Rev 5 | Go to most recent revision | Only display areas with differences | Regard whitespace | Details | Blame | Last modification | View Log | RSS feed
Rev 5 | Rev 11 | ||
---|---|---|---|
1 | #!/usr/bin/php |
1 | #!/usr/bin/php |
2 | <?php |
2 | <?php |
3 | 3 | ||
4 | # |
4 | # |
5 | # VWhois (ViaThinkSoft WHOIS, a fork of generic Whois / gwhois) |
5 | # VGWhoIs (ViaThinkSoft Global WhoIs, a fork of generic Whois / gwhois) |
6 | # Subprogram: pk TLD whois |
6 | # Subprogram: pk TLD whois |
7 | # |
7 | # |
8 | # (c) 2012 by Daniel Marschall, ViaThinkSoft <info@daniel-marschall.de> |
8 | # (c) 2012 by Daniel Marschall, ViaThinkSoft <info@daniel-marschall.de> |
9 | # |
9 | # |
10 | # License: https://www.gnu.org/licenses/gpl-2.0.html (GPL version 2) |
10 | # License: https://www.gnu.org/licenses/gpl-2.0.html (GPL version 2) |
11 | # |
11 | # |
12 | 12 | ||
13 | require_once __DIR__ . '/../../shared/php_includes/common_functions.inc.php'; |
13 | require_once __DIR__ . '/../../shared/php_includes/common_functions.inc.php'; |
14 | 14 | ||
15 | $domain = isset($argv[1]) ? $argv[1] : ''; |
15 | $domain = isset($argv[1]) ? $argv[1] : ''; |
16 | 16 | ||
17 | $url = "http://pk5.pknic.net.pk/pk5/lookup.PK"; |
17 | $url = "http://pk5.pknic.net.pk/pk5/lookup.PK"; |
18 | 18 | ||
19 | $res = "% Parsing via regex from '$url'\n\n"; |
19 | $res = "% Parsing via regex from '$url'\n\n"; |
20 | 20 | ||
21 | $x = file_get_contents2($url, 'name='.$domain); |
21 | $x = file_get_contents2($url, 'name='.$domain); |
22 | 22 | ||
23 | if (strpos($x, '<XPC_RESULT_NOTFOUND/>') !== false) { |
23 | if (strpos($x, '<XPC_RESULT_NOTFOUND/>') !== false) { |
24 | define('BEGIN', '<td id="Tmain">'); |
24 | define('BEGIN', '<td id="Tmain">'); |
25 | define('END', '<XPC_RESULT_NOTFOUND/>'); |
25 | define('END', '<XPC_RESULT_NOTFOUND/>'); |
26 | } else { |
26 | } else { |
27 | define('BEGIN', '<p class="pkheading">'); |
27 | define('BEGIN', '<p class="pkheading">'); |
28 | define('END', '<SPAN class="sideHead">'); |
28 | define('END', '<SPAN class="sideHead">'); |
29 | } |
29 | } |
30 | 30 | ||
31 | preg_match_all('@'.preg_quote(BEGIN, '@').'(.*)'.preg_quote(END, '@').'@ismU', $x, $m); |
31 | preg_match_all('@'.preg_quote(BEGIN, '@').'(.*)'.preg_quote(END, '@').'@ismU', $x, $m); |
32 | 32 | ||
33 | if (!isset($m[1][0])) { |
33 | if (!isset($m[1][0])) { |
34 | echo "Error while parsing the web content. Could not find limitations.\n"; |
34 | echo "Error while parsing the web content. Could not find limitations.\n"; |
35 | exit(1); |
35 | exit(1); |
36 | } |
36 | } |
37 | $x = $m[1][0]; |
37 | $x = $m[1][0]; |
38 | 38 | ||
39 | $x = strip_tags($x); |
39 | $x = strip_tags($x); |
40 | 40 | ||
41 | // é -> É @ strtoupper() |
41 | // é -> É @ strtoupper() |
42 | /* |
42 | /* |
43 | $locals = array('es_ES@euro', 'es_ES', 'es'); |
43 | $locals = array('es_ES@euro', 'es_ES', 'es'); |
44 | reset($locals); |
44 | reset($locals); |
45 | while (list(, $locale) = each ($locals)) { |
45 | while (list(, $locale) = each ($locals)) { |
46 | if ( setlocale(LC_CTYPE, $locale) == $locale ) { |
46 | if ( setlocale(LC_CTYPE, $locale) == $locale ) { |
47 | break; // Exit when we were successfull |
47 | break; // Exit when we were successfull |
48 | } |
48 | } |
49 | } |
49 | } |
50 | */ |
50 | */ |
51 | 51 | ||
52 | $x = str_replace(' ', ' ', $x); |
52 | $x = str_replace(' ', ' ', $x); |
53 | 53 | ||
54 | $x = html_entity_decode($x); |
54 | $x = html_entity_decode($x); |
55 | 55 | ||
56 | $x = preg_replace("| +|", ' ', $x); |
56 | $x = preg_replace("| +|", ' ', $x); |
57 | $x = preg_replace("|\n *|", "\n", $x); |
57 | $x = preg_replace("|\n *|", "\n", $x); |
58 | $x = preg_replace("| *\n|", "\n", $x); |
58 | $x = preg_replace("| *\n|", "\n", $x); |
59 | $x = preg_replace("|\n+|", "\n", $x); |
59 | $x = preg_replace("|\n+|", "\n", $x); |
60 | 60 | ||
61 | $x = str_replace(":\n", ": ", $x); |
61 | $x = str_replace(":\n", ": ", $x); |
62 | 62 | ||
63 | while (strpos($x, "\t") !== false) $x = str_replace("\t", '', $x); |
63 | while (strpos($x, "\t") !== false) $x = str_replace("\t", '', $x); |
64 | while (strpos($x, ' ') !== false) $x = str_replace(' ', ' ', $x); |
64 | while (strpos($x, ' ') !== false) $x = str_replace(' ', ' ', $x); |
65 | 65 | ||
66 | # Avoid "Contact person: Address:" if there is no contact person. Add a line break |
66 | # Avoid "Contact person: Address:" if there is no contact person. Add a line break |
67 | $x = preg_replace('@^([^:\n]+):\s+([^\n:]+):@m', "\\1:\n\\2:", $x); |
67 | $x = preg_replace('@^([^:\n]+):\s+([^\n:]+):@m', "\\1:\n\\2:", $x); |
68 | 68 | ||
69 | $x = make_tabs($x); |
69 | $x = make_tabs($x); |
70 | 70 | ||
71 | $x = trim($x); |
71 | $x = trim($x); |
72 | 72 | ||
73 | $x = preg_replace("@\n\s+\n@", "\n\n", $x); |
73 | $x = preg_replace("@\n\s+\n@", "\n\n", $x); |
74 | 74 | ||
75 | while (strpos($x, "\n\n") !== false) $x = str_replace("\n\n", "\n", $x); |
75 | while (strpos($x, "\n\n") !== false) $x = str_replace("\n\n", "\n", $x); |
76 | 76 | ||
77 | $x = preg_replace('@The Domain record for(.*)\n@', 'The Domain record for\\1'."\n\n", $x); |
77 | $x = preg_replace('@The Domain record for(.*)\n@', 'The Domain record for\\1'."\n\n", $x); |
78 | 78 | ||
79 | $special_words = array( |
79 | $special_words = array( |
80 | 'Technical Contact', |
80 | 'Technical Contact', |
81 | 'Billing Contact', |
81 | 'Billing Contact', |
82 | 'Nameservers' |
82 | 'Nameservers' |
83 | ); |
83 | ); |
84 | 84 | ||
85 | foreach ($special_words as $s) { |
85 | foreach ($special_words as $s) { |
86 | $x = str_replace($s, "\n".uc_latin1($s)."\n", $x); |
86 | $x = str_replace($s, "\n".uc_latin1($s)."\n", $x); |
87 | } |
87 | } |
88 | 88 | ||
89 | echo $res.trim_each_line($x)."\n"; |
89 | echo $res.trim_each_line($x)."\n"; |