1>http://help.yahoo.com/l/us/yahoo/search/mobilecrawler/mobilecrawler-01.html</Link1> |
||
14959 | <Link2></Link2> |
||
14960 | </user-agent> |
||
14961 | <user-agent> |
||
14962 | <ID>id_n_s_1050</ID> |
||
14963 | <String>Nokia7110/1.0 (05.01) (Google WAP Proxy/1.0)</String> |
||
14964 | <Description>Google WAP proxy</Description> |
||
14965 | <Type>P</Type> |
||
14966 | <Comment></Comment> |
||
14967 | <Link1>http://www.google.com/</Link1> |
||
14968 | <Link2></Link2> |
||
14969 | </user-agent> |
||
14970 | <user-agent> |
||
14971 | <ID>id_n_s_1051</ID> |
||
14972 | <String>NokodoBot/1.x (+http://nokodo.com/bot.htm)</String> |
||
14973 | <Description>Nokodo public beta search robot (67.18.222.xx)</Description> |
||
14974 | <Type>R</Type> |
||
14975 | <Comment></Comment> |
||
14976 | <Link1>http://www.nokodo.com/</Link1> |
||
14977 | <Link2></Link2> |
||
14978 | </user-agent> |
||
14979 | <user-agent> |
||
14980 | <ID>id_n_s_1052</ID> |
||
14981 | <String>Norbert the Spider(Burf.com)</String> |
||
14982 | <Description>Burf.com UK Search Engine robot</Description> |
||
14983 | <Type>R</Type> |
||
14984 | <Comment></Comment> |
||
14985 | <Link1>http://www.burf.com/</Link1> |
||
14986 | <Link2></Link2> |
||
14987 | </user-agent> |
||
14988 | <user-agent> |
||
14989 | <ID>id_n_s_1053</ID> |
||
14990 | <String>noxtrumbot/1.0 (crawler@noxtrum.com)</String> |
||
14991 | <Description>noXtrum search robot (Spain)</Description> |
||
14992 | <Type>R</Type> |
||
14993 | <Comment>194.224.199.xx</Comment> |
||
14994 | <Link1>http://www.noxtrum.com/</Link1> |
||
14995 | <Link2></Link2> |
||
14996 | </user-agent> |
||
14997 | <user-agent> |
||
14998 | <ID>id_n_s_040506_2</ID> |
||
14999 | <String>noyona_0_1</String> |
||
15000 | <Description>Noyona job search (preview)</Description> |
||
15001 | <Type>R</Type> |
||
15002 | <Comment>207.210.106.1xx</Comment> |
||
15003 | <Link1>http://www.noyona.com/index.pl</Link1> |
||
15004 | <Link2></Link2> |
||
15005 | </user-agent> |
||
15006 | <user-agent> |
||
15007 | <ID>id_n_s_1054</ID> |
||
15008 | <String>NP/0.1 (NP; http://www.nameprotect.com; npbot@nameprotect.com)</String> |
||
15009 | <Description>Nameprotect copyright search robot (24.177.134.x)</Description> |
||
15010 | <Type>R</Type> |
||
15011 | <Comment>s. also - aipbot/1.0 (aipbot; http://www.aipbot.com... - NPBot ...</Comment> |
||
15012 | <Link1>http://www.nameprotect.com/</Link1> |
||
15013 | <Link2></Link2> |
||
15014 | </user-agent> |
||
15015 | <user-agent> |
||
15016 | <ID>id_n_s_1553</ID> |
||
15017 | <String>NPBot (http://www.nameprotect.com/botinfo.html)</String> |
||
15018 | <Description>Nameprotect copyright search robot (24.177.134.x)</Description> |
||
15019 | <Type>R</Type> |
||
15020 | <Comment></Comment> |
||
15021 | <Link1>http://www.nameprotect.com/</Link1> |
||
15022 | <Link2></Link2> |
||
15023 | </user-agent> |
||
15024 | <user-agent> |
||
15025 | <ID>id_n_s_1552</ID> |
||
15026 | <String>NPBot-1/2.0</String> |
||
15027 | <Description>Nameprotect copyright search robot (24.177.134.x)</Description> |
||
15028 | <Type>R</Type> |
||
15029 | <Comment></Comment> |
||
15030 | <Link1>http://www.nameprotect.com/</Link1> |
||
15031 | <Link2></Link2> |
||
15032 | </user-agent> |
||
15033 | <user-agent> |
||
15034 | <ID>id_n_s_291205_3</ID> |
||
15035 | <String>Nsauditor/1.x</String> |
||
15036 | <Description>Nsauditor Network Security Auditor</Description> |
||
15037 | <Type>S</Type> |
||
15038 | <Comment></Comment> |
||
15039 | <Link1>http://www.nsauditor.com/</Link1> |
||
15040 | <Link2></Link2> |
||
15041 | </user-agent> |
||
15042 | <user-agent> |
||
15043 | <ID>id_n_s_1055</ID> |
||
15044 | <String>NSPlayer/10.0.0.xxxx WMFSDK/10.0</String> |
||
15045 | <Description>NetShow Media Player = Windows Media Player 10</Description> |
||
15046 | <Type>B</Type> |
||
15047 | <Comment></Comment> |
||
15048 | <Link1></Link1> |
||
15049 | <Link2></Link2> |
||
15050 | </user-agent> |
||
15051 | <user-agent> |
||
15052 | <ID>id_n_s_281207_2</ID> |
||
15053 | <String>nsyght.com/Nutch-1.0-dev (nsyght.com; Nsyght.com)</String> |
||
15054 | <Description>Nsyght social search application</Description> |
||
15055 | <Type>R</Type> |
||
15056 | <Comment></Comment> |
||
15057 | <Link1>http://search.nsyght.com/</Link1> |
||
15058 | <Link2></Link2> |
||
15059 | </user-agent> |
||
15060 | <user-agent> |
||
15061 | <ID>id_n_s_161007_1</ID> |
||
15062 | <String>nsyght.com/Nutch-x.x (nsyght.com; search.nsyght.com)</String> |
||
15063 | <Description>Nsyght social search application</Description> |
||
15064 | <Type>R</Type> |
||
15065 | <Comment></Comment> |
||
15066 | <Link1>http://search.nsyght.com/</Link1> |
||
15067 | <Link2></Link2> |
||
15068 | </user-agent> |
||
15069 | <user-agent> |
||
15070 | <ID>id_n_s_1056</ID> |
||
15071 | <String>nttdirectory_robot/0.9 (super-robot@super.navi.ocn.ne.jp)</String> |
||
15072 | <Description>NTT Directory robot</Description> |
||
15073 | <Type>R</Type> |
||
15074 | <Comment></Comment> |
||
15075 | <Link1>http://navi.ocn.ne.jp/</Link1> |
||
15076 | <Link2></Link2> |
||
15077 | </user-agent> |
||
15078 | <user-agent> |
||
15079 | <ID>id_n_s_180206_1</ID> |
||
15080 | <String>Nucleus SiteList LinkChecker/1.1</String> |
||
15081 | <Description>Nucleus CMS SiteList link managing plugin</Description> |
||
15082 | <Type>C</Type> |
||
15083 | <Comment></Comment> |
||
15084 | <Link1>http://wakka.xiffy.nl/sitelist</Link1> |
||
15085 | <Link2></Link2> |
||
15086 | </user-agent> |
||
15087 | <user-agent> |
||
15088 | <ID>id_n_s_1058</ID> |
||
15089 | <String>nuSearch Spider <a href='http://www.nusearch.com'>www.nusearch.com</a> (compatible; MSIE 4.01)</String> |
||
15090 | <Description>nuSearch spider (84.9.136.xxx)</Description> |
||
15091 | <Type>R</Type> |
||
15092 | <Comment></Comment> |
||
15093 | <Link1>http://www.nusearch.com/</Link1> |
||
15094 | <Link2></Link2> |
||
15095 | </user-agent> |
||
15096 | <user-agent> |
||
15097 | <ID>id_n_s_1057</ID> |
||
15098 | <String>NuSearch Spider (compatible; MSIE 6.0)</String> |
||
15099 | <Description>nuSearch spider (84.9.136.xxx)</Description> |
||
15100 | <Type>R</Type> |
||
15101 | <Comment></Comment> |
||
15102 | <Link1>http://www.nusearch.com/</Link1> |
||
15103 | <Link2></Link2> |
||
15104 | </user-agent> |
||
15105 | <user-agent> |
||
15106 | <ID>id_n_s_1059</ID> |
||
15107 | <String>NuSearch Spider www.nusearch.com</String> |
||
15108 | <Description>nuSearch spider (84.9.136.xxx)</Description> |
||
15109 | <Type>R</Type> |
||
15110 | <Comment></Comment> |
||
15111 | <Link1>http://www.nusearch.com/</Link1> |
||
15112 | <Link2></Link2> |
||
15113 | </user-agent> |
||
15114 | <user-agent> |
||
15115 | <ID>id_n_s_1060</ID> |
||
15116 | <String>Nutch</String> |
||
15117 | <Description>Nutch open source robot</Description> |
||
15118 | <Type>R</Type> |
||
15119 | <Comment></Comment> |
||
15120 | <Link1>http://www.nutch.org/docs/bot.html</Link1> |
||
15121 | <Link2></Link2> |
||
15122 | </user-agent> |
||
15123 | <user-agent> |
||
15124 | <ID>id_n_s_211107_1</ID> |
||
15125 | <String>Nutch crawler/Nutch-0.9 (picapage.com; admin@picapage.com)</String> |
||
15126 | <Description>Picapage search for handheld devices using Nutch</Description> |
||
15127 | <Type>R</Type> |
||
15128 | <Comment></Comment> |
||
15129 | <Link1>http://picapage.biz/</Link1> |
||
15130 | <Link2></Link2> |
||
15131 | </user-agent> |
||
15132 | <user-agent> |
||
15133 | <ID>id_n_s_230408_1</ID> |
||
15134 | <String>Nutch/Nutch-0.9 (Eurobot; http://www.ayell.eu )</String> |
||
15135 | <Description>Ayell Euronet business directory robot using Nutch</Description> |
||
15136 | <Type>R</Type> |
||
15137 | <Comment></Comment> |
||
15138 | <Link1>http://www.ayell.eu/</Link1> |
||
15139 | <Link2></Link2> |
||
15140 | </user-agent> |
||
15141 | <user-agent> |
||
15142 | <ID>id_n_s_120406_1</ID> |
||
15143 | <String>NutchCVS/0.06-dev (Nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@lists.sourceforge.net)</String> |
||
15144 | <Description>Netsweeper content filtering engine (66.207.120.2xx) powered by Nutch</Description> |
||
15145 | <Type>P</Type> |
||
15146 | <Comment>uses also: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7.5) Gecko/20041107 Firefox/1.0</Comment> |
||
15147 | <Link1>http://www.netsweeper.com/</Link1> |
||
15148 | <Link2></Link2> |
||
15149 | </user-agent> |
||
15150 | <user-agent> |
||
15151 | <ID>id_n_s_1061</ID> |
||
15152 | <String>NutchCVS/0.0x-dev (Nutch; http://www.nutch.org/docs/bot.html; nutch-agent@lists.sourceforge.net)</String> |
||
15153 | <Description>Nutch open source robot</Description> |
||
15154 | <Type>R</Type> |
||
15155 | <Comment></Comment> |
||
15156 | <Link1>http://www.nutch.org/docs/bot.html</Link1> |
||
15157 | <Link2></Link2> |
||
15158 | </user-agent> |
||
15159 | <user-agent> |
||
15160 | <ID>id_n_s_010406_1</ID> |
||
15161 | <String>NutchCVS/0.7.1 (Nutch running at UW; http://www.nutch.org/docs/en/bot.html; sycrawl@cs.washington.edu)</String> |
||
15162 | <Description>Robot from University of Washington Computer Science & Engineering (128.208.6.2xx)</Description> |
||
15163 | <Type>R</Type> |
||
15164 | <Comment>powered by Nutch</Comment> |
||
15165 | <Link1>http://qbert.cs.washington.edu/</Link1> |
||
15166 | <Link2></Link2> |
||
15167 | </user-agent> |
||
15168 | <user-agent> |
||
15169 | <ID>id_n_s_251006_2</ID> |
||
15170 | <String>NutchEC2Test/Nutch-0.9-dev (Testing Nutch on Amazon EC2.; http://lucene.apache.org/nutch/bot.html; ec2test at lucene.com)</String> |
||
15171 | <Description>Amazon Elastic Compute Cloud (Amazon EC2) robot</Description> |
||
15172 | <Type>R</Type> |
||
15173 | <Comment>216.182.236.xx</Comment> |
||
15174 | <Link1>http://www.amazon.com/b/ref=sc_fe_l_2/104-6713356-1433533?ie=UTF8&node=201590011&no=3435361&me=A36L942TSJ2AJA</Link1> |
||
15175 | <Link2></Link2> |
||
15176 | </user-agent> |
||
15177 | <user-agent> |
||
15178 | <ID>id_n_s_1062</ID> |
||
15179 | <String>NutchOrg/0.0x-dev (Nutch; http://www.nutch.org/docs/bot.html; nutch-agent@lists.sourceforge.net)</String> |
||
15180 | <Description>Nutch open source robot</Description> |
||
15181 | <Type>R</Type> |
||
15182 | <Comment></Comment> |
||
15183 | <Link1>http://www.nutch.org/docs/bot.html</Link1> |
||
15184 | <Link2></Link2> |
||
15185 | </user-agent> |
||
15186 | <user-agent> |
||
15187 | <ID>id_n_s_210108_1</ID> |
||
15188 | <String>nutchsearch/Nutch-0.9 (Nutch Search 1.0; herceg_novi at yahoo dot com)</String> |
||
15189 | <Description>Unknown robot using Nutch (maybe private crawling) via Cox network (70.187.130.25x)</Description> |
||
15190 | <Type>R</Type> |
||
15191 | <Comment>reads robots.txt</Comment> |
||
15192 | <Link1>http://lucene.apache.org/nutch/</Link1> |
||
15193 | <Link2></Link2> |
||
15194 | </user-agent> |
||
15195 | <user-agent> |
||
15196 | <ID>id_n_s_041106_1</ID> |
||
15197 | <String>NutchVinegarCrawl/Nutch-0.8.1 (Vinegar; http://www.cs.washington.edu; eytanadar at gmail dot com)</String> |
||
15198 | <Description>Unknown crawler from University of Washington - Computer science</Description> |
||
15199 | <Type>R</Type> |
||
15200 | <Comment>128.208.3.1xx</Comment> |
||
15201 | <Link1>http://www.cs.washington.edu/</Link1> |
||
15202 | <Link2></Link2> |
||
15203 | </user-agent> |
||
15204 | <user-agent> |
||
15205 | <ID>id_n_s_1063</ID> |
||
15206 | <String>obidos-bot (just looking for books.)</String> |
||
15207 | <Description>Weblog bookwatch robot</Description> |
||
15208 | <Type>R</Type> |
||
15209 | <Comment></Comment> |
||
15210 | <Link1>http://www.onfocus.com/bookwatch/</Link1> |
||
15211 | <Link2></Link2> |
||
15212 | </user-agent> |
||
15213 | <user-agent> |
||
15214 | <ID>id_n_s_1064</ID> |
||
15215 | <String>ObjectsSearch/0.01-dev (ObjectsSearch;http://www.ObjectsSearch.com/bot.html; support@thesoftwareobjects.com)</String> |
||
15216 | <Description>Objects Search robot</Description> |
||
15217 | <Type>R</Type> |
||
15218 | <Comment></Comment> |
||
15219 | <Link1>http://www.objectssearch.com/</Link1> |
||
15220 | <Link2></Link2> |
||
15221 | </user-agent> |
||
15222 | <user-agent> |
||
15223 | <ID>id_n_s_1065</ID> |
||
15224 | <String>ObjectsSearch/0.0x (ObjectsSearch; http://www.ObjectsSearch.com/bot.html; support@thesoftwareobjects.com)</String> |
||
15225 | <Description>Objects Search robot</Description> |
||
15226 | <Type>R</Type> |
||
15227 | <Comment></Comment> |
||
15228 | <Link1>http://www.objectssearch.com/</Link1> |
||
15229 | <Link2></Link2> |
||
15230 | </user-agent> |
||
15231 | <user-agent> |
||
15232 | <ID>id_n_s_1066</ID> |
||
15233 | <String>oBot ((compatible;Win32))</String> |
||
15234 | <Description>Cobion Germany Brand Protection Services robot</Description> |
||
15235 | <Type>R</Type> |
||
15236 | <Comment></Comment> |
||
15237 | <Link1>http://www.cobion.com/</Link1> |
||
15238 | <Link2></Link2> |
||
15239 | </user-agent> |
||
15240 | <user-agent> |
||
15241 | <ID>id_n_s_1067</ID> |
||
15242 | <String>Ocelli/1.x (http://www.globalspec.com/Ocelli)</String> |
||
15243 | <Description>GlobalSpec Engineering Search robot (66.194.55.xxx)</Description> |
||
15244 | <Type>R</Type> |
||
15245 | <Comment></Comment> |
||
15246 | <Link1>http://www.globalspec.com/</Link1> |
||
15247 | <Link2></Link2> |
||
15248 | </user-agent> |
||
15249 | <user-agent> |
||
15250 | <ID>id_n_s_1068</ID> |
||
15251 | <String>Octopus</String> |
||
15252 | <Description>Octopus download manager</Description> |
||
15253 | <Type>D</Type> |
||
15254 | <Comment></Comment> |
||
15255 | <Link1>http://moskalyuk.com/octopus/</Link1> |
||
15256 | <Link2></Link2> |
||
15257 | </user-agent> |
||
15258 | <user-agent> |
||
15259 | <ID>id_n_s_230306_1</ID> |
||
15260 | <String>Octora Beta - www.octora.com</String> |
||
15261 | <Description>Octora blog or RSS information crawler - beta (66.228.114.xx)</Description> |
||
15262 | <Type>R</Type> |
||
15263 | <Comment></Comment> |
||
15264 | <Link1>http://www.octora.com/</Link1> |
||
15265 | <Link2></Link2> |
||
15266 | </user-agent> |
||
15267 | <user-agent> |
||
15268 | <ID>id_n_s_230606_4</ID> |
||
15269 | <String>Octora Beta Bot - www.octora.com</String> |
||
15270 | <Description>Octora RSS feed search</Description> |
||
15271 | <Type>R</Type> |
||
15272 | <Comment>66.228.114.xx</Comment> |
||
15273 | <Link1>http://www.octora.com/</Link1> |
||
15274 | <Link2></Link2> |
||
15275 | </user-agent> |
||
15276 | <user-agent> |
||
15277 | <ID>id_n_s_1069</ID> |
||
15278 | <String>Offline Explorer 1.*</String> |
||
15279 | <Description>Meta Products Offlinebrowser</Description> |
||
15280 | <Type>B D</Type> |
||
15281 | <Comment></Comment> |
||
15282 | <Link1>http://www.metaproducts.com/</Link1> |
||
15283 | <Link2></Link2> |
||
15284 | </user-agent> |
||
15285 | <user-agent> |
||
15286 | <ID>id_n_s_1070</ID> |
||
15287 | <String>OliverPerry</String> |
||
15288 | <Description>Claymont robot / Internetseer Web Site Monitoring</Description> |
||
15289 | <Type>R C</Type> |
||
15290 | <Comment></Comment> |
||
15291 | <Link1>http://www.claymont.com/</Link1> |
||
15292 | <Link2></Link2> |
||
15293 | </user-agent> |
||
15294 | <user-agent> |
||
15295 | <ID>id_n_s_1071</ID> |
||
15296 | <String>OmniExplorer_Bot/1.0x (+http://www.omni-explorer.com) Internet CategorizerOmniExplorer http://www.omni-explorer.com/ car & shopping search (64.62.175.xxx)</String> |
||
15297 | <Description>OmniExplorer car & shopping search (64.62.175.xxx)</Description> |
||
15298 | <Type>R</Type> |
||
15299 | <Comment>based on YottaCars... (see there)</Comment> |
||
15300 | <Link1>http://www.omni-explorer.com</Link1> |
||
15301 | <Link2></Link2> |
||
15302 | </user-agent> |
||
15303 | <user-agent> |
||
15304 | <ID>id_n_s_1072</ID> |
||
15305 | <String>OmniExplorer_Bot/1.0x (+http://www.omni-explorer.com) Job Crawler</String> |
||
15306 | <Description>OmniExplorer car & shopping search (64.62.175.xxx)</Description> |
||
15307 | <Type>R</Type> |
||
15308 | <Comment>based on YottaCars... (see there)</Comment> |
||
15309 | <Link1>http://www.omni-explorer.com</Link1> |
||
15310 | <Link2></Link2> |
||
15311 | </user-agent> |
||
15312 | <user-agent> |
||
15313 | <ID>id_n_s_1073</ID> |
||
15314 | <String>OmniExplorer_Bot/1.1x (+http://www.omni-explorer.com) Torrent Crawler</String> |
||
15315 | <Description>OmniExplorer car & shopping search (64.62.175.xxx)</Description> |
||
15316 | <Type>R</Type> |
||
15317 | <Comment>based on YottaCars... (see there)</Comment> |
||
15318 | <Link1>http://www.omni-explorer.com</Link1> |
||
15319 | <Link2></Link2> |
||
15320 | </user-agent> |
||
15321 | <user-agent> |
||
15322 | <ID>id_n_s_1074</ID> |
||
15323 | <String>OmniExplorer_Bot/x.xx (+http://www.omni-explorer.com) WorldIndexer</String> |
||
15324 | <Description>OmniExplorer car & shopping search (64.62.175.xxx)</Description> |
||
15325 | <Type>R</Type> |
||
15326 | <Comment>based on YottaCars... (see there)</Comment> |
||
15327 | <Link1>http://www.omni-explorer.com</Link1> |
||
15328 | <Link2></Link2> |
||
15329 | </user-agent> |
||
15330 | <user-agent> |
||
15331 | <ID>id_n_s_290106_3</ID> |
||
15332 | <String>onCHECK Linkchecker von www.scientec.de fuer www.onsinn.de</String> |
||
15333 | <Description>onsearch.de German web directory link checking </Description> |
||
15334 | <Type>C</Type> |
||
15335 | <Comment>85.176.108.2xx</Comment> |
||
15336 | <Link1>http://www.onsearch.de/</Link1> |
||
15337 | <Link2></Link2> |
||
15338 | </user-agent> |
||
15339 | <user-agent> |
||
15340 | <ID>id_n_s_290106_2</ID> |
||
15341 | <String>onCHECK-Robot, www.onsearch.de</String> |
||
15342 | <Description>onsearch.de German web directory link checking </Description> |
||
15343 | <Type>C</Type> |
||
15344 | <Comment>85.176.108.2xx</Comment> |
||
15345 | <Link1>http://www.onsearch.de/</Link1> |
||
15346 | <Link2></Link2> |
||
15347 | </user-agent> |
||
15348 | <user-agent> |
||
15349 | <ID>id_n_s_1075</ID> |
||
15350 | <String>Onet.pl SA- http://szukaj.onet.pl</String> |
||
15351 | <Description>onet.pl Szukaj (Search) robot (213.180.128.1xx)</Description> |
||
15352 | <Type>R</Type> |
||
15353 | <Comment>s. also - Mozilla/5.0 (compatible; OnetSzukaj/5.0....</Comment> |
||
15354 | <Link1>http://szukaj.onet.pl/</Link1> |
||
15355 | <Link2></Link2> |
||
15356 | </user-agent> |
||
15357 | <user-agent> |
||
15358 | <ID>id_n_s_1076</ID> |
||
15359 | <String>online link validator (http://www.dead-links.com/)</String> |
||
15360 | <Description>Dead-Links.com link validation spider</Description> |
||
15361 | <Type>C</Type> |
||
15362 | <Comment></Comment> |
||
15363 | <Link1>http://www.dead-links.com/</Link1> |
||
15364 | <Link2></Link2> |
||
15365 | </user-agent> |
||
15366 | <user-agent> |
||
15367 | <ID>id_n_s_040206_3</ID> |
||
15368 | <String>Online24-Bot (Version: 1.0x, powered by www.online24.de)</String> |
||
15369 | <Description>Online24 shopping portal (Germany) link checking</Description> |
||
15370 | <Type>C</Type> |
||
15371 | <Comment></Comment> |
||
15372 | <Link1>http://www.online24.de/</Link1> |
||
15373 | <Link2></Link2> |
||
15374 | </user-agent> |
||
15375 | <user-agent> |
||
15376 | <ID>id_n_s_1077</ID> |
||
15377 | <String>OntoSpider/1.0 libwww-perl/5.65</String> |
||
15378 | <Description>OntoSpider - Dutch robot for a research project. (195.11.244.xx)</Description> |
||
15379 | <Type>R</Type> |
||
15380 | <Comment></Comment> |
||
15381 | <Link1>http://ontospider.i-n.info</Link1> |
||
15382 | <Link2></Link2> |
||
15383 | </user-agent> |
||
15384 | <user-agent> |
||
15385 | <ID>id_n_s_030110_6</ID> |
||
15386 | <String>OOZBOT/0.20 ( http://www.setooz.com/oozbot.html ; agentname at setooz dot_com )</String> |
||
15387 | <Description>SeetooZ search crawler</Description> |
||
15388 | <Type>R</Type> |
||
15389 | <Comment>67.215.230.xx</Comment> |
||
15390 | <Link1>http://www.setooz.com/</Link1> |
||
15391 | <Link2></Link2> |
||
15392 | </user-agent> |
||
15393 | <user-agent> |
||
15394 | <ID>id_g_m_280508_4</ID> |
||
15395 | <String>OpenAcoon v4.0.x (www.openacoon.de)</String> |
||
15396 | <Description>OpenAcoon open source search engine (used by Acoon search)</Description> |
||
15397 | <Type>R</Type> |
||
15398 | <Comment>(80.237.209.xx)</Comment> |
||
15399 | <Link1>http://www.openacoon.de/</Link1> |
||
15400 | <Link2>http://www.acoon.de/</Link2> |
||
15401 | </user-agent> |
||
15402 | <user-agent> |
||
15403 | <ID>id_n_s_1078</ID> |
||
15404 | <String>Openbot/3.0+(robot-response@openfind.com.tw;+http://www.openfind.com.tw/robot.html)</String> |
||
15405 | <Description>Openfind.com.tw robot</Description> |
||
15406 | <Type>R</Type> |
||
15407 | <Comment></Comment> |
||
15408 | <Link1>http://www.openfind.com.tw/</Link1> |
||
15409 | <Link2></Link2> |
||
15410 | </user-agent> |
||
15411 | <user-agent> |
||
15412 | <ID>id_n_s_1079</ID> |
||
15413 | <String>Openfind data gatherer- Openbot/3.0+(robot-response@openfind.com.tw;+http://www.openfind.com.tw/robot.html)</String> |
||
15414 | <Description>Openfind.com.tw robot</Description> |
||
15415 | <Type>R</Type> |
||
15416 | <Comment></Comment> |
||
15417 | <Link1>http://www.openfind.com.tw/</Link1> |
||
15418 | <Link2></Link2> |
||
15419 | </user-agent> |
||
15420 | <user-agent> |
||
15421 | <ID>id_n_s_1080</ID> |
||
15422 | <String>Openfind Robot/1.1A2</String> |
||
15423 | <Description>Openfind.com.tw robot</Description> |
||
15424 | <Type>R</Type> |
||
15425 | <Comment></Comment> |
||
15426 | <Link1>http://www.openfind.com.tw/</Link1> |
||
15427 | <Link2></Link2> |
||
15428 | </user-agent> |
||
15429 | <user-agent> |
||
15430 | <ID>id_n_s_250107_2</ID> |
||
15431 | <String>OpenISearch/1.x (www.openisearch.com)</String> |
||
15432 | <Description>open i search robot - search engine in development</Description> |
||
15433 | <Type>R</Type> |
||
15434 | <Comment>216.182.236.1xx</Comment> |
||
15435 | <Link1>http://www.openisearch.com/</Link1> |
||
15436 | <Link2></Link2> |
||
15437 | </user-agent> |
||
15438 | <user-agent> |
||
15439 | <ID>id_n_s_291105_4</ID> |
||
15440 | <String>OpenTaggerBot (http://www.opentagger.com/opentaggerbot.htm)</String> |
||
15441 | <Description>Opentagger social bookmarking system</Description> |
||
15442 | <Type>R</Type> |
||
15443 | <Comment></Comment> |
||
15444 | <Link1>http://www.opentagger.com/</Link1> |
||
15445 | <Link2></Link2> |
||
15446 | </user-agent> |
||
15447 | <user-agent> |
||
15448 | <ID>id_n_s_1081</ID> |
||
15449 | <String>OpenTextSiteCrawler/2.9.2</String> |
||
15450 | <Description>OpenText crawler</Description> |
||
15451 | <Type>R</Type> |
||
15452 | <Comment></Comment> |
||
15453 | <Link1>http://www.opentext.net/</Link1> |
||
15454 | <Link2></Link2> |
||
15455 | </user-agent> |
||
15456 | <user-agent> |
||
15457 | <ID>id_n_s_310806_1</ID> |
||
15458 | <String>OpenWebSpider/0.x.x (http://www.openwebspider.org)</String> |
||
15459 | <Description>OpenWebSpider - Open Source web search engine</Description> |
||
15460 | <Type>R</Type> |
||
15461 | <Comment></Comment> |
||
15462 | <Link1>http://www.openwebspider.org/</Link1> |
||
15463 | <Link2></Link2> |
||
15464 | </user-agent> |
||
15465 | <user-agent> |
||
15466 | <ID>id_n_s_1082</ID> |
||
15467 | <String>OpenWebSpider/x</String> |
||
15468 | <Description>OpenWebSpider - Open Source web search engine</Description> |
||
15469 | <Type>R</Type> |
||
15470 | <Comment></Comment> |
||
15471 | <Link1>http://www.openwebspider.org/</Link1> |
||
15472 | <Link2></Link2> |
||
15473 | </user-agent> |
||
15474 | <user-agent> |
||
15475 | <ID>id_n_s_1083</ID> |
||
15476 | <String>Opera/5.0 (Linux 2.0.38 i386; U) [en]</String> |
||
15477 | <Description>Opera 5.0 Linux</Description> |
||
15478 | <Type>B</Type> |
||
15479 | <Comment></Comment> |
||
15480 | <Link1></Link1> |
||
15481 | <Link2></Link2> |
||
15482 | </user-agent> |
||
15483 | <user-agent> |
||
15484 | <ID>id_n_s_1084</ID> |
||
15485 | <String>Opera/5.11 (Windows ME; U) [ru]</String> |
||
15486 | <Description>Opera 5.11 faked WinME referer</Description> |
||
15487 | <Type>B</Type> |
||
15488 | <Comment></Comment> |
||
15489 | <Link1></Link1> |
||
15490 | <Link2></Link2> |
||
15491 | </user-agent> |
||
15492 | <user-agent> |
||
15493 | <ID>id_n_s_1085</ID> |
||
15494 | <String>Opera/5.12 (Windows 98; U) [en]</String> |
||
15495 | <Description>Opera 5.12 Win98</Description> |
||
15496 | <Type>B</Type> |
||
15497 | <Comment></Comment> |
||
15498 | <Link1></Link1> |
||
15499 | <Link2></Link2> |
||
15500 | </user-agent> |
||
15501 | <user-agent> |
||
15502 | <ID>id_n_s_1086</ID> |
||
15503 | <String>Opera/6.01 (larbin@unspecified.mail)</String> |
||
15504 | <Description>unknown robot from gw.ocg-corp.com (209.126.176.x)</Description> |
||
15505 | <Type></Type> |
||
15506 | <Comment>see also: - MSIE-5.13 (larbin@.....) - WinampMPEG/2.00 larbin@....</Comment> |
||
15507 | <Link1></Link1> |
||
15508 | <Link2></Link2> |
||
15509 | </user-agent> |
||
15510 | <user-agent> |
||
15511 | <ID>id_n_s_1087</ID> |
||
15512 | <String>Opera/6.x (Linux 2.4.8-26mdk i686; U) [en]</String> |
||
15513 | <Description>Opera 6.x- Mandrake Linux</Description> |
||
15514 | <Type>B</Type> |
||
15515 | <Comment></Comment> |
||
15516 | <Link1></Link1> |
||
15517 | <Link2></Link2> |
||
15518 | </user-agent> |
||
15519 | <user-agent> |
||
15520 | <ID>id_n_s_1088</ID> |
||
15521 | <String>Opera/6.x (Windows NT 4.0; U) [de]</String> |
||
15522 | <Description>Opera 6.x WinNT</Description> |
||
15523 | <Type>B</Type> |
||
15524 | <Comment></Comment> |
||
15525 | <Link1></Link1> |
||
15526 | <Link2></Link2> |
||
15527 | </user-agent> |
||
15528 | <user-agent> |
||
15529 | <ID>id_n_s_1089</ID> |
||
15530 | <String>Opera/7.x (Windows NT 5.1; U) [en]</String> |
||
15531 | <Description>Opera 7.x WinXP</Description> |
||
15532 | <Type>B</Type> |
||
15533 | <Comment></Comment> |
||
15534 | <Link1></Link1> |
||
15535 | <Link2></Link2> |
||
15536 | </user-agent> |
||
15537 | <user-agent> |
||
15538 | <ID>id_n_s_1090</ID> |
||
15539 | <String>Opera/8.xx (Windows NT 5.1; U; en)</String> |
||
15540 | <Description>Opera 8.x (Beta) WinXP</Description> |
||
15541 | <Type>B</Type> |
||
15542 | <Comment></Comment> |
||
15543 | <Link1></Link1> |
||
15544 | <Link2></Link2> |
||
15545 | </user-agent> |
||
15546 | <user-agent> |
||
15547 | <ID>id_n_s_141105_2</ID> |
||
15548 | <String>Opera/9.0 (Windows NT 5.1; U; en)</String> |
||
15549 | <Description>Opera 9 (Beta) Browser</Description> |
||
15550 | <Type>B</Type> |
||
15551 | <Comment></Comment> |
||
15552 | <Link1>http://snapshot.opera.com/</Link1> |
||
15553 | <Link2></Link2> |
||
15554 | </user-agent> |
||
15555 | <user-agent> |
||
15556 | <ID>id_n_s_250606_1</ID> |
||
15557 | <String>Opera/9.00 (Windows NT 5.1; U; de)</String> |
||
15558 | <Description>Opera 9 (final)</Description> |
||
15559 | <Type>B</Type> |
||
15560 | <Comment></Comment> |
||
15561 | <Link1>http://www.opera.com/</Link1> |
||
15562 | <Link2></Link2> |
||
15563 | </user-agent> |
||
15564 | <user-agent> |
||
15565 | <ID>id_n_s_201008_1</ID> |
||
15566 | <String>Opera/9.60 (Windows NT 5.1; U; de) Presto/2.1.1</String> |
||
15567 | <Description>Opera browser 9.6x on WinXP (Presto = Operas rendering engine)</Description> |
||
15568 | <Type>B</Type> |
||
15569 | <Comment></Comment> |
||
15570 | <Link1>http://my.opera.com/ODIN/blog/a-look-under-the-hood-of-opera-9-6</Link1> |
||
15571 | <Link2></Link2> |
||
15572 | </user-agent> |
||
15573 | <user-agent> |
||
15574 | <ID>id_n_s_1091</ID> |
||
15575 | <String>OpidooBOT (larbin2.6.3@unspecified.mail)</String> |
||
15576 | <Description>Opidoo Search Belgium robot (62.4.83.xxx)</Description> |
||
15577 | <Type>R</Type> |
||
15578 | <Comment></Comment> |
||
15579 | <Link1>http://www.opidoo.com/</Link1> |
||
15580 | <Link2></Link2> |
||
15581 | </user-agent> |
||
15582 | <user-agent> |
||
15583 | <ID>id_n_s_080208_1</ID> |
||
15584 | <String>OPWV-SDK UP.Browser/7.0.2.3.119 (GUI) MMP/2.0 Push/PO</String> |
||
15585 | <Description>Open Wave Phone Simulator SDK</Description> |
||
15586 | <Type>B</Type> |
||
15587 | <Comment></Comment> |
||
15588 | <Link1>http://developer.openwave.com/dvl/tools_and_sdk/phone_simulator/</Link1> |
||
15589 | <Link2></Link2> |
||
15590 | </user-agent> |
||
15591 | <user-agent> |
||
15592 | <ID>id_n_s_190406_2</ID> |
||
15593 | <String>Oracle Application Server Web Cache 10g</String> |
||
15594 | <Description>Oracle Application Server cache</Description> |
||
15595 | <Type>P</Type> |
||
15596 | <Comment></Comment> |
||
15597 | <Link1>http://www.oracle.com/appserver/index.html</Link1> |
||
15598 | <Link2></Link2> |
||
15599 | </user-agent> |
||
15600 | <user-agent> |
||
15601 | <ID>id_n_s_1092</ID> |
||
15602 | <String>Oracle iMTCrawler</String> |
||
15603 | <Description>Oracle interMedia Text - Text and web documents indexing</Description> |
||
15604 | <Type>D</Type> |
||
15605 | <Comment></Comment> |
||
15606 | <Link1>http://www.oracle.com/technology//products/text/index.html</Link1> |
||
15607 | <Link2></Link2> |
||
15608 | </user-agent> |
||
15609 | <user-agent> |
||
15610 | <ID>id_n_s_1093</ID> |
||
15611 | <String>Oracle Ultra Search</String> |
||
15612 | <Description>Oracle Search</Description> |
||
15613 | <Type>R</Type> |
||
15614 | <Comment></Comment> |
||
15615 | <Link1>http://www.oracle.com/</Link1> |
||
15616 | <Link2></Link2> |
||
15617 | </user-agent> |
||
15618 | <user-agent> |
||
15619 | <ID>id_n_s_220306_1</ID> |
||
15620 | <String>OrangeSpider</String> |
||
15621 | <Description>Orangeslicer semantic search (Beta) Germany (193.201.52.1xx)</Description> |
||
15622 | <Type>R</Type> |
||
15623 | <Comment></Comment> |
||
15624 | <Link1>http://www.orangeslicer.com/</Link1> |
||
15625 | <Link2></Link2> |
||
15626 | </user-agent> |
||
15627 | <user-agent> |
||
15628 | <ID>id_n_s_1094</ID> |
||
15629 | <String>Orbiter/T-2.0 (+http://www.dailyorbit.com/bot.htm)</String> |
||
15630 | <Description>Orbiter - DailyOrbit search spider</Description> |
||
15631 | <Type>R</Type> |
||
15632 | <Comment></Comment> |
||
15633 | <Link1>http://www.dailyorbit.com/</Link1> |
||
15634 | <Link2></Link2> |
||
15635 | </user-agent> |
||
15636 | <user-agent> |
||
15637 | <ID>id_n_s_150206_1</ID> |
||
15638 | <String>Orca Browser (http://www.orcabrowser.com)</String> |
||
15639 | <Description>Orca browser - based on Gecko</Description> |
||
15640 | <Type>B</Type> |
||
15641 | <Comment></Comment> |
||
15642 | <Link1>http://www.orcabrowser.com</Link1> |
||
15643 | <Link2></Link2> |
||
15644 | </user-agent> |
||
15645 | <user-agent> |
||
15646 | <ID>id_n_s_251205_1</ID> |
||
15647 | <String>OSSProxy 1.3.305.321 (Build 305.321 Win32 en-us)(Dec 21 2005 16:30:54)</String> |
||
15648 | <Description>Marketscore (was Netsetter) internet accelerator</Description> |
||
15649 | <Type>P</Type> |
||
15650 | <Comment>Spyware proxy service</Comment> |
||
15651 | <Link1>http://www.marketscore.com/Home.aspx</Link1> |
||
15652 | <Link2></Link2> |
||
15653 | </user-agent> |
||
15654 | <user-agent> |
||
15655 | <ID>id_n_s_141105_1</ID> |
||
15656 | <String>OutfoxBot/0.x (For internet experiments; http://; outfox.agent@gmail.com)</String> |
||
15657 | <Description>Unknown robot from Chinanet (220.181.8.xxx)</Description> |
||
15658 | <Type></Type> |
||
15659 | <Comment></Comment> |
||
15660 | <Link1></Link1> |
||
15661 | <Link2></Link2> |
||
15662 | </user-agent> |
||
15663 | <user-agent> |
||
15664 | <ID>id_n_s_221106_1</ID> |
||
15665 | <String>OutfoxMelonBot/0.5 (for internet experiments; http://; outfoxbot@gmail.com)</String> |
||
15666 | <Description>Unknown robot from Chinanet (60.191.80.1)</Description> |
||
15667 | <Type></Type> |
||
15668 | <Comment></Comment> |
||
15669 | <Link1></Link1> |
||
15670 | <Link2></Link2> |
||
15671 | </user-agent> |
||
15672 | <user-agent> |
||
15673 | <ID>id_n_s_1095</ID> |
||
15674 | <String>Overture-WebCrawler/3.8/Fresh (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)</String> |
||
15675 | <Description>Overture/Fast/Alltheweb crawler (66.77.73.xxx)</Description> |
||
15676 | <Type>R</Type> |
||
15677 | <Comment></Comment> |
||
15678 | <Link1>http://www.alltheweb.com/</Link1> |
||
15679 | <Link2></Link2> |
||
15680 | </user-agent> |
||
15681 | <user-agent> |
||
15682 | <ID>id_n_s_1096</ID> |
||
15683 | <String>OWR_Crawler 0.1</String> |
||
15684 | <Description>Unknown robot from 198.169.127.xx (innovationplace.com)</Description> |
||
15685 | <Type></Type> |
||
15686 | <Comment></Comment> |
||
15687 | <Link1></Link1> |
||
15688 | <Link2></Link2> |
||
15689 | </user-agent> |
||
15690 | <user-agent> |
||
15691 | <ID>id_n_s_090906_1</ID> |
||
15692 | <String>ozelot/2.7.3 (Search engine indexer; www.flying-cat.de/ozelot; ozelot@flying-cat.de)</String> |
||
15693 | <Description>Ozelot - Flying Cat's search engine robot (Germany)</Description> |
||
15694 | <Type>R</Type> |
||
15695 | <Comment>87.139.106.xx</Comment> |
||
15696 | <Link1>http://www.flying-cat.de/ozelot/</Link1> |
||
15697 | <Link2></Link2> |
||
15698 | </user-agent> |
||
15699 | <user-agent> |
||
15700 | <ID>id_n_s_290108_2</ID> |
||
15701 | <String>PADLibrary Spider</String> |
||
15702 | <Description>PADLibrary.com - PAD file software robot for FindFiles.com</Description> |
||
15703 | <Type>R</Type> |
||
15704 | <Comment>72.167.37.20x</Comment> |
||
15705 | <Link1>http://padlibrary.com/</Link1> |
||
15706 | <Link2>http://www.findfiles.com/</Link2> |
||
15707 | </user-agent> |
||
15708 | <user-agent> |
||
15709 | <ID>id_n_s_150207_3</ID> |
||
15710 | <String>PageBitesHyperBot/600 (http://www.pagebites.com/)</String> |
||
15711 | <Description>Pagebites job search crawler</Description> |
||
15712 | <Type>R</Type> |
||
15713 | <Comment>208.185.247.xx</Comment> |
||
15714 | <Link1>http://www.pagebites.com/</Link1> |
||
15715 | <Link2></Link2> |
||
15716 | </user-agent> |
||
15717 | <user-agent> |
||
15718 | <ID>id_n_s_111206_1</ID> |
||
15719 | <String>Pagebull http://www.pagebull.com/</String> |
||
15720 | <Description>Pagebull visual search engine</Description> |
||
15721 | <Type>R</Type> |
||
15722 | <Comment>209.9.228.1xx</Comment> |
||
15723 | <Link1>http://www.pagebull.com/</Link1> |
||
15724 | <Link2></Link2> |
||
15725 | </user-agent> |
||
15726 | <user-agent> |
||
15727 | <ID>id_n_s_051207_3</ID> |
||
15728 | <String>Pagestacker Bot</String> |
||
15729 | <Description>Pagestacker online bookmark service</Description> |
||
15730 | <Type>C</Type> |
||
15731 | <Comment>70.85.129.12x</Comment> |
||
15732 | <Link1>http://www.pagestacker.com/</Link1> |
||
15733 | <Link2></Link2> |
||
15734 | </user-agent> |
||
15735 | <user-agent> |
||
15736 | <ID>id_n_s_290506_1</ID> |
||
15737 | <String>page_verifier (http://www.securecomputing.com/goto/pv)</String> |
||
15738 | <Description>Secure Computing SmartFilter Tools - malware crawler</Description> |
||
15739 | <Type>R</Type> |
||
15740 | <Comment>206.169.110.xx</Comment> |
||
15741 | <Link1>http://www.securecomputing.com/PageVerifier.cfm</Link1> |
||
15742 | <Link2></Link2> |
||
15743 | </user-agent> |
||
15744 | <user-agent> |
||
15745 | <ID>id_n_s_1097</ID> |
||
15746 | <String>PagmIEDownload</String> |
||
15747 | <Description>Downloadmanager ?</Description> |
||
15748 | <Type>D</Type> |
||
15749 | <Comment></Comment> |
||
15750 | <Link1></Link1> |
||
15751 | <Link2></Link2> |
||
15752 | </user-agent> |
||
15753 | <user-agent> |
||
15754 | <ID>id_n_s_1098</ID> |
||
15755 | <String>parallelContextFocusCrawler1.1parallelContextFocusCrawler1.1</String> |
||
15756 | <Description>CFC crawler used by Italian academic and research network (GARR)</Description> |
||
15757 | <Type>R</Type> |
||
15758 | <Comment></Comment> |
||
15759 | <Link1>http://www.garr.it/</Link1> |
||
15760 | <Link2></Link2> |
||
15761 | </user-agent> |
||
15762 | <user-agent> |
||
15763 | <ID>id_n_s_1099</ID> |
||
15764 | <String>ParaSite/1.0b (http://www.ianett.com/parasite/)</String> |
||
15765 | <Description>http://www.ianett.com robot</Description> |
||
15766 | <Type>R</Type> |
||
15767 | <Comment></Comment> |
||
15768 | <Link1>http://www.ianett.com/</Link1> |
||
15769 | <Link2></Link2> |
||
15770 | </user-agent> |
||
15771 | <user-agent> |
||
15772 | <ID>id_n_s_1100</ID> |
||
15773 | <String>Patwebbot (http://www.herz-power.de/technik.html)</String> |
||
15774 | <Description>Patsearch (Germany) robot</Description> |
||
15775 | <Type>R</Type> |
||
15776 | <Comment></Comment> |
||
15777 | <Link1>http://www.herz-power.de/</Link1> |
||
15778 | <Link2></Link2> |
||
15779 | </user-agent> |
||
15780 | <user-agent> |
||
15781 | <ID>id_n_s_1101</ID> |
||
15782 | <String>pavuk/0.9pl29b i686-pc-linux-gnu</String> |
||
15783 | <Description>Pavuk web downloading program for Unix</Description> |
||
15784 | <Type>D</Type> |
||
15785 | <Comment></Comment> |
||
15786 | <Link1>http://www.idata.sk/%7Eondrej/pavuk/about.html</Link1> |
||
15787 | <Link2></Link2> |
||
15788 | </user-agent> |
||
15789 | <user-agent> |
||
15790 | <ID>id_n_s_1102</ID> |
||
15791 | <String>PBrowse 1.4b</String> |
||
15792 | <Description>Some site scanning tool via diff. IPs- i.e.: - cox.net (68.4.xxx.xxx)</Description> |
||
15793 | <Type>S</Type> |
||
15794 | <Comment>- UA sometimes DSurf15a</Comment> |
||
15795 | <Link1></Link1> |
||
15796 | <Link2></Link2> |
||
15797 | </user-agent> |
||
15798 | <user-agent> |
||
15799 | <ID>id_n_s_1103</ID> |
||
15800 | <String>pd02_1.0.0 pd02_1.0.0@dzimi@post.sk</String> |
||
15801 | <Description>Post.sk / Eurotel.sk robot</Description> |
||
15802 | <Type>R</Type> |
||
15803 | <Comment></Comment> |
||
15804 | <Link1></Link1> |
||
15805 | <Link2></Link2> |
||
15806 | </user-agent> |
||
15807 | <user-agent> |
||
15808 | <ID>id_n_s_1104</ID> |
||
15809 | <String>PEAR HTTP_Request class ( http://pear.php.net/ )</String> |
||
15810 | <Description>Pear HTTP_Request PHP extension package</Description> |
||
15811 | <Type></Type> |
||
15812 | <Comment></Comment> |
||
15813 | <Link1>http://pear.php.net/</Link1> |
||
15814 | <Link2></Link2> |
||
15815 | </user-agent> |
||
15816 | <user-agent> |
||
15817 | <ID>id_n_s_1105</ID> |
||
15818 | <String>PEERbot www.peerbot.com</String> |
||
15819 | <Description>Peerbot - favicon search robot</Description> |
||
15820 | <Type>R</Type> |
||
15821 | <Comment></Comment> |
||
15822 | <Link1>http://www.peerbot.com/</Link1> |
||
15823 | <Link2></Link2> |
||
15824 | </user-agent> |
||
15825 | <user-agent> |
||
15826 | <ID>id_n_s_1106</ID> |
||
15827 | <String>PeopleChat/Search_Engine</String> |
||
15828 | <Description>Unknown robot from 64.5.48.xxx (Plethoric.net)</Description> |
||
15829 | <Type></Type> |
||
15830 | <Comment></Comment> |
||
15831 | <Link1></Link1> |
||
15832 | <Link2></Link2> |
||
15833 | </user-agent> |
||
15834 | <user-agent> |
||
15835 | <ID>id_n_s_1107</ID> |
||
15836 | <String>PEval 1.4b</String> |
||
15837 | <Description>Some site scanning tool via diff. IPs</Description> |
||
15838 | <Type>S</Type> |
||
15839 | <Comment>s. DBrowse- PSurf etc.</Comment> |
||
15840 | <Link1></Link1> |
||
15841 | <Link2></Link2> |
||
15842 | </user-agent> |
||
15843 | <user-agent> |
||
15844 | <ID>id_n_s_1108</ID> |
||
15845 | <String>PHP/3.x.xx</String> |
||
15846 | <Description>diff. IPs / services</Description> |
||
15847 | <Type></Type> |
||
15848 | <Comment></Comment> |
||
15849 | <Link1></Link1> |
||
15850 | <Link2></Link2> |
||
15851 | </user-agent> |
||
15852 | <user-agent> |
||
15853 | <ID>id_n_s_1109</ID> |
||
15854 | <String>PHP/4.0.4pl1</String> |
||
15855 | <Description>diff. IPs / services</Description> |
||
15856 | <Type></Type> |
||
15857 | <Comment></Comment> |
||
15858 | <Link1></Link1> |
||
15859 | <Link2></Link2> |
||
15860 | </user-agent> |
||
15861 | <user-agent> |
||
15862 | <ID>id_n_s_1110</ID> |
||
15863 | <String>PHP/4.0.6</String> |
||
15864 | <Description>diff. IPs / services- i.e.: -NTT/Verio Inc. link checker</Description> |
||
15865 | <Type>C</Type> |
||
15866 | <Comment>in conjunction w. Weblink's Checker UA</Comment> |
||
15867 | <Link1>http://www.verio.com/</Link1> |
||
15868 | <Link2></Link2> |
||
15869 | </user-agent> |
||
15870 | <user-agent> |
||
15871 | <ID>id_n_s_1111</ID> |
||
15872 | <String>PHP/4.1.1</String> |
||
15873 | <Description>diff. IPs / services- i.e.: - Phenominet.com link checking</Description> |
||
15874 | <Type>C</Type> |
||
15875 | <Comment></Comment> |
||
15876 | <Link1>http://www.phenominet.com</Link1> |
||
15877 | <Link2></Link2> |
||
15878 | </user-agent> |
||
15879 | <user-agent> |
||
15880 | <ID>id_n_s_1112</ID> |
||
15881 | <String>PHP/4.1.2</String> |
||
15882 | <Description>diff. IPs / services- i.e.: - 209.114.200.xx = MyNetCrawler link checking - 216.139.207.xxx = Mixcat crawler</Description> |
||
15883 | <Type></Type> |
||
15884 | <Comment>Mixcat s. also Felix and Morris</Comment> |
||
15885 | <Link1>http://mynetcrawler.com/</Link1> |
||
15886 | <Link2>http://mixcat.com</Link2> |
||
15887 | </user-agent> |
||
15888 | <user-agent> |
||
15889 | <ID>id_n_s_1113</ID> |
||
15890 | <String>PicoSearch/1.0</String> |
||
15891 | <Description>Pico Search robot</Description> |
||
15892 | <Type>R</Type> |
||
15893 | <Comment></Comment> |
||
15894 | <Link1>http://www.picosearch.com/</Link1> |
||
15895 | <Link2></Link2> |
||
15896 | </user-agent> |
||
15897 | <user-agent> |
||
15898 | <ID>id_n_s_010506_3</ID> |
||
15899 | <String>Piffany_Web_Scraper_v0.x</String> |
||
15900 | <Description>Piffany targeted search web spider</Description> |
||
15901 | <Type>R</Type> |
||
15902 | <Comment></Comment> |
||
15903 | <Link1>http://www.piffany.com/</Link1> |
||
15904 | <Link2>http://www.piffany.com/spider.html</Link2> |
||
15905 | </user-agent> |
||
15906 | <user-agent> |
||
15907 | <ID>id_n_s_010506_2</ID> |
||
15908 | <String>Piffany_Web_Spider_v0.x</String> |
||
15909 | <Description>Piffany targeted search web spider</Description> |
||
15910 | <Type>R</Type> |
||
15911 | <Comment></Comment> |
||
15912 | <Link1>http://www.piffany.com/</Link1> |
||
15913 | <Link2>http://www.piffany.com/spider.html</Link2> |
||
15914 | </user-agent> |
||
15915 | <user-agent> |
||
15916 | <ID>id_n_s_1114</ID> |
||
15917 | <String>PigeonBot1.0 BETA</String> |
||
15918 | <Description>Whois Source domain name information robot (66.249.26.xx)- s.also: - SurveyBot</Description> |
||
15919 | <Type>R C</Type> |
||
15920 | <Comment></Comment> |
||
15921 | <Link1>http://www.whois.sc/</Link1> |
||
15922 | <Link2></Link2> |
||
15923 | </user-agent> |
||
15924 | <user-agent> |
||
15925 | <ID>id_n_s_1115</ID> |
||
15926 | <String>PingALink Monitoring Services 1.0</String> |
||
15927 | <Description>PingALink website monitoring</Description> |
||
15928 | <Type>R C</Type> |
||
15929 | <Comment></Comment> |
||
15930 | <Link1>http://www.pingalink.com/</Link1> |
||
15931 | <Link2></Link2> |
||
15932 | </user-agent> |
||
15933 | <user-agent> |
||
15934 | <ID>id_n_s_1116</ID> |
||
15935 | <String>PingALink Monitoring Services 1.0 (http://www.pingalink.com)</String> |
||
15936 | <Description>PingALink website monitoring</Description> |
||
15937 | <Type>R C</Type> |
||
15938 | <Comment></Comment> |
||
15939 | <Link1>http://www.pingalink.com/</Link1> |
||
15940 | <Link2></Link2> |
||
15941 | </user-agent> |
||
15942 | <user-agent> |
||
15943 | <ID>id_n_s_120607_1</ID> |
||
15944 | <String>Pingdom GIGRIB (http://www.pingdom.com)</String> |
||
15945 | <Description>Pingdom web site monitoring</Description> |
||
15946 | <Type>C</Type> |
||
15947 | <Comment>66.98.148.xx</Comment> |
||
15948 | <Link1>http://www.pingdom.com/</Link1> |
||
15949 | <Link2></Link2> |
||
15950 | </user-agent> |
||
15951 | <user-agent> |
||
15952 | <ID>id_n_s_1117</ID> |
||
15953 | <String>pipeLiner/0.3a (PipeLine Spider;http://www.pipeline-search.com/webmaster.html; webmaster'at'pipeline-search.com)</String> |
||
15954 | <Description>pipeline search (DMOZ based) search robot (24.106.39. xxx)</Description> |
||
15955 | <Type>R</Type> |
||
15956 | <Comment></Comment> |
||
15957 | <Link1>http://www.pipeline-search.com/</Link1> |
||
15958 | <Link2></Link2> |
||
15959 | </user-agent> |
||
15960 | <user-agent> |
||
15961 | <ID>id_n_s_1118</ID> |
||
15962 | <String>pipeLiner/0.xx (PipeLine Spider; http://www.pipeline-search.com/webmaster.html)</String> |
||
15963 | <Description>pipeline search (DMOZ based) search robot (24.106.39. xxx)</Description> |
||
15964 | <Type>R</Type> |
||
15965 | <Comment></Comment> |
||
15966 | <Link1>http://www.pipeline-search.com/</Link1> |
||
15967 | <Link2></Link2> |
||
15968 | </user-agent> |
||
15969 | <user-agent> |
||
15970 | <ID>id_n_s_1119</ID> |
||
15971 | <String>Pita</String> |
||
15972 | <Description>Pita crawler</Description> |
||
15973 | <Type>R</Type> |
||
15974 | <Comment>now WebVac s. there</Comment> |
||
15975 | <Link1>http://www-diglib.stanford.edu/~testbed/doc2/WebBase/webbase-pages.html</Link1> |
||
15976 | <Link2></Link2> |
||
15977 | </user-agent> |
||
15978 | <user-agent> |
||
15979 | <ID>id_n_s_1120</ID> |
||
15980 | <String>Pizilla++ ver 2.45</String> |
||
15981 | <Description>Private user-agent via Hurricane Electric Internet Services</Description> |
||
15982 | <Type>B ?</Type> |
||
15983 | <Comment></Comment> |
||
15984 | <Link1>http://www.he.net/</Link1> |
||
15985 | <Link2></Link2> |
||
15986 | </user-agent> |
||
15987 | <user-agent> |
||
15988 | <ID>id_n_s_1121</ID> |
||
15989 | <String>PJspider/3.0 (pjspider@portaljuice.com; http://www.portaljuice.com)</String> |
||
15990 | <Description>Portaljuice spider</Description> |
||
15991 | <Type>R</Type> |
||
15992 | <Comment></Comment> |
||
15993 | <Link1>http://www.portaljuice.com/</Link1> |
||
15994 | <Link2></Link2> |
||
15995 | </user-agent> |
||
15996 | <user-agent> |
||
15997 | <ID>id_n_s_121106_1</ID> |
||
15998 | <String>Plagger/0.x.xx (http://plagger.org/)</String> |
||
15999 | <Description>Plagger - pluggable RSS/Atom feed aggregator written in Perl</Description> |
||
16000 | <Type>B</Type> |
||
16001 | <Comment></Comment> |
||
16002 | <Link1>http://plagger.org/trac</Link1> |
||
16003 | <Link2></Link2> |
||
16004 | </user-agent> |
||
16005 | <user-agent> |
||
16006 | <ID>id_n_s_1122</ID> |
||
16007 | <String>PlagiarBot/1.0</String> |
||
16008 | <Description>unknown ucsd.edu robot</Description> |
||
16009 | <Type>R</Type> |
||
16010 | <Comment></Comment> |
||
16011 | <Link1></Link1> |
||
16012 | <Link2></Link2> |
||
16013 | </user-agent> |
||
16014 | <user-agent> |
||
16015 | <ID>id_n_s_1123</ID> |
||
16016 | <String>PlantyNet_WebRobot_V1.9 dhkang@plantynet.com</String> |
||
16017 | <Description>Plantynet web filtering services - Blacklist DB robot</Description> |
||
16018 | <Type>R P</Type> |
||
16019 | <Comment></Comment> |
||
16020 | <Link1>http://www.plantynet.com/</Link1> |
||
16021 | <Link2></Link2> |
||
16022 | </user-agent> |
||
16023 | <user-agent> |
||
16024 | <ID>id_n_s_120106_1</ID> |
||
16025 | <String>plinki/0.1 (you got plinked! (thats a good thing..); http://www.plinki.com; crawl@plinki.com)</String> |
||
16026 | <Description>Unknown UA from 66.220.23.2xx</Description> |
||
16027 | <Type></Type> |
||
16028 | <Comment>Doesn't read robots.txt - Plinki.com's website has no content</Comment> |
||
16029 | <Link1>http://www.plinki.com/</Link1> |
||
16030 | <Link2></Link2> |
||
16031 | </user-agent> |
||
16032 | <user-agent> |
||
16033 | <ID>id_n_s_061206_2</ID> |
||
16034 | <String>PluckFeedCrawler/2.0 (compatible; Mozilla 4.0; MSIE 5.5; http://www.pluck.com; 1 subscribers)</String> |
||
16035 | <Description>Pluck RSS feed crawler</Description> |
||
16036 | <Type>R</Type> |
||
16037 | <Comment>66.179.81.1xx</Comment> |
||
16038 | <Link1>http://www.pluck.com/</Link1> |
||
16039 | <Link2></Link2> |
||
16040 | </user-agent> |
||
16041 | <user-agent> |
||
16042 | <ID>id_n_s_140807_1</ID> |
||
16043 | <String>Pluggd/Nutch-0.9 (automated crawler http://www.pluggd.com;support at pluggd dot com)</String> |
||
16044 | <Description>Pluggd Podcast search engine</Description> |
||
16045 | <Type>R</Type> |
||
16046 | <Comment>209.85.62.1xx</Comment> |
||
16047 | <Link1>http://www.pluggd.com/</Link1> |
||
16048 | <Link2></Link2> |
||
16049 | </user-agent> |
||
16050 | <user-agent> |
||
16051 | <ID>id_n_s_1124</ID> |
||
16052 | <String>Pockey-GetHTML/4.12.0 (Win32; GUI; ix86)</String> |
||
16053 | <Description>Yutaka Endo's Pockey / GetHTML / GetHTMLW - some downloading tool from Japan</Description> |
||
16054 | <Type>D</Type> |
||
16055 | <Comment></Comment> |
||
16056 | <Link1>http://www.vector.co.jp/soft/win95/net/se077067.html</Link1> |
||
16057 | <Link2></Link2> |
||
16058 | </user-agent> |
||
16059 | <user-agent> |
||
16060 | <ID>id_n_s_1125</ID> |
||
16061 | <String>Pockey-GetHTML/x.xx</String> |
||
16062 | <Description>Yutaka Endo's Pockey / GetHTML / GetHTMLW - some downloading tool from Japan</Description> |
||
16063 | <Type>D</Type> |
||
16064 | <Comment></Comment> |
||
16065 | <Link1>http://www.vector.co.jp/soft/win95/net/se077067.html</Link1> |
||
16066 | <Link2></Link2> |
||
16067 | </user-agent> |
||
16068 | <user-agent> |
||
16069 | <ID>id_n_s_1126</ID> |
||
16070 | <String>Pockey/x.x.x</String> |
||
16071 | <Description>Yutaka Endo's Pockey / GetHTML / GetHTMLW - some downloading tool from Japan</Description> |
||
16072 | <Type>D</Type> |
||
16073 | <Comment></Comment> |
||
16074 | <Link1>http://www.vector.co.jp/soft/win95/net/se077067.html</Link1> |
||
16075 | <Link2></Link2> |
||
16076 | </user-agent> |
||
16077 | <user-agent> |
||
16078 | <ID>id_n_s_1127</ID> |
||
16079 | <String>Pockey7.x.x(WIN32GUI)</String> |
||
16080 | <Description>Yutaka Endo's Pockey / GetHTML / GetHTMLW - some downloading tool from Japan</Description> |
||
16081 | <Type>D</Type> |
||
16082 | <Comment></Comment> |
||
16083 | <Link1>http://www.vector.co.jp/soft/win95/net/se077067.html</Link1> |
||
16084 | <Link2></Link2> |
||
16085 | </user-agent> |
||
16086 | <user-agent> |
||
16087 | <ID>id_n_s_1128</ID> |
||
16088 | <String>POE-Component-Client-HTTP/0.64 (perl; N; POE; en; rv:0.640000)</String> |
||
16089 | <Description>HTTP user-agent for POE (portable networking framework for Perl )</Description> |
||
16090 | <Type></Type> |
||
16091 | <Comment></Comment> |
||
16092 | <Link1>http://search.cpan.org/dist/POE-Component-Client-HTTP/HTTP.pm</Link1> |
||
16093 | <Link2></Link2> |
||
16094 | </user-agent> |
||
16095 | <user-agent> |
||
16096 | <ID>id_n_s_291105_2</ID> |
||
16097 | <String>Poirot</String> |
||
16098 | <Description>ThePlanet/jaja-jak-globusy.com Google Adsense refferer spam bot from 70.85.116.* / 70.84.128.xxx / 70.85.193.xxx</Description> |
||
16099 | <Type>S</Type> |
||
16100 | <Comment>appears also as LWP::Simple/5.803 - Mozilla/4.76 [en] (Win98; U) - Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)</Comment> |
||
16101 | <Link1>http://spamhuntress.com/wiki/Manila_Industries</Link1> |
||
16102 | <Link2></Link2> |
||
16103 | </user-agent> |
||
16104 | <user-agent> |
||
16105 | <ID>id_n_s_1129</ID> |
||
16106 | <String>polybot 1.0 (http://cis.poly.edu/polybot/)</String> |
||
16107 | <Description>Polybot webcrawler</Description> |
||
16108 | <Type>R</Type> |
||
16109 | <Comment></Comment> |
||
16110 | <Link1>http://cis.poly.edu/polybot/</Link1> |
||
16111 | <Link2></Link2> |
||
16112 | </user-agent> |
||
16113 | <user-agent> |
||
16114 | <ID>id_n_s_1130</ID> |
||
16115 | <String>Pompos/1.x http://dir.com/pompos.html</String> |
||
16116 | <Description>Dir.com / Iliad French recherche robot</Description> |
||
16117 | <Type>R</Type> |
||
16118 | <Comment></Comment> |
||
16119 | <Link1>http://www.iliad.fr/</Link1> |
||
16120 | <Link2></Link2> |
||
16121 | </user-agent> |
||
16122 | <user-agent> |
||
16123 | <ID>id_n_s_1131</ID> |
||
16124 | <String>Pompos/1.x pompos@iliad.fr</String> |
||
16125 | <Description>Iliad / Free French recherche robot</Description> |
||
16126 | <Type>R</Type> |
||
16127 | <Comment></Comment> |
||
16128 | <Link1>http://www.iliad.fr/</Link1> |
||
16129 | <Link2></Link2> |
||
16130 | </user-agent> |
||
16131 | <user-agent> |
||
16132 | <ID>id_n_s_1132</ID> |
||
16133 | <String>Popdexter/1.0</String> |
||
16134 | <Description>Popdex - web site popularity crawler</Description> |
||
16135 | <Type>R</Type> |
||
16136 | <Comment></Comment> |
||
16137 | <Link1>http://www.popdex.com/</Link1> |
||
16138 | <Link2></Link2> |
||
16139 | </user-agent> |
||
16140 | <user-agent> |
||
16141 | <ID>id_n_s_1133</ID> |
||
16142 | <String>Port Huron Labs</String> |
||
16143 | <Description>Unknown spam bot / harvester (63.223.10.***)</Description> |
||
16144 | <Type>S</Type> |
||
16145 | <Comment>s. also - Wells Search II</Comment> |
||
16146 | <Link1></Link1> |
||
16147 | <Link2></Link2> |
||
16148 | </user-agent> |
||
16149 | <user-agent> |
||
16150 | <ID>id_n_s_1134</ID> |
||
16151 | <String>PortalBSpider/2.0 (spider@portalb.com)</String> |
||
16152 | <Description>PortalB (now Alacra search) spider</Description> |
||
16153 | <Type>R</Type> |
||
16154 | <Comment></Comment> |
||
16155 | <Link1>http://www.portalb.com/alacra/index.htm</Link1> |
||
16156 | <Link2></Link2> |
||
16157 | </user-agent> |
||
16158 | <user-agent> |
||
16159 | <ID>id_n_s_080706_2</ID> |
||
16160 | <String>portalmmm/2.0 S500i(c20;TB)</String> |
||
16161 | <Description>portalmmm IMode mobile browser</Description> |
||
16162 | <Type>B</Type> |
||
16163 | <Comment></Comment> |
||
16164 | <Link1></Link1> |
||
16165 | <Link2></Link2> |
||
16166 | </user-agent> |
||
16167 | <user-agent> |
||
16168 | <ID>id_n_s_1135</ID> |
||
16169 | <String>PostFavorites</String> |
||
16170 | <Description>Yahoo (66.94.237.1xx / 216.109.121.xx) favorites tracking robot</Description> |
||
16171 | <Type>C</Type> |
||
16172 | <Comment></Comment> |
||
16173 | <Link1></Link1> |
||
16174 | <Link2></Link2> |
||
16175 | </user-agent> |
||
16176 | <user-agent> |
||
16177 | <ID>id_n_s_1136</ID> |
||
16178 | <String>potbot 1.0</String> |
||
16179 | <Description>Potbot : A simple IRC bot written in Perl</Description> |
||
16180 | <Type>R</Type> |
||
16181 | <Comment></Comment> |
||
16182 | <Link1>http://sourceforge.net/projects/potbot/</Link1> |
||
16183 | <Link2></Link2> |
||
16184 | </user-agent> |
||
16185 | <user-agent> |
||
16186 | <ID>id_n_s_050408_2</ID> |
||
16187 | <String>PRCrawler/Nutch-0.9 (data mining development project; crawler@projectrialto.com)</String> |
||
16188 | <Description>Project Rialto - data mining development project</Description> |
||
16189 | <Type>R</Type> |
||
16190 | <Comment></Comment> |
||
16191 | <Link1>http://projectrialto.com/index.html</Link1> |
||
16192 | <Link2></Link2> |
||
16193 | </user-agent> |
||
16194 | <user-agent> |
||
16195 | <ID>id_n_s_1137</ID> |
||
16196 | <String>PrivacyFinder Cache Bot v1.0</String> |
||
16197 | <Description>CUPS robot for AT&T Privacy Bird Privacy Preferences (P3P) enhancements</Description> |
||
16198 | <Type>R</Type> |
||
16199 | <Comment></Comment> |
||
16200 | <Link1>http://cups.cs.cmu.edu/</Link1> |
||
16201 | <Link2>http://privacybird.com/</Link2> |
||
16202 | </user-agent> |
||
16203 | <user-agent> |
||
16204 | <ID>id_n_s_111205_2</ID> |
||
16205 | <String>PrivacyFinder/1.1</String> |
||
16206 | <Description>CUPS robot for AT&T Privacy Bird Privacy Preferences (P3P) enhancements</Description> |
||
16207 | <Type>R</Type> |
||
16208 | <Comment></Comment> |
||
16209 | <Link1>http://cups.cs.cmu.edu/</Link1> |
||
16210 | <Link2>http://privacybird.com/</Link2> |
||
16211 | </user-agent> |
||
16212 | <user-agent> |
||
16213 | <ID>id_n_s_1138</ID> |
||
16214 | <String>Privoxy/3.0 (Anonymous)</String> |
||
16215 | <Description>Privoxy web proxy</Description> |
||
16216 | <Type>P</Type> |
||
16217 | <Comment>s.also (Privoxy/1.0)</Comment> |
||
16218 | <Link1>http://www.privoxy.org/</Link1> |
||
16219 | <Link2></Link2> |
||
16220 | </user-agent> |
||
16221 | <user-agent> |
||
16222 | <ID>id_n_s_1139</ID> |
||
16223 | <String>Production Bot 0116B</String> |
||
16224 | <Description>Some site scanning tool from diff. IPs- i.e.: - 67.99.33.x (lightningcon.broadwing.net)</Description> |
||
16225 | <Type>S</Type> |
||
16226 | <Comment></Comment> |
||
16227 | <Link1></Link1> |
||
16228 | <Link2></Link2> |
||
16229 | </user-agent> |
||
16230 | <user-agent> |
||
16231 | <ID>id_n_s_1140</ID> |
||
16232 | <String>Production Bot 2016B</String> |
||
16233 | <Description>Some site scanning tool from diff. IPs- i.e.: - 216.232.64.xx (telus.net)</Description> |
||
16234 | <Type>S</Type> |
||
16235 | <Comment></Comment> |
||
16236 | <Link1></Link1> |
||
16237 | <Link2></Link2> |
||
16238 | </user-agent> |
||
16239 | <user-agent> |
||
16240 | <ID>id_n_s_1141</ID> |
||
16241 | <String>Production Bot DOT 3016B</String> |
||
16242 | <Description>Some site scanning tool from diff. IPs- i.e.: - 141.154.181.xxx (east.verizon.net)</Description> |
||
16243 | <Type>S</Type> |
||
16244 | <Comment></Comment> |
||
16245 | <Link1></Link1> |
||
16246 | <Link2></Link2> |
||
16247 | </user-agent> |
||
16248 | <user-agent> |
||
16249 | <ID>id_n_s_1142</ID> |
||
16250 | <String>Program Shareware 1.0.2</String> |
||
16251 | <Description>Some spam bot</Description> |
||
16252 | <Type>S</Type> |
||
16253 | <Comment>- see here: http://www.kloth.net/internet/badbots-2004.php</Comment> |
||
16254 | <Link1>http://www.kloth.net/internet/badbots-2004.php</Link1> |
||
16255 | <Link2></Link2> |
||
16256 | </user-agent> |
||
16257 | <user-agent> |
||
16258 | <ID>id_n_s_1143</ID> |
||
16259 | <String>Progressive Download</String> |
||
16260 | <Description>unknown</Description> |
||
16261 | <Type></Type> |
||
16262 | <Comment></Comment> |
||
16263 | <Link1></Link1> |
||
16264 | <Link2></Link2> |
||
16265 | </user-agent> |
||
16266 | <user-agent> |
||
16267 | <ID>id_n_s_1144</ID> |
||
16268 | <String>Progressive Download HTTP check</String> |
||
16269 | <Description>unknown</Description> |
||
16270 | <Type></Type> |
||
16271 | <Comment></Comment> |
||
16272 | <Link1></Link1> |
||
16273 | <Link2></Link2> |
||
16274 | </user-agent> |
||
16275 | <user-agent> |
||
16276 | <ID>id_n_s_1145</ID> |
||
16277 | <String>Project XP5 [2.03.07-111203]</String> |
||
16278 | <Description>XP5 robot</Description> |
||
16279 | <Type>R</Type> |
||
16280 | <Comment></Comment> |
||
16281 | <Link1>http://marty.anstey.ca/projects/robots/index.html</Link1> |
||
16282 | <Link2></Link2> |
||
16283 | </user-agent> |
||
16284 | <user-agent> |
||
16285 | <ID>id_n_s_1146</ID> |
||
16286 | <String>PROve AnswerBot 4.0</String> |
||
16287 | <Description>Answerchase PROve Answerbot</Description> |
||
16288 | <Type>R</Type> |
||
16289 | <Comment></Comment> |
||
16290 | <Link1>http://www.answerchase.com/</Link1> |
||
16291 | <Link2></Link2> |
||
16292 | </user-agent> |
||
16293 | <user-agent> |
||
16294 | <ID>id_n_s_1147</ID> |
||
16295 | <String>ProWebGuide Link Checker (http://www.prowebguide.com)</String> |
||
16296 | <Description>ProWebguide robot</Description> |
||
16297 | <Type>R</Type> |
||
16298 | <Comment></Comment> |
||
16299 | <Link1>http://www.prowebguide.com/</Link1> |
||
16300 | <Link2></Link2> |
||
16301 | </user-agent> |
||
16302 | <user-agent> |
||
16303 | <ID>id_n_s_1148</ID> |
||
16304 | <String>psbot/0.1 (+http://www.picsearch.com/bot.html)</String> |
||
16305 | <Description>Picsearch robot (62.119.21.13x)</Description> |
||
16306 | <Type>R</Type> |
||
16307 | <Comment></Comment> |
||
16308 | <Link1>http://www.picsearch.com/</Link1> |
||
16309 | <Link2></Link2> |
||
16310 | </user-agent> |
||
16311 | <user-agent> |
||
16312 | <ID>id_n_s_1149</ID> |
||
16313 | <String>PSurf15a 11</String> |
||
16314 | <Description>Some site scanning tool via diff. IPs- i.e.: QWest Net</Description> |
||
16315 | <Type>S</Type> |
||
16316 | <Comment></Comment> |
||
16317 | <Link1></Link1> |
||
16318 | <Link2></Link2> |
||
16319 | </user-agent> |
||
16320 | <user-agent> |
||
16321 | <ID>id_n_s_1150</ID> |
||
16322 | <String>PSurf15a 51</String> |
||
16323 | <Description>Some site scanning tool via diff. IPs- i.e.: Optonline net (24.191.xxx.xxx)</Description> |
||
16324 | <Type>S</Type> |
||
16325 | <Comment></Comment> |
||
16326 | <Link1></Link1> |
||
16327 | <Link2></Link2> |
||
16328 | </user-agent> |
||
16329 | <user-agent> |
||
16330 | <ID>id_n_s_1151</ID> |
||
16331 | <String>PSurf15a VA</String> |
||
16332 | <Description>Some site scanning tool via diff. IPs- i.e.: - choiceone.net (216.153.xxx.xxx) - attbi.com (12.250.xxx.xxx) - optonline.net (24.191.xxx.xxx)</Description> |
||
16333 | <Type>S</Type> |
||
16334 | <Comment>UA sometimes SSurf15a 11 or random letters like RXMYRCJ</Comment> |
||
16335 | <Link1></Link1> |
||
16336 | <Link2></Link2> |
||
16337 | </user-agent> |
||
16338 | <user-agent> |
||
16339 | <ID>id_n_s_160606_1</ID> |
||
16340 | <String>psycheclone</String> |
||
16341 | <Description>Unknown website grabbing / ripping for unknown purposes from 208.66.195.x - Digitalinfinity.org Russia</Description> |
||
16342 | <Type>S</Type> |
||
16343 | <Comment>no active website</Comment> |
||
16344 | <Link1></Link1> |
||
16345 | <Link2></Link2> |
||
16346 | </user-agent> |
||
16347 | <user-agent> |
||
16348 | <ID>id_n_s_1152</ID> |
||
16349 | <String>PubCrawl (pubcrawl.stanford.edu)</String> |
||
16350 | <Description>Some robot from Stanford University (171.64.75.xxx = PubCrawl.Stanford.EDU)</Description> |
||
16351 | <Type>R</Type> |
||
16352 | <Comment></Comment> |
||
16353 | <Link1></Link1> |
||
16354 | <Link2></Link2> |
||
16355 | </user-agent> |
||
16356 | <user-agent> |
||
16357 | <ID>id_n_s_1153</ID> |
||
16358 | <String>puf/0.91beta6a (Linux 2.2.18; i686)</String> |
||
16359 | <Description>Parallel URL Fetcher downloading tool</Description> |
||
16360 | <Type>D</Type> |
||
16361 | <Comment></Comment> |
||
16362 | <Link1>http://puf.sourceforge.net/</Link1> |
||
16363 | <Link2></Link2> |
||
16364 | </user-agent> |
||
16365 | <user-agent> |
||
16366 | <ID>id_n_s_1154</ID> |
||
16367 | <String>puf/0.93.2a (Linux 2.4.18; i686)</String> |
||
16368 | <Description>Parallel URL Fetcher downloading tool</Description> |
||
16369 | <Type>D</Type> |
||
16370 | <Comment></Comment> |
||
16371 | <Link1>http://puf.sourceforge.net/</Link1> |
||
16372 | <Link2></Link2> |
||
16373 | </user-agent> |
||
16374 | <user-agent> |
||
16375 | <ID>id_n_s_130407_1</ID> |
||
16376 | <String>pulseBot (pulse Web Miner)</String> |
||
16377 | <Description>WebarooBot - Webaroo web site search / theme based downloading tool (64.124.122.2xx)</Description> |
||
16378 | <Type>R</Type> |
||
16379 | <Comment>s. also RufusBot</Comment> |
||
16380 | <Link1>http://www.webaroo.com/index</Link1> |
||
16381 | <Link2>http://www.webaroo.com/company/site-owners</Link2> |
||
16382 | </user-agent> |
||
16383 | <user-agent> |
||
16384 | <ID>id_n_s_1155</ID> |
||
16385 | <String>PureSight</String> |
||
16386 | <Description>PureSight Internet content filter</Description> |
||
16387 | <Type>P</Type> |
||
16388 | <Comment></Comment> |
||
16389 | <Link1>http://www.puresight.com/Products/PureSightHomeDescription.shtml</Link1> |
||
16390 | <Link2></Link2> |
||
16391 | </user-agent> |
||
16392 | <user-agent> |
||
16393 | <ID>id_n_s_1156</ID> |
||
16394 | <String>PuxaRapido v1.0</String> |
||
16395 | <Description>Puxa Rapido download manager</Description> |
||
16396 | <Type>D</Type> |
||
16397 | <Comment></Comment> |
||
16398 | <Link1>http://www.puxarapido.com.br/</Link1> |
||
16399 | <Link2></Link2> |
||
16400 | </user-agent> |
||
16401 | <user-agent> |
||
16402 | <ID>id_n_s_230907_2</ID> |
||
16403 | <String>PWeBot/1.2 Inspector (http://www.programacionweb.net/robot.php)</String> |
||
16404 | <Description>ProgramacionWeb.net PWeBot link checking (Argentina)</Description> |
||
16405 | <Type>R</Type> |
||
16406 | <Comment>62.149.236.2xx</Comment> |
||
16407 | <Link1>http://www.programacionweb.net/robot-en.php</Link1> |
||
16408 | <Link2>http://www.programacionweb.net/</Link2> |
||
16409 | </user-agent> |
||
16410 | <user-agent> |
||
16411 | <ID>id_n_s_1157</ID> |
||
16412 | <String>PycURL</String> |
||
16413 | <Description>Fast Search robot (using PycURL Python component- s. below)</Description> |
||
16414 | <Type>R</Type> |
||
16415 | <Comment></Comment> |
||
16416 | <Link1>http://www.fastsearch.net/</Link1> |
||
16417 | <Link2>http://pycurl.sourceforge.net/</Link2> |
||
16418 | </user-agent> |
||
16419 | <user-agent> |
||
16420 | <ID>id_n_s_060107_1</ID> |
||
16421 | <String>PycURL/7.xx.x</String> |
||
16422 | <Description>PycURL - Python interface to libcurl</Description> |
||
16423 | <Type>D</Type> |
||
16424 | <Comment></Comment> |
||
16425 | <Link1>http://pycurl.sourceforge.net/</Link1> |
||
16426 | <Link2></Link2> |
||
16427 | </user-agent> |
||
16428 | <user-agent> |
||
16429 | <ID>id_n_s_1158</ID> |
||
16430 | <String>Python-urllib/1.1x</String> |
||
16431 | <Description>Python URL fetcher - robot used by Naver Japan/Korea</Description> |
||
16432 | <Type>R</Type> |
||
16433 | <Comment>s. also nabot- dloader- NaverBot & Cowbot</Comment> |
||
16434 | <Link1>http://www.indyproject.org/</Link1> |
||
16435 | <Link2>http://www.python.org/</Link2> |
||
16436 | </user-agent> |
||
16437 | <user-agent> |
||
16438 | <ID>id_n_s_1159</ID> |
||
16439 | <String>Python-urllib/2.0a1</String> |
||
16440 | <Description>Python URL fetcher - robot used by Google</Description> |
||
16441 | <Type>R</Type> |
||
16442 | <Comment></Comment> |
||
16443 | <Link1>http://labs.google.com</Link1> |
||
16444 | <Link2>http://www.python.org/</Link2> |
||
16445 | </user-agent> |
||
16446 | <user-agent> |
||
16447 | <ID>id_n_s_1160</ID> |
||
16448 | <String>Qango.com Web Directory (http://www.qango.com/)</String> |
||
16449 | <Description>Qango.com Web Directory robot</Description> |
||
16450 | <Type>R</Type> |
||
16451 | <Comment></Comment> |
||
16452 | <Link1>http://www.qango.com/</Link1> |
||
16453 | <Link2></Link2> |
||
16454 | </user-agent> |
||
16455 | <user-agent> |
||
16456 | <ID>id_n_s_170408_1</ID> |
||
16457 | <String>QEAVis Agent/Nutch-0.9 (Quantitative Evaluation of Academic Websites Visibility; http://nlp.uned.es/qeavis</String> |
||
16458 | <Description>QEAVis: Quantitative Evaluation of Academic Websites Visibility using Nutch</Description> |
||
16459 | <Type>R</Type> |
||
16460 | <Comment>83.33.209.10x</Comment> |
||
16461 | <Link1>http://nlp.uned.es/qeavis/</Link1> |
||
16462 | <Link2></Link2> |
||
16463 | </user-agent> |
||
16464 | <user-agent> |
||
16465 | <ID>id_n_s_1161</ID> |
||
16466 | <String>QPCreep Test Rig ( We are not indexing- just testing )</String> |
||
16467 | <Description>Quepasa!com (Latin American search) robot</Description> |
||
16468 | <Type>R</Type> |
||
16469 | <Comment></Comment> |
||
16470 | <Link1>http://www.quepasa.com/</Link1> |
||
16471 | <Link2></Link2> |
||
16472 | </user-agent> |
||
16473 | <user-agent> |
||
16474 | <ID>id_n_s_1162</ID> |
||
16475 | <String>QuepasaCreep ( crawler@quepasacorp.com )</String> |
||
16476 | <Description>Quepasa!com (Latin American search) robot</Description> |
||
16477 | <Type>R</Type> |
||
16478 | <Comment></Comment> |
||
16479 | <Link1>http://www.quepasa.com/</Link1> |
||
16480 | <Link2></Link2> |
||
16481 | </user-agent> |
||
16482 | <user-agent> |
||
16483 | <ID>id_n_s_1163</ID> |
||
16484 | <String>QuepasaCreep v0.9.1x</String> |
||
16485 | <Description>Quepasa!com (Latin American search) robot</Description> |
||
16486 | <Type>R</Type> |
||
16487 | <Comment></Comment> |
||
16488 | <Link1>http://www.quepasa.com/</Link1> |
||
16489 | <Link2></Link2> |
||
16490 | </user-agent> |
||
16491 | <user-agent> |
||
16492 | <ID>id_n_s_1164</ID> |
||
16493 | <String>QueryN Metasearch</String> |
||
16494 | <Description>QueryN Metasearch robot</Description> |
||
16495 | <Type>R</Type> |
||
16496 | <Comment></Comment> |
||
16497 | <Link1>http://www.queryn.com/queryn/</Link1> |
||
16498 | <Link2></Link2> |
||
16499 | </user-agent> |
||
16500 | <user-agent> |
||
16501 | <ID>id_n_s_230108_2</ID> |
||
16502 | <String>Quicksilver (Blacktree,MacOSX)</String> |
||
16503 | <Description>Blacktrees Quicksilver helper application for Mac</Description> |
||
16504 | <Type>B</Type> |
||
16505 | <Comment></Comment> |
||
16506 | <Link1>http://docs.blacktree.com/quicksilver/what_is_quicksilver</Link1> |
||
16507 | <Link2></Link2> |
||
16508 | </user-agent> |
||
16509 | <user-agent> |
||
16510 | <ID>id_n_s_230606_3</ID> |
||
16511 | <String>QuickTime\xaa.7.0.4 (qtver=7.0.4;cpu=PPC;os=Mac 10.3.9)</String> |
||
16512 | <Description>Quicktime for Macintosh</Description> |
||
16513 | <Type>B</Type> |
||
16514 | <Comment></Comment> |
||
16515 | <Link1></Link1> |
||
16516 | <Link2></Link2> |
||
16517 | </user-agent> |
||
16518 | <user-agent> |
||
16519 | <ID>id_n_s_060107_4</ID> |
||
16520 | <String>QweeryBot/3.01 ( http://qweerybot.qweery.nl)</String> |
||
16521 | <Description>Qweerybot for the Qweery search engine (in development) - Netherland</Description> |
||
16522 | <Type>R</Type> |
||
16523 | <Comment>85.158.204.2xx</Comment> |
||
16524 | <Link1>http://qweerybot.qweery.nl/</Link1> |
||
16525 | <Link2></Link2> |
||
16526 | </user-agent> |
||
16527 | <user-agent> |
||
16528 | <ID>id_n_s_060107_3</ID> |
||
16529 | <String>Qweery_robot.txt_CheckBot/3.01 (http://qweerybot.qweery.com)</String> |
||
16530 | <Description>Qweerybot for the Qweery search engine (in development) - Netherland</Description> |
||
16531 | <Type>R</Type> |
||
16532 | <Comment>85.158.204.2xx</Comment> |
||
16533 | <Link1>http://qweerybot.qweery.nl/</Link1> |
||
16534 | <Link2></Link2> |
||
16535 | </user-agent> |
||
16536 | <user-agent> |
||
16537 | <ID>id_n_s_160208_1</ID> |
||
16538 | <String>R6_CommentReader_(www.radian6.com/crawler)</String> |
||
16539 | <Description>Radian6 RSS feed comment crawler</Description> |
||
16540 | <Type>R</Type> |
||
16541 | <Comment></Comment> |
||
16542 | <Link1>http://www.radian6.com/cms/index.php</Link1> |
||
16543 | <Link2>http://www.radian6.com/crawler/</Link2> |
||
16544 | </user-agent> |
||
16545 | <user-agent> |
||
16546 | <ID>id_n_s_160208_2</ID> |
||
16547 | <String>R6_FeedFetcher_(www.radian6.com/crawler)</String> |
||
16548 | <Description>Radian6 Rss feed crawler</Description> |
||
16549 | <Type>R</Type> |
||
16550 | <Comment></Comment> |
||
16551 | <Link1>http://www.radian6.com/cms/index.php</Link1> |
||
16552 | <Link2>http://www.radian6.com/crawler/</Link2> |
||
16553 | </user-agent> |
||
16554 | <user-agent> |
||
16555 | <ID>id_n_s_1165</ID> |
||
16556 | <String>rabaz (rabaz at gigabaz dot com)</String> |
||
16557 | <Description>gigaBaz - the brainbot (Germany) robot</Description> |
||
16558 | <Type>R</Type> |
||
16559 | <Comment></Comment> |
||
16560 | <Link1>http://brainbot.com//site3</Link1> |
||
16561 | <Link2></Link2> |
||
16562 | </user-agent> |
||
16563 | <user-agent> |
||
16564 | <ID>id_n_s_1166</ID> |
||
16565 | <String>RaBot/1.0 Agent-admin/phortse@hanmail.net</String> |
||
16566 | <Description>DAUMOA - Daum search Korea robot (211.115.109.xxx)</Description> |
||
16567 | <Type>R</Type> |
||
16568 | <Comment>s. also Mozilla/4.0 (compatible; MSIE is not me; DAUMOA ...</Comment> |
||
16569 | <Link1>http://www.daum.net/</Link1> |
||
16570 | <Link2></Link2> |
||
16571 | </user-agent> |
||
16572 | <user-agent> |
||
16573 | <ID>id_n_s_1167</ID> |
||
16574 | <String>Rainbot1.1</String> |
||
16575 | <Description>Bot Provider for the All Womans Bot Service?</Description> |
||
16576 | <Type></Type> |
||
16577 | <Comment> - site is dead</Comment> |
||
16578 | <Link1>http://bservice.org/bots/</Link1> |
||
16579 | <Link2></Link2> |
||
16580 | </user-agent> |
||
16581 | <user-agent> |
||
16582 | <ID>id_n_s_1168</ID> |
||
16583 | <String>ramBot xtreme x.x</String> |
||
16584 | <Description>Intersearch.de (was www.intersearch.de) robot (Germany)</Description> |
||
16585 | <Type>R</Type> |
||
16586 | <Comment></Comment> |
||
16587 | <Link1></Link1> |
||
16588 | <Link2></Link2> |
||
16589 | </user-agent> |
||
16590 | <user-agent> |
||
16591 | <ID>id_n_s_160406_2</ID> |
||
16592 | <String>RAMPyBot - www.giveRAMP.com/0.1 (RAMPyBot - www.giveRAMP.com; http://www.giveramp.com/bot.html; support@giveRAMP.com)</String> |
||
16593 | <Description>giveRAMP Search Engine robot (64.69.43.1xx)</Description> |
||
16594 | <Type>R</Type> |
||
16595 | <Comment></Comment> |
||
16596 | <Link1>http://www.giveramp.com/</Link1> |
||
16597 | <Link2></Link2> |
||
16598 | </user-agent> |
||
16599 | <user-agent> |
||
16600 | <ID>id_n_s_260206_1</ID> |
||
16601 | <String>RAMPyBot/0.8-dev (Nutch; http://lucene.apache.org/nutch/bot.html; nutch-agent@lucene.apache.org)</String> |
||
16602 | <Description>giveRAMP Search Engine robot (64.69.43.1xx)</Description> |
||
16603 | <Type>R</Type> |
||
16604 | <Comment>powered by Nutch</Comment> |
||
16605 | <Link1>http://www.giveramp.com/</Link1> |
||
16606 | <Link2>http://lucene.apache.org/nutch/</Link2> |
||
16607 | </user-agent> |
||
16608 | <user-agent> |
||
16609 | <ID>id_n_s_1169</ID> |
||
16610 | <String>Rank Exec (rankexec.com) Reciprocal Link Manager 1.x/bot</String> |
||
16611 | <Description>Rank Exec reciprocal link checking</Description> |
||
16612 | <Type>C</Type> |
||
16613 | <Comment></Comment> |
||
16614 | <Link1>http://www.rankexec.com/</Link1> |
||
16615 | <Link2></Link2> |
||
16616 | </user-agent> |
||
16617 | <user-agent> |
||
16618 | <ID>id_n_s_180408_5</ID> |
||
16619 | <String>Rankivabot/3.2 (www.rankiva.com; 3.2; vzmxikn)</String> |
||
16620 | <Description>Rankiva website popularity robot</Description> |
||
16621 | <Type>R</Type> |
||
16622 | <Comment></Comment> |
||
16623 | <Link1>http://www.rankiva.com/</Link1> |
||
16624 | <Link2></Link2> |
||
16625 | </user-agent> |
||
16626 | <user-agent> |
||
16627 | <ID>id_n_s_1170</ID> |
||
16628 | <String>Rational SiteCheck (Windows NT)</String> |
||
16629 | <Description>Innova/IBM Rational SiteCheck - Rational robot</Description> |
||
16630 | <Type>R</Type> |
||
16631 | <Comment></Comment> |
||
16632 | <Link1>http://www.rational.com.ar/defaultenglish.html</Link1> |
||
16633 | <Link2></Link2> |
||
16634 | </user-agent> |
||
16635 | <user-agent> |
||
16636 | <ID>id_n_s_290708_2</ID> |
||
16637 | <String>RAYSPIDER/Nutch-0.9</String> |
||
16638 | <Description>Unknown spider from Raytheon Company - maybe Raytheon High Speed Guard proxy</Description> |
||
16639 | <Type>P</Type> |
||
16640 | <Comment>199.46.198.xxx</Comment> |
||
16641 | <Link1>http://www.raytheon.com/</Link1> |
||
16642 | <Link2></Link2> |
||
16643 | </user-agent> |
||
16644 | <user-agent> |
||
16645 | <ID>id_n_s_230207_3</ID> |
||
16646 | <String>ReadABlog Spider (compatible; 1.1; feed update; www.readablog.com)</String> |
||
16647 | <Description>Read A Blog - RSS feed and blog search engine</Description> |
||
16648 | <Type>C</Type> |
||
16649 | <Comment>70.85.24.xx</Comment> |
||
16650 | <Link1>http://www.readablog.com/</Link1> |
||
16651 | <Link2></Link2> |
||
16652 | </user-agent> |
||
16653 | <user-agent> |
||
16654 | <ID>id_n_s_1171</ID> |
||
16655 | <String>RealDownload/4.0.0.4x</String> |
||
16656 | <Description>RealDownload download manager</Description> |
||
16657 | <Type>D</Type> |
||
16658 | <Comment></Comment> |
||
16659 | <Link1>http://service.real.com/help/faq/rdown4/rdownfaqa01.html</Link1> |
||
16660 | <Link2></Link2> |
||
16661 | </user-agent> |
||
16662 | <user-agent> |
||
16663 | <ID>id_n_s_100408_3</ID> |
||
16664 | <String>REAP-crawler Nutch/Nutch-1.0-dev (Reap Project; http://reap.cs.cmu.edu/REAP-crawler/; Reap Project)</String> |
||
16665 | <Description>The REAP Web Crawler for the REAP project</Description> |
||
16666 | <Type>C</Type> |
||
16667 | <Comment></Comment> |
||
16668 | <Link1>http://reap.cs.cmu.edu/REAP-crawler/</Link1> |
||
16669 | <Link2>http://reap.cs.cmu.edu/</Link2> |
||
16670 | </user-agent> |
||
16671 | <user-agent> |
||
16672 | <ID>id_n_s_1172</ID> |
||
16673 | <String>Reaper [2.03.10-031204] (http://www.sitesearch.ca/reaper/)</String> |
||
16674 | <Description>Reaper robot for SiteSearch</Description> |
||
16675 | <Type>R</Type> |
||
16676 | <Comment></Comment> |
||
16677 | <Link1>http://marty.anstey.ca/projects/robots/reaper.html</Link1> |
||
16678 | <Link2></Link2> |
||
16679 | </user-agent> |
||
16680 | <user-agent> |
||
16681 | <ID>id_n_s_1173</ID> |
||
16682 | <String>Reaper/2.0x (+http://www.sitesearch.ca/reaper)</String> |
||
16683 | <Description>Reaper robot for SiteSearch</Description> |
||
16684 | <Type>R</Type> |
||
16685 | <Comment></Comment> |
||
16686 | <Link1>http://marty.anstey.ca/projects/robots/reaper.html</Link1> |
||
16687 | <Link2></Link2> |
||
16688 | </user-agent> |
||
16689 | <user-agent> |
||
16690 | <ID>id_n_s_1174</ID> |
||
16691 | <String>REBOL Core 2.x.x.x.x</String> |
||
16692 | <Description>REBOL messaging language for distributed Internet apps</Description> |
||
16693 | <Type></Type> |
||
16694 | <Comment></Comment> |
||
16695 | <Link1>http://www.rebol.com/</Link1> |
||
16696 | <Link2></Link2> |
||
16697 | </user-agent> |
||
16698 | <user-agent> |
||
16699 | <ID>id_n_s_250307_1</ID> |
||
16700 | <String>REBOL View 1.x.x.x.x</String> |
||
16701 | <Description>REBOL/View - machine independent internet client application</Description> |
||
16702 | <Type>B</Type> |
||
16703 | <Comment></Comment> |
||
16704 | <Link1>http://www.rebol.com/prod-view.html</Link1> |
||
16705 | <Link2></Link2> |
||
16706 | </user-agent> |
||
16707 | <user-agent> |
||
16708 | <ID>id_n_s_1175</ID> |
||
16709 | <String>RebusnetBot (+http://www.rebusnet.biz)</String> |
||
16710 | <Description>Rebusnet software site - link / submission checking</Description> |
||
16711 | <Type>R C</Type> |
||
16712 | <Comment></Comment> |
||
16713 | <Link1>http://www.rebusnet.biz</Link1> |
||
16714 | <Link2></Link2> |
||
16715 | </user-agent> |
||
16716 | <user-agent> |
||
16717 | <ID>id_n_s_1176</ID> |
||
16718 | <String>RebusnetPADBot/1.5x (+http://www.rebusnet.biz)</String> |
||
16719 | <Description>Rebusnet software site - link / submission checking</Description> |
||
16720 | <Type>R C</Type> |
||
16721 | <Comment></Comment> |
||
16722 | <Link1>http://www.rebusnet.biz</Link1> |
||
16723 | <Link2></Link2> |
||
16724 | </user-agent> |
||
16725 | <user-agent> |
||
16726 | <ID>id_n_s_171205_1</ID> |
||
16727 | <String>reciprocal links checker (http://www.recip-links.com/)</String> |
||
16728 | <Description>Online reciprocal link checker</Description> |
||
16729 | <Type>C</Type> |
||
16730 | <Comment></Comment> |
||
16731 | <Link1>http://www.recip-links.com/</Link1> |
||
16732 | <Link2></Link2> |
||
16733 | </user-agent> |
||
16734 | <user-agent> |
||
16735 | <ID>id_n_s_110307_2</ID> |
||
16736 | <String>RedBot/redbot-1.0 (Rediff.com Crawler; redbot at rediff dot com)</String> |
||
16737 | <Description>rediff.com search link checking</Description> |
||
16738 | <Type>C</Type> |
||
16739 | <Comment>220.226.198.xx</Comment> |
||
16740 | <Link1>http://www.rediff.com/</Link1> |
||
16741 | <Link2></Link2> |
||
16742 | </user-agent> |
||
16743 | <user-agent> |
||
16744 | <ID>id_n_s_130106_1</ID> |
||
16745 | <String>RedCarpet/1.2 (http://www.redcarpet-inc.com/robots.html)</String> |
||
16746 | <Description>RedCarpet crawler for Pronto price comparison search(66.179.107.1xx)</Description> |
||
16747 | <Type>R</Type> |
||
16748 | <Comment></Comment> |
||
16749 | <Link1>http://www.redcarpet-inc.com/robots.html</Link1> |
||
16750 | <Link2>http://www.pronto.com/</Link2> |
||
16751 | </user-agent> |
||
16752 | <user-agent> |
||
16753 | <ID>id_n_s_171205_2</ID> |
||
16754 | <String>RedCell/0.1 (InfoSec Search Bot (Coming Soon); http://www.telegenetic.net/bot.html; lhall@telegenetic.net)</String> |
||
16755 | <Description>Der Bot for telegenetic.net's security related search (65.220.67.2xx)</Description> |
||
16756 | <Type>R</Type> |
||
16757 | <Comment>Based on Nutch</Comment> |
||
16758 | <Link1>http://www.telegenetic.net/bot.html</Link1> |
||
16759 | <Link2></Link2> |
||
16760 | </user-agent> |
||
16761 | <user-agent> |
||
16762 | <ID>id_n_s_040106_1</ID> |
||
16763 | <String>RedCell/0.1 (RedCell; telegenetic.net/bot.html; lhall_at_telegenetic.net)</String> |
||
16764 | <Description>Der Bot for telegenetic.net's security related search (65.220.67.2xx)</Description> |
||
16765 | <Type>R</Type> |
||
16766 | <Comment>Based on Nutch</Comment> |
||
16767 | <Link1>http://www.telegenetic.net/bot.html</Link1> |
||
16768 | <Link2></Link2> |
||
16769 | </user-agent> |
||
16770 | <user-agent> |
||
16771 | <ID>id_n_s_1177</ID> |
||
16772 | <String>RedKernel WWW-Spider 2/0 (+http://www-spider.redkernel-softwares.com/)</String> |
||
16773 | <Description>RedKernel Softwares robot</Description> |
||
16774 | <Type>R</Type> |
||
16775 | <Comment></Comment> |
||
16776 | <Link1>http://www.redkernel-softwares.com/</Link1> |
||
16777 | <Link2></Link2> |
||
16778 | </user-agent> |
||
16779 | <user-agent> |
||
16780 | <ID>id_n_s_1178</ID> |
||
16781 | <String>REL Link Checker Lite x.x</String> |
||
16782 | <Description>REL Link Checker Lite free version of Web Link Validator</Description> |
||
16783 | <Type>C</Type> |
||
16784 | <Comment></Comment> |
||
16785 | <Link1>http://www.relsoftware.com/rlc/</Link1> |
||
16786 | <Link2></Link2> |
||
16787 | </user-agent> |
||
16788 | <user-agent> |
||
16789 | <ID>id_n_s_1179</ID> |
||
16790 | <String>RepoMonkey Bait & Tackle/v1.01</String> |
||
16791 | <Description>unknown</Description> |
||
16792 | <Type></Type> |
||
16793 | <Comment></Comment> |
||
16794 | <Link1></Link1> |
||
16795 | <Link2></Link2> |
||
16796 | </user-agent> |
||
16797 | <user-agent> |
||
16798 | <ID>id_n_s_1180</ID> |
||
16799 | <String>Rewebber/1.2 libwww-perl/5.41</String> |
||
16800 | <Description>Rewebber proxy service</Description> |
||
16801 | <Type>P</Type> |
||
16802 | <Comment></Comment> |
||
16803 | <Link1>http://www.rewebber.com/</Link1> |
||
16804 | <Link2></Link2> |
||
16805 | </user-agent> |
||
16806 | <user-agent> |
||
16807 | <ID>id_n_s_1181</ID> |
||
16808 | <String>rico/0.1</String> |
||
16809 | <Description>Applied Semantics Auto-Categorizer for QWestDex Direct</Description> |
||
16810 | <Type>R</Type> |
||
16811 | <Comment></Comment> |
||
16812 | <Link1>http://www.dotcomdirectory.com</Link1> |
||
16813 | <Link2></Link2> |
||
16814 | </user-agent> |
||
16815 | <user-agent> |
||
16816 | <ID>id_n_s_241105_2</ID> |
||
16817 | <String>RixBot (http://babelserver.org/rix)</String> |
||
16818 | <Description>RixBot Rebol Indexer for the RIX - Rebol related search (195.204.121.xx)</Description> |
||
16819 | <Type>R</Type> |
||
16820 | <Comment></Comment> |
||
16821 | <Link1>http://babelserver.org/rix</Link1> |
||
16822 | <Link2></Link2> |
||
16823 | </user-agent> |
||
16824 | <user-agent> |
||
16825 | <ID>id_n_s_070406_2</ID> |
||
16826 | <String>RMA/1.0 (compatible; RealMedia)</String> |
||
16827 | <Description>StreamBox VCR user agent</Description> |
||
16828 | <Type>D</Type> |
||
16829 | <Comment></Comment> |
||
16830 | <Link1>http://all-streaming-media.com/streaming-media-faq/faq-streambox-vcr-download-problems.htm</Link1> |
||
16831 | <Link2></Link2> |
||
16832 | </user-agent> |
||
16833 | <user-agent> |
||
16834 | <ID>id_n_s_1182</ID> |
||
16835 | <String>RMA/1.0 (compatible; RealMedia)</String> |
||
16836 | <Description>Real Media server acting as client</Description> |
||
16837 | <Type>B P</Type> |
||
16838 | <Comment></Comment> |
||
16839 | <Link1>http://service.real.com/help/library/whitepapers/wpaper.html</Link1> |
||
16840 | <Link2></Link2> |
||
16841 | </user-agent> |
||
16842 | <user-agent> |
||
16843 | <ID>id_n_s_061206_4</ID> |
||
16844 | <String>RoboCrawl (http://www.canadiancontent.net)</String> |
||
16845 | <Description>Canadian Content search crawler</Description> |
||
16846 | <Type>R</Type> |
||
16847 | <Comment></Comment> |
||
16848 | <Link1>http://www.canadiancontent.net/</Link1> |
||
16849 | <Link2></Link2> |
||
16850 | </user-agent> |
||
16851 | <user-agent> |
||
16852 | <ID>id_n_s_1183</ID> |
||
16853 | <String>RoboCrawl (www.canadiancontent.net)</String> |
||
16854 | <Description>Canadian Content Search (207.44.220.xx) robot</Description> |
||
16855 | <Type>R</Type> |
||
16856 | <Comment></Comment> |
||
16857 | <Link1>http://www.canadiancontent.net/</Link1> |
||
16858 | <Link2></Link2> |
||
16859 | </user-agent> |
||
16860 | <user-agent> |
||
16861 | <ID>id_n_s_1184</ID> |
||
16862 | <String>RoboPal (http://www.findpal.com/)</String> |
||
16863 | <Description>FindPal Australia metasearch robot (61.68.139.xx)</Description> |
||
16864 | <Type>R</Type> |
||
16865 | <Comment></Comment> |
||
16866 | <Link1>http://www.findpal.com/</Link1> |
||
16867 | <Link2></Link2> |
||
16868 | </user-agent> |
||
16869 | <user-agent> |
||
16870 | <ID>id_n_s_1187</ID> |
||
16871 | <String>Robot/www.pj-search.com</String> |
||
16872 | <Description>PopJapanSearch robot</Description> |
||
16873 | <Type>R</Type> |
||
16874 | <Comment></Comment> |
||
16875 | <Link1>http://www.pj-search.com/</Link1> |
||
16876 | <Link2></Link2> |
||
16877 | </user-agent> |
||
16878 | <user-agent> |
||
16879 | <ID>id_n_s_1185</ID> |
||
16880 | <String>Robot: NutchCrawler- Owner: wdavies@acm.org</String> |
||
16881 | <Description>Experimental robot using Wget via attbi.net</Description> |
||
16882 | <Type>R</Type> |
||
16883 | <Comment></Comment> |
||
16884 | <Link1></Link1> |
||
16885 | <Link2></Link2> |
||
16886 | </user-agent> |
||
16887 | <user-agent> |
||
16888 | <ID>id_n_s_1186</ID> |
||
16889 | <String>Robot@SuperSnooper.Com</String> |
||
16890 | <Description>Supersnooper robot</Description> |
||
16891 | <Type>R</Type> |
||
16892 | <Comment></Comment> |
||
16893 | <Link1>http://www.Supersnooper.com/</Link1> |
||
16894 | <Link2></Link2> |
||
16895 | </user-agent> |
||
16896 | <user-agent> |
||
16897 | <ID>id_n_s_1188</ID> |
||
16898 | <String>Robozilla/1.0</String> |
||
16899 | <Description>Netscape Directory / DMOZ Open Directory link crawler</Description> |
||
16900 | <Type>R</Type> |
||
16901 | <Comment></Comment> |
||
16902 | <Link1>http://directory.mozilla.org/</Link1> |
||
16903 | <Link2></Link2> |
||
16904 | </user-agent> |
||
16905 | <user-agent> |
||
16906 | <ID>id_n_s_220208_1</ID> |
||
16907 | <String>Rome Client (http://tinyurl.com/64t5n) Ver: 0.9</String> |
||
16908 | <Description>ROME - Open source Java tools for RSS and Atom feeds</Description> |
||
16909 | <Type>B</Type> |
||
16910 | <Comment></Comment> |
||
16911 | <Link1>https://rome.dev.java.net/</Link1> |
||
16912 | <Link2></Link2> |
||
16913 | </user-agent> |
||
16914 | <user-agent> |
||
16915 | <ID>id_n_s_1189</ID> |
||
16916 | <String>Rotondo/3.1 libwww/5.3.1</String> |
||
16917 | <Description>Qualigo.de robot</Description> |
||
16918 | <Type>R</Type> |
||
16919 | <Comment></Comment> |
||
16920 | <Link1>http://www.qualigo.de/</Link1> |
||
16921 | <Link2></Link2> |
||
16922 | </user-agent> |
||
16923 | <user-agent> |
||
16924 | <ID>id_n_s_1190</ID> |
||
16925 | <String>RPT-HTTPClient/0.3-x</String> |
||
16926 | <Description>different IPs using the HTTPClient library (mostly link checking)</Description> |
||
16927 | <Type>C</Type> |
||
16928 | <Comment>Java1.4.0</Comment> |
||
16929 | <Link1>http://www.innovation.ch/java/HTTPClient/</Link1> |
||
16930 | <Link2></Link2> |
||
16931 | </user-agent> |
||
16932 | <user-agent> |
||
16933 | <ID>id_n_s_1191</ID> |
||
16934 | <String>RRC (crawler_admin@bigfoot.com)</String> |
||
16935 | <Description>Metacarta.com (66.28.xx.xxx) robot</Description> |
||
16936 | <Type>R</Type> |
||
16937 | <Comment>s. Larbin...</Comment> |
||
16938 | <Link1>http://www.metacarta.com</Link1> |
||
16939 | <Link2></Link2> |
||
16940 | </user-agent> |
||
16941 | <user-agent> |
||
16942 | <ID>id_n_s_250707_5</ID> |
||
16943 | <String>RssBandit/1.5.0.10 (.NET CLR 1.1.4322.2407; WinNT 5.1.2600.0; http://www.rssbandit.org) (.NET CLR 1.1.4322.2407; WinNT 5.1.2600.0; )</String> |
||
16944 | <Description>RSS Bandit RSS/Atom reader for .NET framework</Description> |
||
16945 | <Type>B</Type> |
||
16946 | <Comment></Comment> |
||
16947 | <Link1>http://www.rssbandit.org/</Link1> |
||
16948 | <Link2></Link2> |
||
16949 | </user-agent> |
||
16950 | <user-agent> |
||
16951 | <ID>id_n_s_230607_3</ID> |
||
16952 | <String>RSSMicro.com RSS/Atom Feed Robot</String> |
||
16953 | <Description>RSS Micro Search - RSS feed search engine</Description> |
||
16954 | <Type>R</Type> |
||
16955 | <Comment>209.216.63.xx</Comment> |
||
16956 | <Link1>http://www.rssmicro.com/</Link1> |
||
16957 | <Link2></Link2> |
||
16958 | </user-agent> |
||
16959 | <user-agent> |
||
16960 | <ID>id_n_s_080307_2</ID> |
||
16961 | <String>RSSOwl/1.2.3 2006-11-26 (Windows; U; zhtw)</String> |
||
16962 | <Description>RSSOwl embedded RSS feed reader</Description> |
||
16963 | <Type>B</Type> |
||
16964 | <Comment></Comment> |
||
16965 | <Link1>http://www.rssowl.org/</Link1> |
||
16966 | <Link2></Link2> |
||
16967 | </user-agent> |
||
16968 | <user-agent> |
||
16969 | <ID>id_n_s_060108_1</ID> |
||
16970 | <String>RSSOwl/1.2.4 Preview Release 2007-04-15 (Windows; U; zhtw)</String> |
||
16971 | <Description>RSSOwl embedded RSS feed reader</Description> |
||
16972 | <Type>B</Type> |
||
16973 | <Comment></Comment> |
||
16974 | <Link1>http://www.rssowl.org/</Link1> |
||
16975 | <Link2></Link2> |
||
16976 | </user-agent> |
||
16977 | <user-agent> |
||
16978 | <ID>id_n_s_181006_3</ID> |
||
16979 | <String>RssReader/1.0.xx.x (http://www.rssreader.com) Microsoft Windows NT 5.1.2600.0</String> |
||
16980 | <Description>Ykoon RssReader news feed reader</Description> |
||
16981 | <Type>B</Type> |
||
16982 | <Comment></Comment> |
||
16983 | <Link1>http://www.rssreader.com/</Link1> |
||
16984 | <Link2></Link2> |
||
16985 | </user-agent> |
||
16986 | <user-agent> |
||
16987 | <ID>id_n_s_1192</ID> |
||
16988 | <String>RSurf15a 41</String> |
||
16989 | <Description>Some site scanning tool via diff. IPs- i.e.: - dslx.net (208.35.1x.xxx) - Home.com</Description> |
||
16990 | <Type>S</Type> |
||
16991 | <Comment></Comment> |
||
16992 | <Link1></Link1> |
||
16993 | <Link2></Link2> |
||
16994 | </user-agent> |
||
16995 | <user-agent> |
||
16996 | <ID>id_n_s_1193</ID> |
||
16997 | <String>RSurf15a 51</String> |
||
16998 | <Description>Some site scanning tool via diff. IPs- i.e.: - dslx.net (208.35.1x.xxx) - Home.com</Description> |
||
16999 | <Type>S</Type> |
||
17000 | <Comment></Comment> |
||
17001 | <Link1></Link1> |
||
17002 | <Link2></Link2> |
||
17003 | </user-agent> |
||
17004 | <user-agent> |
||
17005 | <ID>id_n_s_1194</ID> |
||
17006 | <String>RSurf15a 81</String> |
||
17007 | <Description>Some site scanning tool via diff. IPs- i.e.: - dslx.net (208.35.1x.xxx) - Home.com</Description> |
||
17008 | <Type>S</Type> |
||
17009 | <Comment></Comment> |
||
17010 | <Link1></Link1> |
||
17011 | <Link2></Link2> |
||
17012 | </user-agent> |
||
17013 | <user-agent> |
||
17014 | <ID>id_n_s_080206_2</ID> |
||
17015 | <String>Rubbot/1.0 (+http://rubhub.com/)</String> |
||
17016 | <Description>rubhub blog spider</Description> |
||
17017 | <Type>C</Type> |
||
17018 | <Comment>based on XFN relationship lookup engine</Comment> |
||
17019 | <Link1>http://rubhub.com/main/</Link1> |
||
17020 | <Link2>http://gmpg.org/xfn/more</Link2> |
||
17021 | </user-agent> |
||
17022 | <user-agent> |
||
17023 | <ID>id_n_s_191105_1</ID> |
||
17024 | <String>RufusBot (Rufus Web Miner; http://64.124.122.252/feedback.html)</String> |
||
17025 | <Description>WebarooBot - Webaroo web site search / theme based downloading tool (64.124.122.2xx)</Description> |
||
17026 | <Type>R</Type> |
||
17027 | <Comment>s. also pulseBot</Comment> |
||
17028 | <Link1>http://www.webaroo.com/index</Link1> |
||
17029 | <Link2>http://www.webaroo.com/company/site-owners</Link2> |
||
17030 | </user-agent> |
||
17031 | <user-agent> |
||
17032 | <ID>id_n_s_020407_1</ID> |
||
17033 | <String>RufusBot (Rufus Web Miner; http://www.webaroo.com/rooSiteOwners.html)</String> |
||
17034 | <Description>WebarooBot - Webaroo web site search / theme based downloading tool (64.124.122.2xx)</Description> |
||
17035 | <Type>R</Type> |
||
17036 | <Comment>s. also pulseBot</Comment> |
||
17037 | <Link1>http://www.webaroo.com/index</Link1> |
||
17038 | <Link2>http://www.webaroo.com/company/site-owners</Link2> |
||
17039 | </user-agent> |
||
17040 | <user-agent> |
||
17041 | <ID>id_n_s_1195</ID> |
||
17042 | <String>Rumours-Agent</String> |
||
17043 | <Description>unknown robot from rumours.jp (202.214.69.xxx)</Description> |
||
17044 | <Type></Type> |
||
17045 | <Comment></Comment> |
||
17046 | <Link1></Link1> |
||
17047 | <Link2></Link2> |
||
17048 | </user-agent> |
||
17049 | <user-agent> |
||
17050 | <ID>id_n_s_1196</ID> |
||
17051 | <String>RX Bar</String> |
||
17052 | <Description>RX (Reflexive Search) Bar for IE</Description> |
||
17053 | <Type>B</Type> |
||
17054 | <Comment></Comment> |
||
17055 | <Link1>http://www.searchenginebar.com/</Link1> |
||
17056 | <Link2></Link2> |
||
17057 | </user-agent> |
||
17058 | <user-agent> |
||
17059 | <ID>id_n_s_160506_1</ID> |
||
17060 | <String>S&L Spider (http://search.hirners.com/)</String> |
||
17061 | <Description>Search & Links directory spider</Description> |
||
17062 | <Type>C</Type> |
||
17063 | <Comment>80.108.7.xx</Comment> |
||
17064 | <Link1>http://search.hirners.com/</Link1> |
||
17065 | <Link2></Link2> |
||
17066 | </user-agent> |
||
17067 | <user-agent> |
||
17068 | <ID>id_n_s_1197</ID> |
||
17069 | <String>S.T.A.L.K.E.R. (http://www.seo-tools.net/en/bot.aspx)</String> |
||
17070 | <Description>SEO-Tools.net link checking ?</Description> |
||
17071 | <Type>C</Type> |
||
17072 | <Comment></Comment> |
||
17073 | <Link1>http://www.seo-tools.net/</Link1> |
||
17074 | <Link2></Link2> |
||
17075 | </user-agent> |
||
17076 | <user-agent> |
||
17077 | <ID>id_n_s_1198</ID> |
||
17078 | <String>SafariBookmarkChecker (+http://www.coriolis.ch/)</String> |
||
17079 | <Description>SafariBookmarkChecker for Mac OS X</Description> |
||
17080 | <Type>C</Type> |
||
17081 | <Comment></Comment> |
||
17082 | <Link1>http://www.coriolis.ch/</Link1> |
||
17083 | <Link2></Link2> |
||
17084 | </user-agent> |
||
17085 | <user-agent> |
||
17086 | <ID>id_n_s_061107_1</ID> |
||
17087 | <String>sait/Nutch-0.9 (SAIT Research; http://www.samsung.com)</String> |
||
17088 | <Description>sait robot - unknown robot from Samsung International Korea</Description> |
||
17089 | <Type>R</Type> |
||
17090 | <Comment>202.20.190.xx</Comment> |
||
17091 | <Link1>http://samsungnetworks.co.kr/eng/index.jsp</Link1> |
||
17092 | <Link2></Link2> |
||
17093 | </user-agent> |
||
17094 | <user-agent> |
||
17095 | <ID>id_n_s_191105_2</ID> |
||
17096 | <String>SandCrawler - Compatibility Testing</String> |
||
17097 | <Description>Sandcrawler robot from Microsoft (131.107.0.xx)</Description> |
||
17098 | <Type>R</Type> |
||
17099 | <Comment></Comment> |
||
17100 | <Link1></Link1> |
||
17101 | <Link2></Link2> |
||
17102 | </user-agent> |
||
17103 | <user-agent> |
||
17104 | <ID>id_n_s_170109_3</ID> |
||
17105 | <String>SapphireWebCrawler/1.0 (Sapphire Web Crawler using Nutch; http://boston.lti.cs.cmu.edu/crawler/; mhoy@cs.cmu.edu)</String> |
||
17106 | <Description>Sapphire Web Crawler from Carnegie Mellon University's Language Technologies Institute</Description> |
||
17107 | <Type>R</Type> |
||
17108 | <Comment></Comment> |
||
17109 | <Link1>http://boston.lti.cs.cmu.edu/crawler/</Link1> |
||
17110 | <Link2></Link2> |
||
17111 | </user-agent> |
||
17112 | <user-agent> |
||
17113 | <ID>id_n_s_170109_4</ID> |
||
17114 | <String>SapphireWebCrawler/Nutch-1.0-dev (Sapphire Web Crawler using Nutch; http://boston.lti.cs.cmu.edu/crawler/; mhoy@cs.cmu.edu)</String> |
||
17115 | <Description>Sapphire Web Crawler from Carnegie Mellon University's Language Technologies Institute</Description> |
||
17116 | <Type>R</Type> |
||
17117 | <Comment></Comment> |
||
17118 | <Link1>http://boston.lti.cs.cmu.edu/crawler/</Link1> |
||
17119 | <Link2></Link2> |
||
17120 | </user-agent> |
||
17121 | <user-agent> |
||
17122 | <ID>id_n_s_021205_4</ID> |
||
17123 | <String>savvybot/0.2</String> |
||
17124 | <Description>WebSavvy Directory robot</Description> |
||
17125 | <Type>R</Type> |
||
17126 | <Comment></Comment> |
||
17127 | <Link1>http://www.websavvy.cc/bot.php</Link1> |
||
17128 | <Link2></Link2> |
||
17129 | </user-agent> |
||
17130 | <user-agent> |
||
17131 | <ID>id_n_s_1199</ID> |
||
17132 | <String>SBIder/0.7 (SBIder; http://www.sitesell.com/sbider.html; http://support.sitesell.com/contact-support.html)</String> |
||
17133 | <Description>SiteSell SBIder Nutch based crawler</Description> |
||
17134 | <Type>R</Type> |
||
17135 | <Comment></Comment> |
||
17136 | <Link1>http://www.sitesell.com/</Link1> |
||
17137 | <Link2></Link2> |
||
17138 | </user-agent> |
||
17139 | <user-agent> |
||
17140 | <ID>id_n_s_030106_2</ID> |
||
17141 | <String>SBIder/0.8-dev (SBIder; http://www.sitesell.com/sbider.html; http://support.sitesell.com/contact-support.html)</String> |
||
17142 | <Description>SiteSell SBIder Nutch based crawler</Description> |
||
17143 | <Type>R</Type> |
||
17144 | <Comment></Comment> |
||
17145 | <Link1>http://www.sitesell.com/</Link1> |
||
17146 | <Link2></Link2> |
||
17147 | </user-agent> |
||
17148 | <user-agent> |
||
17149 | <ID>id_n_s_1200</ID> |
||
17150 | <String>SBL-BOT (http://sbl.net)</String> |
||
17151 | <Description>Softbyte Labs Black Widow web site ripper</Description> |
||
17152 | <Type>D B</Type> |
||
17153 | <Comment></Comment> |
||
17154 | <Link1>http://sbl.net/</Link1> |
||
17155 | <Link2></Link2> |
||
17156 | </user-agent> |
||
17157 | <user-agent> |
||
17158 | <ID>id_n_s_1201</ID> |
||
17159 | <String>ScanWeb</String> |
||
17160 | <Description>ScanWeb - regular expression based web page searching tool</Description> |
||
17161 | <Type>R</Type> |
||
17162 | <Comment></Comment> |
||
17163 | <Link1>http://eserver.host.sk/</Link1> |
||
17164 | <Link2></Link2> |
||
17165 | </user-agent> |
||
17166 | <user-agent> |
||
17167 | <ID>id_n_s_301006_1</ID> |
||
17168 | <String>ScholarUniverse/0.8 (Nutch;+http://scholaruniverse.com/bot.jsp; fetch-agent@scholaruniverse.com)</String> |
||
17169 | <Description>ScholarUniverse - Scholarly experts search robot</Description> |
||
17170 | <Type>R</Type> |
||
17171 | <Comment>209.216.243.xx</Comment> |
||
17172 | <Link1>http://www.scholaruniverse.com/index.jsp</Link1> |
||
17173 | <Link2></Link2> |
||
17174 | </user-agent> |
||
17175 | <user-agent> |
||
17176 | <ID>id_n_s_1202</ID> |
||
17177 | <String>schwarzmann.biz-Spider_for_paddel.org+(http://www.innerprise.net/usp-spider.asp)</String> |
||
17178 | <Description>URL Spider Pro (USP) used by German Schwarzmann GmbH</Description> |
||
17179 | <Type>R</Type> |
||
17180 | <Comment></Comment> |
||
17181 | <Link1>http://www.schwarzmann.biz/</Link1> |
||
17182 | <Link2></Link2> |
||
17183 | </user-agent> |
||
17184 | <user-agent> |
||
17185 | <ID>id_n_s_1203</ID> |
||
17186 | <String>Science Traveller International 1X/1.0</String> |
||
17187 | <Description>1X Web Browser</Description> |
||
17188 | <Type>B</Type> |
||
17189 | <Comment></Comment> |
||
17190 | <Link1>http://www.scitrav.com/</Link1> |
||
17191 | <Link2></Link2> |
||
17192 | </user-agent> |
||
17193 | <user-agent> |
||
17194 | <ID>id_n_s_190407_1</ID> |
||
17195 | <String>ScollSpider/2.0 (+http://www.webwobot.com/ScollSpider.php)</String> |
||
17196 | <Description>WebWobot UK search engine robot (82.43.129.2xx)</Description> |
||
17197 | <Type>R</Type> |
||
17198 | <Comment>s. also Mozilla/3.0 (compatible; ScollSpider ...</Comment> |
||
17199 | <Link1>http://www.webwobot.com/</Link1> |
||
17200 | <Link2></Link2> |
||
17201 | </user-agent> |
||
17202 | <user-agent> |
||
17203 | <ID>id_n_s_1206</ID> |
||
17204 | <String>Scooter-3.0.EU</String> |
||
17205 | <Description>Altavista robot</Description> |
||
17206 | <Type>R</Type> |
||
17207 | <Comment></Comment> |
||
17208 | <Link1>http://www.altavista.com/</Link1> |
||
17209 | <Link2></Link2> |
||
17210 | </user-agent> |
||
17211 | <user-agent> |
||
17212 | <ID>id_n_s_1207</ID> |
||
17213 | <String>Scooter-3.0.FS</String> |
||
17214 | <Description>Altavista robot</Description> |
||
17215 | <Type>R</Type> |
||
17216 | <Comment></Comment> |
||
17217 | <Link1>http://www.altavista.com/</Link1> |
||
17218 | <Link2></Link2> |
||
17219 | </user-agent> |
||
17220 | <user-agent> |
||
17221 | <ID>id_n_s_1208</ID> |
||
17222 | <String>Scooter-3.0.HD</String> |
||
17223 | <Description>Altavista robot</Description> |
||
17224 | <Type>R</Type> |
||
17225 | <Comment></Comment> |
||
17226 | <Link1>http://www.altavista.com/</Link1> |
||
17227 | <Link2></Link2> |
||
17228 | </user-agent> |
||
17229 | <user-agent> |
||
17230 | <ID>id_n_s_1209</ID> |
||
17231 | <String>Scooter-3.0.VNS</String> |
||
17232 | <Description>Altavista robot</Description> |
||
17233 | <Type>R</Type> |
||
17234 | <Comment></Comment> |
||
17235 | <Link1>http://www.altavista.com/</Link1> |
||
17236 | <Link2></Link2> |
||
17237 | </user-agent> |
||
17238 | <user-agent> |
||
17239 | <ID>id_n_s_1210</ID> |
||
17240 | <String>Scooter-3.0QI</String> |
||
17241 | <Description>Altavista robot</Description> |
||
17242 | <Type>R</Type> |
||
17243 | <Comment></Comment> |
||
17244 | <Link1>http://www.altavista.com/</Link1> |
||
17245 | <Link2></Link2> |
||
17246 | </user-agent> |
||
17247 | <user-agent> |
||
17248 | <ID>id_n_s_1211</ID> |
||
17249 | <String>Scooter-3.2</String> |
||
17250 | <Description>Altavista robot</Description> |
||
17251 | <Type>R</Type> |
||
17252 | <Comment></Comment> |
||
17253 | <Link1>http://www.altavista.com/</Link1> |
||
17254 | <Link2></Link2> |
||
17255 | </user-agent> |
||
17256 | <user-agent> |
||
17257 | <ID>id_n_s_1212</ID> |
||
17258 | <String>Scooter-3.2.BT</String> |
||
17259 | <Description>Altavista robot</Description> |
||
17260 | <Type>R</Type> |
||
17261 | <Comment></Comment> |
||
17262 | <Link1>http://www.altavista.com/</Link1> |
||
17263 | <Link2></Link2> |
||
17264 | </user-agent> |
||
17265 | <user-agent> |
||
17266 | <ID>id_n_s_1213</ID> |
||
17267 | <String>Scooter-3.2.DIL</String> |
||
17268 | <Description>Altavista robot</Description> |
||
17269 | <Type>R</Type> |
||
17270 | <Comment></Comment> |
||
17271 | <Link1>http://www.altavista.com/</Link1> |
||
17272 | <Link2></Link2> |
||
17273 | </user-agent> |
||
17274 | <user-agent> |
||
17275 | <ID>id_n_s_1214</ID> |
||
17276 | <String>Scooter-3.2.EX</String> |
||
17277 | <Description>Altavista robot</Description> |
||
17278 | <Type>R</Type> |
||
17279 | <Comment></Comment> |
||
17280 | <Link1>http://www.altavista.com/</Link1> |
||
17281 | <Link2></Link2> |
||
17282 | </user-agent> |
||
17283 | <user-agent> |
||
17284 | <ID>id_n_s_1215</ID> |
||
17285 | <String>Scooter-3.2.JT</String> |
||
17286 | <Description>Altavista robot</Description> |
||
17287 | <Type>R</Type> |
||
17288 | <Comment></Comment> |
||
17289 | <Link1>http://www.altavista.com/</Link1> |
||
17290 | <Link2></Link2> |
||
17291 | </user-agent> |
||
17292 | <user-agent> |
||
17293 | <ID>id_n_s_1216</ID> |
||
17294 | <String>Scooter-3.2.NIV</String> |
||
17295 | <Description>Altavista robot</Description> |
||
17296 | <Type>R</Type> |
||
17297 | <Comment></Comment> |
||
17298 | <Link1>http://www.altavista.com/</Link1> |
||
17299 | <Link2></Link2> |
||
17300 | </user-agent> |
||
17301 | <user-agent> |
||
17302 | <ID>id_n_s_1217</ID> |
||
17303 | <String>Scooter-3.2.SF0</String> |
||
17304 | <Description>Altavista robot</Description> |
||
17305 | <Type>R</Type> |
||
17306 | <Comment></Comment> |
||
17307 | <Link1>http://www.altavista.com/</Link1> |
||
17308 | <Link2></Link2> |
||
17309 | </user-agent> |
||
17310 | <user-agent> |
||
17311 | <ID>id_n_s_1218</ID> |
||
17312 | <String>Scooter-3.2.snippet</String> |
||
17313 | <Description>Altavista robot</Description> |
||
17314 | <Type>R</Type> |
||
17315 | <Comment></Comment> |
||
17316 | <Link1>http://www.altavista.com/</Link1> |
||
17317 | <Link2></Link2> |
||
17318 | </user-agent> |
||
17319 | <user-agent> |
||
17320 | <ID>id_n_s_1219</ID> |
||
17321 | <String>Scooter-3.3dev</String> |
||
17322 | <Description>Altavista robot</Description> |
||
17323 | <Type>R</Type> |
||
17324 | <Comment></Comment> |
||
17325 | <Link1>http://www.altavista.com/</Link1> |
||
17326 | <Link2></Link2> |
||
17327 | </user-agent> |
||
17328 | <user-agent> |
||
17329 | <ID>id_n_s_1220</ID> |
||
17330 | <String>Scooter-ARS-1.1</String> |
||
17331 | <Description>Altavista robot</Description> |
||
17332 | <Type>R</Type> |
||
17333 | <Comment></Comment> |
||
17334 | <Link1>http://www.altavista.com/</Link1> |
||
17335 | <Link2></Link2> |
||
17336 | </user-agent> |
||
17337 | <user-agent> |
||
17338 | <ID>id_n_s_1221</ID> |
||
17339 | <String>Scooter-ARS-1.1-ih</String> |
||
17340 | <Description>Altavista robot</Description> |
||
17341 | <Type>R</Type> |
||
17342 | <Comment></Comment> |
||
17343 | <Link1>http://www.altavista.com/</Link1> |
||
17344 | <Link2></Link2> |
||
17345 | </user-agent> |
||
17346 | <user-agent> |
||
17347 | <ID>id_n_s_1222</ID> |
||
17348 | <String>scooter-venus-3.0.vns</String> |
||
17349 | <Description>Altavista robot</Description> |
||
17350 | <Type>R</Type> |
||
17351 | <Comment></Comment> |
||
17352 | <Link1>http://www.altavista.com/</Link1> |
||
17353 | <Link2></Link2> |
||
17354 | </user-agent> |
||
17355 | <user-agent> |
||
17356 | <ID>id_n_s_1223</ID> |
||
17357 | <String>Scooter-W3-1.0</String> |
||
17358 | <Description>Altavista robot</Description> |
||
17359 | <Type>R</Type> |
||
17360 | <Comment></Comment> |
||
17361 | <Link1>http://www.altavista.com/</Link1> |
||
17362 | <Link2></Link2> |
||
17363 | </user-agent> |
||
17364 | <user-agent> |
||
17365 | <ID>id_n_s_1224</ID> |
||
17366 | <String>Scooter-W3.1.2</String> |
||
17367 | <Description>Altavista robot</Description> |
||
17368 | <Type>R</Type> |
||
17369 | <Comment></Comment> |
||
17370 | <Link1>http://www.altavista.com/</Link1> |
||
17371 | <Link2></Link2> |
||
17372 | </user-agent> |
||
17373 | <user-agent> |
||
17374 | <ID>id_n_s_1225</ID> |
||
17375 | <String>Scooter/1.0</String> |
||
17376 | <Description>Altavista robot</Description> |
||
17377 | <Type>R</Type> |
||
17378 | <Comment></Comment> |
||
17379 | <Link1>http://www.altavista.com/</Link1> |
||
17380 | <Link2></Link2> |
||
17381 | </user-agent> |
||
17382 | <user-agent> |
||
17383 | <ID>id_n_s_1226</ID> |
||
17384 | <String>Scooter/1.0 scooter@pa.dec.com</String> |
||
17385 | <Description>Altavista robot</Description> |
||
17386 | <Type>R</Type> |
||
17387 | <Comment></Comment> |
||
17388 | <Link1>http://www.altavista.com/</Link1> |
||
17389 | <Link2></Link2> |
||
17390 | </user-agent> |
||
17391 | <user-agent> |
||
17392 | <ID>id_n_s_1227</ID> |
||
17393 | <String>Scooter/1.1 (custom)</String> |
||
17394 | <Description>Altavista robot</Description> |
||
17395 | <Type>R</Type> |
||
17396 | <Comment></Comment> |
||
17397 | <Link1>http://www.altavista.com/</Link1> |
||
17398 | <Link2></Link2> |
||
17399 | </user-agent> |
||
17400 | <user-agent> |
||
17401 | <ID>id_n_s_1228</ID> |
||
17402 | <String>Scooter/2.0 G.R.A.B. V1.1.0</String> |
||
17403 | <Description>Altavista robot</Description> |
||
17404 | <Type>R</Type> |
||
17405 | <Comment></Comment> |
||
17406 | <Link1>http://www.altavista.com/</Link1> |
||
17407 | <Link2></Link2> |
||
17408 | </user-agent> |
||
17409 | <user-agent> |
||
17410 | <ID>id_n_s_1229</ID> |
||
17411 | <String>Scooter/2.0 G.R.A.B. X2.0</String> |
||
17412 | <Description>Altavista robot</Description> |
||
17413 | <Type>R</Type> |
||
17414 | <Comment></Comment> |
||
17415 | <Link1>http://www.altavista.com/</Link1> |
||
17416 | <Link2></Link2> |
||
17417 | </user-agent> |
||
17418 | <user-agent> |
||
17419 | <ID>id_n_s_1230</ID> |
||
17420 | <String>Scooter/3.3</String> |
||
17421 | <Description>Altavista robot</Description> |
||
17422 | <Type>R</Type> |
||
17423 | <Comment></Comment> |
||
17424 | <Link1>http://www.altavista.com/</Link1> |
||
17425 | <Link2></Link2> |
||
17426 | </user-agent> |
||
17427 | <user-agent> |
||
17428 | <ID>id_n_s_1232</ID> |
||
17429 | <String>Scooter/3.3.QA.pczukor</String> |
||
17430 | <Description>Altavista robot</Description> |
||
17431 | <Type>R</Type> |
||
17432 | <Comment></Comment> |
||
17433 | <Link1>http://www.altavista.com/</Link1> |
||
17434 | <Link2></Link2> |
||
17435 | </user-agent> |
||
17436 | <user-agent> |
||
17437 | <ID>id_n_s_1233</ID> |
||
17438 | <String>Scooter/3.3.vscooter</String> |
||
17439 | <Description>Altavista robot</Description> |
||
17440 | <Type>R</Type> |
||
17441 | <Comment></Comment> |
||
17442 | <Link1>http://www.altavista.com/</Link1> |
||
17443 | <Link2></Link2> |
||
17444 | </user-agent> |
||
17445 | <user-agent> |
||
17446 | <ID>id_n_s_1231</ID> |
||
17447 | <String>Scooter/3.3_SF</String> |
||
17448 | <Description>Altavista robot</Description> |
||
17449 | <Type>R</Type> |
||
17450 | <Comment></Comment> |
||
17451 | <Link1>http://www.altavista.com/</Link1> |
||
17452 | <Link2></Link2> |
||
17453 | </user-agent> |
||
17454 | <user-agent> |
||
17455 | <ID>id_n_s_1234</ID> |
||
17456 | <String>Scooter2_Mercator_x-x.0</String> |
||
17457 | <Description>Altavista using Mercator robot</Description> |
||
17458 | <Type>R</Type> |
||
17459 | <Comment></Comment> |
||
17460 | <Link1>http://www.altavista.com/</Link1> |
||
17461 | <Link2>http://www.research.compaq.com/SRC/mercator/</Link2> |
||
17462 | </user-agent> |
||
17463 | <user-agent> |
||
17464 | <ID>id_n_s_1204</ID> |
||
17465 | <String>Scooter_bh0-3.0.3</String> |
||
17466 | <Description>Altavista robot</Description> |
||
17467 | <Type>R</Type> |
||
17468 | <Comment></Comment> |
||
17469 | <Link1>http://www.altavista.com/</Link1> |
||
17470 | <Link2></Link2> |
||
17471 | </user-agent> |
||
17472 | <user-agent> |
||
17473 | <ID>id_n_s_1205</ID> |
||
17474 | <String>Scooter_trk3-3.0.3</String> |
||
17475 | <Description>Altavista robot</Description> |
||
17476 | <Type>R</Type> |
||
17477 | <Comment></Comment> |
||
17478 | <Link1>http://www.altavista.com/</Link1> |
||
17479 | <Link2></Link2> |
||
17480 | </user-agent> |
||
17481 | <user-agent> |
||
17482 | <ID>id_n_s_190306_3</ID> |
||
17483 | <String>Scope (Mars+)</String> |
||
17484 | <Description>Scope Navigator mobile browser (Japan)</Description> |
||
17485 | <Type>B</Type> |
||
17486 | <Comment></Comment> |
||
17487 | <Link1>http://www.programmer.co.jp/scope.shtml</Link1> |
||
17488 | <Link2></Link2> |
||
17489 | </user-agent> |
||
17490 | <user-agent> |
||
17491 | <ID>id_n_s_1235</ID> |
||
17492 | <String>ScoutAbout</String> |
||
17493 | <Description>Some nec.com robot using Research Republic ScoutAbout Research Tool</Description> |
||
17494 | <Type>R</Type> |
||
17495 | <Comment></Comment> |
||
17496 | <Link1>http://www.researchrepublic.com/</Link1> |
||
17497 | <Link2></Link2> |
||
17498 | </user-agent> |
||
17499 | <user-agent> |
||
17500 | <ID>id_n_s_051207_4</ID> |
||
17501 | <String>ScoutAnt/0.1; +http://www.ant.com/what_is_ant.com/</String> |
||
17502 | <Description>Ant.com search robot</Description> |
||
17503 | <Type>R</Type> |
||
17504 | <Comment>66.230.171.17x</Comment> |
||
17505 | <Link1>http://www.ant.com/</Link1> |
||
17506 | <Link2></Link2> |
||
17507 | </user-agent> |
||
17508 | <user-agent> |
||
17509 | <ID>id_n_s_271105_3</ID> |
||
17510 | <String>scoutmaster</String> |
||
17511 | <Description>ScoutMaster information retrieval software</Description> |
||
17512 | <Type>R</Type> |
||
17513 | <Comment></Comment> |
||
17514 | <Link1>http://www.scoutmaster.de/</Link1> |
||
17515 | <Link2></Link2> |
||
17516 | </user-agent> |
||
17517 | <user-agent> |
||
17518 | <ID>id_n_s_1236</ID> |
||
17519 | <String>Scrubby/2.x (http://www.scrubtheweb.com/)</String> |
||
17520 | <Description>Scrub the web robot (66.93.156.xx)</Description> |
||
17521 | <Type>R</Type> |
||
17522 | <Comment>s.also Mozilla/5.0 (compatible; Scrubby/2.2 ...</Comment> |
||
17523 | <Link1>http://www.scrubtheweb.com/</Link1> |
||
17524 | <Link2></Link2> |
||
17525 | </user-agent> |
||
17526 | <user-agent> |
||
17527 | <ID>id_n_s_030308_3</ID> |
||
17528 | <String>Scrubby/3.0 (+http://www.scrubtheweb.com/help/technology.html)</String> |
||
17529 | <Description>Scrub the web robot (66.93.156.xx)</Description> |
||
17530 | <Type>R</Type> |
||
17531 | <Comment>s.also Mozilla/5.0 (compatible; Scrubby/2.2 ...</Comment> |
||
17532 | <Link1>http://www.scrubtheweb.com/</Link1> |
||
17533 | <Link2></Link2> |
||
17534 | </user-agent> |
||
17535 | <user-agent> |
||
17536 | <ID>id_n_s_1240</ID> |
||
17537 | <String>Search+</String> |
||
17538 | <Description>URL Search+ search software</Description> |
||
17539 | <Type>R</Type> |
||
17540 | <Comment></Comment> |
||
17541 | <Link1>http://srchplus.chat.ru/index.htm</Link1> |
||
17542 | <Link2></Link2> |
||
17543 | </user-agent> |
||
17544 | <user-agent> |
||
17545 | <ID>id_n_s_110606_3</ID> |
||
17546 | <String>Search-Engine-Studio</String> |
||
17547 | <Description>Xtreem Search Engine Studio - SE software</Description> |
||
17548 | <Type>R</Type> |
||
17549 | <Comment></Comment> |
||
17550 | <Link1>http://www.xtreeme.com/search-engine-studio/</Link1> |
||
17551 | <Link2></Link2> |
||
17552 | </user-agent> |
||
17553 | <user-agent> |
||
17554 | <ID>id_n_s_1237</ID> |
||
17555 | <String>search.ch V1.4</String> |
||
17556 | <Description>Search.ch robot</Description> |
||
17557 | <Type>R</Type> |
||
17558 | <Comment></Comment> |
||
17559 | <Link1>http://www.search.ch/</Link1> |
||
17560 | <Link2></Link2> |
||
17561 | </user-agent> |
||
17562 | <user-agent> |
||
17563 | <ID>id_n_s_1238</ID> |
||
17564 | <String>search.ch V1.4.2 (spiderman@search.ch; http://www.search.ch)</String> |
||
17565 | <Description>Search.ch robot</Description> |
||
17566 | <Type>R</Type> |
||
17567 | <Comment></Comment> |
||
17568 | <Link1>http://www.search.ch/</Link1> |
||
17569 | <Link2></Link2> |
||
17570 | </user-agent> |
||
17571 | <user-agent> |
||
17572 | <ID>id_n_s_1239</ID> |
||
17573 | <String>Search/1.0 (http://www.innerprise.net/es-spider.asp)</String> |
||
17574 | <Description>Enterprise Search web indexing / site searching tool</Description> |
||
17575 | <Type>R</Type> |
||
17576 | <Comment></Comment> |
||
17577 | <Link1>http://www.innerprise.net/es-bi.asp</Link1> |
||
17578 | <Link2></Link2> |
||
17579 | </user-agent> |
||
17580 | <user-agent> |
||
17581 | <ID>id_n_s_1241</ID> |
||
17582 | <String>searchbot admin@google.com</String> |
||
17583 | <Description>Unknown robot / website grabber from Chinatelecom (219.142.78.xxx)</Description> |
||
17584 | <Type>S</Type> |
||
17585 | <Comment></Comment> |
||
17586 | <Link1></Link1> |
||
17587 | <Link2></Link2> |
||
17588 | </user-agent> |
||
17589 | <user-agent> |
||
17590 | <ID>id_n_s_1242</ID> |
||
17591 | <String>SearchByUsa/2 (SearchByUsa; http://www.SearchByUsa.com/bot.html; info@SearchByUsa.com)</String> |
||
17592 | <Description>SearchByUSA robot (69.150.7.xxx)</Description> |
||
17593 | <Type>R</Type> |
||
17594 | <Comment></Comment> |
||
17595 | <Link1>http://www.searchbyusa.com/</Link1> |
||
17596 | <Link2></Link2> |
||
17597 | </user-agent> |
||
17598 | <user-agent> |
||
17599 | <ID>id_n_s_231006_1</ID> |
||
17600 | <String>SearchdayBot</String> |
||
17601 | <Description>Searchday (Germany) search robot</Description> |
||
17602 | <Type>R</Type> |
||
17603 | <Comment>85.25.131.1xx</Comment> |
||
17604 | <Link1>http://www.searchday.de/</Link1> |
||
17605 | <Link2></Link2> |
||
17606 | </user-agent> |
||
17607 | <user-agent> |
||
17608 | <ID>id_n_s_1243</ID> |
||
17609 | <String>SearchExpress Spider0.99</String> |
||
17610 | <Description>Searchexpress spider</Description> |
||
17611 | <Type>R</Type> |
||
17612 | <Comment></Comment> |
||
17613 | <Link1>http://www.searchexpress.com/</Link1> |
||
17614 | <Link2></Link2> |
||
17615 | </user-agent> |
||
17616 | <user-agent> |
||
17617 | <ID>id_n_s_1245</ID> |
||
17618 | <String>SearchGuild/DMOZ/Experiment (searchguild@gmail.com)</String> |
||
17619 | <Description>Searchguild forum & directory robot (81.3.75.xxx)</Description> |
||
17620 | <Type>R</Type> |
||
17621 | <Comment></Comment> |
||
17622 | <Link1>http://searchguild.com/</Link1> |
||
17623 | <Link2></Link2> |
||
17624 | </user-agent> |
||
17625 | <user-agent> |
||
17626 | <ID>id_n_s_1244</ID> |
||
17627 | <String>SearchGuild_DMOZ_Experiment (chris@searchguild.com)</String> |
||
17628 | <Description>Searchguild forum & directory robot (81.3.75.xxx)</Description> |
||
17629 | <Type>R</Type> |
||
17630 | <Comment></Comment> |
||
17631 | <Link1>http://searchguild.com/</Link1> |
||
17632 | <Link2></Link2> |
||
17633 | </user-agent> |
||
17634 | <user-agent> |
||
17635 | <ID>id_n_s_1246</ID> |
||
17636 | <String>Searchit-Now Robot/2.2 (+http://www.searchit-now.co.uk)</String> |
||
17637 | <Description>Searchit robot (69.93.107.xx)</Description> |
||
17638 | <Type>R</Type> |
||
17639 | <Comment></Comment> |
||
17640 | <Link1>http://www.searchit-now.co.uk</Link1> |
||
17641 | <Link2></Link2> |
||
17642 | </user-agent> |
||
17643 | <user-agent> |
||
17644 | <ID>id_n_s_220906_3</ID> |
||
17645 | <String>Searchmee! Spider v0.98a</String> |
||
17646 | <Description>Searchmee! Search Engine (prototype) robot by findanisp.com</Description> |
||
17647 | <Type>R</Type> |
||
17648 | <Comment>64.202.100.</Comment> |
||
17649 | <Link1>http://www.searchmee.com/</Link1> |
||
17650 | <Link2></Link2> |
||
17651 | </user-agent> |
||
17652 | <user-agent> |
||
17653 | <ID>id_n_s_100506_1</ID> |
||
17654 | <String>SearchSight/2.0 (http://SearchSight.com/)</String> |
||
17655 | <Description>SearchSight search robot</Description> |
||
17656 | <Type>R</Type> |
||
17657 | <Comment></Comment> |
||
17658 | <Link1>http://searchsight.com/</Link1> |
||
17659 | <Link2></Link2> |
||
17660 | </user-agent> |
||
17661 | <user-agent> |
||
17662 | <ID>id_n_s_1247</ID> |
||
17663 | <String>SearchSpider.com/1.1</String> |
||
17664 | <Description>SearchSpider robot</Description> |
||
17665 | <Type>R</Type> |
||
17666 | <Comment></Comment> |
||
17667 | <Link1>http://www.searchspider.com/</Link1> |
||
17668 | <Link2></Link2> |
||
17669 | </user-agent> |
||
17670 | <user-agent> |
||
17671 | <ID>id_n_s_1248</ID> |
||
17672 | <String>Searchspider/1.2 (SearchSpider; http://www.searchspider.com; webmaster@searchspider.com)</String> |
||
17673 | <Description>SearchSpider robot</Description> |
||
17674 | <Type>R</Type> |
||
17675 | <Comment></Comment> |
||
17676 | <Link1>http://www.searchspider.com/</Link1> |
||
17677 | <Link2></Link2> |
||
17678 | </user-agent> |
||
17679 | <user-agent> |
||
17680 | <ID>id_n_s_1249</ID> |
||
17681 | <String>SearchTone2.0 - IDEARE</String> |
||
17682 | <Description>Janas (Ideare.com / Tiscali.it) robot</Description> |
||
17683 | <Type>R</Type> |
||
17684 | <Comment></Comment> |
||
17685 | <Link1>http://www.ideare.com/</Link1> |
||
17686 | <Link2>http://www.tiscali.it</Link2> |
||
17687 | </user-agent> |
||
17688 | <user-agent> |
||
17689 | <ID>id_n_s_1250</ID> |
||
17690 | <String>Seekbot/1.0 (http://www.seekbot.net/bot.html) HTTPFetcher/0.3</String> |
||
17691 | <Description>seekport. beta search (Germany) robot</Description> |
||
17692 | <Type>R</Type> |
||
17693 | <Comment>195.27.215.xx</Comment> |
||
17694 | <Link1>http://www.seekbot.net/</Link1> |
||
17695 | <Link2></Link2> |
||
17696 | </user-agent> |
||
17697 | <user-agent> |
||
17698 | <ID>id_n_s_1251</ID> |
||
17699 | <String>Seekbot/1.0 (http://www.seekbot.net/bot.html) RobotsTxtFetcher/1.0 (XDF)</String> |
||
17700 | <Description>seekport. beta search (Germany) robot</Description> |
||
17701 | <Type>R</Type> |
||
17702 | <Comment>195.27.215.xx</Comment> |
||
17703 | <Link1>http://www.seekbot.net/</Link1> |
||
17704 | <Link2></Link2> |
||
17705 | </user-agent> |
||
17706 | <user-agent> |
||
17707 | <ID>id_n_s_1252</ID> |
||
17708 | <String>Seekbot/1.0 (http://www.seekbot.net/bot.html) RobotsTxtFetcher/1.2</String> |
||
17709 | <Description>seekport. beta search (Germany) robot</Description> |
||
17710 | <Type>R</Type> |
||
17711 | <Comment>195.27.215.xx</Comment> |
||
17712 | <Link1>http://www.seekbot.net/</Link1> |
||
17713 | <Link2></Link2> |
||
17714 | </user-agent> |
||
17715 | <user-agent> |
||
17716 | <ID>id_n_s_1253</ID> |
||
17717 | <String>Seeker.lookseek.com</String> |
||
17718 | <Description>Lookseek search robot / link checking</Description> |
||
17719 | <Type>R</Type> |
||
17720 | <Comment>12.199.64.xx</Comment> |
||
17721 | <Link1>http://www.lookseek.com/</Link1> |
||
17722 | <Link2></Link2> |
||
17723 | </user-agent> |
||
17724 | <user-agent> |
||
17725 | <ID>id_n_s_011006_3</ID> |
||
17726 | <String>semaforo.net</String> |
||
17727 | <Description>semaforo.net web filtering software</Description> |
||
17728 | <Type>P</Type> |
||
17729 | <Comment></Comment> |
||
17730 | <Link1>http://www.semaforo.net/en/default.htm</Link1> |
||
17731 | <Link2></Link2> |
||
17732 | </user-agent> |
||
17733 | <user-agent> |
||
17734 | <ID>id_n_s_020807_2</ID> |
||
17735 | <String>Semager/1.1 (http://www.semager.de/blog/semager-bots/)</String> |
||
17736 | <Description>Semager.de (was NG-Search) semantic search - Germany</Description> |
||
17737 | <Type>R</Type> |
||
17738 | <Comment>212.114.209.2xx</Comment> |
||
17739 | <Link1>http://www.semager.de/</Link1> |
||
17740 | <Link2>http://www.semager.de/blog/semager-bots/</Link2> |
||
17741 | </user-agent> |
||
17742 | <user-agent> |
||
17743 | <ID>id_n_s_230507_2</ID> |
||
17744 | <String>Semager/1.x (http://www.semager.de)</String> |
||
17745 | <Description>Semager.de (was NG-Search) semantic search - Germany</Description> |
||
17746 | <Type>R</Type> |
||
17747 | <Comment>212.114.209.2xx</Comment> |
||
17748 | <Link1>http://www.semager.de/</Link1> |
||
17749 | <Link2>http://www.semager.de/blog/semager-bots/</Link2> |
||
17750 | </user-agent> |
||
17751 | <user-agent> |
||
17752 | <ID>id_n_s_1254</ID> |
||
17753 | <String>semanticdiscovery/0.x</String> |
||
17754 | <Description>Semantic Discovery domain checking tool</Description> |
||
17755 | <Type>R C</Type> |
||
17756 | <Comment></Comment> |
||
17757 | <Link1>http://www.semanticdiscovery.com/products.html</Link1> |
||
17758 | <Link2></Link2> |
||
17759 | </user-agent> |
||
17760 | <user-agent> |
||
17761 | <ID>id_n_s_1255</ID> |
||
17762 | <String>Sensis Web Crawler (search_comments\at\sensis\dot\com\dot\au)</String> |
||
17763 | <Description>Sensis Australia search robot</Description> |
||
17764 | <Type>R</Type> |
||
17765 | <Comment></Comment> |
||
17766 | <Link1>http://www.sensis.com.au/</Link1> |
||
17767 | <Link2></Link2> |
||
17768 | </user-agent> |
||
17769 | <user-agent> |
||
17770 | <ID>id_n_s_1256</ID> |
||
17771 | <String>Sensis.com.au Web Crawler (search_comments\at\sensis\dot\com\dot\au)</String> |
||
17772 | <Description>Sensis Australia search robot</Description> |
||
17773 | <Type>R</Type> |
||
17774 | <Comment></Comment> |
||
17775 | <Link1>http://www.sensis.com.au/</Link1> |
||
17776 | <Link2></Link2> |
||
17777 | </user-agent> |
||
17778 | <user-agent> |
||
17779 | <ID>id_n_s_1257</ID> |
||
17780 | <String>SeznamBot/1.0</String> |
||
17781 | <Description>Seznam Search (Czech Republic) robot</Description> |
||
17782 | <Type>R</Type> |
||
17783 | <Comment>212.80.76.xx</Comment> |
||
17784 | <Link1>http://www.seznam.cz/</Link1> |
||
17785 | <Link2></Link2> |
||
17786 | </user-agent> |
||
17787 | <user-agent> |
||
17788 | <ID>id_n_s_1258</ID> |
||
17789 | <String>SeznamBot/1.0 (+http://fulltext.seznam.cz/)</String> |
||
17790 | <Description>Seznam Search (Czech Republic) robot</Description> |
||
17791 | <Type>R</Type> |
||
17792 | <Comment>212.80.76.xx</Comment> |
||
17793 | <Link1>http://www.seznam.cz/</Link1> |
||
17794 | <Link2></Link2> |
||
17795 | </user-agent> |
||
17796 | <user-agent> |
||
17797 | <ID>id_n_s_080907_2</ID> |
||
17798 | <String>SeznamBot/2.0-test (+http://fulltext.sblog.cz/)</String> |
||
17799 | <Description>Seznam Search (Czech Republic) robot</Description> |
||
17800 | <Type>R</Type> |
||
17801 | <Comment>212.80.76.xx</Comment> |
||
17802 | <Link1>http://www.seznam.cz/</Link1> |
||
17803 | <Link2></Link2> |
||
17804 | </user-agent> |
||
17805 | <user-agent> |
||
17806 | <ID>id_n_s_280208_2</ID> |
||
17807 | <String>ShablastBot 1.0</String> |
||
17808 | <Description>Unknown robot from Shablast.com - Website has no content - Ignores robots.txt</Description> |
||
17809 | <Type>S</Type> |
||
17810 | <Comment>67.228.100.1xx / 67.228.102.2xx</Comment> |
||
17811 | <Link1>http://shablast.com/</Link1> |
||
17812 | <Link2></Link2> |
||
17813 | </user-agent> |
||
17814 | <user-agent> |
||
17815 | <ID>id_n_s_1259</ID> |
||
17816 | <String>Shareaza v1.x.x.xx</String> |
||
17817 | <Description>Shareaza P2P peer-to-peer download client</Description> |
||
17818 | <Type>D B</Type> |
||
17819 | <Comment></Comment> |
||
17820 | <Link1>http://www.shareaza.com/</Link1> |
||
17821 | <Link2></Link2> |
||
17822 | </user-agent> |
||
17823 | <user-agent> |
||
17824 | <ID>id_n_s_1260</ID> |
||
17825 | <String>SharewarePlazaFileCheckBot/1.0+(+http://www.SharewarePlaza.com)</String> |
||
17826 | <Description>SharewarePlaza File Check Bot - link checking</Description> |
||
17827 | <Type>R C</Type> |
||
17828 | <Comment></Comment> |
||
17829 | <Link1>http://www.sharewareplaza.com/</Link1> |
||
17830 | <Link2></Link2> |
||
17831 | </user-agent> |
||
17832 | <user-agent> |
||
17833 | <ID>id_n_s_1261</ID> |
||
17834 | <String>Shim Crawler</String> |
||
17835 | <Description>Chikayama-Taura Lab Shim-Crawler used for The Kototoi Project (Japan) - (133.11.36.xx)</Description> |
||
17836 | <Type>R</Type> |
||
17837 | <Comment>s. also Shim-Crawler ...</Comment> |
||
17838 | <Link1>http://www.logos.ic.i.u-tokyo.ac.jp/crawler/index.en.html</Link1> |
||
17839 | <Link2>http://www.kototoi.org/index.html</Link2> |
||
17840 | </user-agent> |
||
17841 | <user-agent> |
||
17842 | <ID>id_n_s_240106_2</ID> |
||
17843 | <String>Shim-Crawler(Mozilla-compatible; http://www.logos.ic.i.u-tokyo.ac.jp/crawler/; crawl@logos.ic.i.u-tokyo.ac.jp)</String> |
||
17844 | <Description>Chikayama-Taura Lab Shim-Crawler used for The Kototoi Project (Japan) - (133.11.36.xx)</Description> |
||
17845 | <Type>R</Type> |
||
17846 | <Comment>s. also Shim Crawler</Comment> |
||
17847 | <Link1>http://www.logos.ic.i.u-tokyo.ac.jp/crawler/index.en.html</Link1> |
||
17848 | <Link2>http://www.kototoi.org/index.html</Link2> |
||
17849 | </user-agent> |
||
17850 | <user-agent> |
||
17851 | <ID>id_n_s_131205_1</ID> |
||
17852 | <String>ShopWiki/1.0 ( +http://www.shopwiki.com/)</String> |
||
17853 | <Description>ShopWiki shopping search based on LittleWiki search</Description> |
||
17854 | <Type>R</Type> |
||
17855 | <Comment>4.78.166.1xx</Comment> |
||
17856 | <Link1>http://www.shopwiki.com/</Link1> |
||
17857 | <Link2>http://dev.littlewiki.com/wiki/Home</Link2> |
||
17858 | </user-agent> |
||
17859 | <user-agent> |
||
17860 | <ID>id_n_s_250706_1</ID> |
||
17861 | <String>ShopWiki/1.0 ( +http://www.shopwiki.com/wiki/Help:Bot)</String> |
||
17862 | <Description>ShopWiki shopping search based on LittleWiki search</Description> |
||
17863 | <Type>R</Type> |
||
17864 | <Comment>4.78.166.1xx</Comment> |
||
17865 | <Link1>http://www.shopwiki.com/</Link1> |
||
17866 | <Link2>http://dev.littlewiki.com/wiki/Home</Link2> |
||
17867 | </user-agent> |
||
17868 | <user-agent> |
||
17869 | <ID>id_n_s_1262</ID> |
||
17870 | <String>Shoula.com Crawler 2.0</String> |
||
17871 | <Description>Shoula Search Engine crawler</Description> |
||
17872 | <Type>R</Type> |
||
17873 | <Comment></Comment> |
||
17874 | <Link1>http://www.shoula.com/</Link1> |
||
17875 | <Link2></Link2> |
||
17876 | </user-agent> |
||
17877 | <user-agent> |
||
17878 | <ID>id_n_s_230107_1</ID> |
||
17879 | <String>SietsCrawler/1.1 (+http://www.siets.biz)</String> |
||
17880 | <Description>Siets Crawler - Web based site crawling application</Description> |
||
17881 | <Type>R</Type> |
||
17882 | <Comment></Comment> |
||
17883 | <Link1>http://www.siets.biz/products/crawler/</Link1> |
||
17884 | <Link2></Link2> |
||
17885 | </user-agent> |
||
17886 | <user-agent> |
||
17887 | <ID>id_n_s_070308_1</ID> |
||
17888 | <String>Sigram/Nutch-1.0-dev (Test agent for Nutch development; http://www.sigram.com/bot.html; bot at sigram dot com)</String> |
||
17889 | <Description>Sigram's Nutch robot - crawler testing</Description> |
||
17890 | <Type>R</Type> |
||
17891 | <Comment></Comment> |
||
17892 | <Link1>http://www.sigram.com/bot.html</Link1> |
||
17893 | <Link2></Link2> |
||
17894 | </user-agent> |
||
17895 | <user-agent> |
||
17896 | <ID>id_n_s_050906_1</ID> |
||
17897 | <String>Siigle Orumcex v.001 Turkey (http://www.siigle.com)</String> |
||
17898 | <Description>Siigle search (Turkey) robot</Description> |
||
17899 | <Type>R</Type> |
||
17900 | <Comment>62.68.196.xx</Comment> |
||
17901 | <Link1>http://www.siigle.com/</Link1> |
||
17902 | <Link2></Link2> |
||
17903 | </user-agent> |
||
17904 | <user-agent> |
||
17905 | <ID>id_n_s_171006_1</ID> |
||
17906 | <String>silk/1.0</String> |
||
17907 | <Description>Slider Search directory robot (194.213.194.2xx)</Description> |
||
17908 | <Type>R</Type> |
||
17909 | <Comment>s. also Slider_Search...</Comment> |
||
17910 | <Link1>http://www.slider.com/index.html</Link1> |
||
17911 | <Link2></Link2> |
||
17912 | </user-agent> |
||
17913 | <user-agent> |
||
17914 | <ID>id_n_s_281205_1</ID> |
||
17915 | <String>silk/1.0 (+http://www.slider.com/silk.htm)/3.7</String> |
||
17916 | <Description>Slider Search directory robot (194.213.194.2xx)</Description> |
||
17917 | <Type>R</Type> |
||
17918 | <Comment>s. also Slider_Search...</Comment> |
||
17919 | <Link1>http://www.slider.com/index.html</Link1> |
||
17920 | <Link2></Link2> |
||
17921 | </user-agent> |
||
17922 | <user-agent> |
||
17923 | <ID>id_n_s_131206_2</ID> |
||
17924 | <String>SimpleFavPanel/1.2</String> |
||
17925 | <Description>SimpleFavPanel - IE newsfeed panel plugin</Description> |
||
17926 | <Type>B</Type> |
||
17927 | <Comment></Comment> |
||
17928 | <Link1>http://www.egrath.net/index.php?ExplorerBarPlus%2F%A5%D1%A5%CD%A5%EB%B0%EC%CD%F7%2FSimpleFavPanel</Link1> |
||
17929 | <Link2></Link2> |
||
17930 | </user-agent> |
||
17931 | <user-agent> |
||
17932 | <ID>id_n_s_1263</ID> |
||
17933 | <String>Simpy 1.x; http://www.simpy.com/</String> |
||
17934 | <Description>Simpy bookmarking and personal search engine</Description> |
||
17935 | <Type>R C</Type> |
||
17936 | <Comment>s. also Argus</Comment> |
||
17937 | <Link1>http://www.simpy.com/</Link1> |
||
17938 | <Link2></Link2> |
||
17939 | </user-agent> |
||
17940 | <user-agent> |
||
17941 | <ID>id_n_s_1264</ID> |
||
17942 | <String>Simpy/1.x (Simpy; http://www.simpy.com/?ref=bot; feedback at simpy dot com)</String> |
||
17943 | <Description>Simpy bookmarking and personal search engine</Description> |
||
17944 | <Type>R C</Type> |
||
17945 | <Comment>s. also Argus</Comment> |
||
17946 | <Link1>http://www.simpy.com/</Link1> |
||
17947 | <Link2></Link2> |
||
17948 | </user-agent> |
||
17949 | <user-agent> |
||
17950 | <ID>id_n_s_180707_2</ID> |
||
17951 | <String>Sirketcebot/v.01 (http://www.sirketce.com/bot.html)</String> |
||
17952 | <Description>Sirketçe search - Turkey</Description> |
||
17953 | <Type>R</Type> |
||
17954 | <Comment>88.255.173.xx</Comment> |
||
17955 | <Link1>http://www.sirketce.com/</Link1> |
||
17956 | <Link2></Link2> |
||
17957 | </user-agent> |
||
17958 | <user-agent> |
||
17959 | <ID>id_n_s_070207_3</ID> |
||
17960 | <String>SiteBar/3.x.x (Bookmark Server; http://sitebar.org/)</String> |
||
17961 | <Description>SiteBar online bookmark manager</Description> |
||
17962 | <Type>C</Type> |
||
17963 | <Comment></Comment> |
||
17964 | <Link1>http://sitebar.org/</Link1> |
||
17965 | <Link2></Link2> |
||
17966 | </user-agent> |
||
17967 | <user-agent> |
||
17968 | <ID>id_n_s_1265</ID> |
||
17969 | <String>SiteBar/x.x</String> |
||
17970 | <Description>SiteBar bookmark server</Description> |
||
17971 | <Type>C</Type> |
||
17972 | <Comment></Comment> |
||
17973 | <Link1>http://sitebar.sourceforge.net/</Link1> |
||
17974 | <Link2></Link2> |
||
17975 | </user-agent> |
||
17976 | <user-agent> |
||
17977 | <ID>id_n_s_1266</ID> |
||
17978 | <String>SiteBar/x.x.x (Bookmark Server; http://sitebar.org/)</String> |
||
17979 | <Description>SiteBar bookmark server</Description> |
||
17980 | <Type>C</Type> |
||
17981 | <Comment></Comment> |
||
17982 | <Link1>http://sitebar.sourceforge.net/</Link1> |
||
17983 | <Link2></Link2> |
||
17984 | </user-agent> |
||
17985 | <user-agent> |
||
17986 | <ID>id_n_s_1267</ID> |
||
17987 | <String>sitecheck.internetseer.com</String> |
||
17988 | <Description>Internetseer Web Site Monitoring / Claymont robot</Description> |
||
17989 | <Type>R C</Type> |
||
17990 | <Comment></Comment> |
||
17991 | <Link1>http://www.internetseer.com/</Link1> |
||
17992 | <Link2>http://www.claymont.com/</Link2> |
||
17993 | </user-agent> |
||
17994 | <user-agent> |
||
17995 | <ID>id_n_s_1268</ID> |
||
17996 | <String>sitecheck.internetseer.com (For more info see: http://sitecheck.internetseer.com)</String> |
||
17997 | <Description>Internetseer Web Site Monitoring</Description> |
||
17998 | <Type>R C</Type> |
||
17999 | <Comment></Comment> |
||
18000 | <Link1>http://www.internetseer.com/</Link1> |
||
18001 | <Link2></Link2> |
||
18002 | </user-agent> |
||
18003 | <user-agent> |
||
18004 | <ID>id_n_s_1269</ID> |
||
18005 | <String>SiteRecon+(xx)</String> |
||
18006 | <Description>SiteRecon website monitoring spider at xx minute intervals</Description> |
||
18007 | <Type>R C</Type> |
||
18008 | <Comment></Comment> |
||
18009 | <Link1>http://www.siterecon.com/</Link1> |
||
18010 | <Link2></Link2> |
||
18011 | </user-agent> |
||
18012 | <user-agent> |
||
18013 | <ID>id_n_s_1270</ID> |
||
18014 | <String>SiteSnagger</String> |
||
18015 | <Description>PC Magazin web site downloadmanager</Description> |
||
18016 | <Type>D</Type> |
||
18017 | <Comment></Comment> |
||
18018 | <Link1>http://www.zdnet.com/pcmag/pctech/content/17/04/ut1704.001.html</Link1> |
||
18019 | <Link2></Link2> |
||
18020 | </user-agent> |
||
18021 | <user-agent> |
||
18022 | <ID>id_n_s_1271</ID> |
||
18023 | <String>SiteSpider +(http://www.SiteSpider.com/)</String> |
||
18024 | <Description>Site Spider robot (66.249.17.xx)</Description> |
||
18025 | <Type>R</Type> |
||
18026 | <Comment></Comment> |
||
18027 | <Link1>http://www.SiteSpider.com/</Link1> |
||
18028 | <Link2></Link2> |
||
18029 | </user-agent> |
||
18030 | <user-agent> |
||
18031 | <ID>id_n_s_021205_3</ID> |
||
18032 | <String>SiteSucker/1.x.x</String> |
||
18033 | <Description>SiteSucker Mac website downloading tool</Description> |
||
18034 | <Type>D</Type> |
||
18035 | <Comment></Comment> |
||
18036 | <Link1>http://www.sitesucker.us/</Link1> |
||
18037 | <Link2></Link2> |
||
18038 | </user-agent> |
||
18039 | <user-agent> |
||
18040 | <ID>id_n_s_140306_2</ID> |
||
18041 | <String>SiteTaggerBot (http://www.sitetagger.com/bot.htm)</String> |
||
18042 | <Description>SiteTagger.com bookmark organizer</Description> |
||
18043 | <Type>C</Type> |
||
18044 | <Comment></Comment> |
||
18045 | <Link1>http://www.sitetagger.com/</Link1> |
||
18046 | <Link2></Link2> |
||
18047 | </user-agent> |
||
18048 | <user-agent> |
||
18049 | <ID>id_n_s_030407_1</ID> |
||
18050 | <String>SiteTruth.com site rating system</String> |
||
18051 | <Description>SiteTruth - Automatic site legitimacy rating system</Description> |
||
18052 | <Type>R</Type> |
||
18053 | <Comment>69.64.67.xx</Comment> |
||
18054 | <Link1>http://www.sitetruth.com/</Link1> |
||
18055 | <Link2></Link2> |
||
18056 | </user-agent> |
||
18057 | <user-agent> |
||
18058 | <ID>id_n_s_1272</ID> |
||
18059 | <String>SiteWinder</String> |
||
18060 | <Description>Webwasher.com (217.146.159.xx) internet filter</Description> |
||
18061 | <Type>B P</Type> |
||
18062 | <Comment></Comment> |
||
18063 | <Link1>http://www.webwasher.com/</Link1> |
||
18064 | <Link2></Link2> |
||
18065 | </user-agent> |
||
18066 | <user-agent> |
||
18067 | <ID>id_n_s_1273</ID> |
||
18068 | <String>SiteXpert</String> |
||
18069 | <Description>Xtreeme SiteXpert sitemap & search engine builder</Description> |
||
18070 | <Type>R</Type> |
||
18071 | <Comment></Comment> |
||
18072 | <Link1>http://www.xtreeme.com/sitexpert/index.php</Link1> |
||
18073 | <Link2></Link2> |
||
18074 | </user-agent> |
||
18075 | <user-agent> |
||
18076 | <ID>id_n_s_1274</ID> |
||
18077 | <String>Skampy/0.9.x (http://www.skaffe.com/skampy-info.html)</String> |
||
18078 | <Description>Skaffe.com directory link checker</Description> |
||
18079 | <Type>R</Type> |
||
18080 | <Comment></Comment> |
||
18081 | <Link1>http://www.skaffe.com/</Link1> |
||
18082 | <Link2></Link2> |
||
18083 | </user-agent> |
||
18084 | <user-agent> |
||
18085 | <ID>id_n_s_1275</ID> |
||
18086 | <String>Skimpy/0.x (http://www.skaffe.com/skampy-info.html)</String> |
||
18087 | <Description>Skaffe.com directory link checker</Description> |
||
18088 | <Type>R</Type> |
||
18089 | <Comment></Comment> |
||
18090 | <Link1>http://www.skaffe.com/</Link1> |
||
18091 | <Link2></Link2> |
||
18092 | </user-agent> |
||
18093 | <user-agent> |
||
18094 | <ID>id_n_s_090706_1</ID> |
||
18095 | <String>Skywalker/0.1 (Skywalker; anonymous; anonymous)</String> |
||
18096 | <Description>Visvo distributed website crawler based on Nutch</Description> |
||
18097 | <Type>R</Type> |
||
18098 | <Comment>63.133.162.xx</Comment> |
||
18099 | <Link1>http://www.visvo.com/bot.html</Link1> |
||
18100 | <Link2></Link2> |
||
18101 | </user-agent> |
||
18102 | <user-agent> |
||
18103 | <ID>id_n_s_1276</ID> |
||
18104 | <String>Slarp/0.1</String> |
||
18105 | <Description>Only.com robot</Description> |
||
18106 | <Type>R</Type> |
||
18107 | <Comment></Comment> |
||
18108 | <Link1>http://www.only.com/</Link1> |
||
18109 | <Link2></Link2> |
||
18110 | </user-agent> |
||
18111 | <user-agent> |
||
18112 | <ID>id_n_s_1277</ID> |
||
18113 | <String>Sleipnir</String> |
||
18114 | <Description>Sleipnir - Japanese Explorer based browser & search bar</Description> |
||
18115 | <Type>B</Type> |
||
18116 | <Comment></Comment> |
||
18117 | <Link1>http://www20.pos.to/~sleipnir/software/sleipnir/index.html</Link1> |
||
18118 | <Link2></Link2> |
||
18119 | </user-agent> |
||
18120 | <user-agent> |
||
18121 | <ID>id_n_s_1278</ID> |
||
18122 | <String>Sleipnir Version 1.xx</String> |
||
18123 | <Description>Sleipnir - Japanese Explorer based browser & search bar</Description> |
||
18124 | <Type>B</Type> |
||
18125 | <Comment></Comment> |
||
18126 | <Link1>http://www20.pos.to/~sleipnir/software/sleipnir/index.html</Link1> |
||
18127 | <Link2></Link2> |
||
18128 | </user-agent> |
||
18129 | <user-agent> |
||
18130 | <ID>id_n_s_170207_5</ID> |
||
18131 | <String>Sleipnir Version2.x</String> |
||
18132 | <Description>Sleipnir - Japanese Explorer based browser & search bar</Description> |
||
18133 | <Type>B</Type> |
||
18134 | <Comment></Comment> |
||
18135 | <Link1>http://www20.pos.to/~sleipnir/software/sleipnir/index.html</Link1> |
||
18136 | <Link2></Link2> |
||
18137 | </user-agent> |
||
18138 | <user-agent> |
||
18139 | <ID>id_n_s_260706_1</ID> |
||
18140 | <String>Sleipnir/2.xx</String> |
||
18141 | <Description>Sleipnir - Japanese Explorer based browser & search bar</Description> |
||
18142 | <Type>B</Type> |
||
18143 | <Comment></Comment> |
||
18144 | <Link1>http://www20.pos.to/~sleipnir/software/sleipnir/index.html</Link1> |
||
18145 | <Link2></Link2> |
||
18146 | </user-agent> |
||
18147 | <user-agent> |
||
18148 | <ID>id_n_s_1279</ID> |
||
18149 | <String>Slider_Search_v1-de</String> |
||
18150 | <Description>Slider Search directory robot (194.213.194.2xx)</Description> |
||
18151 | <Type>R</Type> |
||
18152 | <Comment>s. also silk/1.0...</Comment> |
||
18153 | <Link1>http://www.slider.com/index.html</Link1> |
||
18154 | <Link2></Link2> |
||
18155 | </user-agent> |
||
18156 | <user-agent> |
||
18157 | <ID>id_n_s_1280</ID> |
||
18158 | <String>SlimBrowser</String> |
||
18159 | <Description>Slim Browser (IE based browser) - uses this user agent for favicon.ico only</Description> |
||
18160 | <Type>B</Type> |
||
18161 | <Comment></Comment> |
||
18162 | <Link1>http://www.flashpeak.com/sbrowser/</Link1> |
||
18163 | <Link2></Link2> |
||
18164 | </user-agent> |
||
18165 | <user-agent> |
||
18166 | <ID>id_n_s_1281</ID> |
||
18167 | <String>Slurp/2.0 (slurp@inktomi.com; http://www.inktomi.com/slurp.html)</String> |
||
18168 | <Description>Inktomi (Hotbot-Lycos-NBCi) robot</Description> |
||
18169 | <Type>R</Type> |
||
18170 | <Comment></Comment> |
||
18171 | <Link1>http://www.inktomi.com/slurp.html</Link1> |
||
18172 | <Link2></Link2> |
||
18173 | </user-agent> |
||
18174 | <user-agent> |
||
18175 | <ID>id_n_s_1282</ID> |
||
18176 | <String>Slurp/2.0-KiteWeekly (slurp@inktomi.com; http://www.inktomi.com/slurp.html)</String> |
||
18177 | <Description>Inktomi (Hotbot-Lycos-NBCi) robot</Description> |
||
18178 | <Type>R</Type> |
||
18179 | <Comment></Comment> |
||
18180 | <Link1>http://www.inktomi.com/slurp.html</Link1> |
||
18181 | <Link2></Link2> |
||
18182 | </user-agent> |
||
18183 | <user-agent> |
||
18184 | <ID>id_n_s_1283</ID> |
||
18185 | <String>Slurp/si (slurp@inktomi.com; http://www.inktomi.com/slurp.html)</String> |
||
18186 | <Description>Inktomi (Hotbot-Lycos-NBCi) robot</Description> |
||
18187 | <Type>R</Type> |
||
18188 | <Comment></Comment> |
||
18189 | <Link1>http://www.inktomi.com/slurp.html</Link1> |
||
18190 | <Link2></Link2> |
||
18191 | </user-agent> |
||
18192 | <user-agent> |
||
18193 | <ID>id_n_s_240806_1</ID> |
||
18194 | <String>Slurpy Verifier/1.0</String> |
||
18195 | <Description>Inktomi (Hotbot-Lycos-NBCi) robot - 72.30.61.xx(x)</Description> |
||
18196 | <Type>R</Type> |
||
18197 | <Comment>s. also Mozilla/3.0 (Slurp/.....</Comment> |
||
18198 | <Link1>http://www.inktomi.com/</Link1> |
||
18199 | <Link2></Link2> |
||
18200 | </user-agent> |
||
18201 | <user-agent> |
||
18202 | <ID>id_n_s_1284</ID> |
||
18203 | <String>SlySearch (slysearch@slysearch.com)</String> |
||
18204 | <Description>Slysearch robot (now Turnitin robot)</Description> |
||
18205 | <Type>R</Type> |
||
18206 | <Comment></Comment> |
||
18207 | <Link1>http://www.slysearch.com/</Link1> |
||
18208 | <Link2></Link2> |
||
18209 | </user-agent> |
||
18210 | <user-agent> |
||
18211 | <ID>id_n_s_1285</ID> |
||
18212 | <String>SlySearch/1.0 http://www.plagiarism.org/crawler/robotinfo.html</String> |
||
18213 | <Description>Slysearch robot (now Turnitin robot)</Description> |
||
18214 | <Type>R</Type> |
||
18215 | <Comment></Comment> |
||
18216 | <Link1>http://www.slysearch.com/</Link1> |
||
18217 | <Link2></Link2> |
||
18218 | </user-agent> |
||
18219 | <user-agent> |
||
18220 | <ID>id_n_s_1286</ID> |
||
18221 | <String>SlySearch/1.x http://www.slysearch.com</String> |
||
18222 | <Description>Slysearch robot (now Turnitin robot)</Description> |
||
18223 | <Type>R</Type> |
||
18224 | <Comment></Comment> |
||
18225 | <Link1>http://www.slysearch.com/</Link1> |
||
18226 | <Link2></Link2> |
||
18227 | </user-agent> |
||
18228 | <user-agent> |
||
18229 | <ID>id_n_s_1287</ID> |
||
18230 | <String>SmartDownload/1.2.67 (Win32; Jan 12 1999)</String> |
||
18231 | <Description>Netzip/Smartdownload download manager</Description> |
||
18232 | <Type>D</Type> |
||
18233 | <Comment></Comment> |
||
18234 | <Link1>http://www.netzip.com/</Link1> |
||
18235 | <Link2></Link2> |
||
18236 | </user-agent> |
||
18237 | <user-agent> |
||
18238 | <ID>id_n_s_1288</ID> |
||
18239 | <String>SmartDownload/1.2.77 (Win32; Feb 1 2000)</String> |
||
18240 | <Description>Netzip/Smartdownload download manager</Description> |
||
18241 | <Type>D</Type> |
||
18242 | <Comment></Comment> |
||
18243 | <Link1>http://www.netzip.com/</Link1> |
||
18244 | <Link2></Link2> |
||
18245 | </user-agent> |
||
18246 | <user-agent> |
||
18247 | <ID>id_n_s_1289</ID> |
||
18248 | <String>SmartDownload/1.2.77 (Win32; Jun 19 2001)</String> |
||
18249 | <Description>Netzip/Smartdownload download manager</Description> |
||
18250 | <Type>D</Type> |
||
18251 | <Comment></Comment> |
||
18252 | <Link1>http://www.netzip.com/</Link1> |
||
18253 | <Link2></Link2> |
||
18254 | </user-agent> |
||
18255 | <user-agent> |
||
18256 | <ID>id_n_s_1290</ID> |
||
18257 | <String>smartwit.com</String> |
||
18258 | <Description>Loop Improvements NRS Enterprise search (69.44.155.xx[x])</Description> |
||
18259 | <Type>R</Type> |
||
18260 | <Comment></Comment> |
||
18261 | <Link1>http://www.loopimprovements.com/</Link1> |
||
18262 | <Link2>http://demo.loopimprovements.com/demo/</Link2> |
||
18263 | </user-agent> |
||
18264 | <user-agent> |
||
18265 | <ID>id_n_s_020307_2</ID> |
||
18266 | <String>SmiffyDCMetaSpider/1.0</String> |
||
18267 | <Description>SmiffyDCMetaSpider - Robot to check the retro-adding of Dublin Core metadata</Description> |
||
18268 | <Type>R</Type> |
||
18269 | <Comment>64.71.152.xx</Comment> |
||
18270 | <Link1>http://www.smiffysplace.com</Link1> |
||
18271 | <Link2>http://www.smiffysplace.com/smiffydcmetaspider</Link2> |
||
18272 | </user-agent> |
||
18273 | <user-agent> |
||
18274 | <ID>id_n_s_1291</ID> |
||
18275 | <String>sna-0.0.1 (mikemuzio@msn.com)</String> |
||
18276 | <Description>Snoopy PHP-client</Description> |
||
18277 | <Type></Type> |
||
18278 | <Comment>see Snoopy</Comment> |
||
18279 | <Link1>http://sourceforge.net/projects/snoopy/</Link1> |
||
18280 | <Link2></Link2> |
||
18281 | </user-agent> |
||
18282 | <user-agent> |
||
18283 | <ID>id_n_s_1292</ID> |
||
18284 | <String>sna-0.0.1 mikeelliott@hotmail.com</String> |
||
18285 | <Description>Snoopy PHP-client</Description> |
||
18286 | <Type></Type> |
||
18287 | <Comment>see Snoopy</Comment> |
||
18288 | <Link1>http://sourceforge.net/projects/snoopy/</Link1> |
||
18289 | <Link2></Link2> |
||
18290 | </user-agent> |
||
18291 | <user-agent> |
||
18292 | <ID>id_n_s_080106_1</ID> |
||
18293 | <String>snap.com beta crawler v0</String> |
||
18294 | <Description>Unknown bot from bb2.net (66.234.139.xxx) also as Snapbot/1.0</Description> |
||
18295 | <Type>S</Type> |
||
18296 | <Comment>Gets only the robots.txt - Not from Snap.com / Idealab (63.251.211.xxx)</Comment> |
||
18297 | <Link1>http://www.kloth.net/internet/badbots.php</Link1> |
||
18298 | <Link2></Link2> |
||
18299 | </user-agent> |
||
18300 | <user-agent> |
||
18301 | <ID>id_n_s_250506_1</ID> |
||
18302 | <String>Snapbot/1.0</String> |
||
18303 | <Description>Unknown bot from bb2.net (66.234.139.xxx) - also as snap.com</Description> |
||
18304 | <Type>S</Type> |
||
18305 | <Comment>Not from Snap.com / Idealab (63.251.211.xxx)</Comment> |
||
18306 | <Link1>http://www.kloth.net/internet/badbots.php</Link1> |
||
18307 | <Link2></Link2> |
||
18308 | </user-agent> |
||
18309 | <user-agent> |
||
18310 | <ID>id_n_s_250408_1</ID> |
||
18311 | <String>Snapbot/1.0 (Snap Shots, +http://www.snap.com)</String> |
||
18312 | <Description>Unknown bot from Psinet / Cogentco - not from Snap.com</Description> |
||
18313 | <Type>S</Type> |
||
18314 | <Comment>38.98.19.6x</Comment> |
||
18315 | <Link1></Link1> |
||
18316 | <Link2></Link2> |
||
18317 | </user-agent> |
||
18318 | <user-agent> |
||
18319 | <ID>id_n_s_270906_2</ID> |
||
18320 | <String>Snappy/1.1 ( http://www.urltrends.com/ )</String> |
||
18321 | <Description>My UrlTrends online web ranking service</Description> |
||
18322 | <Type>C</Type> |
||
18323 | <Comment>205.138.199.1xx / 209.85.36.x</Comment> |
||
18324 | <Link1>http://www.urltrends.com/</Link1> |
||
18325 | <Link2></Link2> |
||
18326 | </user-agent> |
||
18327 | <user-agent> |
||
18328 | <ID>id_n_s_100707_1</ID> |
||
18329 | <String>Snarfer/0.x.x (http://www.snarfware.com/)</String> |
||
18330 | <Description>Snarfer RSS reader</Description> |
||
18331 | <Type>B</Type> |
||
18332 | <Comment></Comment> |
||
18333 | <Link1>http://www.snarfware.com/</Link1> |
||
18334 | <Link2></Link2> |
||
18335 | </user-agent> |
||
18336 | <user-agent> |
||
18337 | <ID>id_n_s_1293</ID> |
||
18338 | <String>SnoopRob/x.x</String> |
||
18339 | <Description>Unknown robot from 217.229.156.xx (T-Online Germany)</Description> |
||
18340 | <Type></Type> |
||
18341 | <Comment></Comment> |
||
18342 | <Link1></Link1> |
||
18343 | <Link2></Link2> |
||
18344 | </user-agent> |
||
18345 | <user-agent> |
||
18346 | <ID>id_n_s_1294</ID> |
||
18347 | <String>Snoopy v1.xx</String> |
||
18348 | <Description>Snoopy PHP-client</Description> |
||
18349 | <Type></Type> |
||
18350 | <Comment>s. also sna-x.x.x</Comment> |
||
18351 | <Link1>http://sourceforge.net/projects/snoopy/</Link1> |
||
18352 | <Link2></Link2> |
||
18353 | </user-agent> |
||
18354 | <user-agent> |
||
18355 | <ID>id_n_s_1295</ID> |
||
18356 | <String>Snoopy v1.xx- : User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; MyIE2)</String> |
||
18357 | <Description>Snoopy PHP-client</Description> |
||
18358 | <Type></Type> |
||
18359 | <Comment>s. also sna-x.x.x</Comment> |
||
18360 | <Link1>http://sourceforge.net/projects/snoopy/</Link1> |
||
18361 | <Link2></Link2> |
||
18362 | </user-agent> |
||
18363 | <user-agent> |
||
18364 | <ID>id_n_s_1296</ID> |
||
18365 | <String>Snoopy_v0.xx</String> |
||
18366 | <Description>Snoopy PHP-client</Description> |
||
18367 | <Type></Type> |
||
18368 | <Comment>s. also sna-x.x.x</Comment> |
||
18369 | <Link1>http://sourceforge.net/projects/snoopy/</Link1> |
||
18370 | <Link2></Link2> |
||
18371 | </user-agent> |
||
18372 | <user-agent> |
||
18373 | <ID>id_n_s_1297</ID> |
||
18374 | <String>SnykeBot/0.6 (http://www.snyke.com)</String> |
||
18375 | <Description>Snyke.com France robot</Description> |
||
18376 | <Type>R</Type> |
||
18377 | <Comment></Comment> |
||
18378 | <Link1>http://www.snyke.com/</Link1> |
||
18379 | <Link2></Link2> |
||
18380 | </user-agent> |
||
18381 | <user-agent> |
||
18382 | <ID>id_n_s_250706_2</ID> |
||
18383 | <String>SocSciBot ()</String> |
||
18384 | <Description>Link crawler for the social sciences</Description> |
||
18385 | <Type>R</Type> |
||
18386 | <Comment></Comment> |
||
18387 | <Link1>http://socscibot.wlv.ac.uk/</Link1> |
||
18388 | <Link2></Link2> |
||
18389 | </user-agent> |
||
18390 | <user-agent> |
||
18391 | <ID>id_n_s_170407_1</ID> |
||
18392 | <String>SoftBank/1.0/812SH/SHJ001 Browser/NetFront/3.3 Profile/MIDP-2.0 Configuration/CLDC-1.1</String> |
||
18393 | <Description>NetFront browser on Softbank mobile phone</Description> |
||
18394 | <Type>B</Type> |
||
18395 | <Comment></Comment> |
||
18396 | <Link1>http://www.access-company.com/products/netfrontmobile/browser/index.html</Link1> |
||
18397 | <Link2>http://mb.softbank.jp/mb/en/product/</Link2> |
||
18398 | </user-agent> |
||
18399 | <user-agent> |
||
18400 | <ID>id_n_s_1298</ID> |
||
18401 | <String>SoftHypermarketFileCheckBot/1.0+(+http://www.softhypermaket.com)</String> |
||
18402 | <Description>Soft Hypermarket link checking</Description> |
||
18403 | <Type>R</Type> |
||
18404 | <Comment></Comment> |
||
18405 | <Link1>http://www.softhypermarket.com/</Link1> |
||
18406 | <Link2></Link2> |
||
18407 | </user-agent> |
||
18408 | <user-agent> |
||
18409 | <ID>id_n_s_1299</ID> |
||
18410 | <String>Softizerbot (http://www.softizer.com)</String> |
||
18411 | <Description>Softizer.com software directory link checking</Description> |
||
18412 | <Type>C</Type> |
||
18413 | <Comment>72.9.97.xx</Comment> |
||
18414 | <Link1>http://www.softizer.com/</Link1> |
||
18415 | <Link2></Link2> |
||
18416 | </user-agent> |
||
18417 | <user-agent> |
||
18418 | <ID>id_n_s_090208_1</ID> |
||
18419 | <String>sogou develop spider</String> |
||
18420 | <Description>Unknown UA from Chinanet (220.181.26.1xx) faking Sogou search robot</Description> |
||
18421 | <Type>S</Type> |
||
18422 | <Comment>s. also sohu agent & Sogou web spider</Comment> |
||
18423 | <Link1></Link1> |
||
18424 | <Link2></Link2> |
||
18425 | </user-agent> |
||
18426 | <user-agent> |
||
18427 | <ID>id_n_s_011207_2</ID> |
||
18428 | <String>Sogou Orion spider/3.0(+http://www.sogou.com/docs/help/webmasters.htm#07)</String> |
||
18429 | <Description>Unknown UA from Chinanet (220.181.18.xx) faking Sogou search robot</Description> |
||
18430 | <Type>S</Type> |
||
18431 | <Comment>s. also sohu agent , Sogou web spider & sogou develop spider</Comment> |
||
18432 | <Link1></Link1> |
||
18433 | <Link2></Link2> |
||
18434 | </user-agent> |
||
18435 | <user-agent> |
||
18436 | <ID>id_n_s_150106_1</ID> |
||
18437 | <String>sogou spider</String> |
||
18438 | <Description>Unknown UA from Chinanet (220.181.26.1xx) faking Sogou search robot</Description> |
||
18439 | <Type>S</Type> |
||
18440 | <Comment>s. also sohu agent , Sogou web spider & sogou develop spider</Comment> |
||
18441 | <Link1></Link1> |
||
18442 | <Link2></Link2> |
||
18443 | </user-agent> |
||
18444 | <user-agent> |
||
18445 | <ID>id_n_s_280407_1</ID> |
||
18446 | <String>Sogou web spider/3.0(+http://www.sogou.com/docs/help/webmasters.htm#07)</String> |
||
18447 | <Description>Unknown UA from Chinanet (220.181.26.1xx) faking Sogou search robot</Description> |
||
18448 | <Type>S</Type> |
||
18449 | <Comment>s. also sohu agent , sogou spider & sogou develop spider</Comment> |
||
18450 | <Link1></Link1> |
||
18451 | <Link2></Link2> |
||
18452 | </user-agent> |
||
18453 | <user-agent> |
||
18454 | <ID>id_n_s_291105_1</ID> |
||
18455 | <String>sohu agent</String> |
||
18456 | <Description>Unknown UA from Chinanet (220.181.26.1xx) faking Sogou search robot</Description> |
||
18457 | <Type>S</Type> |
||
18458 | <Comment>s. also sogou spider , sogou spider & sogou develop spider</Comment> |
||
18459 | <Link1></Link1> |
||
18460 | <Link2></Link2> |
||
18461 | </user-agent> |
||
18462 | <user-agent> |
||
18463 | <ID>id_n_s_1300</ID> |
||
18464 | <String>sohu-search</String> |
||
18465 | <Description>Sohu (Search Fox) search robot China (61.135.131.xxx)</Description> |
||
18466 | <Type>R</Type> |
||
18467 | <Comment>this UA also comes from 220.181.26.xxx (not Sohus IP range) as spam bot - s.also sohu agent</Comment> |
||
18468 | <Link1>http://www.sohu.com/</Link1> |
||
18469 | <Link2></Link2> |
||
18470 | </user-agent> |
||
18471 | <user-agent> |
||
18472 | <ID>id_n_s_160308_3</ID> |
||
18473 | <String>Sosospider+(+http://help.soso.com/webspider.htm)</String> |
||
18474 | <Description>SOSO search (China) spider</Description> |
||
18475 | <Type>R</Type> |
||
18476 | <Comment></Comment> |
||
18477 | <Link1>http://www.soso.com/</Link1> |
||
18478 | <Link2>http://help.soso.com/webspider.htm</Link2> |
||
18479 | </user-agent> |
||
18480 | <user-agent> |
||
18481 | <ID>id_n_s_1301</ID> |
||
18482 | <String>Space Bison/0.02 [fu] (Win67; X; SK)</String> |
||
18483 | <Description>Default Proxomitron (discontinued) filtering proxy user agent identifier</Description> |
||
18484 | <Type>P B</Type> |
||
18485 | <Comment></Comment> |
||
18486 | <Link1>http://duke.usask.ca/~macphed/prox/</Link1> |
||
18487 | <Link2></Link2> |
||
18488 | </user-agent> |
||
18489 | <user-agent> |
||
18490 | <ID>id_n_s_1302</ID> |
||
18491 | <String>SpeedDownload/1.x</String> |
||
18492 | <Description>Speed Download (Mac) download manager</Description> |
||
18493 | <Type>D</Type> |
||
18494 | <Comment></Comment> |
||
18495 | <Link1>http://www.yazsoft.com/</Link1> |
||
18496 | <Link2></Link2> |
||
18497 | </user-agent> |
||
18498 | <user-agent> |
||
18499 | <ID>id_n_s_1303</ID> |
||
18500 | <String>speedfind ramBot xtreme 8.1</String> |
||
18501 | <Description>Speedfind.de robot</Description> |
||
18502 | <Type>R</Type> |
||
18503 | <Comment></Comment> |
||
18504 | <Link1>http://www.speedfind.de/</Link1> |
||
18505 | <Link2></Link2> |
||
18506 | </user-agent> |
||
18507 | <user-agent> |
||
18508 | <ID>id_n_s_1304</ID> |
||
18509 | <String>Speedy Spider (Beta/x.x; speedy@entireweb.com)</String> |
||
18510 | <Description>Entireweb search robot</Description> |
||
18511 | <Type>R</Type> |
||
18512 | <Comment>62.13.25.2xx</Comment> |
||
18513 | <Link1>http://www.entireweb.com/</Link1> |
||
18514 | <Link2></Link2> |
||
18515 | </user-agent> |
||
18516 | <user-agent> |
||
18517 | <ID>id_n_s_070906_1</ID> |
||
18518 | <String>Speedy Spider (Entireweb; Beta/1.0; http://www.entireweb.com/about/search_tech/speedyspider/)</String> |
||
18519 | <Description>Entireweb search spider</Description> |
||
18520 | <Type>R</Type> |
||
18521 | <Comment>62.13.25.2xx</Comment> |
||
18522 | <Link1>http://www.entireweb.com/</Link1> |
||
18523 | <Link2></Link2> |
||
18524 | </user-agent> |
||
18525 | <user-agent> |
||
18526 | <ID>id_n_s_1305</ID> |
||
18527 | <String>Speedy_Spider (http://www.entireweb.com)</String> |
||
18528 | <Description>Entireweb search robot</Description> |
||
18529 | <Type>R</Type> |
||
18530 | <Comment>62.13.25.2xx</Comment> |
||
18531 | <Link1>http://www.entireweb.com/</Link1> |
||
18532 | <Link2></Link2> |
||
18533 | </user-agent> |
||
18534 | <user-agent> |
||
18535 | <ID>id_n_s_050208_4</ID> |
||
18536 | <String>Sphere Scout&v4.0 - scout at sphere dot com</String> |
||
18537 | <Description>Sphere blog and news search robot</Description> |
||
18538 | <Type>R</Type> |
||
18539 | <Comment>64.40.11[7-8].[x]xx</Comment> |
||
18540 | <Link1>http://www.sphere.com/</Link1> |
||
18541 | <Link2></Link2> |
||
18542 | </user-agent> |
||
18543 | <user-agent> |
||
18544 | <ID>id_n_s_040106_3</ID> |
||
18545 | <String>Sphider</String> |
||
18546 | <Description>Sphider - a lightweight search engine in PHP</Description> |
||
18547 | <Type>R</Type> |
||
18548 | <Comment></Comment> |
||
18549 | <Link1>http://www.cs.ioc.ee/~ando/sphider/</Link1> |
||
18550 | <Link2></Link2> |
||
18551 | </user-agent> |
||
18552 | <user-agent> |
||
18553 | <ID>id_n_s_1306</ID> |
||
18554 | <String>Spida/0.1</String> |
||
18555 | <Description>Only.com robot</Description> |
||
18556 | <Type>R</Type> |
||
18557 | <Comment>in conjunction with LWP::Simple/5.53</Comment> |
||
18558 | <Link1>http://www.only.com/</Link1> |
||
18559 | <Link2></Link2> |
||
18560 | </user-agent> |
||
18561 | <user-agent> |
||
18562 | <ID>id_n_s_1307</ID> |
||
18563 | <String>Spider-Sleek/2.0 (+http://search-info.com/linktous.html)</String> |
||
18564 | <Description>Search-Info ODP/DMOZ spider</Description> |
||
18565 | <Type>R</Type> |
||
18566 | <Comment></Comment> |
||
18567 | <Link1>http://search-info.com/</Link1> |
||
18568 | <Link2></Link2> |
||
18569 | </user-agent> |
||
18570 | <user-agent> |
||
18571 | <ID>id_n_s_1308</ID> |
||
18572 | <String>spider.batsch.com</String> |
||
18573 | <Description>Batsch robot</Description> |
||
18574 | <Type>R</Type> |
||
18575 | <Comment> - site unreachable</Comment> |
||
18576 | <Link1>http://www.batsch.com</Link1> |
||
18577 | <Link2></Link2> |
||
18578 | </user-agent> |
||
18579 | <user-agent> |
||
18580 | <ID>id_n_s_110206_4</ID> |
||
18581 | <String>Spider.TerraNautic.net - v:1.04</String> |
||
18582 | <Description>TerraNautic spider for Schnellsuchen touristic search (Germany)</Description> |
||
18583 | <Type>C</Type> |
||
18584 | <Comment></Comment> |
||
18585 | <Link1>http://www.terranautic.net/</Link1> |
||
18586 | <Link2>http://www.schnellsuchen.com/</Link2> |
||
18587 | </user-agent> |
||
18588 | <user-agent> |
||
18589 | <ID>id_n_s_1309</ID> |
||
18590 | <String>spider.yellopet.com - www.yellopet.com</String> |
||
18591 | <Description>Yellopet spider</Description> |
||
18592 | <Type>R</Type> |
||
18593 | <Comment></Comment> |
||
18594 | <Link1>http://www.yellopet.com/</Link1> |
||
18595 | <Link2></Link2> |
||
18596 | </user-agent> |
||
18597 | <user-agent> |
||
18598 | <ID>id_n_s_1310</ID> |
||
18599 | <String>Spider/maxbot.com admin@maxbot.com</String> |
||
18600 | <Description>Maxbot .gov .mil .edu indexing robot</Description> |
||
18601 | <Type>R</Type> |
||
18602 | <Comment></Comment> |
||
18603 | <Link1>http://www.maxbot.com/</Link1> |
||
18604 | <Link2></Link2> |
||
18605 | </user-agent> |
||
18606 | <user-agent> |
||
18607 | <ID>id_n_s_1311</ID> |
||
18608 | <String>SpiderKU/0.x</String> |
||
18609 | <Description>Unknown robot from CPE at Kasetsart University (158.108.35.xxx)</Description> |
||
18610 | <Type>R</Type> |
||
18611 | <Comment></Comment> |
||
18612 | <Link1>http://www.cpe.ku.ac.th/</Link1> |
||
18613 | <Link2></Link2> |
||
18614 | </user-agent> |
||
18615 | <user-agent> |
||
18616 | <ID>id_n_s_1312</ID> |
||
18617 | <String>SpiderMan</String> |
||
18618 | <Description>Yahoo Search user agent or spider (202.165.102.xxx)</Description> |
||
18619 | <Type>R</Type> |
||
18620 | <Comment></Comment> |
||
18621 | <Link1>http://search.yahoo.com/</Link1> |
||
18622 | <Link2></Link2> |
||
18623 | </user-agent> |
||
18624 | <user-agent> |
||
18625 | <ID>id_n_s_1313</ID> |
||
18626 | <String>SpiderMonkey/7.0x (SpiderMonkey.ca info at http://spidermonkey.ca/sm.shtml)</String> |
||
18627 | <Description>SpiderMonkey Canada robot</Description> |
||
18628 | <Type>R</Type> |
||
18629 | <Comment></Comment> |
||
18630 | <Link1>http://spidermonkey.ca/</Link1> |
||
18631 | <Link2></Link2> |
||
18632 | </user-agent> |
||
18633 | <user-agent> |
||
18634 | <ID>id_n_s_1314</ID> |
||
18635 | <String>Spinne/2.0</String> |
||
18636 | <Description>Spider.de robot</Description> |
||
18637 | <Type>R</Type> |
||
18638 | <Comment></Comment> |
||
18639 | <Link1>http://www.spider.de/</Link1> |
||
18640 | <Link2></Link2> |
||
18641 | </user-agent> |
||
18642 | <user-agent> |
||
18643 | <ID>id_n_s_1315</ID> |
||
18644 | <String>Spinne/2.0 med</String> |
||
18645 | <Description>Medkatalog (medical catalogue) Austria robot</Description> |
||
18646 | <Type>R</Type> |
||
18647 | <Comment></Comment> |
||
18648 | <Link1>http://www.medkatalog.com/</Link1> |
||
18649 | <Link2></Link2> |
||
18650 | </user-agent> |
||
18651 | <user-agent> |
||
18652 | <ID>id_n_s_1316</ID> |
||
18653 | <String>Spinne/2.0 med_AH</String> |
||
18654 | <Description>Medkatalog (medical catalogue) Austria robot</Description> |
||
18655 | <Type>R</Type> |
||
18656 | <Comment></Comment> |
||
18657 | <Link1>http://www.medkatalog.com/</Link1> |
||
18658 | <Link2></Link2> |
||
18659 | </user-agent> |
||
18660 | <user-agent> |
||
18661 | <ID>id_n_s_180707_3</ID> |
||
18662 | <String>Spock Crawler (http://www.spock.com/crawler)</String> |
||
18663 | <Description>Spock - people search application - via Amazon web services</Description> |
||
18664 | <Type>R</Type> |
||
18665 | <Comment>72.44.62.1xx</Comment> |
||
18666 | <Link1>http://www.spock.com/crawler</Link1> |
||
18667 | <Link2>http://www.amazon.com/gp/browse.html?node=3435361</Link2> |
||
18668 | </user-agent> |
||
18669 | <user-agent> |
||
18670 | <ID>id_n_s_1317</ID> |
||
18671 | <String>sportsuchmaschine.de-Robot (Version: 1.02- powered by www.sportsuchmaschine.de)</String> |
||
18672 | <Description>Sportsuchmaschine (German sports related search) link checking / robot</Description> |
||
18673 | <Type>R</Type> |
||
18674 | <Comment></Comment> |
||
18675 | <Link1>http://www.sportsuchmaschine.de/</Link1> |
||
18676 | <Link2></Link2> |
||
18677 | </user-agent> |
||
18678 | <user-agent> |
||
18679 | <ID>id_n_s_040306_1</ID> |
||
18680 | <String>sproose/0.1-alpha (sproose crawler; http://www.sproose.com/bot.html; crawler@sproose.com)</String> |
||
18681 | <Description>Sproose personalized search (38.100.225.xx)</Description> |
||
18682 | <Type>R</Type> |
||
18683 | <Comment>powered by Nutch</Comment> |
||
18684 | <Link1>http://www.sproose.com/</Link1> |
||
18685 | <Link2>http://lucene.apache.org/nutch/</Link2> |
||
18686 | </user-agent> |
||
18687 | <user-agent> |
||
18688 | <ID>id_n_s_1318</ID> |
||
18689 | <String>SQ Webscanner</String> |
||
18690 | <Description>SQ Webscanner Mac download manager</Description> |
||
18691 | <Type>D</Type> |
||
18692 | <Comment>product is discontinued</Comment> |
||
18693 | <Link1>http://macinsearch.com/users/webscanner/</Link1> |
||
18694 | <Link2></Link2> |
||
18695 | </user-agent> |
||
18696 | <user-agent> |
||
18697 | <ID>id_n_s_1319</ID> |
||
18698 | <String>Squid-Prefetch</String> |
||
18699 | <Description>Simple page-prefetch for Squid web proxy</Description> |
||
18700 | <Type>P</Type> |
||
18701 | <Comment></Comment> |
||
18702 | <Link1>http://packages.debian.org/stable/web/squid-prefetch</Link1> |
||
18703 | <Link2></Link2> |
||
18704 | </user-agent> |
||
18705 | <user-agent> |
||
18706 | <ID>id_n_s_171105_2</ID> |
||
18707 | <String>squidclam</String> |
||
18708 | <Description>Squidclam is a replacement for SquidClamAV-Redirector</Description> |
||
18709 | <Type>P</Type> |
||
18710 | <Comment>s.also SquidClamAV_Redirector 1.x.x</Comment> |
||
18711 | <Link1>http://sourceforge.net/projects/squidclam</Link1> |
||
18712 | <Link2></Link2> |
||
18713 | </user-agent> |
||
18714 | <user-agent> |
||
18715 | <ID>id_n_s_1320</ID> |
||
18716 | <String>SquidClamAV_Redirector 1.x.x</String> |
||
18717 | <Description>SCAVR - Squid helper script for scanning download URLs for viruses</Description> |
||
18718 | <Type>P</Type> |
||
18719 | <Comment>s.also squidclam</Comment> |
||
18720 | <Link1>http://www.jackal-net.at/tiki-read_article.php?articleId=1</Link1> |
||
18721 | <Link2></Link2> |
||
18722 | </user-agent> |
||
18723 | <user-agent> |
||
18724 | <ID>id_n_s_1321</ID> |
||
18725 | <String>Sqworm/2.9.81-BETA (beta_release; 20011102-760; i686-pc-linux-gnu)</String> |
||
18726 | <Description>AOL Search / Pacific Internet Exchange robot</Description> |
||
18727 | <Type>R</Type> |
||
18728 | <Comment></Comment> |
||
18729 | <Link1>http://www.aol.com/</Link1> |
||
18730 | <Link2></Link2> |
||
18731 | </user-agent> |
||
18732 | <user-agent> |
||
18733 | <ID>id_n_s_1322</ID> |
||
18734 | <String>Sqworm/2.9.85-BETA (beta_release; 20011115-775; i686-pc-linux-gnu)</String> |
||
18735 | <Description>diff. IPs / services i.e.: - Inria.fr robot - Websense (Internet filtering) robot</Description> |
||
18736 | <Type>R</Type> |
||
18737 | <Comment></Comment> |
||
18738 | <Link1>http://www.inria.fr/</Link1> |
||
18739 | <Link2>http://www.websense.com/</Link2> |
||
18740 | </user-agent> |
||
18741 | <user-agent> |
||
18742 | <ID>id_n_s_1323</ID> |
||
18743 | <String>Sqworm/2.9.89-BETA (beta_release; 20020130-839; i686-pc-linux-gnu) </String> |
||
18744 | <Description>Time Warner Telecom user robot ?</Description> |
||
18745 | <Type></Type> |
||
18746 | <Comment></Comment> |
||
18747 | <Link1></Link1> |
||
18748 | <Link2></Link2> |
||
18749 | </user-agent> |
||
18750 | <user-agent> |
||
18751 | <ID>id_n_s_1324</ID> |
||
18752 | <String>SSurf15a 11 </String> |
||
18753 | <Description>Some site scanning tool via diff. IPs i.e.: - choiceone.net (216.153.xxx.xxx) - epix.net (216.108.198.xx)</Description> |
||
18754 | <Type>S</Type> |
||
18755 | <Comment>see also - PSurf15a VA or random letters like - AWSCBA - URVUSLNAM</Comment> |
||
18756 | <Link1></Link1> |
||
18757 | <Link2></Link2> |
||
18758 | </user-agent> |
||
18759 | <user-agent> |
||
18760 | <ID>id_n_s_1325</ID> |
||
18761 | <String>StackRambler/x.x </String> |
||
18762 | <Description>Rambler search (Russia) robot (81.19.6x.xx)</Description> |
||
18763 | <Type>R</Type> |
||
18764 | <Comment></Comment> |
||
18765 | <Link1>http://www.rambler.ru</Link1> |
||
18766 | <Link2></Link2> |
||
18767 | </user-agent> |
||
18768 | <user-agent> |
||
18769 | <ID>id_n_s_1326</ID> |
||
18770 | <String>Stamina/1.4</String> |
||
18771 | <Description>Stamina download manager</Description> |
||
18772 | <Type>D</Type> |
||
18773 | <Comment></Comment> |
||
18774 | <Link1>http://www.wildbits.com/stamina/</Link1> |
||
18775 | <Link2></Link2> |
||
18776 | </user-agent> |
||
18777 | <user-agent> |
||
18778 | <ID>id_n_s_1327</ID> |
||
18779 | <String>Star Downloader</String> |
||
18780 | <Description>Star Downloader download manager</Description> |
||
18781 | <Type>D</Type> |
||
18782 | <Comment></Comment> |
||
18783 | <Link1>http://www.stardownloader.com/</Link1> |
||
18784 | <Link2></Link2> |
||
18785 | </user-agent> |
||
18786 | <user-agent> |
||
18787 | <ID>id_n_s_140106_3</ID> |
||
18788 | <String>StarDownloader/1.xx</String> |
||
18789 | <Description>Star Downloader download manager</Description> |
||
18790 | <Type>D</Type> |
||
18791 | <Comment></Comment> |
||
18792 | <Link1>http://www.stardownloader.com/</Link1> |
||
18793 | <Link2></Link2> |
||
18794 | </user-agent> |
||
18795 | <user-agent> |
||
18796 | <ID>id_n_s_1328</ID> |
||
18797 | <String>stat statcrawler@gmail.com</String> |
||
18798 | <Description>Experimental search engine spider from 66.92.186.xxx</Description> |
||
18799 | <Type>R</Type> |
||
18800 | <Comment>66.92.186.xxx</Comment> |
||
18801 | <Link1></Link1> |
||
18802 | <Link2></Link2> |
||
18803 | </user-agent> |
||
18804 | <user-agent> |
||
18805 | <ID>id_n_s_1329</ID> |
||
18806 | <String>Steeler/1.x (http://www.tkl.iis.u-tokyo.ac.jp/~crawler/)</String> |
||
18807 | <Description>Steeler crawler</Description> |
||
18808 | <Type>R</Type> |
||
18809 | <Comment></Comment> |
||
18810 | <Link1>http://www.tkl.iis.u-tokyo.ac.jp/~crawler/</Link1> |
||
18811 | <Link2></Link2> |
||
18812 | </user-agent> |
||
18813 | <user-agent> |
||
18814 | <ID>id_n_s_031107_5</ID> |
||
18815 | <String>Steeler/3.3 (http://www.tkl.iis.u-tokyo.ac.jp/~crawler/)</String> |
||
18816 | <Description>Steeler - University of Tokyo web crawler</Description> |
||
18817 | <Type>R</Type> |
||
18818 | <Comment>157.82.156.xx[x]</Comment> |
||
18819 | <Link1>http://www.tkl.iis.u-tokyo.ac.jp/~crawler/crawler.html.en</Link1> |
||
18820 | <Link2></Link2> |
||
18821 | </user-agent> |
||
18822 | <user-agent> |
||
18823 | <ID>id_n_s_060106_1</ID> |
||
18824 | <String>Strategic Board Bot (+http://www.strategicboard.com)</String> |
||
18825 | <Description>Strategic Board blog & news search robot</Description> |
||
18826 | <Type>R</Type> |
||
18827 | <Comment></Comment> |
||
18828 | <Link1>http://www.strategicboard.com/</Link1> |
||
18829 | <Link2></Link2> |
||
18830 | </user-agent> |
||
18831 | <user-agent> |
||
18832 | <ID>id_n_s_140906_2</ID> |
||
18833 | <String>Strategic Board Bot (+http://www.strategicboard.com)</String> |
||
18834 | <Description>Strategic Board blogs and news aggregator robot</Description> |
||
18835 | <Type>R</Type> |
||
18836 | <Comment>62.0.99.2xx</Comment> |
||
18837 | <Link1>http://www.strategicboard.com/</Link1> |
||
18838 | <Link2></Link2> |
||
18839 | </user-agent> |
||
18840 | <user-agent> |
||
18841 | <ID>id_n_s_1330</ID> |
||
18842 | <String>Submission Spider at surfsafely.com</String> |
||
18843 | <Description>Surfsafely submission verifier</Description> |
||
18844 | <Type>R</Type> |
||
18845 | <Comment></Comment> |
||
18846 | <Link1>http://www.surfsafely.com/</Link1> |
||
18847 | <Link2></Link2> |
||
18848 | </user-agent> |
||
18849 | <user-agent> |
||
18850 | <ID>id_n_s_210106_4</ID> |
||
18851 | <String>suchbaer.de</String> |
||
18852 | <Description>Suchbaer.de (Germany) search robot</Description> |
||
18853 | <Type>R</Type> |
||
18854 | <Comment></Comment> |
||
18855 | <Link1>http://www.suchbaer.de/</Link1> |
||
18856 | <Link2></Link2> |
||
18857 | </user-agent> |
||
18858 | <user-agent> |
||
18859 | <ID>id_n_s_010206_3</ID> |
||
18860 | <String>suchbaer.de (CrawlerAgent v0.103)</String> |
||
18861 | <Description>Suchbaer.de (Germany) search robot</Description> |
||
18862 | <Type>R</Type> |
||
18863 | <Comment></Comment> |
||
18864 | <Link1>http://www.suchbaer.de/</Link1> |
||
18865 | <Link2></Link2> |
||
18866 | </user-agent> |
||
18867 | <user-agent> |
||
18868 | <ID>id_n_s_1331</ID> |
||
18869 | <String>suchbot</String> |
||
18870 | <Description>Suchbot Germany robot</Description> |
||
18871 | <Type>R</Type> |
||
18872 | <Comment></Comment> |
||
18873 | <Link1>http://www.suchbot.de/</Link1> |
||
18874 | <Link2></Link2> |
||
18875 | </user-agent> |
||
18876 | <user-agent> |
||
18877 | <ID>id_n_s_1332</ID> |
||
18878 | <String>Suchknecht.at-Robot</String> |
||
18879 | <Description>Suchknecht Austria robot</Description> |
||
18880 | <Type>R</Type> |
||
18881 | <Comment></Comment> |
||
18882 | <Link1>http://www.suchknecht.at/</Link1> |
||
18883 | <Link2></Link2> |
||
18884 | </user-agent> |
||
18885 | <user-agent> |
||
18886 | <ID>id_n_s_120206_1</ID> |
||
18887 | <String>suchpadbot/1.0 (+http://www.suchpad.de)</String> |
||
18888 | <Description>suchpad search Germany robot (213.239.194.xx)</Description> |
||
18889 | <Type>R</Type> |
||
18890 | <Comment></Comment> |
||
18891 | <Link1>http://www.suchpad.de/</Link1> |
||
18892 | <Link2></Link2> |
||
18893 | </user-agent> |
||
18894 | <user-agent> |
||
18895 | <ID>id_n_s_160107_2</ID> |
||
18896 | <String>Sunrise XP/2.x</String> |
||
18897 | <Description>Sunrise XP handheld news / website reader and converter</Description> |
||
18898 | <Type>B</Type> |
||
18899 | <Comment></Comment> |
||
18900 | <Link1>http://sourceforge.net/projects/sunrisexp</Link1> |
||
18901 | <Link2></Link2> |
||
18902 | </user-agent> |
||
18903 | <user-agent> |
||
18904 | <ID>id_n_s_230406_4</ID> |
||
18905 | <String>Sunrise/0.42g (Windows XP)</String> |
||
18906 | <Description>Sunrise XP web sites and newsfeeds converter and handheld reader</Description> |
||
18907 | <Type>B</Type> |
||
18908 | <Comment></Comment> |
||
18909 | <Link1>http://www.sunrisexp.com/</Link1> |
||
18910 | <Link2></Link2> |
||
18911 | </user-agent> |
||
18912 | <user-agent> |
||
18913 | <ID>id_n_s_1333</ID> |
||
18914 | <String>SuperBot/x.x (Win32)</String> |
||
18915 | <Description>SuperBot website copier</Description> |
||
18916 | <Type>D</Type> |
||
18917 | <Comment></Comment> |
||
18918 | <Link1>http://www.sparkleware.com/superbot/index.html</Link1> |
||
18919 | <Link2></Link2> |
||
18920 | </user-agent> |
||
18921 | <user-agent> |
||
18922 | <ID>id_n_s_260108_2</ID> |
||
18923 | <String>SuperBot/x.x.x.xx (Windows XP)</String> |
||
18924 | <Description>SuperBot website copier</Description> |
||
18925 | <Type>D</Type> |
||
18926 | <Comment></Comment> |
||
18927 | <Link1>http://www.sparkleware.com/superbot/index.html</Link1> |
||
18928 | <Link2></Link2> |
||
18929 | </user-agent> |
||
18930 | <user-agent> |
||
18931 | <ID>id_n_s_1334</ID> |
||
18932 | <String>Superdownloads Spiderman</String> |
||
18933 | <Description>Ubbi Superdownloads (Brazil) link checking</Description> |
||
18934 | <Type>C</Type> |
||
18935 | <Comment></Comment> |
||
18936 | <Link1>http://superdownloads.ubbi.com.br/</Link1> |
||
18937 | <Link2></Link2> |
||
18938 | </user-agent> |
||
18939 | <user-agent> |
||
18940 | <ID>id_n_s_1335</ID> |
||
18941 | <String>SURF </String> |
||
18942 | <Description>SurfControl Web Filtering</Description> |
||
18943 | <Type>P</Type> |
||
18944 | <Comment></Comment> |
||
18945 | <Link1>http://www.surfcontrol.com/</Link1> |
||
18946 | <Link2></Link2> |
||
18947 | </user-agent> |
||
18948 | <user-agent> |
||
18949 | <ID>id_n_s_1336</ID> |
||
18950 | <String>SurferF3 1/0</String> |
||
18951 | <Description>Wanadoo Rechereche robot</Description> |
||
18952 | <Type>R</Type> |
||
18953 | <Comment></Comment> |
||
18954 | <Link1>http://www.wanadoo.fr/qqo/</Link1> |
||
18955 | <Link2></Link2> |
||
18956 | </user-agent> |
||
18957 | <user-agent> |
||
18958 | <ID>id_n_s_1337</ID> |
||
18959 | <String>SurfMaster</String> |
||
18960 | <Description>Maskbit Surfmaster bookmark tool</Description> |
||
18961 | <Type>C</Type> |
||
18962 | <Comment></Comment> |
||
18963 | <Link1>http://www.maskbit.com/surfmaster.htm</Link1> |
||
18964 | <Link2></Link2> |
||
18965 | </user-agent> |
||
18966 | <user-agent> |
||
18967 | <ID>id_n_s_1338</ID> |
||
18968 | <String>SurveyBot/2.2 <a href='http://www.whois.sc'>Whois Source</a></String> |
||
18969 | <Description>Whois Source domain name information robot (66.249.26.xx)</Description> |
||
18970 | <Type>R C</Type> |
||
18971 | <Comment>s.also: PigeonBot</Comment> |
||
18972 | <Link1>http://www.whois.sc/</Link1> |
||
18973 | <Link2></Link2> |
||
18974 | </user-agent> |
||
18975 | <user-agent> |
||
18976 | <ID>id_n_s_1339</ID> |
||
18977 | <String>SurveyBot/2.3 (Whois Source)</String> |
||
18978 | <Description>Whois Source domain name information robot (66.249.26.xx)</Description> |
||
18979 | <Type>R C</Type> |
||
18980 | <Comment>s.also: PigeonBot</Comment> |
||
18981 | <Link1>http://www.whois.sc/</Link1> |
||
18982 | <Link2></Link2> |
||
18983 | </user-agent> |
||
18984 | <user-agent> |
||
18985 | <ID>id_n_s_1340</ID> |
||
18986 | <String>suzuran</String> |
||
18987 | <Description>Yokogao Search Engine robot (Kanazawa University)</Description> |
||
18988 | <Type>R</Type> |
||
18989 | <Comment></Comment> |
||
18990 | <Link1>http://web.kanazawa-u.ac.jp/esearch.html</Link1> |
||
18991 | <Link2></Link2> |
||
18992 | </user-agent> |
||
18993 | <user-agent> |
||
18994 | <ID>id_n_s_1341</ID> |
||
18995 | <String>SWB/V1.4 (HP)</String> |
||
18996 | <Description>HP Secure Web Browser for OpenVMS</Description> |
||
18997 | <Type>B</Type> |
||
18998 | <Comment></Comment> |
||
18999 | <Link1>http://h71000.www7.hp.com/openvms/products/ips/cswb/cswb.html</Link1> |
||
19000 | <Link2></Link2> |
||
19001 | </user-agent> |
||
19002 | <user-agent> |
||
19003 | <ID>id_n_s_1342</ID> |
||
19004 | <String>swbot/0.9c libwww/5.3.1</String> |
||
19005 | <Description>unknown</Description> |
||
19006 | <Type></Type> |
||
19007 | <Comment></Comment> |
||
19008 | <Link1></Link1> |
||
19009 | <Link2></Link2> |
||
19010 | </user-agent> |
||
19011 | <user-agent> |
||
19012 | <ID>id_n_s_1343</ID> |
||
19013 | <String>Swooglebot/2.0. (+http://swoogle.umbc.edu/swooglebot.htm)</String> |
||
19014 | <Description>Swooglebot Swoogle's semantic web crawler</Description> |
||
19015 | <Type>R</Type> |
||
19016 | <Comment></Comment> |
||
19017 | <Link1>http://swoogle.umbc.edu</Link1> |
||
19018 | <Link2></Link2> |
||
19019 | </user-agent> |
||
19020 | <user-agent> |
||
19021 | <ID>id_n_s_060106_2</ID> |
||
19022 | <String>SWSBot-Images/1.2 http://www.smartwaresoft.com/swsbot12.html</String> |
||
19023 | <Description>SWSBot - SmartWareSoft (85.186.255.xx) software search engine created for Playfuls.com</Description> |
||
19024 | <Type>R</Type> |
||
19025 | <Comment></Comment> |
||
19026 | <Link1>http://www.smartwaresoft.com/swsbot12.html</Link1> |
||
19027 | <Link2>http://www.playfuls.com/</Link2> |
||
19028 | </user-agent> |
||
19029 | <user-agent> |
||
19030 | <ID>id_n_s_300106_2</ID> |
||
19031 | <String>SygolBot http://www.sygol.net</String> |
||
19032 | <Description>Sygol Search (Italy) robot</Description> |
||
19033 | <Type>R</Type> |
||
19034 | <Comment>s.also <http://www.sygol.com/></Comment> |
||
19035 | <Link1>http://www.sygol.com/</Link1> |
||
19036 | <Link2></Link2> |
||
19037 | </user-agent> |
||
19038 | <user-agent> |
||
19039 | <ID>id_n_s_1344</ID> |
||
19040 | <String>Sylera/1.2.x</String> |
||
19041 | <Description>Sylera browser (Japan)</Description> |
||
19042 | <Type>B</Type> |
||
19043 | <Comment></Comment> |
||
19044 | <Link1>http://tabbrowser.ktplan.jp/valinor/sylera.html</Link1> |
||
19045 | <Link2></Link2> |
||
19046 | </user-agent> |
||
19047 | <user-agent> |
||
19048 | <ID>id_n_s_1345</ID> |
||
19049 | <String>SyncBot</String> |
||
19050 | <Description>Mindspring.com user robot</Description> |
||
19051 | <Type></Type> |
||
19052 | <Comment></Comment> |
||
19053 | <Link1>http://www.mindspring.com/</Link1> |
||
19054 | <Link2></Link2> |
||
19055 | </user-agent> |
||
19056 | <user-agent> |
||
19057 | <ID>id_n_s_1346</ID> |
||
19058 | <String>SyncIT/x.x</String> |
||
19059 | <Description>SyncIT link validation</Description> |
||
19060 | <Type>C</Type> |
||
19061 | <Comment></Comment> |
||
19062 | <Link1>http://www.bookmarksync.com/</Link1> |
||
19063 | <Link2></Link2> |
||
19064 | </user-agent> |
||
19065 | <user-agent> |
||
19066 | <ID>id_n_s_140906_1</ID> |
||
19067 | <String>Syndirella/0.91pre</String> |
||
19068 | <Description>Syndirella desktop information aggregator (beta)</Description> |
||
19069 | <Type>B</Type> |
||
19070 | <Comment></Comment> |
||
19071 | <Link1>http://www.yole.ru/projects/syndirella/</Link1> |
||
19072 | <Link2></Link2> |
||
19073 | </user-agent> |
||
19074 | <user-agent> |
||
19075 | <ID>id_n_s_1347</ID> |
||
19076 | <String>SynoBot</String> |
||
19077 | <Description>Synomia (France) robot</Description> |
||
19078 | <Type>R</Type> |
||
19079 | <Comment></Comment> |
||
19080 | <Link1>http://www.synomia.fr/</Link1> |
||
19081 | <Link2></Link2> |
||
19082 | </user-agent> |
||
19083 | <user-agent> |
||
19084 | <ID>id_n_s_150406_1</ID> |
||
19085 | <String>Syntryx ANT Scout Chassis Pheromone; Mozilla/4.0 compatible crawler</String> |
||
19086 | <Description>Syntryx Solution Suite - domain / keyword crawler (216.7.179.xx)</Description> |
||
19087 | <Type>R</Type> |
||
19088 | <Comment></Comment> |
||
19089 | <Link1>http://www.syntryx.com/</Link1> |
||
19090 | <Link2></Link2> |
||
19091 | </user-agent> |
||
19092 | <user-agent> |
||
19093 | <ID>id_n_s_1348</ID> |
||
19094 | <String>Szukacz/1.x</String> |
||
19095 | <Description>Szukacz.pl (Polish search) robot</Description> |
||
19096 | <Type>R</Type> |
||
19097 | <Comment></Comment> |
||
19098 | <Link1>http://www.szukacz.pl/</Link1> |
||
19099 | <Link2></Link2> |
||
19100 | </user-agent> |
||
19101 | <user-agent> |
||
19102 | <ID>id_n_s_1349</ID> |
||
19103 | <String>Szukacz/1.x (robot; www.szukacz.pl/jakdzialarobot.html; szukacz@proszynski.pl)</String> |
||
19104 | <Description>Szukacz.pl (Polish search) robot</Description> |
||
19105 | <Type>R</Type> |
||
19106 | <Comment></Comment> |
||
19107 | <Link1>http://www.szukacz.pl/</Link1> |
||
19108 | <Link2></Link2> |
||
19109 | </user-agent> |
||
19110 | <user-agent> |
||
19111 | <ID>id_t_z_220106_2</ID> |
||
19112 | <String>T-Online Browser</String> |
||
19113 | <Description>German T-Online browser & internet suite </Description> |
||
19114 | <Type>B</Type> |
||
19115 | <Comment></Comment> |
||
19116 | <Link1>http://service.t-online.de/c/06/52/67/652672.html</Link1> |
||
19117 | <Link2></Link2> |
||
19118 | </user-agent> |
||
19119 | <user-agent> |
||
19120 | <ID>id_t_z_070807_1</ID> |
||
19121 | <String>tags2dir.com/0.8 (+http://tags2dir.com/directory/)</String> |
||
19122 | <Description>tags2dir.com directory index</Description> |
||
19123 | <Type>R</Type> |
||
19124 | <Comment>74.115.102.1xx</Comment> |
||
19125 | <Link1>http://tags2dir.com/directory/</Link1> |
||
19126 | <Link2></Link2> |
||
19127 | </user-agent> |
||
19128 | <user-agent> |
||
19129 | <ID>id_t_z_1350</ID> |
||
19130 | <String>Tagword (http://tagword.com/dmoz_survey.php)</String> |
||
19131 | <Description>TAGword DMOZ survey - ODP link checking robot</Description> |
||
19132 | <Type>R</Type> |
||
19133 | <Comment></Comment> |
||
19134 | <Link1>http://tagword.com/dmoz_survey.php</Link1> |
||
19135 | <Link2></Link2> |
||
19136 | </user-agent> |
||
19137 | <user-agent> |
||
19138 | <ID>id_t_z_271105_2</ID> |
||
19139 | <String>Tagyu Agent/1.0</String> |
||
19140 | <Description>Tagyu - del.icio.us bookmark collection online tag generator</Description> |
||
19141 | <Type></Type> |
||
19142 | <Comment></Comment> |
||
19143 | <Link1>http://www.tagyu.com/</Link1> |
||
19144 | <Link2>http://del.icio.us/</Link2> |
||
19145 | </user-agent> |
||
19146 | <user-agent> |
||
19147 | <ID>id_t_z_1351</ID> |
||
19148 | <String>Talkro Web-Shot/1.0 (E-mail: webshot@daumsoft.com- Home: http://222.122.15.190/webshot)</String> |
||
19149 | <Description>Daumsoft Talkro IR robot</Description> |
||
19150 | <Type>R</Type> |
||
19151 | <Comment></Comment> |
||
19152 | <Link1>http://www.daumsoft.com/</Link1> |
||
19153 | <Link2></Link2> |
||
19154 | </user-agent> |
||
19155 | <user-agent> |
||
19156 | <ID>id_t_z_1352</ID> |
||
19157 | <String>TAMU_CS_IRL_CRAWLER/1.0</String> |
||
19158 | <Description>Texas A&M University - Dept. of Computer Science crawler (server or link checking ?)</Description> |
||
19159 | <Type>R C</Type> |
||
19160 | <Comment></Comment> |
||
19161 | <Link1>http://www.cs.tamu.edu/</Link1> |
||
19162 | <Link2></Link2> |
||
19163 | </user-agent> |
||
19164 | <user-agent> |
||
19165 | <ID>id_t_z_1353</ID> |
||
19166 | <String>targetblaster.com/0.9k</String> |
||
19167 | <Description>Targetblaster user link validation ?</Description> |
||
19168 | <Type>R C</Type> |
||
19169 | <Comment></Comment> |
||
19170 | <Link1>http://www.targetblaster.com/</Link1> |
||
19171 | <Link2></Link2> |
||
19172 | </user-agent> |
||
19173 | <user-agent> |
||
19174 | <ID>id_t_z_230706_2</ID> |
||
19175 | <String>TargetYourNews.com bot</String> |
||
19176 | <Description>Target Your News - user submitted links</Description> |
||
19177 | <Type>C</Type> |
||
19178 | <Comment>72.36.160.xxx</Comment> |
||
19179 | <Link1>http://targetyournews.com/</Link1> |
||
19180 | <Link2></Link2> |
||
19181 | </user-agent> |
||
19182 | <user-agent> |
||
19183 | <ID>id_t_z_201006_1</ID> |
||
19184 | <String>TCDBOT/Nutch-0.8 (PhD student research;http://www.tcd.ie; mcgettrs at t c d dot IE)</String> |
||
19185 | <Description>Trinity College Dublin (Ireland) TCDBOT</Description> |
||
19186 | <Type>R</Type> |
||
19187 | <Comment>134.226.1.xx</Comment> |
||
19188 | <Link1>http://www.tcd.ie/</Link1> |
||
19189 | <Link2></Link2> |
||
19190 | </user-agent> |
||
19191 | <user-agent> |
||
19192 | <ID>id_t_z_1354</ID> |
||
19193 | <String>TE</String> |
||
19194 | <Description>HTTP header for transfer encoding used as user agent name ?</Description> |
||
19195 | <Type></Type> |
||
19196 | <Comment></Comment> |
||
19197 | <Link1></Link1> |
||
19198 | <Link2></Link2> |
||
19199 | </user-agent> |
||
19200 | <user-agent> |
||
19201 | <ID>id_t_z_1355</ID> |
||
19202 | <String>TeamSoft WinInet Component</String> |
||
19203 | <Description>WinInet Internet client app.</Description> |
||
19204 | <Type></Type> |
||
19205 | <Comment></Comment> |
||
19206 | <Link1>http://www.winsoft.sk/wininet.htm</Link1> |
||
19207 | <Link2></Link2> |
||
19208 | </user-agent> |
||
19209 | <user-agent> |
||
19210 | <ID>id_t_z_1356</ID> |
||
19211 | <String>TECOMAC-Crawler/0.x</String> |
||
19212 | <Description>Tecomac Gmbh (Germany) crawler software - now Arexera Information Technologies</Description> |
||
19213 | <Type>R</Type> |
||
19214 | <Comment></Comment> |
||
19215 | <Link1>http://www.arexera.de/</Link1> |
||
19216 | <Link2></Link2> |
||
19217 | </user-agent> |
||
19218 | <user-agent> |
||
19219 | <ID>id_t_z_1357</ID> |
||
19220 | <String>Tecomi Bot (http://www.tecomi.com/bot.htm)</String> |
||
19221 | <Description>Tecomi (Germany) beta / test robot (84.201.65.xxx)</Description> |
||
19222 | <Type>R</Type> |
||
19223 | <Comment></Comment> |
||
19224 | <Link1>http://www.tecomi.com/Suchmaschine</Link1> |
||
19225 | <Link2></Link2> |
||
19226 | </user-agent> |
||
19227 | <user-agent> |
||
19228 | <ID>id_t_z_101107_2</ID> |
||
19229 | <String>Teemer (NetSeer, Inc. is a Los Angeles based Internet startup company.; http://www.netseer.com/crawler.html; crawler@netseer.com)</String> |
||
19230 | <Description>Teemer crawler for NetSeer search (beta) via Amazon Web Services - see also NetSeer/Nutch</Description> |
||
19231 | <Type>R</Type> |
||
19232 | <Comment>67.202.26.1xx</Comment> |
||
19233 | <Link1>http://www.netseer.com/</Link1> |
||
19234 | <Link2>http://www.amazon.com/gp/browse.html?node=3435361</Link2> |
||
19235 | </user-agent> |
||
19236 | <user-agent> |
||
19237 | <ID>id_t_z_1358</ID> |
||
19238 | <String>Teleport Pro/1.2x(.1xxx)</String> |
||
19239 | <Description>Teleport (website) downloading tool</Description> |
||
19240 | <Type>D</Type> |
||
19241 | <Comment></Comment> |
||
19242 | <Link1>http://www.tenmax.com/teleport/pro/home.htm</Link1> |
||
19243 | <Link2></Link2> |
||
19244 | </user-agent> |
||
19245 | <user-agent> |
||
19246 | <ID>id_t_z_1359</ID> |
||
19247 | <String>Teoma MP</String> |
||
19248 | <Description>Teoma crawler (65.214.36.xx[x])</Description> |
||
19249 | <Type>R</Type> |
||
19250 | <Comment></Comment> |
||
19251 | <Link1>http://www.teoma.com/</Link1> |
||
19252 | <Link2></Link2> |
||
19253 | </user-agent> |
||
19254 | <user-agent> |
||
19255 | <ID>id_t_z_1361</ID> |
||
19256 | <String>teomaagent crawler-admin@teoma.com</String> |
||
19257 | <Description>Teoma crawler (65.214.36.xx[x])</Description> |
||
19258 | <Type>R</Type> |
||
19259 | <Comment></Comment> |
||
19260 | <Link1>http://www.teoma.com/</Link1> |
||
19261 | <Link2></Link2> |
||
19262 | </user-agent> |
||
19263 | <user-agent> |
||
19264 | <ID>id_t_z_1362</ID> |
||
19265 | <String>teomaagent1 [crawler-admin@teoma.com]</String> |
||
19266 | <Description>Teoma crawler (65.214.36.xx[x])</Description> |
||
19267 | <Type>R</Type> |
||
19268 | <Comment></Comment> |
||
19269 | <Link1>http://www.teoma.com/</Link1> |
||
19270 | <Link2></Link2> |
||
19271 | </user-agent> |
||
19272 | <user-agent> |
||
19273 | <ID>id_t_z_1360</ID> |
||
19274 | <String>teoma_agent1</String> |
||
19275 | <Description>Teoma crawler (65.214.36.xx[x])</Description> |
||
19276 | <Type>R</Type> |
||
19277 | <Comment></Comment> |
||
19278 | <Link1>http://www.teoma.com/</Link1> |
||
19279 | <Link2></Link2> |
||
19280 | </user-agent> |
||
19281 | <user-agent> |
||
19282 | <ID>id_t_z_1363</ID> |
||
19283 | <String>Teradex Mapper; mapper@teradex.com; http://www.teradex.com</String> |
||
19284 | <Description>Teradex Directory robot</Description> |
||
19285 | <Type>R</Type> |
||
19286 | <Comment></Comment> |
||
19287 | <Link1>http://directory.teradex.com/</Link1> |
||
19288 | <Link2></Link2> |
||
19289 | </user-agent> |
||
19290 | <user-agent> |
||
19291 | <ID>id_t_z_010406_4</ID> |
||
19292 | <String>TeragramCrawler</String> |
||
19293 | <Description>Teragram multilingual text & data processing software</Description> |
||
19294 | <Type>D ?</Type> |
||
19295 | <Comment></Comment> |
||
19296 | <Link1>http://www.teragram.com/</Link1> |
||
19297 | <Link2></Link2> |
||
19298 | </user-agent> |
||
19299 | <user-agent> |
||
19300 | <ID>id_t_z_150807_2</ID> |
||
19301 | <String>terraminds-bot/1.0 (support@terraminds.de)</String> |
||
19302 | <Description>Terraminds blog search (Germany)</Description> |
||
19303 | <Type>R</Type> |
||
19304 | <Comment>88.198.44.2xx</Comment> |
||
19305 | <Link1>http://www.terraminds.de/</Link1> |
||
19306 | <Link2></Link2> |
||
19307 | </user-agent> |
||
19308 | <user-agent> |
||
19309 | <ID>id_t_z_220406_1</ID> |
||
19310 | <String>TerrawizBot/1.0 (+http://www.terrawiz.com/bot.html)</String> |
||
19311 | <Description>Terrawiz Indian Search Engine robot</Description> |
||
19312 | <Type>R</Type> |
||
19313 | <Comment>209.128.80.1xx</Comment> |
||
19314 | <Link1>http://www.terrawiz.com/</Link1> |
||
19315 | <Link2></Link2> |
||
19316 | </user-agent> |
||
19317 | <user-agent> |
||
19318 | <ID>id_t_z_1364</ID> |
||
19319 | <String>Test spider</String> |
||
19320 | <Description>Noceans Information Portfolio Manager (66.35.69.x)</Description> |
||
19321 | <Type>R</Type> |
||
19322 | <Comment></Comment> |
||
19323 | <Link1>http://www.noceans.com/</Link1> |
||
19324 | <Link2></Link2> |
||
19325 | </user-agent> |
||
19326 | <user-agent> |
||
19327 | <ID>id_t_z_160507_1</ID> |
||
19328 | <String>TestCrawler/Nutch-0.9 (Testing Crawler for Research ; http://balihoo.com/index.aspx; tgautier at balihoo dot com)</String> |
||
19329 | <Description>Balihoo - Search Engine for Advertising Media</Description> |
||
19330 | <Type>R</Type> |
||
19331 | <Comment>204.228.230.xx</Comment> |
||
19332 | <Link1>http://balihoo.com/</Link1> |
||
19333 | <Link2></Link2> |
||
19334 | </user-agent> |
||
19335 | <user-agent> |
||
19336 | <ID>id_t_z_1365</ID> |
||
19337 | <String>The Expert HTML Source Viewer (http://www.expert-html.com)</String> |
||
19338 | <Description>Expert HTML online source viewer</Description> |
||
19339 | <Type>D B</Type> |
||
19340 | <Comment>in conjunction with lwp-trivial/1.35</Comment> |
||
19341 | <Link1>http://www.expert-html.net - site is offline</Link1> |
||
19342 | <Link2></Link2> |
||
19343 | </user-agent> |
||
19344 | <user-agent> |
||
19345 | <ID>id_t_z_281207_3</ID> |
||
19346 | <String>TheRarestParser/0.2a (http://therarestwords.com/)</String> |
||
19347 | <Description>The Rarest Words - Linguistic experiment crawler via Amazon Web Services</Description> |
||
19348 | <Type>R</Type> |
||
19349 | <Comment>67.202.27.19x</Comment> |
||
19350 | <Link1>http://therarestwords.com/</Link1> |
||
19351 | <Link2>http://www.amazon.com/gp/browse.html?node=3435361</Link2> |
||
19352 | </user-agent> |
||
19353 | <user-agent> |
||
19354 | <ID>id_t_z_1366</ID> |
||
19355 | <String>TheSuBot/0.1 (www.thesubot.de)</String> |
||
19356 | <Description>TheSuBot robot (Germany) for an unknown theme based search engine</Description> |
||
19357 | <Type>R</Type> |
||
19358 | <Comment></Comment> |
||
19359 | <Link1>http://www.thesubot.de/</Link1> |
||
19360 | <Link2></Link2> |
||
19361 | </user-agent> |
||
19362 | <user-agent> |
||
19363 | <ID>id_t_z_171106_1</ID> |
||
19364 | <String>thumbshots-de-Bot (Version: 1.02, powered by www.thumbshots.de)</String> |
||
19365 | <Description>ThumbShots website thumbnail service (Germany) robot</Description> |
||
19366 | <Type>D</Type> |
||
19367 | <Comment>212.112.238.xx</Comment> |
||
19368 | <Link1>http://www.thumbshots.de/</Link1> |
||
19369 | <Link2></Link2> |
||
19370 | </user-agent> |
||
19371 | <user-agent> |
||
19372 | <ID>id_t_z_1367</ID> |
||
19373 | <String>thumbshots-de-Bot (Version: 1.02- powered by www.thumbshots.de)</String> |
||
19374 | <Description>ThumbShots.de (Germany) robot</Description> |
||
19375 | <Type>R</Type> |
||
19376 | <Comment></Comment> |
||
19377 | <Link1>http://www.thumbshots.de/</Link1> |
||
19378 | <Link2></Link2> |
||
19379 | </user-agent> |
||
19380 | <user-agent> |
||
19381 | <ID>id_t_z_250206_1</ID> |
||
19382 | <String>timboBot/0.9 http://www.breakingblogs.com/timbo_bot.html</String> |
||
19383 | <Description>Breaking Blogs timbo bot blog robot</Description> |
||
19384 | <Type>R</Type> |
||
19385 | <Comment></Comment> |
||
19386 | <Link1>http://www.breakingblogs.com/</Link1> |
||
19387 | <Link2></Link2> |
||
19388 | </user-agent> |
||
19389 | <user-agent> |
||
19390 | <ID>id_t_z_140106_4</ID> |
||
19391 | <String>http://www.timelyweb.com/</String> |
||
19392 | <Description>TimelyWeb web page monitoring tool</Description> |
||
19393 | <Type>C</Type> |
||
19394 | <Comment>s. also EldoS ...</Comment> |
||
19395 | <Link1>http://www.eldos.org/timelyweb/timelyweb.html</Link1> |
||
19396 | <Link2></Link2> |
||
19397 | </user-agent> |
||
19398 | <user-agent> |
||
19399 | <ID>id_t_z_180408_6</ID> |
||
19400 | <String>TinEye/1.1 (http://tineye.com/crawler.html)</String> |
||
19401 | <Description>TinEye crawler for an open image search project</Description> |
||
19402 | <Type>R</Type> |
||
19403 | <Comment></Comment> |
||
19404 | <Link1>http://tineye.com/crawler.html</Link1> |
||
19405 | <Link2></Link2> |
||
19406 | </user-agent> |
||
19407 | <user-agent> |
||
19408 | <ID>id_t_z_1368</ID> |
||
19409 | <String>tivraSpider/1.0 (crawler@tivra.com)</String> |
||
19410 | <Description>Tivra spider from AT&T Labs Research</Description> |
||
19411 | <Type>R</Type> |
||
19412 | <Comment>see this document: http://trec.nist.gov/pubs/trec9/papers/att-trec9.ps</Comment> |
||
19413 | <Link1>http://trec.nist.gov/pubs/trec9/papers/att-trec9.ps</Link1> |
||
19414 | <Link2></Link2> |
||
19415 | </user-agent> |
||
19416 | <user-agent> |
||
19417 | <ID>id_t_z_1369</ID> |
||
19418 | <String>TJG/Spider</String> |
||
19419 | <Description>Tjgroup spider</Description> |
||
19420 | <Type>R</Type> |
||
19421 | <Comment></Comment> |
||
19422 | <Link1>http://www.tjgroup.com/</Link1> |
||
19423 | <Link2></Link2> |
||
19424 | </user-agent> |
||
19425 | <user-agent> |
||
19426 | <ID>id_t_z_1370</ID> |
||
19427 | <String>TJvMultiHttpGrabber Component</String> |
||
19428 | <Description>TJvHttpGrabber (JEDI Visual Component Library)</Description> |
||
19429 | <Type></Type> |
||
19430 | <Comment>Possibly used by Bit Torrent Search </Comment> |
||
19431 | <Link1>http://homepages.borland.com/jedi/jedihelp/item.php?Id=22015</Link1> |
||
19432 | <Link2>http://www.btsearch.net/</Link2> |
||
19433 | </user-agent> |
||
19434 | <user-agent> |
||
19435 | <ID>id_t_z_1371</ID> |
||
19436 | <String>Tkensaku/x.x(http://www.tkensaku.com/q.html)</String> |
||
19437 | <Description>Tkensaku Search (Japan) robot from 210.239.46.xxx (www.tken.com)</Description> |
||
19438 | <Type>R</Type> |
||
19439 | <Comment></Comment> |
||
19440 | <Link1>http://www.tkensaku.com/q.html</Link1> |
||
19441 | <Link2></Link2> |
||
19442 | </user-agent> |
||
19443 | <user-agent> |
||
19444 | <ID>id_t_z_1372</ID> |
||
19445 | <String>toCrawl/UrlDispatcher</String> |
||
19446 | <Description>Unknown robot from 195.68.98.xx (coltfrance.com)</Description> |
||
19447 | <Type></Type> |
||
19448 | <Comment></Comment> |
||
19449 | <Link1></Link1> |
||
19450 | <Link2></Link2> |
||
19451 | </user-agent> |
||
19452 | <user-agent> |
||
19453 | <ID>id_t_z_200207_1</ID> |
||
19454 | <String>Topodia/1.2-dev (Topodia - Crawler for HTTP content indexing; http://www.topodia.com/; support@topodia.com)</String> |
||
19455 | <Description>Topodia search engine and personal information assistant (in development)</Description> |
||
19456 | <Type>R</Type> |
||
19457 | <Comment>88.153.148.xx</Comment> |
||
19458 | <Link1>http://www.topodia.com/</Link1> |
||
19459 | <Link2></Link2> |
||
19460 | </user-agent> |
||
19461 | <user-agent> |
||
19462 | <ID>id_t_z_160506_2</ID> |
||
19463 | <String>TOPOS robot/1.1 (http://www.topos.com.ua/)</String> |
||
19464 | <Description>Topos search (Russia) robot</Description> |
||
19465 | <Type>C</Type> |
||
19466 | <Comment>193.17.73.1xx</Comment> |
||
19467 | <Link1>http://www.topos.com.ua/</Link1> |
||
19468 | <Link2></Link2> |
||
19469 | </user-agent> |
||
19470 | <user-agent> |
||
19471 | <ID>id_t_z_1373</ID> |
||
19472 | <String>Toutatis x-xx.x (hoppa.com)</String> |
||
19473 | <Description>Hoppa robot (81.4.78.xxx)</Description> |
||
19474 | <Type>R</Type> |
||
19475 | <Comment></Comment> |
||
19476 | <Link1>http://hoppa.com/</Link1> |
||
19477 | <Link2></Link2> |
||
19478 | </user-agent> |
||
19479 | <user-agent> |
||
19480 | <ID>id_t_z_1374</ID> |
||
19481 | <String>Toutatis x.x (hoppa.com)</String> |
||
19482 | <Description>Hoppa robot (81.4.78.xxx)</Description> |
||
19483 | <Type>R</Type> |
||
19484 | <Comment></Comment> |
||
19485 | <Link1>http://hoppa.com/</Link1> |
||
19486 | <Link2></Link2> |
||
19487 | </user-agent> |
||
19488 | <user-agent> |
||
19489 | <ID>id_t_z_1375</ID> |
||
19490 | <String>Toutatis x.x-x</String> |
||
19491 | <Description>Hoppa robot (81.4.78.xxx)</Description> |
||
19492 | <Type>R</Type> |
||
19493 | <Comment></Comment> |
||
19494 | <Link1>http://hoppa.com/</Link1> |
||
19495 | <Link2></Link2> |
||
19496 | </user-agent> |
||
19497 | <user-agent> |
||
19498 | <ID>id_t_z_050806_2</ID> |
||
19499 | <String>traazibot/testengine (+http://www.traazi.de)</String> |
||
19500 | <Description>Traazi! search (Germany) robot</Description> |
||
19501 | <Type>R</Type> |
||
19502 | <Comment>87.230.5.2xx</Comment> |
||
19503 | <Link1>http://www.traazi.de/</Link1> |
||
19504 | <Link2></Link2> |
||
19505 | </user-agent> |
||
19506 | <user-agent> |
||
19507 | <ID>id_t_z_041007_2</ID> |
||
19508 | <String>Trailfire-bot/0.7.1 (Nutch; http://lucene.apache.org/nutch/bot.html; nutch-agent@lucene.apache.org)</String> |
||
19509 | <Description>Trailfire web collection and annotating system</Description> |
||
19510 | <Type>C</Type> |
||
19511 | <Comment></Comment> |
||
19512 | <Link1>http://www.trailfire.com/</Link1> |
||
19513 | <Link2></Link2> |
||
19514 | </user-agent> |
||
19515 | <user-agent> |
||
19516 | <ID>id_t_z_081207_2</ID> |
||
19517 | <String>Trailfire-bot/0.7.1 (Trailfire page content analyzer; http://trailfire.com; info@trailfire.com)</String> |
||
19518 | <Description>Trailfire web collection and annotating system</Description> |
||
19519 | <Type>C</Type> |
||
19520 | <Comment></Comment> |
||
19521 | <Link1>http://www.trailfire.com/</Link1> |
||
19522 | <Link2></Link2> |
||
19523 | </user-agent> |
||
19524 | <user-agent> |
||
19525 | <ID>id_t_z_260807_2</ID> |
||
19526 | <String>Trailfire/0.7.1 (Nutch; http://lucene.apache.org/nutch/bot.html; nutch-agent@lucene.apache.org)</String> |
||
19527 | <Description>Trailfire web collection and annotating system</Description> |
||
19528 | <Type>C</Type> |
||
19529 | <Comment></Comment> |
||
19530 | <Link1>http://www.trailfire.com/</Link1> |
||
19531 | <Link2></Link2> |
||
19532 | </user-agent> |
||
19533 | <user-agent> |
||
19534 | <ID>id_t_z_1376</ID> |
||
19535 | <String>Trampelpfad-Spider</String> |
||
19536 | <Description>Trampelpfad Webkatalog spider</Description> |
||
19537 | <Type>R</Type> |
||
19538 | <Comment></Comment> |
||
19539 | <Link1>http://www2.trampelpfad.de/</Link1> |
||
19540 | <Link2></Link2> |
||
19541 | </user-agent> |
||
19542 | <user-agent> |
||
19543 | <ID>id_t_z_1377</ID> |
||
19544 | <String>Trampelpfad-Spider-v0.1</String> |
||
19545 | <Description>Trampelpfad Webkatalog spider</Description> |
||
19546 | <Type>R</Type> |
||
19547 | <Comment></Comment> |
||
19548 | <Link1>http://www2.trampelpfad.de/</Link1> |
||
19549 | <Link2></Link2> |
||
19550 | </user-agent> |
||
19551 | <user-agent> |
||
19552 | <ID>id_t_z_1378</ID> |
||
19553 | <String>tricosMetaCheck 1.2216-08-1999 (http://www.tricos.com/metacheck)</String> |
||
19554 | <Description>Tricos meta tag validation</Description> |
||
19555 | <Type>C</Type> |
||
19556 | <Comment></Comment> |
||
19557 | <Link1>http://www.tricos.us/metaone.php</Link1> |
||
19558 | <Link2></Link2> |
||
19559 | </user-agent> |
||
19560 | <user-agent> |
||
19561 | <ID>id_t_z_1379</ID> |
||
19562 | <String>TSurf15a 11</String> |
||
19563 | <Description>some bad user agent</Description> |
||
19564 | <Type>S</Type> |
||
19565 | <Comment>- s. DBrowse- Dsurf etc.</Comment> |
||
19566 | <Link1></Link1> |
||
19567 | <Link2></Link2> |
||
19568 | </user-agent> |
||
19569 | <user-agent> |
||
19570 | <ID>id_t_z_1380</ID> |
||
19571 | <String>TulipChain/5.x (http://ostermiller.org/tulipchain/) Java/1.x.1_0x (http://java.sun.com/) Linux/2.4.17</String> |
||
19572 | <Description>Tulip Chain browser / link checker for Dmoz.org directory</Description> |
||
19573 | <Type>B C R</Type> |
||
19574 | <Comment></Comment> |
||
19575 | <Link1>http://ostermiller.org/tulipchain/</Link1> |
||
19576 | <Link2></Link2> |
||
19577 | </user-agent> |
||
19578 | <user-agent> |
||
19579 | <ID>id_t_z_1381</ID> |
||
19580 | <String>TulipChain/5.xx (http://ostermiller.org/tulipchain/) Java/1.x.1_0x (http://apple.com/) Mac_OS_X/10.2.8</String> |
||
19581 | <Description>Tulip Chain browser / link checker for Dmoz.org directory</Description> |
||
19582 | <Type>B C R</Type> |
||
19583 | <Comment></Comment> |
||
19584 | <Link1>http://ostermiller.org/tulipchain/</Link1> |
||
19585 | <Link2></Link2> |
||
19586 | </user-agent> |
||
19587 | <user-agent> |
||
19588 | <ID>id_t_z_101107_3</ID> |
||
19589 | <String>Tumblr/1.0 RSS syndication (+http://www.tumblr.com/) (support@tumblr.com)</String> |
||
19590 | <Description>Tumblr Tumblelogs RSS and news syndication crawler</Description> |
||
19591 | <Type>R</Type> |
||
19592 | <Comment>72.32.6.15x</Comment> |
||
19593 | <Link1>http://www.tumblr.com/</Link1> |
||
19594 | <Link2></Link2> |
||
19595 | </user-agent> |
||
19596 | <user-agent> |
||
19597 | <ID>id_t_z_1382</ID> |
||
19598 | <String>TurnitinBot/x.x (http://www.turnitin.com/robot/crawlerinfo.html)</String> |
||
19599 | <Description>Turnitin (ex SlySearch) robot for helping educational institutions prevent plagiarism</Description> |
||
19600 | <Type>R</Type> |
||
19601 | <Comment>64.140.49.xx</Comment> |
||
19602 | <Link1>http://www.turnitin.com/robot/crawlerinfo.html</Link1> |
||
19603 | <Link2></Link2> |
||
19604 | </user-agent> |
||
19605 | <user-agent> |
||
19606 | <ID>id_t_z_1383</ID> |
||
19607 | <String>Turnpike Emporium LinkChecker/0.1</String> |
||
19608 | <Description>TurnPike Emporium Directory (207.67.198.x) link checking</Description> |
||
19609 | <Type>R</Type> |
||
19610 | <Comment></Comment> |
||
19611 | <Link1>http://www.turnpike.net/directory.phtml</Link1> |
||
19612 | <Link2></Link2> |
||
19613 | </user-agent> |
||
19614 | <user-agent> |
||
19615 | <ID>id_t_z_1384</ID> |
||
19616 | <String>TutorGig/1.5 (+http://www.tutorgig.com/crawler)</String> |
||
19617 | <Description>TutorGig tutorial search robot</Description> |
||
19618 | <Type>R</Type> |
||
19619 | <Comment></Comment> |
||
19620 | <Link1>http://www.tutorgig.com/crawler/</Link1> |
||
19621 | <Link2></Link2> |
||
19622 | </user-agent> |
||
19623 | <user-agent> |
||
19624 | <ID>id_t_z_1385</ID> |
||
19625 | <String>Tutorial Crawler 1.4 (http://www.tutorgig.com/crawler)</String> |
||
19626 | <Description>TutorGig tutorial search robot</Description> |
||
19627 | <Type>R</Type> |
||
19628 | <Comment></Comment> |
||
19629 | <Link1>http://www.tutorgig.com/crawler/</Link1> |
||
19630 | <Link2></Link2> |
||
19631 | </user-agent> |
||
19632 | <user-agent> |
||
19633 | <ID>id_t_z_1386</ID> |
||
19634 | <String>Twiceler www.cuill.com/robots.html</String> |
||
19635 | <Description>Twiceler experimental web crawler</Description> |
||
19636 | <Type>R</Type> |
||
19637 | <Comment>64.62.136.xxx</Comment> |
||
19638 | <Link1>http://www.cuill.com/</Link1> |
||
19639 | <Link2></Link2> |
||
19640 | </user-agent> |
||
19641 | <user-agent> |
||
19642 | <ID>id_t_z_290407_1</ID> |
||
19643 | <String>Twiceler-0.9 http://www.cuill.com/twiceler/robot.html</String> |
||
19644 | <Description>Twiceler experimental web crawler</Description> |
||
19645 | <Type>R</Type> |
||
19646 | <Comment>64.62.136.xxx</Comment> |
||
19647 | <Link1>http://www.cuill.com/</Link1> |
||
19648 | <Link2></Link2> |
||
19649 | </user-agent> |
||
19650 | <user-agent> |
||
19651 | <ID>id_t_z_291105_5</ID> |
||
19652 | <String>Twisted PageGetter</String> |
||
19653 | <Description>File downloading component from Twisted Python</Description> |
||
19654 | <Type>D</Type> |
||
19655 | <Comment></Comment> |
||
19656 | <Link1>http://twistedmatrix.com/</Link1> |
||
19657 | <Link2></Link2> |
||
19658 | </user-agent> |
||
19659 | <user-agent> |
||
19660 | <ID>id_t_z_140508_5</ID> |
||
19661 | <String>Twitturly / v0.x</String> |
||
19662 | <Description>Twitt(url)y URL tracking service for Twitter via Amazon Web Services</Description> |
||
19663 | <Type>C</Type> |
||
19664 | <Comment>75.101.135.[x]xx</Comment> |
||
19665 | <Link1>http://twitturly.com/</Link1> |
||
19666 | <Link2>http://twitter.com/</Link2> |
||
19667 | </user-agent> |
||
19668 | <user-agent> |
||
19669 | <ID>id_t_z_1387</ID> |
||
19670 | <String>Twotrees Reactive Filter V2.0</String> |
||
19671 | <Description>Twotrees content filter</Description> |
||
19672 | <Type>P</Type> |
||
19673 | <Comment></Comment> |
||
19674 | <Link1>http://www.twotrees.com/</Link1> |
||
19675 | <Link2></Link2> |
||
19676 | </user-agent> |
||
19677 | <user-agent> |
||
19678 | <ID>id_t_z_221207_2</ID> |
||
19679 | <String>Tycoon Agent/Nutch-1.0-dev</String> |
||
19680 | <Description>Tycoon - Hewlett-Packards distributed cluster solution robot</Description> |
||
19681 | <Type>R</Type> |
||
19682 | <Comment>204.123.46.xx[x]</Comment> |
||
19683 | <Link1>http://tycoon.hpl.hp.com/</Link1> |
||
19684 | <Link2></Link2> |
||
19685 | </user-agent> |
||
19686 | <user-agent> |
||
19687 | <ID>id_t_z_1388</ID> |
||
19688 | <String>TygoBot</String> |
||
19689 | <Description>Tygo Search robot</Description> |
||
19690 | <Type>R</Type> |
||
19691 | <Comment></Comment> |
||
19692 | <Link1>http://www.tygo.com/</Link1> |
||
19693 | <Link2></Link2> |
||
19694 | </user-agent> |
||
19695 | <user-agent> |
||
19696 | <ID>id_t_z_1389</ID> |
||
19697 | <String>TygoProwler</String> |
||
19698 | <Description>Tygo Search robot</Description> |
||
19699 | <Type>R</Type> |
||
19700 | <Comment></Comment> |
||
19701 | <Link1>http://www.tygo.com/</Link1> |
||
19702 | <Link2></Link2> |
||
19703 | </user-agent> |
||
19704 | <user-agent> |
||
19705 | <ID>id_t_z_1390</ID> |
||
19706 | <String>UCmore</String> |
||
19707 | <Description>UCMore - IE navigation and search plugin</Description> |
||
19708 | <Type>B</Type> |
||
19709 | <Comment></Comment> |
||
19710 | <Link1>http://www.ucmore.com/</Link1> |
||
19711 | <Link2></Link2> |
||
19712 | </user-agent> |
||
19713 | <user-agent> |
||
19714 | <ID>id_t_z_1391</ID> |
||
19715 | <String>UCMore Crawler App</String> |
||
19716 | <Description>UCMore - IE navigation and search plugin</Description> |
||
19717 | <Type>B</Type> |
||
19718 | <Comment></Comment> |
||
19719 | <Link1>http://www.ucmore.com/</Link1> |
||
19720 | <Link2></Link2> |
||
19721 | </user-agent> |
||
19722 | <user-agent> |
||
19723 | <ID>id_t_z_290208_1</ID> |
||
19724 | <String>UCWEB5.1</String> |
||
19725 | <Description>Ucweb mobile browser</Description> |
||
19726 | <Type>B</Type> |
||
19727 | <Comment></Comment> |
||
19728 | <Link1>http://www.ucweb.com/English/product.shtml</Link1> |
||
19729 | <Link2></Link2> |
||
19730 | </user-agent> |
||
19731 | <user-agent> |
||
19732 | <ID>id_t_z_1392</ID> |
||
19733 | <String>UDM</String> |
||
19734 | <Description>user agent - maybe UdmSearch (see UdmSearch) ?</Description> |
||
19735 | <Type></Type> |
||
19736 | <Comment></Comment> |
||
19737 | <Link1></Link1> |
||
19738 | <Link2></Link2> |
||
19739 | </user-agent> |
||
19740 | <user-agent> |
||
19741 | <ID>id_t_z_1393</ID> |
||
19742 | <String>UdmSearch/3.1.x</String> |
||
19743 | <Description>UdmSearch / MySearch (now mnoGoSeach) offline browser/search client</Description> |
||
19744 | <Type>R B</Type> |
||
19745 | <Comment></Comment> |
||
19746 | <Link1>http://mnogosearch.org/</Link1> |
||
19747 | <Link2></Link2> |
||
19748 | </user-agent> |
||
19749 | <user-agent> |
||
19750 | <ID>id_t_z_1394</ID> |
||
19751 | <String>UIowaCrawler/1.0</String> |
||
19752 | <Description>University of Iowa Crawler- possibly MySpiders</Description> |
||
19753 | <Type>R</Type> |
||
19754 | <Comment></Comment> |
||
19755 | <Link1>http://myspiders.biz.uiowa.edu/</Link1> |
||
19756 | <Link2></Link2> |
||
19757 | </user-agent> |
||
19758 | <user-agent> |
||
19759 | <ID>id_t_z_231106_1</ID> |
||
19760 | <String>UKWizz/Nutch-0.8.1 (UKWizz Nutch crawler; http://www.ukwizz.com/)</String> |
||
19761 | <Description>UKWizz search robot</Description> |
||
19762 | <Type>R</Type> |
||
19763 | <Comment>s. also Mackster</Comment> |
||
19764 | <Link1>http://www.ukwizz.com</Link1> |
||
19765 | <Link2></Link2> |
||
19766 | </user-agent> |
||
19767 | <user-agent> |
||
19768 | <ID>id_t_z_1395</ID> |
||
19769 | <String>Ultraseek</String> |
||
19770 | <Description>Infoseek robot</Description> |
||
19771 | <Type>R</Type> |
||
19772 | <Comment></Comment> |
||
19773 | <Link1>http://www.infoseek.com/</Link1> |
||
19774 | <Link2></Link2> |
||
19775 | </user-agent> |
||
19776 | <user-agent> |
||
19777 | <ID>id_t_z_1396</ID> |
||
19778 | <String>Under the Rainbow 2.2</String> |
||
19779 | <Description>Unknown mail harvester/spambot from 80.58.13.xxx (proxycache.rima-tde.net)</Description> |
||
19780 | <Type>S</Type> |
||
19781 | <Comment></Comment> |
||
19782 | <Link1>http://www.honeypot.be/</Link1> |
||
19783 | <Link2></Link2> |
||
19784 | </user-agent> |
||
19785 | <user-agent> |
||
19786 | <ID>id_a_f_140308_1</ID> |
||
19787 | <String>unknownght.com Web Server IIS vs Apache Survey. See Results at www.DNSRight.com</String> |
||
19788 | <Description>DNS Right - Online DNS tools</Description> |
||
19789 | <Type>C</Type> |
||
19790 | <Comment>203.161.71.17x</Comment> |
||
19791 | <Link1>http://www.dnsright.com/</Link1> |
||
19792 | <Link2></Link2> |
||
19793 | </user-agent> |
||
19794 | <user-agent> |
||
19795 | <ID>id_t_z_1397</ID> |
||
19796 | <String>UofTDB_experiment (leehyun@cs.toronto.edu)</String> |
||
19797 | <Description>Unknown robot from University of Toronto (128.100.5.1xx)</Description> |
||
19798 | <Type>R</Type> |
||
19799 | <Comment></Comment> |
||
19800 | <Link1></Link1> |
||
19801 | <Link2></Link2> |
||
19802 | </user-agent> |
||
19803 | <user-agent> |
||
19804 | <ID>id_t_z_1398</ID> |
||
19805 | <String>UP.Browser/3.01-IG01 UP.Link/3.2.3.4</String> |
||
19806 | <Description>Mobile phone browser</Description> |
||
19807 | <Type>B</Type> |
||
19808 | <Comment></Comment> |
||
19809 | <Link1></Link1> |
||
19810 | <Link2></Link2> |
||
19811 | </user-agent> |
||
19812 | <user-agent> |
||
19813 | <ID>id_t_z_050806_1</ID> |
||
19814 | <String>updated/0.1-alpha (updated crawler; http://www.updated.com; crawler@updated.com)</String> |
||
19815 | <Description>Updated! search robot</Description> |
||
19816 | <Type>R</Type> |
||
19817 | <Comment>38.119.96.1xx</Comment> |
||
19818 | <Link1>http://www.updated.com/</Link1> |
||
19819 | <Link2></Link2> |
||
19820 | </user-agent> |
||
19821 | <user-agent> |
||
19822 | <ID>id_t_z_1399</ID> |
||
19823 | <String>updated/0.1beta (updated.com; http://www.updated.com; crawler@updated.om)</String> |
||
19824 | <Description>Updated! search robot</Description> |
||
19825 | <Type>R</Type> |
||
19826 | <Comment>38.119.96.1xx</Comment> |
||
19827 | <Link1>http://www.updated.com/</Link1> |
||
19828 | <Link2></Link2> |
||
19829 | </user-agent> |
||
19830 | <user-agent> |
||
19831 | <ID>id_t_z_1400</ID> |
||
19832 | <String>UPG1 UP/4.0 (compatible; Blazer 1.0)</String> |
||
19833 | <Description>Handspring (PalmOS powered cellphone) Treo Blazer browser</Description> |
||
19834 | <Type>B</Type> |
||
19835 | <Comment></Comment> |
||
19836 | <Link1></Link1> |
||
19837 | <Link2></Link2> |
||
19838 | </user-agent> |
||
19839 | <user-agent> |
||
19840 | <ID>id_t_z_1401</ID> |
||
19841 | <String>Uptimebot</String> |
||
19842 | <Description>UptimeBot.com online link popularity check</Description> |
||
19843 | <Type>R</Type> |
||
19844 | <Comment></Comment> |
||
19845 | <Link1>http://www.uptimebot.com/</Link1> |
||
19846 | <Link2></Link2> |
||
19847 | </user-agent> |
||
19848 | <user-agent> |
||
19849 | <ID>id_t_z_1402</ID> |
||
19850 | <String>UptimeBot(www.uptimebot.com)</String> |
||
19851 | <Description>UptimeBot.com online link popularity check</Description> |
||
19852 | <Type>R</Type> |
||
19853 | <Comment></Comment> |
||
19854 | <Link1>http://www.uptimebot.com/</Link1> |
||
19855 | <Link2></Link2> |
||
19856 | </user-agent> |
||
19857 | <user-agent> |
||
19858 | <ID>id_t_z_160706_2</ID> |
||
19859 | <String>URI::Fetch/0.06</String> |
||
19860 | <Description>URI::Fetch - client for fetching HTTP pages and syndication feeds (RSS Atom)</Description> |
||
19861 | <Type>D</Type> |
||
19862 | <Comment></Comment> |
||
19863 | <Link1>http://search.cpan.org/dist/URI-Fetch/</Link1> |
||
19864 | <Link2></Link2> |
||
19865 | </user-agent> |
||
19866 | <user-agent> |
||
19867 | <ID>id_t_z_1403</ID> |
||
19868 | <String>URL Spider Pro/x.xx (innerprise.net)</String> |
||
19869 | <Description>Innerprise URL Spider Pro (now ES.NET) web indexing / site searching tool</Description> |
||
19870 | <Type>R</Type> |
||
19871 | <Comment></Comment> |
||
19872 | <Link1>http://www.innerprise.net/</Link1> |
||
19873 | <Link2></Link2> |
||
19874 | </user-agent> |
||
19875 | <user-agent> |
||
19876 | <ID>id_t_z_121106_2</ID> |
||
19877 | <String>URLBase/6.x</String> |
||
19878 | <Description>URLBase - Internet shortcut manager</Description> |
||
19879 | <Type>C</Type> |
||
19880 | <Comment>s. also Mozilla/4.0 (Compatible); URLBase 6</Comment> |
||
19881 | <Link1>http://www.terriadev.com/products/urlbase/</Link1> |
||
19882 | <Link2></Link2> |
||
19883 | </user-agent> |
||
19884 | <user-agent> |
||
19885 | <ID>id_t_z_1406</ID> |
||
19886 | <String>URLBlaze</String> |
||
19887 | <Description>URLBlaze file sharing link toolkit</Description> |
||
19888 | <Type>C</Type> |
||
19889 | <Comment></Comment> |
||
19890 | <Link1>http://www.urlblaze.net/</Link1> |
||
19891 | <Link2></Link2> |
||
19892 | </user-agent> |
||
19893 | <user-agent> |
||
19894 | <ID>id_t_z_011108_4</ID> |
||
19895 | <String>urlfan-bot/1.0; +http://www.urlfan.com/site/bot/350.html</String> |
||
19896 | <Description>://URLFAN news crawler</Description> |
||
19897 | <Type>R</Type> |
||
19898 | <Comment>70.165.48.16x</Comment> |
||
19899 | <Link1>http://www.urlfan.com/</Link1> |
||
19900 | <Link2></Link2> |
||
19901 | </user-agent> |
||
19902 | <user-agent> |
||
19903 | <ID>id_t_z_1407</ID> |
||
19904 | <String>URLGetFile</String> |
||
19905 | <Description>URLGetFile downloading tool</Description> |
||
19906 | <Type>D</Type> |
||
19907 | <Comment></Comment> |
||
19908 | <Link1>http://shazron.com/freeware/java-utils/</Link1> |
||
19909 | <Link2></Link2> |
||
19910 | </user-agent> |
||
19911 | <user-agent> |
||
19912 | <ID>id_t_z_1404</ID> |
||
19913 | <String>URL_Spider_Pro/x.x</String> |
||
19914 | <Description>Innerprise URL Spider Pro (now ES.NET) web indexing / site searching tool</Description> |
||
19915 | <Type>R</Type> |
||
19916 | <Comment></Comment> |
||
19917 | <Link1>http://www.innerprise.net/</Link1> |
||
19918 | <Link2></Link2> |
||
19919 | </user-agent> |
||
19920 | <user-agent> |
||
19921 | <ID>id_t_z_1405</ID> |
||
19922 | <String>URL_Spider_Pro/x.x+(http://www.innerprise.net/usp-spider.asp)</String> |
||
19923 | <Description>Innerprise URL Spider Pro (now ES.NET) web indexing / site searching tool</Description> |
||
19924 | <Type>R</Type> |
||
19925 | <Comment></Comment> |
||
19926 | <Link1>http://www.innerprise.net/</Link1> |
||
19927 | <Link2></Link2> |
||
19928 | </user-agent> |
||
19929 | <user-agent> |
||
19930 | <ID>id_t_z_291006_1</ID> |
||
19931 | <String>User-Agent: BoardReader Favicon Fetcher /1.0 info@boardreader.com</String> |
||
19932 | <Description>BoardReader search favicon fetcher</Description> |
||
19933 | <Type>D</Type> |
||
19934 | <Comment>208.65.71.xx</Comment> |
||
19935 | <Link1>http://www.boardreader.com/</Link1> |
||
19936 | <Link2>http://www.internetadsales.com/modules/news/article.php?storyid=4050</Link2> |
||
19937 | </user-agent> |
||
19938 | <user-agent> |
||
19939 | <ID>id_t_z_081206_1</ID> |
||
19940 | <String>User-Agent: BoardReader Image Fetcher /1.0 info@boardreader.com</String> |
||
19941 | <Description>BoardReader search image fetcher</Description> |
||
19942 | <Type>D</Type> |
||
19943 | <Comment>208.65.71.xx</Comment> |
||
19944 | <Link1>http://www.boardreader.com/</Link1> |
||
19945 | <Link2>http://www.internetadsales.com/modules/news/article.php?storyid=4050</Link2> |
||
19946 | </user-agent> |
||
19947 | <user-agent> |
||
19948 | <ID>id_t_z_060206_2</ID> |
||
19949 | <String>User-Agent: LjSEEK Picture-Bot /1.0 contact@ljseek.com</String> |
||
19950 | <Description>ljpic.com - LiveJournal picture feed search</Description> |
||
19951 | <Type>C</Type> |
||
19952 | <Comment></Comment> |
||
19953 | <Link1>http://www.ljpic.com/</Link1> |
||
19954 | <Link2></Link2> |
||
19955 | </user-agent> |
||
19956 | <user-agent> |
||
19957 | <ID>id_t_z_1408</ID> |
||
19958 | <String>User-Agent: FileHeap! file downloader (http://www.fileheap.com)</String> |
||
19959 | <Description>FileHeap download manager</Description> |
||
19960 | <Type>D</Type> |
||
19961 | <Comment></Comment> |
||
19962 | <Link1>http://www.fileheap.com</Link1> |
||
19963 | <Link2></Link2> |
||
19964 | </user-agent> |
||
19965 | <user-agent> |
||
19966 | <ID>id_t_z_270306_2</ID> |
||
19967 | <String>User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)</String> |
||
19968 | <Description>Malformed UA header from some guestbook/forum spammer</Description> |
||
19969 | <Type>S</Type> |
||
19970 | <Comment></Comment> |
||
19971 | <Link1></Link1> |
||
19972 | <Link2></Link2> |
||
19973 | </user-agent> |
||
19974 | <user-agent> |
||
19975 | <ID>id_t_z_1409</ID> |
||
19976 | <String>User-Agent: Mozilla/4.0 (SKIZZLE! Distributed Internet Spider v1.0 - www.SKIZZLE.com)</String> |
||
19977 | <Description>Skizzle search robot</Description> |
||
19978 | <Type>R</Type> |
||
19979 | <Comment></Comment> |
||
19980 | <Link1>http://www.skizzle.com/</Link1> |
||
19981 | <Link2></Link2> |
||
19982 | </user-agent> |
||
19983 | <user-agent> |
||
19984 | <ID>id_t_z_1410</ID> |
||
19985 | <String>user-agent=Mozilla/3.01Gold</String> |
||
19986 | <Description>unknown robot (reads robots.txt) or sitegrabber. From different IPs- ie.: 62.98.8.xx (wind.it)</Description> |
||
19987 | <Type>R D ?</Type> |
||
19988 | <Comment></Comment> |
||
19989 | <Link1></Link1> |
||
19990 | <Link2></Link2> |
||
19991 | </user-agent> |
||
19992 | <user-agent> |
||
19993 | <ID>id_t_z_1411</ID> |
||
19994 | <String>USyd-NLP-Spider (http://www.it.usyd.edu.au/~vinci/bot.html)</String> |
||
19995 | <Description>University of Sydney NLP Spider for research in Natural Language Processing </Description> |
||
19996 | <Type>R</Type> |
||
19997 | <Comment></Comment> |
||
19998 | <Link1>http://www.it.usyd.edu.au/~vinci/bot.html</Link1> |
||
19999 | <Link2></Link2> |
||
20000 | </user-agent> |
||
20001 | <user-agent> |
||
20002 | <ID>id_t_z_1412</ID> |
||
20003 | <String>UtilMind HTTPGet</String> |
||
20004 | <Description>Web Thief Site Grabber</Description> |
||
20005 | <Type>D</Type> |
||
20006 | <Comment></Comment> |
||
20007 | <Link1>http://www.utilmind.com/scripts/webthief.html</Link1> |
||
20008 | <Link2></Link2> |
||
20009 | </user-agent> |
||
20010 | <user-agent> |
||
20011 | <ID>id_t_z_1413</ID> |
||
20012 | <String>Utopia WebWasher 3.0</String> |
||
20013 | <Description>WebWasher ad filter</Description> |
||
20014 | <Type>P B</Type> |
||
20015 | <Comment></Comment> |
||
20016 | <Link1>http://www.webwasher.com/</Link1> |
||
20017 | <Link2></Link2> |
||
20018 | </user-agent> |
||
20019 | <user-agent> |
||
20020 | <ID>id_t_z_100406_1</ID> |
||
20021 | <String>uTorrent/1500</String> |
||
20022 | <Description>uTorrent BitTorrent client</Description> |
||
20023 | <Type>D</Type> |
||
20024 | <Comment></Comment> |
||
20025 | <Link1>http://www.utorrent.com/</Link1> |
||
20026 | <Link2></Link2> |
||
20027 | </user-agent> |
||
20028 | <user-agent> |
||
20029 | <ID>id_t_z_060108_2</ID> |
||
20030 | <String>VadixBot</String> |
||
20031 | <Description>Unknown bad behaving bot via Road Runner - see link</Description> |
||
20032 | <Type>S</Type> |
||
20033 | <Comment>67.78.34.1[6-7][0-9] - 70.112.211.2x</Comment> |
||
20034 | <Link1>http://mikesblog.americasdebate.com/2007/06/06/vadixbot-look-out/</Link1> |
||
20035 | <Link2></Link2> |
||
20036 | </user-agent> |
||
20037 | <user-agent> |
||
20038 | <ID>id_t_z_050406_4</ID> |
||
20039 | <String>Vagabondo-WAP/2.0 (webcrawler at wise-guys dot nl; http://webagent.wise-guys.nl/)/1.0 Profile</String> |
||
20040 | <Description>WiseGuys WAP pages robot</Description> |
||
20041 | <Type>R</Type> |
||
20042 | <Comment></Comment> |
||
20043 | <Link1>http://www.wise-guys.nl/Contact/index.php?botselected=webagents&lang=uk</Link1> |
||
20044 | <Link2></Link2> |
||
20045 | </user-agent> |
||
20046 | <user-agent> |
||
20047 | <ID>id_t_z_1414</ID> |
||
20048 | <String>Vagabondo/1.x MT (webagent@wise-guys.nl)</String> |
||
20049 | <Description>WiseGuys robot Netherland - 82.94.216.2</Description> |
||
20050 | <Type>R</Type> |
||
20051 | <Comment>s. also Mozilla/3.0 (Vagabondo...</Comment> |
||
20052 | <Link1>http://www.wise-guys.nl/Contact/index.php?botselected=webagents&lang=uk</Link1> |
||
20053 | <Link2></Link2> |
||
20054 | </user-agent> |
||
20055 | <user-agent> |
||
20056 | <ID>id_t_z_1415</ID> |
||
20057 | <String>Vagabondo/2.0 MT</String> |
||
20058 | <Description>WiseGuys robot Netherland - 82.94.216.2</Description> |
||
20059 | <Type>R</Type> |
||
20060 | <Comment>s. also Mozilla/3.0 (Vagabondo...</Comment> |
||
20061 | <Link1>http://www.wise-guys.nl/Contact/index.php?botselected=webagents&lang=uk</Link1> |
||
20062 | <Link2></Link2> |
||
20063 | </user-agent> |
||
20064 | <user-agent> |
||
20065 | <ID>id_t_z_1416</ID> |
||
20066 | <String>Vagabondo/2.0 MT (webagent at wise-guys dot nl)</String> |
||
20067 | <Description>WiseGuys robot Netherland - 82.94.216.2</Description> |
||
20068 | <Type>R</Type> |
||
20069 | <Comment>s. also Mozilla/3.0 (Vagabondo...</Comment> |
||
20070 | <Link1>http://www.wise-guys.nl/Contact/index.php?botselected=webagents&lang=uk</Link1> |
||
20071 | <Link2></Link2> |
||
20072 | </user-agent> |
||
20073 | <user-agent> |
||
20074 | <ID>id_t_z_1417</ID> |
||
20075 | <String>Vagabondo/2.0 MT (webagent@NOSPAMwise-guys.nl)</String> |
||
20076 | <Description>WiseGuys robot Netherland - 82.94.216.2</Description> |
||
20077 | <Type>R</Type> |
||
20078 | <Comment>s. also Mozilla/3.0 (Vagabondo...</Comment> |
||
20079 | <Link1>http://www.wise-guys.nl/Contact/index.php?botselected=webagents&lang=uk</Link1> |
||
20080 | <Link2></Link2> |
||
20081 | </user-agent> |
||
20082 | <user-agent> |
||
20083 | <ID>id_t_z_021205_2</ID> |
||
20084 | <String>Vagabondo/3.0 (webagent at wise-guys dot nl)</String> |
||
20085 | <Description>WiseGuys robot Netherland - 82.94.216.2</Description> |
||
20086 | <Type>R</Type> |
||
20087 | <Comment>s.also - Mozilla/3.0 (Vagabondo...</Comment> |
||
20088 | <Link1>http://www.wise-guys.nl/Contact/index.php?botselected=webagents&lang=uk</Link1> |
||
20089 | <Link2></Link2> |
||
20090 | </user-agent> |
||
20091 | <user-agent> |
||
20092 | <ID>id_t_z_1418</ID> |
||
20093 | <String>Vakes/0.01 (Vakes; http://www.vakes.com/; search@vakes.com)</String> |
||
20094 | <Description>Open Directory link checking from Vakes</Description> |
||
20095 | <Type>R</Type> |
||
20096 | <Comment></Comment> |
||
20097 | <Link1>http://www.vakes.com/</Link1> |
||
20098 | <Link2></Link2> |
||
20099 | </user-agent> |
||
20100 | <user-agent> |
||
20101 | <ID>id_t_z_1420</ID> |
||
20102 | <String>VayalaCreep-v0.0.1 (haploid@haploid.com)</String> |
||
20103 | <Description>unknown level3.net (63.214.172.xxx) robot</Description> |
||
20104 | <Type></Type> |
||
20105 | <Comment></Comment> |
||
20106 | <Link1></Link1> |
||
20107 | <Link2></Link2> |
||
20108 | </user-agent> |
||
20109 | <user-agent> |
||
20110 | <ID>id_t_z_1419</ID> |
||
20111 | <String>Vayala|Creep-v0.0.1 (codepoet@wildties.com)</String> |
||
20112 | <Description>unknown level3.net (63.214.172.xxx) robot</Description> |
||
20113 | <Type></Type> |
||
20114 | <Comment></Comment> |
||
20115 | <Link1></Link1> |
||
20116 | <Link2></Link2> |
||
20117 | </user-agent> |
||
20118 | <user-agent> |
||
20119 | <ID>id_t_z_1421</ID> |
||
20120 | <String>vb wininet</String> |
||
20121 | <Description>iNet Grabber - Internet content grabber</Description> |
||
20122 | <Type>D</Type> |
||
20123 | <Comment></Comment> |
||
20124 | <Link1>http://www.aldostools.com/igrabber.html</Link1> |
||
20125 | <Link2></Link2> |
||
20126 | </user-agent> |
||
20127 | <user-agent> |
||
20128 | <ID>id_t_z_1422</ID> |
||
20129 | <String>versus 0.2 (+http://versus.integis.ch)</String> |
||
20130 | <Description>Versus Project robot - Comparing methods for near-uniform URL sampling</Description> |
||
20131 | <Type>R</Type> |
||
20132 | <Comment></Comment> |
||
20133 | <Link1>http://versus.integis.ch/</Link1> |
||
20134 | <Link2></Link2> |
||
20135 | </user-agent> |
||
20136 | <user-agent> |
||
20137 | <ID>id_t_z_1423</ID> |
||
20138 | <String>versus crawler eda.baykan@epfl.ch</String> |
||
20139 | <Description>Unknown robot from EPFL University Switzerland (128.178.155.xxx)</Description> |
||
20140 | <Type>R</Type> |
||
20141 | <Comment></Comment> |
||
20142 | <Link1>http://www.epfl.ch/Eindex.html</Link1> |
||
20143 | <Link2></Link2> |
||
20144 | </user-agent> |
||
20145 | <user-agent> |
||
20146 | <ID>id_t_z_120408_1</ID> |
||
20147 | <String>Verticrawlbot</String> |
||
20148 | <Description>Verticrawl - Semantic search engine solution (French)</Description> |
||
20149 | <Type>C</Type> |
||
20150 | <Comment></Comment> |
||
20151 | <Link1>http://www.verticrawl.com/fr/homepage.php</Link1> |
||
20152 | <Link2></Link2> |
||
20153 | </user-agent> |
||
20154 | <user-agent> |
||
20155 | <ID>id_t_z_1424</ID> |
||
20156 | <String>VeryGoodSearch.com.DaddyLongLegs</String> |
||
20157 | <Description>VeryGoodSearch.com link submission checking</Description> |
||
20158 | <Type>R</Type> |
||
20159 | <Comment></Comment> |
||
20160 | <Link1>http://www.verygoodsearch.com/</Link1> |
||
20161 | <Link2></Link2> |
||
20162 | </user-agent> |
||
20163 | <user-agent> |
||
20164 | <ID>id_t_z_1425</ID> |
||
20165 | <String>verzamelgids.nl - Networking4all Bot/x.x</String> |
||
20166 | <Description>Verzamelgids NL link checking robot</Description> |
||
20167 | <Type>R</Type> |
||
20168 | <Comment>213.247.50.xx</Comment> |
||
20169 | <Link1>http://www.verzamelgids.nl/</Link1> |
||
20170 | <Link2></Link2> |
||
20171 | </user-agent> |
||
20172 | <user-agent> |
||
20173 | <ID>id_t_z_181006_2</ID> |
||
20174 | <String>Verzamelgids/2.2 (http://www.verzamelgids.nl)</String> |
||
20175 | <Description>Verzamelgids NL link checking robot</Description> |
||
20176 | <Type>R</Type> |
||
20177 | <Comment>213.247.50.xx</Comment> |
||
20178 | <Link1>http://www.verzamelgids.nl/</Link1> |
||
20179 | <Link2></Link2> |
||
20180 | </user-agent> |
||
20181 | <user-agent> |
||
20182 | <ID>id_t_z_030406_1</ID> |
||
20183 | <String>Vespa Crawler</String> |
||
20184 | <Description>Unknown robot from Yahoo Norway</Description> |
||
20185 | <Type>R</Type> |
||
20186 | <Comment>217.144.236.x</Comment> |
||
20187 | <Link1>http://no.yahoo.com/</Link1> |
||
20188 | <Link2></Link2> |
||
20189 | </user-agent> |
||
20190 | <user-agent> |
||
20191 | <ID>id_t_z_190206_1</ID> |
||
20192 | <String>virus_detector (virus_harvester@securecomputing.com)</String> |
||
20193 | <Description>Sidewinder G2 anti-virus and anti-spyware protection</Description> |
||
20194 | <Type>D</Type> |
||
20195 | <Comment></Comment> |
||
20196 | <Link1>http://www.securecomputing.com/sg2_antivirus.cfm?menu=solutions</Link1> |
||
20197 | <Link2></Link2> |
||
20198 | </user-agent> |
||
20199 | <user-agent> |
||
20200 | <ID>id_t_z_140407_1</ID> |
||
20201 | <String>VisBot/2.0 (Visvo.com Crawler; http://www.visvo.com/bot.html; bot@visvo.com)</String> |
||
20202 | <Description>Visbot crawler for a search software under development</Description> |
||
20203 | <Type>R</Type> |
||
20204 | <Comment>63.133.162..xx</Comment> |
||
20205 | <Link1>http://www.visvo.com/bot.html</Link1> |
||
20206 | <Link2></Link2> |
||
20207 | </user-agent> |
||
20208 | <user-agent> |
||
20209 | <ID>id_t_z_1426</ID> |
||
20210 | <String>Visicom Toolbar</String> |
||
20211 | <Description>Some IE toolbar made with Visicom Media Dynamic Toolbar software</Description> |
||
20212 | <Type>B</Type> |
||
20213 | <Comment></Comment> |
||
20214 | <Link1>http://www.dynamictoolbar.com/en/products/toolbar/</Link1> |
||
20215 | <Link2></Link2> |
||
20216 | </user-agent> |
||
20217 | <user-agent> |
||
20218 | <ID>id_t_z_1427</ID> |
||
20219 | <String>Vision Research Lab image spider at vision.ece.ucsb.edu</String> |
||
20220 | <Description>Vision research lab's Cortina - content based image retrieval (128.111.60.xx)</Description> |
||
20221 | <Type>R</Type> |
||
20222 | <Comment></Comment> |
||
20223 | <Link1>http://vision.ece.ucsb.edu/multimedia/cortina.html</Link1> |
||
20224 | <Link2></Link2> |
||
20225 | </user-agent> |
||
20226 | <user-agent> |
||
20227 | <ID>id_t_z_160906_1</ID> |
||
20228 | <String>VLC media player - version 0.8.5 Janus - (c) 1996-2006 the VideoLAN team</String> |
||
20229 | <Description>VLC - Cross-platform media player and streaming server</Description> |
||
20230 | <Type>B</Type> |
||
20231 | <Comment></Comment> |
||
20232 | <Link1>http://www.videolan.org/vlc/</Link1> |
||
20233 | <Link2></Link2> |
||
20234 | </user-agent> |
||
20235 | <user-agent> |
||
20236 | <ID>id_t_z_140806_1</ID> |
||
20237 | <String>VMBot/0.x.x (VMBot; http://www.VerticalMatch.com/; vmbot@tradedot.com)</String> |
||
20238 | <Description>VM - Vertical Search Engine (China)</Description> |
||
20239 | <Type>R</Type> |
||
20240 | <Comment>202.83.221.2xx</Comment> |
||
20241 | <Link1>http://www.verticalmatch.com/</Link1> |
||
20242 | <Link2></Link2> |
||
20243 | </user-agent> |
||
20244 | <user-agent> |
||
20245 | <ID>id_t_z_020106_1</ID> |
||
20246 | <String>Vortex/2.2 (+http://marty.anstey.ca/robots/vortex/)</String> |
||
20247 | <Description>Vortex Web Indexing Robot for a study on internet link distribution</Description> |
||
20248 | <Type>R</Type> |
||
20249 | <Comment></Comment> |
||
20250 | <Link1>http://marty.anstey.ca/projects/robots/vortex/</Link1> |
||
20251 | <Link2></Link2> |
||
20252 | </user-agent> |
||
20253 | <user-agent> |
||
20254 | <ID>id_t_z_041207_1</ID> |
||
20255 | <String>voyager-hc/1.0</String> |
||
20256 | <Description>Kosmix health, auto and travel search crawler (204.14.48.x / 38.113.234.xxx)</Description> |
||
20257 | <Type>R</Type> |
||
20258 | <Comment>s. also - cfetch/1.x - carleson/1.x</Comment> |
||
20259 | <Link1>http://www.kosmix.com/</Link1> |
||
20260 | <Link2></Link2> |
||
20261 | </user-agent> |
||
20262 | <user-agent> |
||
20263 | <ID>id_t_z_231105_1</ID> |
||
20264 | <String>voyager/1.0</String> |
||
20265 | <Description>Kosmix health, auto and travel search crawler (204.14.48.x / 38.113.234.xxx)</Description> |
||
20266 | <Type>R</Type> |
||
20267 | <Comment>s. also - cfetch/1.x - carleson/1.x</Comment> |
||
20268 | <Link1>http://www.kosmix.com/</Link1> |
||
20269 | <Link2></Link2> |
||
20270 | </user-agent> |
||
20271 | <user-agent> |
||
20272 | <ID>id_t_z_301108_3</ID> |
||
20273 | <String>voyager/2.0 (http://www.kosmix.com/html/crawler.html)</String> |
||
20274 | <Description>Kosmix health, auto and travel search crawler (204.14.48.x / 38.113.234.xxx)</Description> |
||
20275 | <Type>R</Type> |
||
20276 | <Comment>s. also - cfetch/1.x - carleson/1.x</Comment> |
||
20277 | <Link1>http://www.kosmix.com/</Link1> |
||
20278 | <Link2></Link2> |
||
20279 | </user-agent> |
||
20280 | <user-agent> |
||
20281 | <ID>id_t_z_171105_3</ID> |
||
20282 | <String>VSE/1.0 (testcrawler@hotmail.com)</String> |
||
20283 | <Description>Vivisimo search crawler (206.210.89.xxx)</Description> |
||
20284 | <Type>R</Type> |
||
20285 | <Comment></Comment> |
||
20286 | <Link1>http://www.vivisimo.com/</Link1> |
||
20287 | <Link2></Link2> |
||
20288 | </user-agent> |
||
20289 | <user-agent> |
||
20290 | <ID>id_t_z_171105_4</ID> |
||
20291 | <String>VSE/1.0 (testcrawler@vivisimo.com)</String> |
||
20292 | <Description>Vivisimo search crawler (206.210.89.xxx)</Description> |
||
20293 | <Type>R</Type> |
||
20294 | <Comment></Comment> |
||
20295 | <Link1>http://www.vivisimo.com/</Link1> |
||
20296 | <Link2></Link2> |
||
20297 | </user-agent> |
||
20298 | <user-agent> |
||
20299 | <ID>id_t_z_1428</ID> |
||
20300 | <String>vspider</String> |
||
20301 | <Description>Verity vspider indexing software</Description> |
||
20302 | <Type>R</Type> |
||
20303 | <Comment></Comment> |
||
20304 | <Link1>http://www.verity.com/</Link1> |
||
20305 | <Link2></Link2> |
||
20306 | </user-agent> |
||
20307 | <user-agent> |
||
20308 | <ID>id_t_z_1429</ID> |
||
20309 | <String>vspider/3.x</String> |
||
20310 | <Description>Verity vspider indexing software</Description> |
||
20311 | <Type>R</Type> |
||
20312 | <Comment></Comment> |
||
20313 | <Link1>http://www.verity.com/</Link1> |
||
20314 | <Link2></Link2> |
||
20315 | </user-agent> |
||
20316 | <user-agent> |
||
20317 | <ID>id_t_z_130707_1</ID> |
||
20318 | <String>VWBOT/Nutch-0.9-dev (VWBOT Nutch Crawler; http://vwbot.cs.uiuc.edu;+vwbot@cs.uiuc.edu</String> |
||
20319 | <Description>VWBot - MetaQuerier Crawler for the MetaQuerier project at the University of Illinois</Description> |
||
20320 | <Type>R</Type> |
||
20321 | <Comment>192.17.240.xx</Comment> |
||
20322 | <Link1>http://vwbot.cs.uiuc.edu/</Link1> |
||
20323 | <Link2>http://metaquerier.cs.uiuc.edu/</Link2> |
||
20324 | </user-agent> |
||
20325 | <user-agent> |
||
20326 | <ID>id_t_z_1431</ID> |
||
20327 | <String>W3C-checklink/3.x.x.x libwww-perl/5.xx</String> |
||
20328 | <Description>W3C Link Checker</Description> |
||
20329 | <Type>C</Type> |
||
20330 | <Comment></Comment> |
||
20331 | <Link1>http://validator.w3.org/checklink</Link1> |
||
20332 | <Link2></Link2> |
||
20333 | </user-agent> |
||
20334 | <user-agent> |
||
20335 | <ID>id_t_z_1432</ID> |
||
20336 | <String>W3C-checklink/4.x [4.xx] libwww-perl/5.xxx</String> |
||
20337 | <Description>W3C Link Checker</Description> |
||
20338 | <Type>C</Type> |
||
20339 | <Comment></Comment> |
||
20340 | <Link1>http://validator.w3.org/checklink</Link1> |
||
20341 | <Link2></Link2> |
||
20342 | </user-agent> |
||
20343 | <user-agent> |
||
20344 | <ID>id_t_z_080806_1</ID> |
||
20345 | <String>W3C-WebCon/5.x.x libwww/5.x.x</String> |
||
20346 | <Description>WebCon - the Libwww command line tool</Description> |
||
20347 | <Type>D</Type> |
||
20348 | <Comment></Comment> |
||
20349 | <Link1>http://www.w3.org/ComLine/</Link1> |
||
20350 | <Link2></Link2> |
||
20351 | </user-agent> |
||
20352 | <user-agent> |
||
20353 | <ID>id_t_z_1433</ID> |
||
20354 | <String>W3CLineMode/5.4.0 libwww/5.x.x</String> |
||
20355 | <Description>W3C Line Mode (character based Web browser)</Description> |
||
20356 | <Type>B</Type> |
||
20357 | <Comment></Comment> |
||
20358 | <Link1>http://www.w3.org/LineMode/</Link1> |
||
20359 | <Link2></Link2> |
||
20360 | </user-agent> |
||
20361 | <user-agent> |
||
20362 | <ID>id_t_z_1434</ID> |
||
20363 | <String>W3CRobot/5.4.0 libwww/5.4.0</String> |
||
20364 | <Description>Unknown link checking using Libwww via Korea Telecom (221.148.44.xxx)</Description> |
||
20365 | <Type>C</Type> |
||
20366 | <Comment></Comment> |
||
20367 | <Link1>http://www.w3.org/Library/</Link1> |
||
20368 | <Link2></Link2> |
||
20369 | </user-agent> |
||
20370 | <user-agent> |
||
20371 | <ID>id_t_z_1430</ID> |
||
20372 | <String>W3C_Validator/1.xxx libwww-perl/5.xx</String> |
||
20373 | <Description>W3C HTML-Code Validator</Description> |
||
20374 | <Type>C</Type> |
||
20375 | <Comment></Comment> |
||
20376 | <Link1>http://validator.w3.org/</Link1> |
||
20377 | <Link2></Link2> |
||
20378 | </user-agent> |
||
20379 | <user-agent> |
||
20380 | <ID>id_t_z_1435</ID> |
||
20381 | <String>w3m/0.x.xx</String> |
||
20382 | <Description>w3m Linux pager / text-based browser</Description> |
||
20383 | <Type>B</Type> |
||
20384 | <Comment></Comment> |
||
20385 | <Link1>http://w3m.sourceforge.net/</Link1> |
||
20386 | <Link2></Link2> |
||
20387 | </user-agent> |
||
20388 | <user-agent> |
||
20389 | <ID>id_t_z_1436</ID> |
||
20390 | <String>W3SiteSearch Crawler_v1.1 http://www.w3sitesearch.de</String> |
||
20391 | <Description>W3 Site Search (Germany) search engine solution</Description> |
||
20392 | <Type>R</Type> |
||
20393 | <Comment></Comment> |
||
20394 | <Link1>http://www.w3sitesearch.de/</Link1> |
||
20395 | <Link2></Link2> |
||
20396 | </user-agent> |
||
20397 | <user-agent> |
||
20398 | <ID>id_t_z_061206_3</ID> |
||
20399 | <String>wadaino.jp-crawler 0.2 (http://wadaino.jp/)</String> |
||
20400 | <Description>Wadain (Japan) Blog / RSS search crawler</Description> |
||
20401 | <Type>R</Type> |
||
20402 | <Comment>202.51.14.1xx</Comment> |
||
20403 | <Link1>http://wadaino.jp/</Link1> |
||
20404 | <Link2></Link2> |
||
20405 | </user-agent> |
||
20406 | <user-agent> |
||
20407 | <ID>id_t_z_1437</ID> |
||
20408 | <String>WannaBe (Macintosh; PPC)</String> |
||
20409 | <Description>Wanna-Be text mode browser</Description> |
||
20410 | <Type>B</Type> |
||
20411 | <Comment></Comment> |
||
20412 | <Link1>http://mindstory.com/wb2/</Link1> |
||
20413 | <Link2></Link2> |
||
20414 | </user-agent> |
||
20415 | <user-agent> |
||
20416 | <ID>id_t_z_270906_1</ID> |
||
20417 | <String>WapOnWindows 1.0</String> |
||
20418 | <Description>WapOnWindows WAP browser for PCs</Description> |
||
20419 | <Type>B</Type> |
||
20420 | <Comment>Site is dead</Comment> |
||
20421 | <Link1>http://www.waponwindows.com/</Link1> |
||
20422 | <Link2></Link2> |
||
20423 | </user-agent> |
||
20424 | <user-agent> |
||
20425 | <ID>id_t_z_250206_2</ID> |
||
20426 | <String>Watchfire WebXM 1.0</String> |
||
20427 | <Description>Watchfire WebXM intranet solution</Description> |
||
20428 | <Type>P</Type> |
||
20429 | <Comment></Comment> |
||
20430 | <Link1>http://www.watchfire.com/products/webxm/default.aspx</Link1> |
||
20431 | <Link2></Link2> |
||
20432 | </user-agent> |
||
20433 | <user-agent> |
||
20434 | <ID>id_t_z_200706_1</ID> |
||
20435 | <String>WAVcheck 1.0.x (http://www.webbanalys.se/apps/WAVcheck/)</String> |
||
20436 | <Description>WAVcheck - Simple Vendor Discovery Tool for detecting client-side tags from web analytics vendors</Description> |
||
20437 | <Type>C</Type> |
||
20438 | <Comment></Comment> |
||
20439 | <Link1>http://www.webbanalys.se/apps/WAVcheck/</Link1> |
||
20440 | <Link2></Link2> |
||
20441 | </user-agent> |
||
20442 | <user-agent> |
||
20443 | <ID>id_t_z_110106_1</ID> |
||
20444 | <String>Wavefire/0.8-dev (Wavefire; http://www.wavefire.com; info@wavefire.com)</String> |
||
20445 | <Description>Wavefire local search community engine (64.141.15.1xx)</Description> |
||
20446 | <Type>R</Type> |
||
20447 | <Comment></Comment> |
||
20448 | <Link1>http://www.wavefire.com/</Link1> |
||
20449 | <Link2></Link2> |
||
20450 | </user-agent> |
||
20451 | <user-agent> |
||
20452 | <ID>id_t_z_110206_5</ID> |
||
20453 | <String>Waypath development crawler - info at waypath dot com</String> |
||
20454 | <Description>Waypath blog discovery engine robot</Description> |
||
20455 | <Type>R</Type> |
||
20456 | <Comment></Comment> |
||
20457 | <Link1>http://www.waypath.com/</Link1> |
||
20458 | <Link2></Link2> |
||
20459 | </user-agent> |
||
20460 | <user-agent> |
||
20461 | <ID>id_t_z_110206_6</ID> |
||
20462 | <String>Waypath Scout v2.x - info at waypath dot com</String> |
||
20463 | <Description>Waypath blog discovery engine robot</Description> |
||
20464 | <Type>R</Type> |
||
20465 | <Comment></Comment> |
||
20466 | <Link1>http://www.waypath.com/</Link1> |
||
20467 | <Link2></Link2> |
||
20468 | </user-agent> |
||
20469 | <user-agent> |
||
20470 | <ID>id_t_z_1438</ID> |
||
20471 | <String>WDG_Validator/1.1</String> |
||
20472 | <Description>WDG HTML-code validator</Description> |
||
20473 | <Type>C</Type> |
||
20474 | <Comment></Comment> |
||
20475 | <Link1>http://www.htmlhelp.tne.co.uk/tools/validator/</Link1> |
||
20476 | <Link2></Link2> |
||
20477 | </user-agent> |
||
20478 | <user-agent> |
||
20479 | <ID>id_t_z_1439</ID> |
||
20480 | <String>Web Image Collector</String> |
||
20481 | <Description>Datafire.com's Web Image Collector (graphics downloading tool)</Description> |
||
20482 | <Type>D</Type> |
||
20483 | <Comment></Comment> |
||
20484 | <Link1>http://www.datafire.com/</Link1> |
||
20485 | <Link2></Link2> |
||
20486 | </user-agent> |
||
20487 | <user-agent> |
||
20488 | <ID>id_t_z_1440</ID> |
||
20489 | <String>Web Link Validator 1.5</String> |
||
20490 | <Description>Relsoft link checking software</Description> |
||
20491 | <Type>C</Type> |
||
20492 | <Comment></Comment> |
||
20493 | <Link1>http://www.relsoftware.com/</Link1> |
||
20494 | <Link2></Link2> |
||
20495 | </user-agent> |
||
20496 | <user-agent> |
||
20497 | <ID>id_t_z_1441</ID> |
||
20498 | <String>Web Snooper</String> |
||
20499 | <Description>RankMeter ranking software</Description> |
||
20500 | <Type>R</Type> |
||
20501 | <Comment></Comment> |
||
20502 | <Link1>http://www.searchutilities.com/</Link1> |
||
20503 | <Link2></Link2> |
||
20504 | </user-agent> |
||
20505 | <user-agent> |
||
20506 | <ID>id_t_z_010206_2</ID> |
||
20507 | <String>web-bekannt (Version: 1.02, powered by www.internetservice-franken.de)</String> |
||
20508 | <Description>Web-bekannt German web directory link checking</Description> |
||
20509 | <Type>C</Type> |
||
20510 | <Comment></Comment> |
||
20511 | <Link1>http://www.web-bekannt.de/</Link1> |
||
20512 | <Link2></Link2> |
||
20513 | </user-agent> |
||
20514 | <user-agent> |
||
20515 | <ID>id_t_z_010206_1</ID> |
||
20516 | <String>web-bekannt (Version: 1.02, powered by www.web-bekannt.de)</String> |
||
20517 | <Description>Web-bekannt German web directory link checking</Description> |
||
20518 | <Type>C</Type> |
||
20519 | <Comment></Comment> |
||
20520 | <Link1>http://www.web-bekannt.de/</Link1> |
||
20521 | <Link2></Link2> |
||
20522 | </user-agent> |
||
20523 | <user-agent> |
||
20524 | <ID>id_t_z_1442</ID> |
||
20525 | <String>Web-Bot V1.03</String> |
||
20526 | <Description>Unkown link or server checking from Würzburg University Germany (132.187.10.xx)</Description> |
||
20527 | <Type>R C</Type> |
||
20528 | <Comment></Comment> |
||
20529 | <Link1>http://informatik.uni-wuerzburg.de/</Link1> |
||
20530 | <Link2></Link2> |
||
20531 | </user-agent> |
||
20532 | <user-agent> |
||
20533 | <ID>id_t_z_1443</ID> |
||
20534 | <String>Web-Robot/5.0 (en-US; web-robot.com/policy.html) Web-Robot Crawler/2.0.3</String> |
||
20535 | <Description>Unknown robot from 69.50.233.x (nectartech.com)</Description> |
||
20536 | <Type></Type> |
||
20537 | <Comment>no active website</Comment> |
||
20538 | <Link1></Link1> |
||
20539 | <Link2></Link2> |
||
20540 | </user-agent> |
||
20541 | <user-agent> |
||
20542 | <ID>id_t_z_010107_2</ID> |
||
20543 | <String>web2express.org/Nutch-0.9-dev (leveled playing field; http://web2express.org/; info at web2express.org)</String> |
||
20544 | <Description>Web2Express / Web2x - Open data searching tool</Description> |
||
20545 | <Type>R</Type> |
||
20546 | <Comment></Comment> |
||
20547 | <Link1>http://search.web2express.org/search/search.html</Link1> |
||
20548 | <Link2></Link2> |
||
20549 | </user-agent> |
||
20550 | <user-agent> |
||
20551 | <ID>id_t_z_050206_1</ID> |
||
20552 | <String>WebAlta Crawler/1.2.1 (http://www.webalta.ru/bot.html)</String> |
||
20553 | <Description>WebAlta search Russia crawler (85.21.201.xx)</Description> |
||
20554 | <Type>R</Type> |
||
20555 | <Comment></Comment> |
||
20556 | <Link1>http://www.webalta.ru/</Link1> |
||
20557 | <Link2></Link2> |
||
20558 | </user-agent> |
||
20559 | <user-agent> |
||
20560 | <ID>id_t_z_250806_1</ID> |
||
20561 | <String>WebarooBot (Webaroo Bot; http://64.124.122.252/feedback.html)</String> |
||
20562 | <Description>WebarooBot / RufusBot from webaroo offline search service</Description> |
||
20563 | <Type>R</Type> |
||
20564 | <Comment>64.124.122.2xx</Comment> |
||
20565 | <Link1>http://www.webaroo.com/</Link1> |
||
20566 | <Link2>http://www.webaroo.com/company/site-owners</Link2> |
||
20567 | </user-agent> |
||
20568 | <user-agent> |
||
20569 | <ID>id_t_z_210407_1</ID> |
||
20570 | <String>WebarooBot (Webaroo Bot; http://www.webaroo.com/rooSiteOwners.html)</String> |
||
20571 | <Description>WebarooBot / RufusBot from webaroo offline search service</Description> |
||
20572 | <Type>R</Type> |
||
20573 | <Comment>64.124.122.2xx</Comment> |
||
20574 | <Link1>http://www.webaroo.com/</Link1> |
||
20575 | <Link2>http://www.webaroo.com/company/site-owners</Link2> |
||
20576 | </user-agent> |
||
20577 | <user-agent> |
||
20578 | <ID>id_t_z_1444</ID> |
||
20579 | <String>WebAuto/3.4xxx (WinNT; I)</String> |
||
20580 | <Description>Yanasoft WebAuto website copier / downloading tool</Description> |
||
20581 | <Type>D</Type> |
||
20582 | <Comment></Comment> |
||
20583 | <Link1>http://www.yanasoft.co.jp/webauto.html</Link1> |
||
20584 | <Link2></Link2> |
||
20585 | </user-agent> |
||
20586 | <user-agent> |
||
20587 | <ID>id_t_z_1445</ID> |
||
20588 | <String>webbandit/4.xx.0</String> |
||
20589 | <Description>Web Bandit personal search software</Description> |
||
20590 | <Type>R</Type> |
||
20591 | <Comment></Comment> |
||
20592 | <Link1>http://softwaresolutions.net/webbandit/</Link1> |
||
20593 | <Link2></Link2> |
||
20594 | </user-agent> |
||
20595 | <user-agent> |
||
20596 | <ID>id_t_z_140106_2</ID> |
||
20597 | <String>WebBug/5.x</String> |
||
20598 | <Description>Amansoft WebBug web server protocol test</Description> |
||
20599 | <Type>C</Type> |
||
20600 | <Comment></Comment> |
||
20601 | <Link1>http://www.cyberspyder.com/webbug.html</Link1> |
||
20602 | <Link2></Link2> |
||
20603 | </user-agent> |
||
20604 | <user-agent> |
||
20605 | <ID>id_t_z_1446</ID> |
||
20606 | <String>Webclipping.com</String> |
||
20607 | <Description>WebClipping.com - online news monitoring service</Description> |
||
20608 | <Type>R</Type> |
||
20609 | <Comment></Comment> |
||
20610 | <Link1>http://www.webclipping.com</Link1> |
||
20611 | <Link2></Link2> |
||
20612 | </user-agent> |
||
20613 | <user-agent> |
||
20614 | <ID>id_t_z_1447</ID> |
||
20615 | <String>webcollage/1.xx</String> |
||
20616 | <Description>WebCollage Syndicator graphics crawler/collector</Description> |
||
20617 | <Type>R D</Type> |
||
20618 | <Comment>s. also collage.cgi/1.xx</Comment> |
||
20619 | <Link1>http://www.webcollage.com/</Link1> |
||
20620 | <Link2></Link2> |
||
20621 | </user-agent> |
||
20622 | <user-agent> |
||
20623 | <ID>id_t_z_1448</ID> |
||
20624 | <String>WebCompass 2.0</String> |
||
20625 | <Description>Quarterdecks WebCompass search tool</Description> |
||
20626 | <Type>R</Type> |
||
20627 | <Comment></Comment> |
||
20628 | <Link1></Link1> |
||
20629 | <Link2></Link2> |
||
20630 | </user-agent> |
||
20631 | <user-agent> |
||
20632 | <ID>id_t_z_1449</ID> |
||
20633 | <String>WebCopier vx.x</String> |
||
20634 | <Description>WebCopier offline browser</Description> |
||
20635 | <Type>D B</Type> |
||
20636 | <Comment></Comment> |
||
20637 | <Link1>http://www.maximumsoft.com/</Link1> |
||
20638 | <Link2></Link2> |
||
20639 | </user-agent> |
||
20640 | <user-agent> |
||
20641 | <ID>id_t_z_1450</ID> |
||
20642 | <String>WebCopier vx.xa</String> |
||
20643 | <Description>WebCopier offline browser</Description> |
||
20644 | <Type>D B</Type> |
||
20645 | <Comment></Comment> |
||
20646 | <Link1>http://www.maximumsoft.com/</Link1> |
||
20647 | <Link2></Link2> |
||
20648 | </user-agent> |
||
20649 | <user-agent> |
||
20650 | <ID>id_t_z_210506_1</ID> |
||
20651 | <String>WebCorp/1.0</String> |
||
20652 | <Description>WebCorp linguistic search engine (UK)</Description> |
||
20653 | <Type>R</Type> |
||
20654 | <Comment>193.60.130.xx</Comment> |
||
20655 | <Link1>http://webcorp.uce.ac.uk/</Link1> |
||
20656 | <Link2></Link2> |
||
20657 | </user-agent> |
||
20658 | <user-agent> |
||
20659 | <ID>id_t_z_1451</ID> |
||
20660 | <String>webcrawl.net</String> |
||
20661 | <Description>Webcrawl Search robot (64.40.105.xxx)</Description> |
||
20662 | <Type>R</Type> |
||
20663 | <Comment></Comment> |
||
20664 | <Link1>http://www.webcrawl.net/</Link1> |
||
20665 | <Link2></Link2> |
||
20666 | </user-agent> |
||
20667 | <user-agent> |
||
20668 | <ID>id_t_z_1452</ID> |
||
20669 | <String>WebDownloader for X x.xx</String> |
||
20670 | <Description>Unix/Linux Web Downloader</Description> |
||
20671 | <Type>D</Type> |
||
20672 | <Comment></Comment> |
||
20673 | <Link1>http://www.krasu.ru/soft/chuchelo/</Link1> |
||
20674 | <Link2></Link2> |
||
20675 | </user-agent> |
||
20676 | <user-agent> |
||
20677 | <ID>id_t_z_1453</ID> |
||
20678 | <String>Webdup/0.9</String> |
||
20679 | <Description>Unknown robot from china-netcom.com</Description> |
||
20680 | <Type></Type> |
||
20681 | <Comment></Comment> |
||
20682 | <Link1></Link1> |
||
20683 | <Link2></Link2> |
||
20684 | </user-agent> |
||
20685 | <user-agent> |
||
20686 | <ID>id_t_z_1454</ID> |
||
20687 | <String>WebFetch</String> |
||
20688 | <Description>WingFlyer WebFetch website downloading tool</Description> |
||
20689 | <Type>D B</Type> |
||
20690 | <Comment></Comment> |
||
20691 | <Link1>http://www.wingflyer.com/</Link1> |
||
20692 | <Link2></Link2> |
||
20693 | </user-agent> |
||
20694 | <user-agent> |
||
20695 | <ID>id_t_z_1455</ID> |
||
20696 | <String>webfetch/5.x.x</String> |
||
20697 | <Description>webfetch - command line tool to fetch files via HTTP</Description> |
||
20698 | <Type>D</Type> |
||
20699 | <Comment></Comment> |
||
20700 | <Link1>http://tony.aiu.to/sa/webfetch/</Link1> |
||
20701 | <Link2></Link2> |
||
20702 | </user-agent> |
||
20703 | <user-agent> |
||
20704 | <ID>id_t_z_310806_2</ID> |
||
20705 | <String>WebFilter Robot 1.0</String> |
||
20706 | <Description>Verso NetSpective WebFilter</Description> |
||
20707 | <Type>P</Type> |
||
20708 | <Comment></Comment> |
||
20709 | <Link1>http://www.verso.com/enterprise/netspective/webfilter.asp</Link1> |
||
20710 | <Link2></Link2> |
||
20711 | </user-agent> |
||
20712 | <user-agent> |
||
20713 | <ID>id_t_z_1456</ID> |
||
20714 | <String>WebFilter Robot 1.x</String> |
||
20715 | <Description>Telemate.net NetSpective WebFilter</Description> |
||
20716 | <Type>P</Type> |
||
20717 | <Comment></Comment> |
||
20718 | <Link1>http://www.telemate.net/</Link1> |
||
20719 | <Link2></Link2> |
||
20720 | </user-agent> |
||
20721 | <user-agent> |
||
20722 | <ID>id_t_z_1457</ID> |
||
20723 | <String>WebFindBot(http://www.web-find.com)</String> |
||
20724 | <Description>Webfind search robot</Description> |
||
20725 | <Type>R</Type> |
||
20726 | <Comment></Comment> |
||
20727 | <Link1>http://www.web-find.com/</Link1> |
||
20728 | <Link2></Link2> |
||
20729 | </user-agent> |
||
20730 | <user-agent> |
||
20731 | <ID>id_t_z_1458</ID> |
||
20732 | <String>Webglimpse 2.xx.x (http://webglimpse.net)</String> |
||
20733 | <Description>Webglimpse search engine software</Description> |
||
20734 | <Type>R</Type> |
||
20735 | <Comment></Comment> |
||
20736 | <Link1>http://www.webglimpse.net/</Link1> |
||
20737 | <Link2></Link2> |
||
20738 | </user-agent> |
||
20739 | <user-agent> |
||
20740 | <ID>id_t_z_150306_2</ID> |
||
20741 | <String>webGobbler/1.x.x</String> |
||
20742 | <Description>webGobbler - Online random image generator</Description> |
||
20743 | <Type>R D</Type> |
||
20744 | <Comment></Comment> |
||
20745 | <Link1>http://sebsauvage.net/webgobbler/</Link1> |
||
20746 | <Link2></Link2> |
||
20747 | </user-agent> |
||
20748 | <user-agent> |
||
20749 | <ID>id_t_z_1459</ID> |
||
20750 | <String>webhack</String> |
||
20751 | <Description>fake ?</Description> |
||
20752 | <Type></Type> |
||
20753 | <Comment></Comment> |
||
20754 | <Link1></Link1> |
||
20755 | <Link2></Link2> |
||
20756 | </user-agent> |
||
20757 | <user-agent> |
||
20758 | <ID>id_t_z_290807_2</ID> |
||
20759 | <String>WebImages 0.3 ( http://herbert.groot.jebbink.nl/?app=WebImages )</String> |
||
20760 | <Description>herbert.groot.jebbink.nl Web Images collage generator</Description> |
||
20761 | <Type>D</Type> |
||
20762 | <Comment>212.204.217.1xx</Comment> |
||
20763 | <Link1>http://herbert.groot.jebbink.nl/</Link1> |
||
20764 | <Link2></Link2> |
||
20765 | </user-agent> |
||
20766 | <user-agent> |
||
20767 | <ID>id_t_z_280306_2</ID> |
||
20768 | <String>WebLight/4.x.x (support@illumit.com; http://www.illumit.com/Products/weblight/)</String> |
||
20769 | <Description>WebLight web analyzer & link checker</Description> |
||
20770 | <Type>C</Type> |
||
20771 | <Comment>s. also Mozilla/4.0 (compatible; MSIE 6.0; Windows 98; support@illumit.com...</Comment> |
||
20772 | <Link1>http://www.illumit.com/Products/weblight/</Link1> |
||
20773 | <Link2></Link2> |
||
20774 | </user-agent> |
||
20775 | <user-agent> |
||
20776 | <ID>id_t_z_1460</ID> |
||
20777 | <String>Weblink's checker/</String> |
||
20778 | <Description>WebLink's link management system for HTTP- FTP and Mail hyperlinks</Description> |
||
20779 | <Type>C</Type> |
||
20780 | <Comment>sometimes in conjunction w. PHP/4.0.6</Comment> |
||
20781 | <Link1>http://www.harlequin.ch/technologien/tools/weblinks.php</Link1> |
||
20782 | <Link2></Link2> |
||
20783 | </user-agent> |
||
20784 | <user-agent> |
||
20785 | <ID>id_t_z_140307_1</ID> |
||
20786 | <String>Weblog Attitude Diffusion 1.0</String> |
||
20787 | <Description>Los Alamos National Laboratoy weblog research project</Description> |
||
20788 | <Type>R</Type> |
||
20789 | <Comment></Comment> |
||
20790 | <Link1>http://www.user-agents.org/agents/weblogattitude.shtml</Link1> |
||
20791 | <Link2>http://www.lanl.gov/</Link2> |
||
20792 | </user-agent> |
||
20793 | <user-agent> |
||
20794 | <ID>id_t_z_230606_1</ID> |
||
20795 | <String>webmeasurement-bot, http://rvs.informatik.uni-leipzig.de</String> |
||
20796 | <Description>Unknown robot from Leipzig University (Germany) faculty for computer science</Description> |
||
20797 | <Type>R</Type> |
||
20798 | <Comment>139.18.38.1xx</Comment> |
||
20799 | <Link1>http://rvs.informatik.uni-leipzig.de/</Link1> |
||
20800 | <Link2></Link2> |
||
20801 | </user-agent> |
||
20802 | <user-agent> |
||
20803 | <ID>id_t_z_1461</ID> |
||
20804 | <String>WebMiner/x.x [en] (Win98; I)</String> |
||
20805 | <Description>WebMiner bulk file downloader</Description> |
||
20806 | <Type>D</Type> |
||
20807 | <Comment></Comment> |
||
20808 | <Link1>http://tribolic.com/webminer/</Link1> |
||
20809 | <Link2></Link2> |
||
20810 | </user-agent> |
||
20811 | <user-agent> |
||
20812 | <ID>id_t_z_1462</ID> |
||
20813 | <String>WeBoX/0.xx</String> |
||
20814 | <Description>WeBoX (Japan) - Browser and web collector</Description> |
||
20815 | <Type>B D</Type> |
||
20816 | <Comment></Comment> |
||
20817 | <Link1>http://www-nishio.ise.eng.osaka-u.ac.jp/~nakamura/webox/</Link1> |
||
20818 | <Link2></Link2> |
||
20819 | </user-agent> |
||
20820 | <user-agent> |
||
20821 | <ID>id_t_z_1463</ID> |
||
20822 | <String>WebPix 1.0 (www.netwu.com)</String> |
||
20823 | <Description>WebPix - picture downloading tool</Description> |
||
20824 | <Type>D</Type> |
||
20825 | <Comment></Comment> |
||
20826 | <Link1>http://www.netwu.com/webpix/</Link1> |
||
20827 | <Link2></Link2> |
||
20828 | </user-agent> |
||
20829 | <user-agent> |
||
20830 | <ID>id_t_z_1464</ID> |
||
20831 | <String>WebQL</String> |
||
20832 | <Description>Caesius WebQL - Custom robot/agent generator / web extraction software</Description> |
||
20833 | <Type>B D</Type> |
||
20834 | <Comment></Comment> |
||
20835 | <Link1>http://www.caesius.com/</Link1> |
||
20836 | <Link2></Link2> |
||
20837 | </user-agent> |
||
20838 | <user-agent> |
||
20839 | <ID>id_t_z_1465</ID> |
||
20840 | <String>WebRACE/1.1 (University of Cyprus- Distributed Crawler)</String> |
||
20841 | <Description>WebRACE - HTTP retrieval- annotation and caching engine</Description> |
||
20842 | <Type>P</Type> |
||
20843 | <Comment></Comment> |
||
20844 | <Link1>http://www.cs.ucy.ac.cy/Projects/eRACE/webrace.html</Link1> |
||
20845 | <Link2></Link2> |
||
20846 | </user-agent> |
||
20847 | <user-agent> |
||
20848 | <ID>id_t_z_130907_1</ID> |
||
20849 | <String>WebRankSpider/1.37 (+http://ulm191.server4you.de/crawler/)</String> |
||
20850 | <Description>WebRankSpider experimental web crawler</Description> |
||
20851 | <Type>R</Type> |
||
20852 | <Comment>62.75.202.1xx</Comment> |
||
20853 | <Link1>http://ulm191.server4you.de/crawler/</Link1> |
||
20854 | <Link2></Link2> |
||
20855 | </user-agent> |
||
20856 | <user-agent> |
||
20857 | <ID>id_t_z_1468</ID> |
||
20858 | <String>WebReaper vx.x - www.webreaper.net</String> |
||
20859 | <Description>Webreaper download manager</Description> |
||
20860 | <Type>D</Type> |
||
20861 | <Comment></Comment> |
||
20862 | <Link1>http://www.webreaper.net/</Link1> |
||
20863 | <Link2></Link2> |
||
20864 | </user-agent> |
||
20865 | <user-agent> |
||
20866 | <ID>id_t_z_1466</ID> |
||
20867 | <String>WebReaper [info@webreaper.net]</String> |
||
20868 | <Description>Webreaper download manager</Description> |
||
20869 | <Type>D</Type> |
||
20870 | <Comment></Comment> |
||
20871 | <Link1>http://www.webreaper.net/</Link1> |
||
20872 | <Link2></Link2> |
||
20873 | </user-agent> |
||
20874 | <user-agent> |
||
20875 | <ID>id_t_z_1467</ID> |
||
20876 | <String>WebReaper [webreaper@webreaper.net]</String> |
||
20877 | <Description>Webreaper download manager</Description> |
||
20878 | <Type>D</Type> |
||
20879 | <Comment></Comment> |
||
20880 | <Link1>http://www.webreaper.net/</Link1> |
||
20881 | <Link2></Link2> |
||
20882 | </user-agent> |
||
20883 | <user-agent> |
||
20884 | <ID>id_t_z_1469</ID> |
||
20885 | <String>WebSearch.COM.AU/3.0.1 (The Australian Search Engine; http://WebSearch.COM.AU; Search@WebSearch.COM.AU)</String> |
||
20886 | <Description>Websearch Australia robot</Description> |
||
20887 | <Type>R</Type> |
||
20888 | <Comment></Comment> |
||
20889 | <Link1>http://WebSearch.COM.AU/</Link1> |
||
20890 | <Link2></Link2> |
||
20891 | </user-agent> |
||
20892 | <user-agent> |
||
20893 | <ID>id_t_z_1470</ID> |
||
20894 | <String>WebSearchBench WebCrawler v0.1(Experimental)</String> |
||
20895 | <Description>Dortmund University WebSearchBench - Open source search software</Description> |
||
20896 | <Type>R</Type> |
||
20897 | <Comment></Comment> |
||
20898 | <Link1>http://websearchbench.cs.uni-dortmund.de/websearch/about.html.de</Link1> |
||
20899 | <Link2></Link2> |
||
20900 | </user-agent> |
||
20901 | <user-agent> |
||
20902 | <ID>id_t_z_1471</ID> |
||
20903 | <String>WebSearchBench WebCrawler V1.0 (Beta)- Prof. Dr.-Ing. Christoph Lindemann- Universität Dortmund- cl@cs.uni-dortmund.de- http://websearchbench.cs.uni-dortmund.de/</String> |
||
20904 | <Description>Dortmund University WebSearchBench - Open source search software</Description> |
||
20905 | <Type>R</Type> |
||
20906 | <Comment></Comment> |
||
20907 | <Link1>http://websearchbench.cs.uni-dortmund.de/websearch/about.html.de</Link1> |
||
20908 | <Link2></Link2> |
||
20909 | </user-agent> |
||
20910 | <user-agent> |
||
20911 | <ID>id_t_z_260806_2</ID> |
||
20912 | <String>Website Explorer/0.9.x.x</String> |
||
20913 | <Description>Web site downloading tool and offline browser (Japan)</Description> |
||
20914 | <Type>D</Type> |
||
20915 | <Comment></Comment> |
||
20916 | <Link1>http://www.umechando.com/webex/</Link1> |
||
20917 | <Link2></Link2> |
||
20918 | </user-agent> |
||
20919 | <user-agent> |
||
20920 | <ID>id_t_z_1472</ID> |
||
20921 | <String>Website eXtractor</String> |
||
20922 | <Description>Website eXtractor web site downloading tool</Description> |
||
20923 | <Type>D</Type> |
||
20924 | <Comment></Comment> |
||
20925 | <Link1>http://www.asona.org/</Link1> |
||
20926 | <Link2>http://www.internet-soft.com/</Link2> |
||
20927 | </user-agent> |
||
20928 | <user-agent> |
||
20929 | <ID>id_t_z_090606_1</ID> |
||
20930 | <String>WebsiteWorth v1.0</String> |
||
20931 | <Description>Sootle web directory Website Worth ranking tool</Description> |
||
20932 | <Type>R</Type> |
||
20933 | <Comment>216.89.111.x</Comment> |
||
20934 | <Link1>http://directory.sootle.com/website-worth/</Link1> |
||
20935 | <Link2></Link2> |
||
20936 | </user-agent> |
||
20937 | <user-agent> |
||
20938 | <ID>id_t_z_1473</ID> |
||
20939 | <String>Webspinne/1.0 webmaster@webspinne.de</String> |
||
20940 | <Description>Webspinne.de robot</Description> |
||
20941 | <Type>R</Type> |
||
20942 | <Comment></Comment> |
||
20943 | <Link1>http://www.webspinne.de/</Link1> |
||
20944 | <Link2></Link2> |
||
20945 | </user-agent> |
||
20946 | <user-agent> |
||
20947 | <ID>id_t_z_1474</ID> |
||
20948 | <String>Websquash.com (Add url robot)</String> |
||
20949 | <Description>Websquash.com Search Engine robot / link checking</Description> |
||
20950 | <Type>R</Type> |
||
20951 | <Comment></Comment> |
||
20952 | <Link1>http://www.websquash.com/</Link1> |
||
20953 | <Link2></Link2> |
||
20954 | </user-agent> |
||
20955 | <user-agent> |
||
20956 | <ID>id_t_z_1475</ID> |
||
20957 | <String>WebStat/1.0 (Unix; beta; 20040314)</String> |
||
20958 | <Description>WebStat - Java statistical computing environment for the web</Description> |
||
20959 | <Type>R</Type> |
||
20960 | <Comment></Comment> |
||
20961 | <Link1>http://www.math.psu.edu/babcock/webstat/version1.0/</Link1> |
||
20962 | <Link2></Link2> |
||
20963 | </user-agent> |
||
20964 | <user-agent> |
||
20965 | <ID>id_t_z_091006_2</ID> |
||
20966 | <String>Webster v0.3 ( http://webster.healeys.net/ )</String> |
||
20967 | <Description>Webster - Rev. Healeys web crawler</Description> |
||
20968 | <Type>R</Type> |
||
20969 | <Comment>24.99.22.xx</Comment> |
||
20970 | <Link1>http://webster.healeys.net/</Link1> |
||
20971 | <Link2>http://webster.healeys.net/search.php</Link2> |
||
20972 | </user-agent> |
||
20973 | <user-agent> |
||
20974 | <ID>id_t_z_1476</ID> |
||
20975 | <String>webster-internet.de pad browser</String> |
||
20976 | <Description>Websters Webmaster Archive (Germany) submission / pad checking</Description> |
||
20977 | <Type>C B</Type> |
||
20978 | <Comment></Comment> |
||
20979 | <Link1>http://webster.de/</Link1> |
||
20980 | <Link2></Link2> |
||
20981 | </user-agent> |
||
20982 | <user-agent> |
||
20983 | <ID>id_t_z_1477</ID> |
||
20984 | <String>WebStripper/2.xx</String> |
||
20985 | <Description>WebStripper download manager</Description> |
||
20986 | <Type>D</Type> |
||
20987 | <Comment></Comment> |
||
20988 | <Link1>http://webstripper.net/index.html</Link1> |
||
20989 | <Link2>http://www.netidea.it</Link2> |
||
20990 | </user-agent> |
||
20991 | <user-agent> |
||
20992 | <ID>id_t_z_1478</ID> |
||
20993 | <String>WebTrafficExpress/x.0</String> |
||
20994 | <Description>WebTrafficExpress IBM server software</Description> |
||
20995 | <Type>P</Type> |
||
20996 | <Comment></Comment> |
||
20997 | <Link1></Link1> |
||
20998 | <Link2></Link2> |
||
20999 | </user-agent> |
||
21000 | <user-agent> |
||
21001 | <ID>id_t_z_1479</ID> |
||
21002 | <String>WebTrends/3.0 (WinNT)</String> |
||
21003 | <Description>Web Trends link analyzer</Description> |
||
21004 | <Type>C</Type> |
||
21005 | <Comment></Comment> |
||
21006 | <Link1>http://www.netiq.com/webtrends/default.asp</Link1> |
||
21007 | <Link2></Link2> |
||
21008 | </user-agent> |
||
21009 | <user-agent> |
||
21010 | <ID>id_t_z_1480</ID> |
||
21011 | <String>WebVac (webmaster@pita.stanford.edu)</String> |
||
21012 | <Description>The Stanford WebBase Project crawler</Description> |
||
21013 | <Type>R</Type> |
||
21014 | <Comment>ex Pita- s. there</Comment> |
||
21015 | <Link1>http://www-diglib.stanford.edu/~testbed/doc2/WebBase/</Link1> |
||
21016 | <Link2></Link2> |
||
21017 | </user-agent> |
||
21018 | <user-agent> |
||
21019 | <ID>id_t_z_1481</ID> |
||
21020 | <String>WebVal/1.0</String> |
||
21021 | <Description>webval - Python link checking tool</Description> |
||
21022 | <Type>C</Type> |
||
21023 | <Comment></Comment> |
||
21024 | <Link1>http://www.alcyone.com/pyos/webval/</Link1> |
||
21025 | <Link2></Link2> |
||
21026 | </user-agent> |
||
21027 | <user-agent> |
||
21028 | <ID>id_t_z_171205_3</ID> |
||
21029 | <String>Webverzeichnis.de - Telefon: 01908 / 26005</String> |
||
21030 | <Description>Webverzeichnis.de (Germany) directory robot</Description> |
||
21031 | <Type>R</Type> |
||
21032 | <Comment></Comment> |
||
21033 | <Link1>http://www.webverzeichnis.de/</Link1> |
||
21034 | <Link2></Link2> |
||
21035 | </user-agent> |
||
21036 | <user-agent> |
||
21037 | <ID>id_t_z_060306_1</ID> |
||
21038 | <String>WebVulnCrawl.unknown/1.0 libwww-perl/5.803</String> |
||
21039 | <Description>Web Vulnerability Crawler</Description> |
||
21040 | <Type>S</Type> |
||
21041 | <Comment>Looking for excluded directories in robots.txt</Comment> |
||
21042 | <Link1>http://webvulncrawl.blogspot.com/2005/12/what-am-i-doing.html</Link1> |
||
21043 | <Link2></Link2> |
||
21044 | </user-agent> |
||
21045 | <user-agent> |
||
21046 | <ID>id_t_z_1482</ID> |
||
21047 | <String>WebWatcherMonitor/2.01</String> |
||
21048 | <Description>Studio Net.Idea's Web Watcher Monitor robot</Description> |
||
21049 | <Type>R C</Type> |
||
21050 | <Comment></Comment> |
||
21051 | <Link1>http://www.web-watcher.com/web-watcher-monitor.html</Link1> |
||
21052 | <Link2></Link2> |
||
21053 | </user-agent> |
||
21054 | <user-agent> |
||
21055 | <ID>id_t_z_1483</ID> |
||
21056 | <String>WebZIP/x.x (http://www.spidersoft.com)</String> |
||
21057 | <Description>WebZip offline browser</Description> |
||
21058 | <Type>B D</Type> |
||
21059 | <Comment></Comment> |
||
21060 | <Link1>http://www.spidersoft.com/</Link1> |
||
21061 | <Link2></Link2> |
||
21062 | </user-agent> |
||
21063 | <user-agent> |
||
21064 | <ID>id_t_z_1484</ID> |
||
21065 | <String>Wells Search II</String> |
||
21066 | <Description>Unknown spam bot / harvester (62.163.**.** / 62.194.**.*)</Description> |
||
21067 | <Type>S</Type> |
||
21068 | <Comment>s.also - Port Huron Labs</Comment> |
||
21069 | <Link1></Link1> |
||
21070 | <Link2></Link2> |
||
21071 | </user-agent> |
||
21072 | <user-agent> |
||
21073 | <ID>id_t_z_1485</ID> |
||
21074 | <String>WEP Search 00</String> |
||
21075 | <Description>Some spam bot- see link</Description> |
||
21076 | <Type>S</Type> |
||
21077 | <Comment></Comment> |
||
21078 | <Link1>http://www.kloth.net/internet/badbots-2004.php</Link1> |
||
21079 | <Link2></Link2> |
||
21080 | </user-agent> |
||
21081 | <user-agent> |
||
21082 | <ID>id_t_z_230606_2</ID> |
||
21083 | <String>West Wind Internet Protocols 4.xx</String> |
||
21084 | <Description>wwIPStuff - Internet client tools for Visual FoxPro</Description> |
||
21085 | <Type>B D</Type> |
||
21086 | <Comment></Comment> |
||
21087 | <Link1>http://www.west-wind.com/wwipstuff.asp</Link1> |
||
21088 | <Link2></Link2> |
||
21089 | </user-agent> |
||
21090 | <user-agent> |
||
21091 | <ID>id_t_z_1486</ID> |
||
21092 | <String>WFARC</String> |
||
21093 | <Description>IBM's Almaden Research robot (Clever search project)</Description> |
||
21094 | <Type>R</Type> |
||
21095 | <Comment>s. also: - http://www.almaden.ibm.com/cs/crawler - FocusedSampler</Comment> |
||
21096 | <Link1>http://www.almaden.ibm.com/cs/k53/clever.html</Link1> |
||
21097 | <Link2></Link2> |
||
21098 | </user-agent> |
||
21099 | <user-agent> |
||
21100 | <ID>id_t_z_1488</ID> |
||
21101 | <String>Wget/1.x(.x)GNU wget http://www.gnu.org/software/wget/wget.html - file downloader</String> |
||
21102 | <Description>GNU wget - file downloader</Description> |
||
21103 | <Type>D</Type> |
||
21104 | <Comment></Comment> |
||
21105 | <Link1>http://www.gnu.org/software/wget/wget.html</Link1> |
||
21106 | <Link2></Link2> |
||
21107 | </user-agent> |
||
21108 | <user-agent> |
||
21109 | <ID>id_t_z_1489</ID> |
||
21110 | <String>Wget/1.x+cvs-stable (Red Hat modified)</String> |
||
21111 | <Description>GNU wget - file downloader</Description> |
||
21112 | <Type>D</Type> |
||
21113 | <Comment></Comment> |
||
21114 | <Link1>http://www.gnu.org/software/wget/wget.html</Link1> |
||
21115 | <Link2></Link2> |
||
21116 | </user-agent> |
||
21117 | <user-agent> |
||
21118 | <ID>id_t_z_1487</ID> |
||
21119 | <String>Wget/1.x.x+cvs</String> |
||
21120 | <Description>GNU wget - file downloader</Description> |
||
21121 | <Type>D</Type> |
||
21122 | <Comment></Comment> |
||
21123 | <Link1>http://www.gnu.org/software/wget/wget.html</Link1> |
||
21124 | <Link2></Link2> |
||
21125 | </user-agent> |
||
21126 | <user-agent> |
||
21127 | <ID>id_t_z_1490</ID> |
||
21128 | <String>Whatsup/x.x</String> |
||
21129 | <Description>Whatsup Gold network monitor</Description> |
||
21130 | <Type>C</Type> |
||
21131 | <Comment></Comment> |
||
21132 | <Link1>http://www.ipswitch.com/products/network-management.html</Link1> |
||
21133 | <Link2></Link2> |
||
21134 | </user-agent> |
||
21135 | <user-agent> |
||
21136 | <ID>id_t_z_1491</ID> |
||
21137 | <String>whatUseek_winona/3.0</String> |
||
21138 | <Description>WhatUSeek / Chubba robot</Description> |
||
21139 | <Type>R</Type> |
||
21140 | <Comment>166.90.205.x</Comment> |
||
21141 | <Link1>http://www.whatuseek.com/</Link1> |
||
21142 | <Link2></Link2> |
||
21143 | </user-agent> |
||
21144 | <user-agent> |
||
21145 | <ID>id_t_z_1492</ID> |
||
21146 | <String>WhizBang! Lab</String> |
||
21147 | <Description>WhizBang! Labs (closed since May 2002) information extraction robot</Description> |
||
21148 | <Type>R</Type> |
||
21149 | <Comment></Comment> |
||
21150 | <Link1></Link1> |
||
21151 | <Link2></Link2> |
||
21152 | </user-agent> |
||
21153 | <user-agent> |
||
21154 | <ID>id_t_z_1493</ID> |
||
21155 | <String>Wildsoft Surfer</String> |
||
21156 | <Description>some download agent</Description> |
||
21157 | <Type>D</Type> |
||
21158 | <Comment>- in conjunction w. dlman</Comment> |
||
21159 | <Link1></Link1> |
||
21160 | <Link2></Link2> |
||
21161 | </user-agent> |
||
21162 | <user-agent> |
||
21163 | <ID>id_t_z_1494</ID> |
||
21164 | <String>Willow Internet Crawler by Twotrees V2.1</String> |
||
21165 | <Description>Twotrees crawler</Description> |
||
21166 | <Type>R</Type> |
||
21167 | <Comment></Comment> |
||
21168 | <Link1>http://www.twotrees.com/</Link1> |
||
21169 | <Link2></Link2> |
||
21170 | </user-agent> |
||
21171 | <user-agent> |
||
21172 | <ID>id_t_z_1495</ID> |
||
21173 | <String>WinampMPEG/2.00 (larbin@unspecified.mail)</String> |
||
21174 | <Description>unknown robot from gw.ocg-corp.com (209.126.176.x)</Description> |
||
21175 | <Type></Type> |
||
21176 | <Comment>see also: - Opera/6.01 (larbin@.....) - MSIE-5.13 larbin@....</Comment> |
||
21177 | <Link1></Link1> |
||
21178 | <Link2></Link2> |
||
21179 | </user-agent> |
||
21180 | <user-agent> |
||
21181 | <ID>id_t_z_1496</ID> |
||
21182 | <String>WincerSong Agent v1.0</String> |
||
21183 | <Description>Super Affiliate Tracker agent by Wincer Song</Description> |
||
21184 | <Type></Type> |
||
21185 | <Comment></Comment> |
||
21186 | <Link1>http://www.superaffiliatetracker.com/index.htm</Link1> |
||
21187 | <Link2></Link2> |
||
21188 | </user-agent> |
||
21189 | <user-agent> |
||
21190 | <ID>id_t_z_191105_3</ID> |
||
21191 | <String>Windows-Media-Player/10.00.00.xxxx</String> |
||
21192 | <Description>Windows Media Player 10</Description> |
||
21193 | <Type>B</Type> |
||
21194 | <Comment></Comment> |
||
21195 | <Link1></Link1> |
||
21196 | <Link2></Link2> |
||
21197 | </user-agent> |
||
21198 | <user-agent> |
||
21199 | <ID>id_t_z_160107_1</ID> |
||
21200 | <String>WinGet 1.1</String> |
||
21201 | <Description>Nicksoft WinGet download manager</Description> |
||
21202 | <Type>D</Type> |
||
21203 | <Comment>Domain is for sale</Comment> |
||
21204 | <Link1></Link1> |
||
21205 | <Link2></Link2> |
||
21206 | </user-agent> |
||
21207 | <user-agent> |
||
21208 | <ID>id_t_z_060406_1</ID> |
||
21209 | <String>WinHTTP Example/1.0</String> |
||
21210 | <Description>Example code for a WinHTTP C++ library crawler</Description> |
||
21211 | <Type>R</Type> |
||
21212 | <Comment></Comment> |
||
21213 | <Link1>http://www.codeguru.com/cpp/i-n/internet/http/article.php/c6237/</Link1> |
||
21214 | <Link2>http://www.microsoft.com/msdownload/platformsdk/sdkupdate/update.htm</Link2> |
||
21215 | </user-agent> |
||
21216 | <user-agent> |
||
21217 | <ID>id_t_z_260506_1</ID> |
||
21218 | <String>WinkBot/0.06 (Wink.com search engine web crawler; http://www.wink.com/Wink:WinkBot; winkbot@wink.com)</String> |
||
21219 | <Description>Wink beta search robot (64.13.136.x)</Description> |
||
21220 | <Type>R</Type> |
||
21221 | <Comment></Comment> |
||
21222 | <Link1>http://www.wink.com/</Link1> |
||
21223 | <Link2></Link2> |
||
21224 | </user-agent> |
||
21225 | <user-agent> |
||
21226 | <ID>id_t_z_010607_1</ID> |
||
21227 | <String>WinPodder (http://winpodder.com)</String> |
||
21228 | <Description>WinPodder - Podcast player and RSS reader</Description> |
||
21229 | <Type>B</Type> |
||
21230 | <Comment></Comment> |
||
21231 | <Link1>http://winpodder.com/</Link1> |
||
21232 | <Link2></Link2> |
||
21233 | </user-agent> |
||
21234 | <user-agent> |
||
21235 | <ID>id_t_z_251105_1</ID> |
||
21236 | <String>WinWAP/3.x (3.x.x.xx; Win32) (Google WAP Proxy/1.0)</String> |
||
21237 | <Description>WinWap - Windows PC WAP browser</Description> |
||
21238 | <Type>B</Type> |
||
21239 | <Comment></Comment> |
||
21240 | <Link1>http://www.winwap.com/products_2_1.php</Link1> |
||
21241 | <Link2></Link2> |
||
21242 | </user-agent> |
||
21243 | <user-agent> |
||
21244 | <ID>id_t_z_111206_2</ID> |
||
21245 | <String>Wir sind die Borg (Version: 1.03, Sie wurden Assimiliert +http://www.yammba.com/suchmaschine/bot.html)</String> |
||
21246 | <Description>Yammba web directory (Germany) link checking</Description> |
||
21247 | <Type>C</Type> |
||
21248 | <Comment></Comment> |
||
21249 | <Link1>http://www.yammba.com/</Link1> |
||
21250 | <Link2></Link2> |
||
21251 | </user-agent> |
||
21252 | <user-agent> |
||
21253 | <ID>id_t_z_130506_2</ID> |
||
21254 | <String>WIRE/0.11 (Linux; i686; Bot,Robot,Spider,Crawler,aromano@cli.di.unipi.it)</String> |
||
21255 | <Description>WIRE crawler used by the University of Pisa - Italy</Description> |
||
21256 | <Type>R</Type> |
||
21257 | <Comment>146.48.82.xx</Comment> |
||
21258 | <Link1>http://www.cwr.cl/projects/WIRE/</Link1> |
||
21259 | <Link2>http://www.unipi.it/english/index.htm</Link2> |
||
21260 | </user-agent> |
||
21261 | <user-agent> |
||
21262 | <ID>id_t_z_1497</ID> |
||
21263 | <String>WIRE/0.x (Linux; i686; Bot,Robot,Spider,Crawler)</String> |
||
21264 | <Description>WIRE - Web information retrieval environment crawler</Description> |
||
21265 | <Type>R</Type> |
||
21266 | <Comment>Used by different IPs for different purposes</Comment> |
||
21267 | <Link1>http://www.cwr.cl/projects/WIRE/</Link1> |
||
21268 | <Link2></Link2> |
||
21269 | </user-agent> |
||
21270 | <user-agent> |
||
21271 | <ID>id_t_z_1498</ID> |
||
21272 | <String>WISEbot/1.0 (WISEbot@koreawisenut.com; http://wisebot.koreawisenut.com)</String> |
||
21273 | <Description>Korea Wisenut robot</Description> |
||
21274 | <Type>R</Type> |
||
21275 | <Comment></Comment> |
||
21276 | <Link1>http://www.koreawisenut.com/</Link1> |
||
21277 | <Link2></Link2> |
||
21278 | </user-agent> |
||
21279 | <user-agent> |
||
21280 | <ID>id_t_z_1499</ID> |
||
21281 | <String>WiseWire-Spider2</String> |
||
21282 | <Description>Wisewire domain checker (Discontinued)</Description> |
||
21283 | <Type>R C</Type> |
||
21284 | <Comment></Comment> |
||
21285 | <Link1>http://www.wisewire.com/</Link1> |
||
21286 | <Link2></Link2> |
||
21287 | </user-agent> |
||
21288 | <user-agent> |
||
21289 | <ID>id_t_z_110107_2</ID> |
||
21290 | <String>wish-project (http://wish.slis.tsukuba.ac.jp/)</String> |
||
21291 | <Description>WISH academic research project for link checking</Description> |
||
21292 | <Type>C</Type> |
||
21293 | <Comment>133.51.22.xx</Comment> |
||
21294 | <Link1>http://wish.slis.tsukuba.ac.jp/</Link1> |
||
21295 | <Link2></Link2> |
||
21296 | </user-agent> |
||
21297 | <user-agent> |
||
21298 | <ID>id_t_z_1500</ID> |
||
21299 | <String>WordChampBot</String> |
||
21300 | <Description>Wordchamp web page vocabulary / translation robot</Description> |
||
21301 | <Type>B D</Type> |
||
21302 | <Comment></Comment> |
||
21303 | <Link1>http://www.wordchamp.com/</Link1> |
||
21304 | <Link2></Link2> |
||
21305 | </user-agent> |
||
21306 | <user-agent> |
||
21307 | <ID>id_t_z_301105_1</ID> |
||
21308 | <String>WordPress/x.x.x.x PHP/4.x.xx</String> |
||
21309 | <Description>WordPress personal Blog publishing platform</Description> |
||
21310 | <Type>B</Type> |
||
21311 | <Comment></Comment> |
||
21312 | <Link1>http://wordpress.org/</Link1> |
||
21313 | <Link2></Link2> |
||
21314 | </user-agent> |
||
21315 | <user-agent> |
||
21316 | <ID>id_t_z_100207_1</ID> |
||
21317 | <String>worio heritrix bot (+http://worio.com/)</String> |
||
21318 | <Description>WORIO (beta) search for computer scientists and programmers using Heritrix open-source crawler</Description> |
||
21319 | <Type>R</Type> |
||
21320 | <Comment>137.82.84.xx</Comment> |
||
21321 | <Link1>http://www.worio.com/</Link1> |
||
21322 | <Link2>http://www.archive.org/</Link2> |
||
21323 | </user-agent> |
||
21324 | <user-agent> |
||
21325 | <ID>id_t_z_291007_1</ID> |
||
21326 | <String>woriobot ( http://www.worio.com/)</String> |
||
21327 | <Description>WORIO (beta) search for computer scientists and programmers via Amazon Web Services</Description> |
||
21328 | <Type>R</Type> |
||
21329 | <Comment>67.202.45.2xx</Comment> |
||
21330 | <Link1>http://www.worio.com/</Link1> |
||
21331 | <Link2>http://www.amazon.com/gp/browse.html?node=3435361</Link2> |
||
21332 | </user-agent> |
||
21333 | <user-agent> |
||
21334 | <ID>id_t_z_1501</ID> |
||
21335 | <String>WorldLight</String> |
||
21336 | <Description>Entireweb Search robot (62.13.25.xxx)</Description> |
||
21337 | <Type>R</Type> |
||
21338 | <Comment>s. also Mozilla/4.0 (compatible; SpeedySpider ....</Comment> |
||
21339 | <Link1>http://www.entireweb.com/</Link1> |
||
21340 | <Link2></Link2> |
||
21341 | </user-agent> |
||
21342 | <user-agent> |
||
21343 | <ID>id_t_z_1502</ID> |
||
21344 | <String>WorQmada/1.0</String> |
||
21345 | <Description>unknown link checking (from 4.18.57.126) ?</Description> |
||
21346 | <Type>C</Type> |
||
21347 | <Comment></Comment> |
||
21348 | <Link1></Link1> |
||
21349 | <Link2></Link2> |
||
21350 | </user-agent> |
||
21351 | <user-agent> |
||
21352 | <ID>id_t_z_1503</ID> |
||
21353 | <String>Wotbox/alpha0.6 (bot@wotbox.com; http://www.wotbox.com)</String> |
||
21354 | <Description>Wotbox spider</Description> |
||
21355 | <Type>R</Type> |
||
21356 | <Comment></Comment> |
||
21357 | <Link1>http://www.wotbox.com/</Link1> |
||
21358 | <Link2></Link2> |
||
21359 | </user-agent> |
||
21360 | <user-agent> |
||
21361 | <ID>id_t_z_1504</ID> |
||
21362 | <String>Wotbox/alpha0.x.x (bot@wotbox.com; http://www.wotbox.com) Java/1.4.1_02</String> |
||
21363 | <Description>Wotbox spider</Description> |
||
21364 | <Type>R</Type> |
||
21365 | <Comment></Comment> |
||
21366 | <Link1>http://www.wotbox.com/</Link1> |
||
21367 | <Link2></Link2> |
||
21368 | </user-agent> |
||
21369 | <user-agent> |
||
21370 | <ID>id_t_z_1505</ID> |
||
21371 | <String>WSB WebCrawler V1.0 (Beta)- cl@cs.uni-dortmund.de</String> |
||
21372 | <Description>WebSearchBench crawler from Dortmund University- Germany</Description> |
||
21373 | <Type>R</Type> |
||
21374 | <Comment></Comment> |
||
21375 | <Link1>http://websearchbench.cs.uni-dortmund.de/</Link1> |
||
21376 | <Link2></Link2> |
||
21377 | </user-agent> |
||
21378 | <user-agent> |
||
21379 | <ID>id_t_z_1506</ID> |
||
21380 | <String>WSB, http://websearchbench.cs.uni-dortmund.de</String> |
||
21381 | <Description>WebSearchBench crawler from Dortmund University- Germany</Description> |
||
21382 | <Type>R</Type> |
||
21383 | <Comment></Comment> |
||
21384 | <Link1>http://websearchbench.cs.uni-dortmund.de/</Link1> |
||
21385 | <Link2></Link2> |
||
21386 | </user-agent> |
||
21387 | <user-agent> |
||
21388 | <ID>id_t_z_1507</ID> |
||
21389 | <String>wume_crawler/1.1 (http://wume.cse.lehigh.edu/~xiq204/crawler/)</String> |
||
21390 | <Description>WUME Lab's web crawler (128.180.121.xxx)</Description> |
||
21391 | <Type>R</Type> |
||
21392 | <Comment></Comment> |
||
21393 | <Link1>http://wume.cse.lehigh.edu/~xiq204/crawler/</Link1> |
||
21394 | <Link2></Link2> |
||
21395 | </user-agent> |
||
21396 | <user-agent> |
||
21397 | <ID>id_t_z_1508</ID> |
||
21398 | <String>Wusage/x.0@boutell.com</String> |
||
21399 | <Description>Wusage log-file analysis</Description> |
||
21400 | <Type>R C</Type> |
||
21401 | <Comment></Comment> |
||
21402 | <Link1>http://www.boutell.com/wusage/</Link1> |
||
21403 | <Link2></Link2> |
||
21404 | </user-agent> |
||
21405 | <user-agent> |
||
21406 | <ID>id_t_z_120106_2</ID> |
||
21407 | <String>Wwlib/Linux</String> |
||
21408 | <Description>WWLib - Wolverhampton Univerity Web Library for classifying web documents</Description> |
||
21409 | <Type>R</Type> |
||
21410 | <Comment></Comment> |
||
21411 | <Link1>http://www.scit.wlv.ac.uk/wwlib/</Link1> |
||
21412 | <Link2></Link2> |
||
21413 | </user-agent> |
||
21414 | <user-agent> |
||
21415 | <ID>id_t_z_1509</ID> |
||
21416 | <String>WWSBOT 1.x [--- http://www.analyzer.nu ---]</String> |
||
21417 | <Description>WWSBOT web server version checker</Description> |
||
21418 | <Type>C</Type> |
||
21419 | <Comment></Comment> |
||
21420 | <Link1>http://www.analyzer.nu/Perl/WWSBOT.html</Link1> |
||
21421 | <Link2></Link2> |
||
21422 | </user-agent> |
||
21423 | <user-agent> |
||
21424 | <ID>id_t_z_170506_2</ID> |
||
21425 | <String>WWW-Mechanize/1.1x</String> |
||
21426 | <Description>Perl web page fetching module</Description> |
||
21427 | <Type>D</Type> |
||
21428 | <Comment></Comment> |
||
21429 | <Link1>http://search.cpan.org/dist/WWW-Mechanize/</Link1> |
||
21430 | <Link2></Link2> |
||
21431 | </user-agent> |
||
21432 | <user-agent> |
||
21433 | <ID>id_t_z_1510</ID> |
||
21434 | <String>www.arianna.it</String> |
||
21435 | <Description>Arianna robot</Description> |
||
21436 | <Type>R</Type> |
||
21437 | <Comment></Comment> |
||
21438 | <Link1>http://arianna.libero.it/</Link1> |
||
21439 | <Link2></Link2> |
||
21440 | </user-agent> |
||
21441 | <user-agent> |
||
21442 | <ID>id_t_z_1511</ID> |
||
21443 | <String>www.business-socket.com registry verify/1.x</String> |
||
21444 | <Description>Business-Socket.com link checking ?</Description> |
||
21445 | <Type>C</Type> |
||
21446 | <Comment></Comment> |
||
21447 | <Link1>http://www.business-socket.com</Link1> |
||
21448 | <Link2></Link2> |
||
21449 | </user-agent> |
||
21450 | <user-agent> |
||
21451 | <ID>id_t_z_221006_2</ID> |
||
21452 | <String>www.doweb.co.uk crawler</String> |
||
21453 | <Description>The DoWeb UK Business directory link checking</Description> |
||
21454 | <Type>C</Type> |
||
21455 | <Comment>85.13.252.x</Comment> |
||
21456 | <Link1>http://www.doweb.co.uk/action_home+page.htm</Link1> |
||
21457 | <Link2></Link2> |
||
21458 | </user-agent> |
||
21459 | <user-agent> |
||
21460 | <ID>id_t_z_1512</ID> |
||
21461 | <String>www4mail/2.x libwww-FM/2.14 (Unix; I)</String> |
||
21462 | <Description>www4mail - web navigation & database search by e-mail</Description> |
||
21463 | <Type></Type> |
||
21464 | <Comment></Comment> |
||
21465 | <Link1>http://www4mail.org/</Link1> |
||
21466 | <Link2></Link2> |
||
21467 | </user-agent> |
||
21468 | <user-agent> |
||
21469 | <ID>id_t_z_1513</ID> |
||
21470 | <String>WWWC/1.0x</String> |
||
21471 | <Description>WWWC Updating check of Web pages. (Japanese only)</Description> |
||
21472 | <Type>C</Type> |
||
21473 | <Comment></Comment> |
||
21474 | <Link1>http://www.nakka.com/soft/index_eng.html</Link1> |
||
21475 | <Link2></Link2> |
||
21476 | </user-agent> |
||
21477 | <user-agent> |
||
21478 | <ID>id_t_z_1514</ID> |
||
21479 | <String>WWWeasel Robot v1.00 (http://wwweasel.de)</String> |
||
21480 | <Description>World Wide Weasel Germany robot</Description> |
||
21481 | <Type>R</Type> |
||
21482 | <Comment></Comment> |
||
21483 | <Link1>http://wwweasel.de/</Link1> |
||
21484 | <Link2></Link2> |
||
21485 | </user-agent> |
||
21486 | <user-agent> |
||
21487 | <ID>id_t_z_1515</ID> |
||
21488 | <String>WWWOFFLE/2.x</String> |
||
21489 | <Description>WWWoffle download manager</Description> |
||
21490 | <Type>D</Type> |
||
21491 | <Comment></Comment> |
||
21492 | <Link1>http://www.gedanken.demon.co.uk/wwwoffle/</Link1> |
||
21493 | <Link2></Link2> |
||
21494 | </user-agent> |
||
21495 | <user-agent> |
||
21496 | <ID>id_t_z_1516</ID> |
||
21497 | <String>wwwster/1.x (Beta- mailto:gue@cis.uni-muenchen.de)</String> |
||
21498 | <Description>Unknown robot from CIS at Munich University</Description> |
||
21499 | <Type>R</Type> |
||
21500 | <Comment>129.187.254.xxx</Comment> |
||
21501 | <Link1>http://www.cis.uni-muenchen.de/</Link1> |
||
21502 | <Link2></Link2> |
||
21503 | </user-agent> |
||
21504 | <user-agent> |
||
21505 | <ID>id_t_z_050208_5</ID> |
||
21506 | <String>wxDownload Fast</String> |
||
21507 | <Description>wxDownload Fast (wxDFast) open source download manager</Description> |
||
21508 | <Type>D</Type> |
||
21509 | <Comment></Comment> |
||
21510 | <Link1>http://dfast.sourceforge.net/index.html</Link1> |
||
21511 | <Link2></Link2> |
||
21512 | </user-agent> |
||
21513 | <user-agent> |
||
21514 | <ID>id_t_z_1517</ID> |
||
21515 | <String>X-Crawler </String> |
||
21516 | <Description>Arexera (Germany) crawler software</Description> |
||
21517 | <Type>R</Type> |
||
21518 | <Comment></Comment> |
||
21519 | <Link1>http://www.arexera.de/de/products/crawler.php</Link1> |
||
21520 | <Link2></Link2> |
||
21521 | </user-agent> |
||
21522 | <user-agent> |
||
21523 | <ID>id_t_z_1518</ID> |
||
21524 | <String>Xaldon WebSpider</String> |
||
21525 | <Description>Xaldon WebSpider offline browser</Description> |
||
21526 | <Type>B D</Type> |
||
21527 | <Comment></Comment> |
||
21528 | <Link1>http://www.xaldon.de/produkte_webspider.html</Link1> |
||
21529 | <Link2></Link2> |
||
21530 | </user-agent> |
||
21531 | <user-agent> |
||
21532 | <ID>id_t_z_1519</ID> |
||
21533 | <String>Xenu Link Sleuth 1.xx</String> |
||
21534 | <Description>Xenu link checker</Description> |
||
21535 | <Type>C</Type> |
||
21536 | <Comment></Comment> |
||
21537 | <Link1>http://home.snafu.de/tilman/xenulink.html</Link1> |
||
21538 | <Link2></Link2> |
||
21539 | </user-agent> |
||
21540 | <user-agent> |
||
21541 | <ID>id_t_z_1520</ID> |
||
21542 | <String>Xenu's Link Sleuth 1.x[a-z]</String> |
||
21543 | <Description>Xenu link checker</Description> |
||
21544 | <Type>C</Type> |
||
21545 | <Comment></Comment> |
||
21546 | <Link1>http://home.snafu.de/tilman/xenulink.html</Link1> |
||
21547 | <Link2></Link2> |
||
21548 | </user-agent> |
||
21549 | <user-agent> |
||
21550 | <ID>id_t_z_270706_2</ID> |
||
21551 | <String>Xerka WebBot v1.0.0 [UPVOpenDir]</String> |
||
21552 | <Description>XerKa text mining and information retrieval software</Description> |
||
21553 | <Type>D</Type> |
||
21554 | <Comment></Comment> |
||
21555 | <Link1>http://www.diana-teknologia.com/www1/english/xerka.htm</Link1> |
||
21556 | <Link2></Link2> |
||
21557 | </user-agent> |
||
21558 | <user-agent> |
||
21559 | <ID>id_t_z_250106_2</ID> |
||
21560 | <String>xine/1.0</String> |
||
21561 | <Description>xine - free Linux / OS/2 multimedia player</Description> |
||
21562 | <Type>B</Type> |
||
21563 | <Comment></Comment> |
||
21564 | <Link1>http://xinehq.de/</Link1> |
||
21565 | <Link2></Link2> |
||
21566 | </user-agent> |
||
21567 | <user-agent> |
||
21568 | <ID>id_t_z_141205_3</ID> |
||
21569 | <String>xirq/0.1-beta (xirq; http://www.xirq.com; xirq@xirq.com)</String> |
||
21570 | <Description>XIRQ search (beta) robot (70.86.206.1xx)</Description> |
||
21571 | <Type>R</Type> |
||
21572 | <Comment></Comment> |
||
21573 | <Link1>http://www.xirq.com/</Link1> |
||
21574 | <Link2></Link2> |
||
21575 | </user-agent> |
||
21576 | <user-agent> |
||
21577 | <ID>id_t_z_160806_1</ID> |
||
21578 | <String>XMLSlurp/0.1 libwww-perl/5.805</String> |
||
21579 | <Description>GPath / XMLSlurp - Expression language for tree structured data</Description> |
||
21580 | <Type></Type> |
||
21581 | <Comment></Comment> |
||
21582 | <Link1>http://groovy.codehaus.org/GPath</Link1> |
||
21583 | <Link2></Link2> |
||
21584 | </user-agent> |
||
21585 | <user-agent> |
||
21586 | <ID>id_t_z_070506_1</ID> |
||
21587 | <String>XRL/2.00b1 (Linux; i686; en-us) (+http://metamark.net/about)</String> |
||
21588 | <Description>Metamark URL Shorten Service</Description> |
||
21589 | <Type>P</Type> |
||
21590 | <Comment></Comment> |
||
21591 | <Link1>http://metamark.net/</Link1> |
||
21592 | <Link2></Link2> |
||
21593 | </user-agent> |
||
21594 | <user-agent> |
||
21595 | <ID>id_t_z_200308_3</ID> |
||
21596 | <String>Xylix</String> |
||
21597 | <Description>Xylix Retrieval System software</Description> |
||
21598 | <Type>C</Type> |
||
21599 | <Comment></Comment> |
||
21600 | <Link1>http://www.xylixsoftware.ch/retrievalsystem.php</Link1> |
||
21601 | <Link2></Link2> |
||
21602 | </user-agent> |
||
21603 | <user-agent> |
||
21604 | <ID>id_t_z_1521</ID> |
||
21605 | <String>xyro_(xcrawler@cosmos.inria.fr)</String> |
||
21606 | <Description>Inria Crawler</Description> |
||
21607 | <Type>R</Type> |
||
21608 | <Comment></Comment> |
||
21609 | <Link1>http://www.inria.fr/</Link1> |
||
21610 | <Link2></Link2> |
||
21611 | </user-agent> |
||
21612 | <user-agent> |
||
21613 | <ID>id_t_z_081205_1</ID> |
||
21614 | <String>Y!J-BSC/1.0 (http://help.yahoo.co.jp/help/jp/search/indexing/indexing-15.html)</String> |
||
21615 | <Description>Yahoo Search Japan robot (211.14.8.2xx)</Description> |
||
21616 | <Type>R</Type> |
||
21617 | <Comment>s. also Mozilla/4.0 (compatible; Y!J...</Comment> |
||
21618 | <Link1>http://www.yahoo.co.jp/</Link1> |
||
21619 | <Link2></Link2> |
||
21620 | </user-agent> |
||
21621 | <user-agent> |
||
21622 | <ID>id_t_z_271006_2</ID> |
||
21623 | <String>Y!J-SRD/1.0</String> |
||
21624 | <Description>Yahoo Search Japan robot (203.216.197.xxx)</Description> |
||
21625 | <Type>R</Type> |
||
21626 | <Comment>s. also DoCoMo/2.0/SO502i (compatible; Y!J-SRD/1.0 ...</Comment> |
||
21627 | <Link1>http://www.yahoo.co.jp/</Link1> |
||
21628 | <Link2></Link2> |
||
21629 | </user-agent> |
||
21630 | <user-agent> |
||
21631 | <ID>id_t_z_240106_3</ID> |
||
21632 | <String>Y!J/1.0 (http://help.yahoo.co.jp/help/jp/search/indexing/indexing-15.html)</String> |
||
21633 | <Description>Yahoo Search Japan robot (211.14.8.2xx)</Description> |
||
21634 | <Type>R</Type> |
||
21635 | <Comment>s. also Mozilla/4.0 (compatible; Y!J...</Comment> |
||
21636 | <Link1>http://www.yahoo.co.jp/</Link1> |
||
21637 | <Link2></Link2> |
||
21638 | </user-agent> |
||
21639 | <user-agent> |
||
21640 | <ID>id_t_z_220206_2</ID> |
||
21641 | <String>Y!OASIS/TEST no-ad Mozilla/4.08 [en] (X11; I; FreeBSD 2.2.8-STABLE i386)</String> |
||
21642 | <Description>Yahoo picture service for mobiles</Description> |
||
21643 | <Type>P</Type> |
||
21644 | <Comment>217.12.4.xx</Comment> |
||
21645 | <Link1></Link1> |
||
21646 | <Link2></Link2> |
||
21647 | </user-agent> |
||
21648 | <user-agent> |
||
21649 | <ID>id_t_z_1522</ID> |
||
21650 | <String>Y!TunnelPro</String> |
||
21651 | <Description>Y!TunnelPro - Yahoo! Messenger companion user agent</Description> |
||
21652 | <Type>B</Type> |
||
21653 | <Comment> s. YTunnelPro</Comment> |
||
21654 | <Link1>http://www.ytunnelpro.com/</Link1> |
||
21655 | <Link2></Link2> |
||
21656 | </user-agent> |
||
21657 | <user-agent> |
||
21658 | <ID>id_t_z_121205_1</ID> |
||
21659 | <String>yacy (www.yacy.net; v20040602; i386 Linux 2.4.26-gentoo-r13; java 1.4.2_06; MET/en)</String> |
||
21660 | <Description>Yacy distributed P2P web search engine robot</Description> |
||
21661 | <Type>R</Type> |
||
21662 | <Comment></Comment> |
||
21663 | <Link1>http://www.yacy.net/</Link1> |
||
21664 | <Link2></Link2> |
||
21665 | </user-agent> |
||
21666 | <user-agent> |
||
21667 | <ID>id_t_z_260306_4</ID> |
||
21668 | <String>yacybot (x86 Windows XP 5.1; java 1.5.0_06; Europe/de) yacy.net</String> |
||
21669 | <Description>Yacy distributed P2P web search engine robot</Description> |
||
21670 | <Type>R</Type> |
||
21671 | <Comment></Comment> |
||
21672 | <Link1>http://www.yacy.net/</Link1> |
||
21673 | <Link2></Link2> |
||
21674 | </user-agent> |
||
21675 | <user-agent> |
||
21676 | <ID>id_t_z_300707_2</ID> |
||
21677 | <String>Yahoo Pipes 1.0</String> |
||
21678 | <Description>(Yahoo) Pipes interactive data aggregator robot</Description> |
||
21679 | <Type>R</Type> |
||
21680 | <Comment></Comment> |
||
21681 | <Link1>http://pipes.yahoo.com/pipes/</Link1> |
||
21682 | <Link2></Link2> |
||
21683 | </user-agent> |
||
21684 | <user-agent> |
||
21685 | <ID>id_t_z_100406_2</ID> |
||
21686 | <String>Yahoo! Mindset</String> |
||
21687 | <Description>Yahoo Mindset: Intent-driven Search (66.228.182.1xx)</Description> |
||
21688 | <Type>R</Type> |
||
21689 | <Comment>s. also Mozilla/4.0</Comment> |
||
21690 | <Link1>http://mindset.research.yahoo.com/</Link1> |
||
21691 | <Link2></Link2> |
||
21692 | </user-agent> |
||
21693 | <user-agent> |
||
21694 | <ID>id_t_z_040106_2</ID> |
||
21695 | <String>Yahoo-Blogs/v3.9 (compatible; Mozilla 4.0; MSIE 5.5; http://help.yahoo.com/help/us/ysearch/crawling/crawling-02.html )</String> |
||
21696 | <Description>Yahoo blog indexing robot (209.191.83.1xx)</Description> |
||
21697 | <Type>R</Type> |
||
21698 | <Comment></Comment> |
||
21699 | <Link1>http://help.yahoo.com/help/us/ysearch/crawling/crawling-02.html</Link1> |
||
21700 | <Link2></Link2> |
||
21701 | </user-agent> |
||
21702 | <user-agent> |
||
21703 | <ID>id_t_z_1523</ID> |
||
21704 | <String>Yahoo-MMAudVid/1.0 (mms dash mmaudvidcrawler dash support at yahoo dash inc dot com)</String> |
||
21705 | <Description>Yahoo multimedia crawler (206.190.43.xx)</Description> |
||
21706 | <Type>R</Type> |
||
21707 | <Comment></Comment> |
||
21708 | <Link1></Link1> |
||
21709 | <Link2></Link2> |
||
21710 | </user-agent> |
||
21711 | <user-agent> |
||
21712 | <ID>id_t_z_080108_2</ID> |
||
21713 | <String>Yahoo-MMAudVid/2.0(mms dash mm aud vid crawler dash support at yahoo dash inc.com ;Mozilla 4.0 compatible; MSIE 7.0;Windows NT 5.0; .NET CLR 2.0)</String> |
||
21714 | <Description>Yahoo multimedia crawler</Description> |
||
21715 | <Type>R</Type> |
||
21716 | <Comment></Comment> |
||
21717 | <Link1></Link1> |
||
21718 | <Link2></Link2> |
||
21719 | </user-agent> |
||
21720 | <user-agent> |
||
21721 | <ID>id_t_z_1524</ID> |
||
21722 | <String>Yahoo-MMCrawler/3.x (mm dash crawler at trd dot overture dot com)</String> |
||
21723 | <Description>Yahoo multimedia crawler via Fastsearch.net (66.77.73.xx)</Description> |
||
21724 | <Type>R</Type> |
||
21725 | <Comment>see also FAST-WebCrawler/3.x Multimedia...</Comment> |
||
21726 | <Link1></Link1> |
||
21727 | <Link2></Link2> |
||
21728 | </user-agent> |
||
21729 | <user-agent> |
||
21730 | <ID>id_t_z_110806_1</ID> |
||
21731 | <String>Yahoo-Test/4.0</String> |
||
21732 | <Description>Yahoo Search robot</Description> |
||
21733 | <Type>R</Type> |
||
21734 | <Comment>216.145.49.xx</Comment> |
||
21735 | <Link1></Link1> |
||
21736 | <Link2></Link2> |
||
21737 | </user-agent> |
||
21738 | <user-agent> |
||
21739 | <ID>id_t_z_1525</ID> |
||
21740 | <String>Yahoo-VerticalCrawler-FormerWebCrawler/3.9 crawler at trd dot overture dot com; http://www.alltheweb.com/help/webmaster/crawler</String> |
||
21741 | <Description>Yahoo crawler via Overture (66.77.73.3x)</Description> |
||
21742 | <Type>R</Type> |
||
21743 | <Comment></Comment> |
||
21744 | <Link1></Link1> |
||
21745 | <Link2></Link2> |
||
21746 | </user-agent> |
||
21747 | <user-agent> |
||
21748 | <ID>id_t_z_010906_2</ID> |
||
21749 | <String>YahooFeedSeeker/2.0 (compatible; Mozilla 4.0; MSIE 5.5; http://publisher.yahoo.com/rssguide)</String> |
||
21750 | <Description>Yahoo Publisher Network RSS crawler</Description> |
||
21751 | <Type>R</Type> |
||
21752 | <Comment></Comment> |
||
21753 | <Link1>http://publisher.yahoo.com/rssguide</Link1> |
||
21754 | <Link2></Link2> |
||
21755 | </user-agent> |
||
21756 | <user-agent> |
||
21757 | <ID>id_t_z_1526</ID> |
||
21758 | <String>YahooSeeker-Testing/v3.9 (compatible; Mozilla 4.0; MSIE 5.5; http://search.yahoo.com/)</String> |
||
21759 | <Description>Yahoo Product Search crawler ( 68.142.195..x)</Description> |
||
21760 | <Type>R</Type> |
||
21761 | <Comment></Comment> |
||
21762 | <Link1></Link1> |
||
21763 | <Link2></Link2> |
||
21764 | </user-agent> |
||
21765 | <user-agent> |
||
21766 | <ID>id_t_z_1527</ID> |
||
21767 | <String>YahooSeeker/1.0 (compatible; Mozilla 4.0; MSIE 5.5; http://help.yahoo.com/help/us/shop/merchant/)</String> |
||
21768 | <Description>Yahoo Product Search crawler ( 66.196.93.x)</Description> |
||
21769 | <Type>R</Type> |
||
21770 | <Comment></Comment> |
||
21771 | <Link1></Link1> |
||
21772 | <Link2></Link2> |
||
21773 | </user-agent> |
||
21774 | <user-agent> |
||
21775 | <ID>id_t_z_1528</ID> |
||
21776 | <String>YahooSeeker/1.0 (compatible; Mozilla 4.0; MSIE 5.5; http://search.yahoo.com/yahooseeker.html)</String> |
||
21777 | <Description>Yahoo Product Search crawler ( 66.196.93.x)</Description> |
||
21778 | <Type>R</Type> |
||
21779 | <Comment></Comment> |
||
21780 | <Link1></Link1> |
||
21781 | <Link2></Link2> |
||
21782 | </user-agent> |
||
21783 | <user-agent> |
||
21784 | <ID>id_t_z_1529</ID> |
||
21785 | <String>YahooSeeker/1.1 (compatible; Mozilla 4.0; MSIE 5.5; http://help.yahoo.com/help/us/shop/merchant/)</String> |
||
21786 | <Description>Yahoo Product Search crawler ( 66.196.93.x)</Description> |
||
21787 | <Type>R</Type> |
||
21788 | <Comment></Comment> |
||
21789 | <Link1></Link1> |
||
21790 | <Link2></Link2> |
||
21791 | </user-agent> |
||
21792 | <user-agent> |
||
21793 | <ID>id_t_z_1530</ID> |
||
21794 | <String>YahooSeeker/bsv3.9 (compatible; Mozilla 4.0; MSIE 5.5; http://help.yahoo.com/help/us/ysearch/crawling/crawling-02.html )</String> |
||
21795 | <Description>Yahoo Product Search crawler ( 68.142.195..x)</Description> |
||
21796 | <Type>R</Type> |
||
21797 | <Comment></Comment> |
||
21798 | <Link1></Link1> |
||
21799 | <Link2></Link2> |
||
21800 | </user-agent> |
||
21801 | <user-agent> |
||
21802 | <ID>id_t_z_1531</ID> |
||
21803 | <String>YahooSeeker/CafeKelsa-dev (compatible; Konqueror/3.2; FreeBSD ;cafekelsa-dev-webmaster@yahoo-inc.com )</String> |
||
21804 | <Description>Yahoo robot</Description> |
||
21805 | <Type>R</Type> |
||
21806 | <Comment>64.157.137.xxx</Comment> |
||
21807 | <Link1></Link1> |
||
21808 | <Link2></Link2> |
||
21809 | </user-agent> |
||
21810 | <user-agent> |
||
21811 | <ID>id_t_z_231106_2</ID> |
||
21812 | <String>Yandex/1.01.001 (compatible; Win16; I)</String> |
||
21813 | <Description>Yandex Search Russia link checking (213.180.206.2xx)</Description> |
||
21814 | <Type>R</Type> |
||
21815 | <Comment>s. also Mozilla/4.0 (compatible; MSIE 5.0; YANDEX)</Comment> |
||
21816 | <Link1>http://www.yandex.ru</Link1> |
||
21817 | <Link2></Link2> |
||
21818 | </user-agent> |
||
21819 | <user-agent> |
||
21820 | <ID>id_t_z_301108_2</ID> |
||
21821 | <String>Yanga WorldSearch Bot v1.1/beta (http://www.yanga.co.uk/)</String> |
||
21822 | <Description>Yanga search robot by Gigabase (Russian Federation)</Description> |
||
21823 | <Type>R</Type> |
||
21824 | <Comment>91.205.124.x</Comment> |
||
21825 | <Link1>http://www.yanga.co.uk/</Link1> |
||
21826 | <Link2></Link2> |
||
21827 | </user-agent> |
||
21828 | <user-agent> |
||
21829 | <ID>id_t_z_1532</ID> |
||
21830 | <String>yarienavoir.net/0.2</String> |
||
21831 | <Description>Yarienavoir search (Belgium) robot</Description> |
||
21832 | <Type>R</Type> |
||
21833 | <Comment>217.71.121.xx</Comment> |
||
21834 | <Link1>http://www.yarienavoir.net/</Link1> |
||
21835 | <Link2></Link2> |
||
21836 | </user-agent> |
||
21837 | <user-agent> |
||
21838 | <ID>id_t_z_300506_1</ID> |
||
21839 | <String>Yeti</String> |
||
21840 | <Description>1noon.com search Korea robot (222.231.21.xxx)</Description> |
||
21841 | <Type>R</Type> |
||
21842 | <Comment>uses also a blank UA field</Comment> |
||
21843 | <Link1>http://www.1noon.com/</Link1> |
||
21844 | <Link2></Link2> |
||
21845 | </user-agent> |
||
21846 | <user-agent> |
||
21847 | <ID>id_t_z_040407_1</ID> |
||
21848 | <String>Yeti/0.01 (nhn/1noon, yetibot@naver.com, check robots.txt daily and follows it)</String> |
||
21849 | <Description>1noon.com search Korea robot (222.231.21.xxx)</Description> |
||
21850 | <Type>R</Type> |
||
21851 | <Comment>uses also a blank UA field</Comment> |
||
21852 | <Link1>http://www.1noon.com/</Link1> |
||
21853 | <Link2></Link2> |
||
21854 | </user-agent> |
||
21855 | <user-agent> |
||
21856 | <ID>id_t_z_301108_1</ID> |
||
21857 | <String>Yeti/1.0 (NHN Corp.; http://help.naver.com/robots/)</String> |
||
21858 | <Description>Naver search (Korea) robot</Description> |
||
21859 | <Type>R</Type> |
||
21860 | <Comment>61.247.222.xx</Comment> |
||
21861 | <Link1>http://www.naver.com/</Link1> |
||
21862 | <Link2></Link2> |
||
21863 | </user-agent> |
||
21864 | <user-agent> |
||
21865 | <ID>id_t_z_290407_2</ID> |
||
21866 | <String>yggdrasil/Nutch-0.9 (yggdrasil biorelated search engine; www dot biotec dot tu minus dresden do de slash schroeder; heiko dot dietze at biotec dot tu minus dresden dot de)</String> |
||
21867 | <Description>yggdrasil spider for GoPubMed biorelated search engine</Description> |
||
21868 | <Type>R</Type> |
||
21869 | <Comment>141.30.193.x[x]</Comment> |
||
21870 | <Link1>http://www.biotec.tu-dresden.de/schroeder</Link1> |
||
21871 | <Link2>http://gopubmed.biotec.tu-dresden.de/</Link2> |
||
21872 | </user-agent> |
||
21873 | <user-agent> |
||
21874 | <ID>id_t_z_211206_3</ID> |
||
21875 | <String>YodaoBot/1.0 (http://www.yodao.com/help/webmaster/spider/; )</String> |
||
21876 | <Description>Yodao search (China)</Description> |
||
21877 | <Type>R</Type> |
||
21878 | <Comment>60.191.80.xx</Comment> |
||
21879 | <Link1>http://www.yodao.com/</Link1> |
||
21880 | <Link2></Link2> |
||
21881 | </user-agent> |
||
21882 | <user-agent> |
||
21883 | <ID>id_t_z_110308_1</ID> |
||
21884 | <String>yoofind/yoofind-0.1-dev (yoono webcrawler; http://www.yoono.com ; MyEmail)</String> |
||
21885 | <Description>Yoono - community based search (193.110.140.xxx / 194.0.179.[x]xx)</Description> |
||
21886 | <Type>R</Type> |
||
21887 | <Comment>s. also Mozilla/5.0 (compatible; Yoono; http://www.yoono.com/) - yoono/1.0 web-crawler ..</Comment> |
||
21888 | <Link1>http://www.yoono.com/</Link1> |
||
21889 | <Link2></Link2> |
||
21890 | </user-agent> |
||
21891 | <user-agent> |
||
21892 | <ID>id_t_z_210106_3</ID> |
||
21893 | <String>yoogliFetchAgent/0.1</String> |
||
21894 | <Description>Yoogli search (under development) agent</Description> |
||
21895 | <Type>R</Type> |
||
21896 | <Comment></Comment> |
||
21897 | <Link1>http://www.yoogli.com/</Link1> |
||
21898 | <Link2></Link2> |
||
21899 | </user-agent> |
||
21900 | <user-agent> |
||
21901 | <ID>id_t_z_120606_1</ID> |
||
21902 | <String>yoono/1.0 web-crawler/1.0</String> |
||
21903 | <Description>Yoono - community based search (193.110.140.xxx / 194.0.179.[x]xx)</Description> |
||
21904 | <Type>R</Type> |
||
21905 | <Comment>s. also Mozilla/5.0 (compatible; Yoono; http://www.yoono.com/) - yoofind/yoofind ..</Comment> |
||
21906 | <Link1>http://www.yoono.com/</Link1> |
||
21907 | <Link2></Link2> |
||
21908 | </user-agent> |
||
21909 | <user-agent> |
||
21910 | <ID>id_t_z_1533</ID> |
||
21911 | <String>YottaCars_Bot/4.12 (+http://www.yottacars.com) Car Search Engine </String> |
||
21912 | <Description>YottaCars bot - YottaCar car search engine ( 64.62.175.xxx)</Description> |
||
21913 | <Type>R</Type> |
||
21914 | <Comment>s. also OmniExplorer_Bot</Comment> |
||
21915 | <Link1>http://www.yottacars.com/</Link1> |
||
21916 | <Link2></Link2> |
||
21917 | </user-agent> |
||
21918 | <user-agent> |
||
21919 | <ID>id_t_z_1534</ID> |
||
21920 | <String>YottaShopping_Bot/4.12 (+http://www.yottashopping.com) Shopping Search Engine</String> |
||
21921 | <Description>YottaShopping bot - YottaShopping search engine ( 64.62.175.xxx) </Description> |
||
21922 | <Type>R</Type> |
||
21923 | <Comment>s. also OmniExplorer_Bot</Comment> |
||
21924 | <Link1>http://www.yottashopping.com/</Link1> |
||
21925 | <Link2></Link2> |
||
21926 | </user-agent> |
||
21927 | <user-agent> |
||
21928 | <ID>id_t_z_1535</ID> |
||
21929 | <String>YTunnelPro</String> |
||
21930 | <Description>Y!TunnelPro - Yahoo! Messenger companion user agent</Description> |
||
21931 | <Type>B</Type> |
||
21932 | <Comment>s. Y!TunnelPro</Comment> |
||
21933 | <Link1>http://www.ytunnelpro.com/</Link1> |
||
21934 | <Link2></Link2> |
||
21935 | </user-agent> |
||
21936 | <user-agent> |
||
21937 | <ID>id_t_z_1536</ID> |
||
21938 | <String>Z-Add Link Checker (http://w3.z-add.co.uk/linkcheck/)</String> |
||
21939 | <Description>Z-Add online link checker</Description> |
||
21940 | <Type>C</Type> |
||
21941 | <Comment></Comment> |
||
21942 | <Link1>http://w3.z-add.co.uk/linkcheck/</Link1> |
||
21943 | <Link2></Link2> |
||
21944 | </user-agent> |
||
21945 | <user-agent> |
||
21946 | <ID>id_t_z_1537</ID> |
||
21947 | <String>Zao-Crawler</String> |
||
21948 | <Description>Zao crawler for Kototoi Project</Description> |
||
21949 | <Type>R</Type> |
||
21950 | <Comment></Comment> |
||
21951 | <Link1>http://www.kototoi.org/zao/</Link1> |
||
21952 | <Link2></Link2> |
||
21953 | </user-agent> |
||
21954 | <user-agent> |
||
21955 | <ID>id_t_z_1538</ID> |
||
21956 | <String>Zao-Crawler 0.2b</String> |
||
21957 | <Description>Zao crawler for Kototoi Project</Description> |
||
21958 | <Type>R</Type> |
||
21959 | <Comment></Comment> |
||
21960 | <Link1>http://www.kototoi.org/zao/</Link1> |
||
21961 | <Link2></Link2> |
||
21962 | </user-agent> |
||
21963 | <user-agent> |
||
21964 | <ID>id_t_z_1539</ID> |
||
21965 | <String>Zao/0.1 (http://www.kototoi.org/zao/)</String> |
||
21966 | <Description>Zao crawler for Kototoi Project</Description> |
||
21967 | <Type>R</Type> |
||
21968 | <Comment></Comment> |
||
21969 | <Link1>http://www.kototoi.org/zao/</Link1> |
||
21970 | <Link2></Link2> |
||
21971 | </user-agent> |
||
21972 | <user-agent> |
||
21973 | <ID>id_t_z_1540</ID> |
||
21974 | <String>ZBot/1.00 (icaulfield@zeus.com)</String> |
||
21975 | <Description>Zeus Internet Marketing Robot based on Webster Pro component</Description> |
||
21976 | <Type>R</Type> |
||
21977 | <Comment></Comment> |
||
21978 | <Link1>http://cyber-robotics.com/</Link1> |
||
21979 | <Link2>http://www.homepagesw.com/</Link2> |
||
21980 | </user-agent> |
||
21981 | <user-agent> |
||
21982 | <ID>id_t_z_111205_5</ID> |
||
21983 | <String>Zearchit</String> |
||
21984 | <Description>Zearchit German search / directory</Description> |
||
21985 | <Type>R</Type> |
||
21986 | <Comment>212.227.109.1xx</Comment> |
||
21987 | <Link1>http://www.zearchit.de/</Link1> |
||
21988 | <Link2></Link2> |
||
21989 | </user-agent> |
||
21990 | <user-agent> |
||
21991 | <ID>id_t_z_130106_2</ID> |
||
21992 | <String>ZeBot_lseek.net (bot@ze.bz)</String> |
||
21993 | <Description>Ze.bz Moteur de Recherche robot</Description> |
||
21994 | <Type>R</Type> |
||
21995 | <Comment>213.251.135.xx</Comment> |
||
21996 | <Link1>http://www.ze.bz/</Link1> |
||
21997 | <Link2></Link2> |
||
21998 | </user-agent> |
||
21999 | <user-agent> |
||
22000 | <ID>id_t_z_1541</ID> |
||
22001 | <String>ZeBot_www.ze.bz (ze.bz@hotmail.com)</String> |
||
22002 | <Description>Ze.bz Moteur de Recherche robot</Description> |
||
22003 | <Type>R</Type> |
||
22004 | <Comment>213.251.135.xx</Comment> |
||
22005 | <Link1>http://www.ze.bz/</Link1> |
||
22006 | <Link2></Link2> |
||
22007 | </user-agent> |
||
22008 | <user-agent> |
||
22009 | <ID>id_t_z_130806_2</ID> |
||
22010 | <String>zedzo.digest/0.1 (http://www.zedzo.com/)</String> |
||
22011 | <Description>ZedZo Search (beta) robot</Description> |
||
22012 | <Type>R</Type> |
||
22013 | <Comment>24.62.50.1xx</Comment> |
||
22014 | <Link1>http://www.zedzo.com/</Link1> |
||
22015 | <Link2></Link2> |
||
22016 | </user-agent> |
||
22017 | <user-agent> |
||
22018 | <ID>id_t_z_210807_2</ID> |
||
22019 | <String>Zend_Http_Client</String> |
||
22020 | <Description>Zend PHP frameworks Zend_Http_Client component</Description> |
||
22021 | <Type>D</Type> |
||
22022 | <Comment></Comment> |
||
22023 | <Link1>http://framework.zend.com/manual/en/zend.http.html</Link1> |
||
22024 | <Link2></Link2> |
||
22025 | </user-agent> |
||
22026 | <user-agent> |
||
22027 | <ID>id_t_z_290208_2</ID> |
||
22028 | <String>zermelo Mozilla/5.0 compatible; heritrix/1.12.1 (+http://www.powerset.com) [email:crawl@powerset.com,email:paul@page-store.com]</String> |
||
22029 | <Description>Powerset Natural Language Search crawler (under development) using Heritrix via Amazon Web Services</Description> |
||
22030 | <Type>R</Type> |
||
22031 | <Comment>67.202.34.xxx</Comment> |
||
22032 | <Link1>http://www.powerset.com/</Link1> |
||
22033 | <Link2>http://www.amazon.com/gp/browse.html?node=3435361</Link2> |
||
22034 | </user-agent> |
||
22035 | <user-agent> |
||
22036 | <ID>id_t_z_1542</ID> |
||
22037 | <String>zerxbot/Version 0.6 libwww-perl/5.79</String> |
||
22038 | <Description>Zerx search robot ?</Description> |
||
22039 | <Type>R</Type> |
||
22040 | <Comment>138.88.147.xxx</Comment> |
||
22041 | <Link1>http://www.zerx.com/</Link1> |
||
22042 | <Link2></Link2> |
||
22043 | </user-agent> |
||
22044 | <user-agent> |
||
22045 | <ID>id_t_z_1543</ID> |
||
22046 | <String>Zeus ThemeSite Viewer Webster Pro V2.9 Win32</String> |
||
22047 | <Description>Zeus Internet Marketing Robot (based on Webster Pro)</Description> |
||
22048 | <Type>R</Type> |
||
22049 | <Comment></Comment> |
||
22050 | <Link1>http://cyber-robotics.com/</Link1> |
||
22051 | <Link2></Link2> |
||
22052 | </user-agent> |
||
22053 | <user-agent> |
||
22054 | <ID>id_t_z_1544</ID> |
||
22055 | <String>Zeus xxxxx Webster Pro V2.9 Win32</String> |
||
22056 | <Description>Zeus Internet Marketing Robot (based on Webster Pro)</Description> |
||
22057 | <Type>R</Type> |
||
22058 | <Comment></Comment> |
||
22059 | <Link1>http://cyber-robotics.com/</Link1> |
||
22060 | <Link2></Link2> |
||
22061 | </user-agent> |
||
22062 | <user-agent> |
||
22063 | <ID>id_t_z_281105_1</ID> |
||
22064 | <String>Zeusbot/0.07 (Ulysseek's web-crawling robot; http://www.zeusbot.com; agent@zeusbot.com)</String> |
||
22065 | <Description>Zeusbot robot for building the Ulsysseek.com index</Description> |
||
22066 | <Type>R</Type> |
||
22067 | <Comment>powered by Nutch</Comment> |
||
22068 | <Link1>http://www.zeusbot.com/</Link1> |
||
22069 | <Link2>http://www.ulysseek.com/</Link2> |
||
22070 | </user-agent> |
||
22071 | <user-agent> |
||
22072 | <ID>id_t_z_1545</ID> |
||
22073 | <String>Ziggy -- The Clown From Hell!!</String> |
||
22074 | <Description>Unknown agent (server- or link checking ?) from 198.173.158.xx</Description> |
||
22075 | <Type>C</Type> |
||
22076 | <Comment></Comment> |
||
22077 | <Link1></Link1> |
||
22078 | <Link2></Link2> |
||
22079 | </user-agent> |
||
22080 | <user-agent> |
||
22081 | <ID>id_t_z_1546</ID> |
||
22082 | <String>ZipppBot/0.xx (ZipppBot; http://www.zippp.net; webmaster@zippp.net)</String> |
||
22083 | <Description>Zipp.net web search robot</Description> |
||
22084 | <Type>R</Type> |
||
22085 | <Comment></Comment> |
||
22086 | <Link1>http://www.zippp.net/</Link1> |
||
22087 | <Link2></Link2> |
||
22088 | </user-agent> |
||
22089 | <user-agent> |
||
22090 | <ID>id_t_z_1547</ID> |
||
22091 | <String>ZIPPPCVS/0.xx (ZipppBot/.xx;http://www.zippp.net; webmaster@zippp.net)</String> |
||
22092 | <Description>Zipp.net web search robot</Description> |
||
22093 | <Type>R</Type> |
||
22094 | <Comment></Comment> |
||
22095 | <Link1>http://www.zippp.net/</Link1> |
||
22096 | <Link2></Link2> |
||
22097 | </user-agent> |
||
22098 | <user-agent> |
||
22099 | <ID>id_t_z_1548</ID> |
||
22100 | <String>Zippy v2.0 - Zippyfinder.com</String> |
||
22101 | <Description>Zippyfinder robot</Description> |
||
22102 | <Type>R</Type> |
||
22103 | <Comment></Comment> |
||
22104 | <Link1>http://www.zippyfinder.com/</Link1> |
||
22105 | <Link2></Link2> |
||
22106 | </user-agent> |
||
22107 | <user-agent> |
||
22108 | <ID>id_t_z_1549</ID> |
||
22109 | <String>Zoo Tycoon 2 Client -- http://www.zootycoon.com</String> |
||
22110 | <Description>Microsoft Zoo Tycoon 2 game client</Description> |
||
22111 | <Type>B</Type> |
||
22112 | <Comment></Comment> |
||
22113 | <Link1>http://www.zootycoon.com</Link1> |
||
22114 | <Link2></Link2> |
||
22115 | </user-agent> |
||
22116 | <user-agent> |
||
22117 | <ID>id_t_z_1550</ID> |
||
22118 | <String>ZoomSpider - wrensoft.com</String> |
||
22119 | <Description>Zoom Search Engine software spider</Description> |
||
22120 | <Type>R</Type> |
||
22121 | <Comment></Comment> |
||
22122 | <Link1>http://www.wrensoft.com/</Link1> |
||
22123 | <Link2></Link2> |
||
22124 | </user-agent> |
||
22125 | <user-agent> |
||
22126 | <ID>id_new_160110_1</ID> |
||
22127 | <String>Zscho.de Crawler/Nutch-1.0-Zscho.de-semantic_patch (Zscho.de Crawler</String> |
||
22128 | <Description> collecting for machine learning; http://zscho.de/ )</Description> |
||
22129 | <Type>Zscho search crawler (Germany)</Type> |
||
22130 | <Comment>R</Comment> |
||
22131 | <Link1>141.65.161.xx</Link1> |
||
22132 | <Link2>http://www.zscho.de/</Link2> |
||
22133 | </user-agent> |
||
22134 | <user-agent> |
||
22135 | <ID>id_t_z_280306_1</ID> |
||
22136 | <String>zspider/0.9-dev http://feedback.redkolibri.com/</String> |
||
22137 | <Description>zspider robot for a new search engine</Description> |
||
22138 | <Type>R</Type> |
||
22139 | <Comment></Comment> |
||
22140 | <Link1>http://feedback.redkolibri.com/</Link1> |
||
22141 | <Link2></Link2> |
||
22142 | </user-agent> |
||
22143 | <user-agent> |
||
22144 | <ID>id_t_z_1551</ID> |
||
22145 | <String>ZyBorg/1.0 (ZyBorg@WISEnut.com; http://www.WISEnut.com)</String> |
||
22146 | <Description>Wisenut robot</Description> |
||
22147 | <Type>R</Type> |
||
22148 | <Comment></Comment> |
||
22149 | <Link1>http://www.wisenutbot.com/</Link1> |
||
22150 | <Link2></Link2> |
||
22151 | </user-agent> |
||
22152 | </user-agents> |