WebSVN – vgwhois – Diff – /trunk/main/subprograms/mq_gf_gp


#!/usr/bin/php
<?php
 
#
#  VGWhoIs (ViaThinkSoft Global WhoIs, a fork of generic Whois / gwhois)
#  Subprogram: mq, gf and gp TLD whois
#
#  (c) 2012 by Daniel Marschall, ViaThinkSoft <info@daniel-marschall.de>
#
#  License: https://www.gnu.org/licenses/gpl-2.0.html (GPL version 2)
#
 
# TODO: for many domains, the format is completely different! do we have a good enough parser?
 
require_once __DIR__ . '/../../shared/php_includes/common_functions.inc.php';
 
$domain = isset($argv[1]) ? $argv[1] : '';
 
$url = "https://www.dom-enic.com/whois.html";
 
$res  = "% Parsing via regex from '$url'\n\n";
 
// Split up "naked" domain name and TLD
if (!preg_match('@^(.*)(\.(mq|gf|gp))$@', $domain, $m)) {
	echo "Error: Can only handle .mq, .gf and .gp TLDs.\n";
	exit(1);
}
$domain = $m[1];
$ext    = $m[2];
 
$x = file_get_contents2($url, 'domain='.urlencode($domain).'&' .
                              'extension='.urlencode($ext).'&' .
                              'Submit=Soumettre');
 
if (strpos($x, /* $domain. */ ' est disponible.') !== false) {
	define('BEGIN', '<div align="center" class="texte1"><p>');
	define('END',   '</p></div>');
} else {
	// For some domains it is <p> and not <h1>
	$x = str_replace('<p class="titre1">WHOIS result</p>', '<h1 class="titre1">WHOIS result</h1>', $x);
	define('BEGIN', '<h1 class="titre1">WHOIS result</h1>');
	// define('END',   '</div>');
	// In comparison to </div>, this includes the disclaimer at the bottom:
	define('END',   '</td>');
}
 
preg_match_all('@'.preg_quote(BEGIN, '@').'(.*)'.preg_quote(END, '@').'@ismU', $x, $m);
 
if (!isset($m[1][0])) {
	echo "Error while parsing the web content. Could not find limitations.\n";
	exit(1);
}
$x = $m[1][0];
 
$x = preg_replace('@<br />(?!\n)@', "\n", $x);
$x = strip_tags($x);
 
$x = html_entity_decode($x);
 
// é -> É @ strtoupper()
/*
$locals = array('es_ES@euro', 'es_ES', 'es');
reset($locals);
while (list(, $locale) = each ($locals)) {
	if ( setlocale(LC_CTYPE, $locale) == $locale ) {                
		break; // Exit when we were successfull
	}
}
*/
 
$x = preg_replace("@\n\s+\n@", "\n\n", $x);
while (strpos($x, "\n\n\n") !== false) $x = str_replace("\n\n\n", "\n\n", $x);
 
$special_words = array(
	'Registrant:',
	'Administrative Contact:',
	'Technical Contact:',
	'Billing Contact:'
);
 
foreach ($special_words as $s) {
	$x = str_replace($s, "\n".uc_latin1($s)."\n", $x);
}
 
$x = trim($x);
 
echo $res.trim_each_line($x)."\n";

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: mq, gf and gp TLD whois	6	# Subprogram: mq, gf and gp 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	# TODO: for many domains, the format is completely different! do we have a good enough parser?	13	# TODO: for many domains, the format is completely different! do we have a good enough parser?
14		14
15	require_once __DIR__ . '/../../shared/php_includes/common_functions.inc.php';	15	require_once __DIR__ . '/../../shared/php_includes/common_functions.inc.php';
16		16
17	$domain = isset($argv[1]) ? $argv[1] : '';	17	$domain = isset($argv[1]) ? $argv[1] : '';
18		18
19	$url = "https://www.dom-enic.com/whois.html";	19	$url = "https://www.dom-enic.com/whois.html";
20		20
21	$res = "% Parsing via regex from '$url'\n\n";	21	$res = "% Parsing via regex from '$url'\n\n";
22		22
23	// Split up "naked" domain name and TLD	23	// Split up "naked" domain name and TLD
24	if (!preg_match('@^(.*)(\.(mq\|gf\|gp))$@', $domain, $m)) {	24	if (!preg_match('@^(.*)(\.(mq\|gf\|gp))$@', $domain, $m)) {
25	echo "Error: Can only handle .mq, .gf and .gp TLDs.\n";	25	echo "Error: Can only handle .mq, .gf and .gp TLDs.\n";
26	exit(1);	26	exit(1);
27	}	27	}
28	$domain = $m[1];	28	$domain = $m[1];
29	$ext = $m[2];	29	$ext = $m[2];
30		30
31	$x = file_get_contents2($url, 'domain='.urlencode($domain).'&' .	31	$x = file_get_contents2($url, 'domain='.urlencode($domain).'&' .
32	'extension='.urlencode($ext).'&' .	32	'extension='.urlencode($ext).'&' .
33	'Submit=Soumettre');	33	'Submit=Soumettre');
34		34
35	if (strpos($x, /* $domain. */ ' est disponible.') !== false) {	35	if (strpos($x, /* $domain. */ ' est disponible.') !== false) {
36	define('BEGIN', '<div align="center" class="texte1"><p>');	36	define('BEGIN', '<div align="center" class="texte1"><p>');
37	define('END', '</p></div>');	37	define('END', '</p></div>');
38	} else {	38	} else {
39	// For some domains it is <p> and not <h1>	39	// For some domains it is <p> and not <h1>
40	$x = str_replace('<p class="titre1">WHOIS result</p>', '<h1 class="titre1">WHOIS result</h1>', $x);	40	$x = str_replace('<p class="titre1">WHOIS result</p>', '<h1 class="titre1">WHOIS result</h1>', $x);
41	define('BEGIN', '<h1 class="titre1">WHOIS result</h1>');	41	define('BEGIN', '<h1 class="titre1">WHOIS result</h1>');
42	// define('END', '</div>');	42	// define('END', '</div>');
43	// In comparison to </div>, this includes the disclaimer at the bottom:	43	// In comparison to </div>, this includes the disclaimer at the bottom:
44	define('END', '</td>');	44	define('END', '</td>');
45	}	45	}
46		46
47	preg_match_all('@'.preg_quote(BEGIN, '@').'(.*)'.preg_quote(END, '@').'@ismU', $x, $m);	47	preg_match_all('@'.preg_quote(BEGIN, '@').'(.*)'.preg_quote(END, '@').'@ismU', $x, $m);
48		48
49	if (!isset($m[1][0])) {	49	if (!isset($m[1][0])) {
50	echo "Error while parsing the web content. Could not find limitations.\n";	50	echo "Error while parsing the web content. Could not find limitations.\n";
51	exit(1);	51	exit(1);
52	}	52	}
53	$x = $m[1][0];	53	$x = $m[1][0];
54		54
55	$x = preg_replace('@<br />(?!\n)@', "\n", $x);	55	$x = preg_replace('@<br />(?!\n)@', "\n", $x);
56	$x = strip_tags($x);	56	$x = strip_tags($x);
57		57
58	$x = html_entity_decode($x);	58	$x = html_entity_decode($x);
59		59
60	// é -> É @ strtoupper()	60	// é -> É @ strtoupper()
61	/*	61	/*
62	$locals = array('es_ES@euro', 'es_ES', 'es');	62	$locals = array('es_ES@euro', 'es_ES', 'es');
63	reset($locals);	63	reset($locals);
64	while (list(, $locale) = each ($locals)) {	64	while (list(, $locale) = each ($locals)) {
65	if ( setlocale(LC_CTYPE, $locale) == $locale ) {	65	if ( setlocale(LC_CTYPE, $locale) == $locale ) {
66	break; // Exit when we were successfull	66	break; // Exit when we were successfull
67	}	67	}
68	}	68	}
69	*/	69	*/
70		70
71	$x = preg_replace("@\n\s+\n@", "\n\n", $x);	71	$x = preg_replace("@\n\s+\n@", "\n\n", $x);
72	while (strpos($x, "\n\n\n") !== false) $x = str_replace("\n\n\n", "\n\n", $x);	72	while (strpos($x, "\n\n\n") !== false) $x = str_replace("\n\n\n", "\n\n", $x);
73		73
74	$special_words = array(	74	$special_words = array(
75	'Registrant:',	75	'Registrant:',
76	'Administrative Contact:',	76	'Administrative Contact:',
77	'Technical Contact:',	77	'Technical Contact:',
78	'Billing Contact:'	78	'Billing Contact:'
79	);	79	);
80		80
81	foreach ($special_words as $s) {	81	foreach ($special_words as $s) {
82	$x = str_replace($s, "\n".uc_latin1($s)."\n", $x);	82	$x = str_replace($s, "\n".uc_latin1($s)."\n", $x);
83	}	83	}
84		84
85	$x = trim($x);	85	$x = trim($x);
86		86
87	echo $res.trim_each_line($x)."\n";	87	echo $res.trim_each_line($x)."\n";

Subversion Repositories vgwhois

vgwhois/trunk/main/subprograms/mq_gf_gp – Rev 5 → 11