class-snoopy.php

Revision 1507, 36.6 kB (checked in by donncha, 8 months ago)
WP Merge
Property svn:eol-style set to `native`

Line
1	<?php
2	if ( !in_array('Snoopy', get_declared_classes() ) ) :
3	/*************************************************
4
5	Snoopy - the PHP net client
6	Author: Monte Ohrt <monte@ispi.net>
7	Copyright (c): 1999-2008 New Digital Group, all rights reserved
8	Version: 1.2.4
9
10	* This library is free software; you can redistribute it and/or
11	* modify it under the terms of the GNU Lesser General Public
12	* License as published by the Free Software Foundation; either
13	* version 2.1 of the License, or (at your option) any later version.
14	*
15	* This library is distributed in the hope that it will be useful,
16	* but WITHOUT ANY WARRANTY; without even the implied warranty of
17	* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18	* Lesser General Public License for more details.
19	*
20	* You should have received a copy of the GNU Lesser General Public
21	* License along with this library; if not, write to the Free Software
22	* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
23
24	You may contact the author of Snoopy by e-mail at:
25	monte@ohrt.com
26
27	The latest version of Snoopy can be obtained from:
28	http://snoopy.sourceforge.net/
29
30	*************************************************/
31
32	class Snoopy
33	{
34	/** Public variables **/
35
36	/* user definable vars */
37
38	var $host = "www.php.net"; // host name we are connecting to
39	var $port = 80; // port we are connecting to
40	var $proxy_host = ""; // proxy host to use
41	var $proxy_port = ""; // proxy port to use
42	var $proxy_user = ""; // proxy user to use
43	var $proxy_pass = ""; // proxy password to use
44
45	var $agent = "Snoopy v1.2.4"; // agent we masquerade as
46	var $referer = ""; // referer info to pass
47	var $cookies = array(); // array of cookies to pass
48	// $cookies["username"]="joe";
49	var $rawheaders = array(); // array of raw headers to send
50	// $rawheaders["Content-type"]="text/html";
51
52	var $maxredirs = 5; // http redirection depth maximum. 0 = disallow
53	var $lastredirectaddr = ""; // contains address of last redirected address
54	var $offsiteok = true; // allows redirection off-site
55	var $maxframes = 0; // frame content depth maximum. 0 = disallow
56	var $expandlinks = true; // expand links to fully qualified URLs.
57	// this only applies to fetchlinks()
58	// submitlinks(), and submittext()
59	var $passcookies = true; // pass set cookies back through redirects
60	// NOTE: this currently does not respect
61	// dates, domains or paths.
62
63	var $user = ""; // user for http authentication
64	var $pass = ""; // password for http authentication
65
66	// http accept types
67	var $accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, /";
68
69	var $results = ""; // where the content is put
70
71	var $error = ""; // error messages sent here
72	var $response_code = ""; // response code returned from server
73	var $headers = array(); // headers returned from server sent here
74	var $maxlength = 500000; // max return data length (body)
75	var $read_timeout = 0; // timeout on read operations, in seconds
76	// supported only since PHP 4 Beta 4
77	// set to 0 to disallow timeouts
78	var $timed_out = false; // if a read operation timed out
79	var $status = 0; // http request status
80
81	var $temp_dir = "/tmp"; // temporary directory that the webserver
82	// has permission to write to.
83	// under Windows, this should be C:\temp
84
85	var $curl_path = "/usr/local/bin/curl";
86	// Snoopy will use cURL for fetching
87	// SSL content if a full system path to
88	// the cURL binary is supplied here.
89	// set to false if you do not have
90	// cURL installed. See http://curl.haxx.se
91	// for details on installing cURL.
92	// Snoopy does not use the cURL
93	// library functions built into php,
94	// as these functions are not stable
95	// as of this Snoopy release.
96
97	/** Private variables **/
98
99	var $_maxlinelen = 4096; // max line length (headers)
100
101	var $_httpmethod = "GET"; // default http request method
102	var $_httpversion = "HTTP/1.0"; // default http request version
103	var $_submit_method = "POST"; // default submit method
104	var $_submit_type = "application/x-www-form-urlencoded"; // default submit type
105	var $_mime_boundary = ""; // MIME boundary for multipart/form-data submit type
106	var $_redirectaddr = false; // will be set if page fetched is a redirect
107	var $_redirectdepth = 0; // increments on an http redirect
108	var $_frameurls = array(); // frame src urls
109	var $_framedepth = 0; // increments on frame depth
110
111	var $_isproxy = false; // set if using a proxy server
112	var $_fp_timeout = 30; // timeout for socket connection
113
114	/======================================================================\
115	Function: fetch
116	Purpose: fetch the contents of a web page
117	(and possibly other protocols in the
118	future like ftp, nntp, gopher, etc.)
119	Input: $URI the location of the page to fetch
120	Output: $this->results the output text from the fetch
121	\======================================================================/
122
123	function fetch($URI)
124	{
125
126	//preg_match("\|^([^:]+)://([^:/]+)(:[\d]+)(.)\|",$URI,$URI_PARTS);
127	$URI_PARTS = parse_url($URI);
128	if (!empty($URI_PARTS["user"]))
129	$this->user = $URI_PARTS["user"];
130	if (!empty($URI_PARTS["pass"]))
131	$this->pass = $URI_PARTS["pass"];
132	if (empty($URI_PARTS["query"]))
133	$URI_PARTS["query"] = '';
134	if (empty($URI_PARTS["path"]))
135	$URI_PARTS["path"] = '';
136
137	switch(strtolower($URI_PARTS["scheme"]))
138	{
139	case "http":
140	$this->host = $URI_PARTS["host"];
141	if(!empty($URI_PARTS["port"]))
142	$this->port = $URI_PARTS["port"];
143	if($this->_connect($fp))
144	{
145	if($this->_isproxy)
146	{
147	// using proxy, send entire URI
148	$this->_httprequest($URI,$fp,$URI,$this->_httpmethod);
149	}
150	else
151	{
152	$path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
153	// no proxy, send only the path
154	$this->_httprequest($path, $fp, $URI, $this->_httpmethod);
155	}
156
157	$this->_disconnect($fp);
158
159	if($this->_redirectaddr)
160	{
161	/* url was redirected, check if we've hit the max depth */
162	if($this->maxredirs > $this->_redirectdepth)
163	{
164	// only follow redirect if it's on this site, or offsiteok is true
165	if(preg_match("\|^http://".preg_quote($this->host)."\|i",$this->_redirectaddr) \|\| $this->offsiteok)
166	{
167	/* follow the redirect */
168	$this->_redirectdepth++;
169	$this->lastredirectaddr=$this->_redirectaddr;
170	$this->fetch($this->_redirectaddr);
171	}
172	}
173	}
174
175	if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0)
176	{
177	$frameurls = $this->_frameurls;
178	$this->_frameurls = array();
179
180	while(list(,$frameurl) = each($frameurls))
181	{
182	if($this->_framedepth < $this->maxframes)
183	{
184	$this->fetch($frameurl);
185	$this->_framedepth++;
186	}
187	else
188	break;
189	}
190	}
191	}
192	else
193	{
194	return false;
195	}
196	return true;
197	break;
198	case "https":
199	if(!$this->curl_path)
200	return false;
201	if(function_exists("is_executable"))
202	if (!is_executable($this->curl_path))
203	return false;
204	$this->host = $URI_PARTS["host"];
205	if(!empty($URI_PARTS["port"]))
206	$this->port = $URI_PARTS["port"];
207	if($this->_isproxy)
208	{
209	// using proxy, send entire URI
210	$this->_httpsrequest($URI,$URI,$this->_httpmethod);
211	}
212	else
213	{
214	$path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
215	// no proxy, send only the path
216	$this->_httpsrequest($path, $URI, $this->_httpmethod);
217	}
218
219	if($this->_redirectaddr)
220	{
221	/* url was redirected, check if we've hit the max depth */
222	if($this->maxredirs > $this->_redirectdepth)
223	{
224	// only follow redirect if it's on this site, or offsiteok is true
225	if(preg_match("\|^http://".preg_quote($this->host)."\|i",$this->_redirectaddr) \|\| $this->offsiteok)
226	{
227	/* follow the redirect */
228	$this->_redirectdepth++;
229	$this->lastredirectaddr=$this->_redirectaddr;
230	$this->fetch($this->_redirectaddr);
231	}
232	}
233	}
234
235	if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0)
236	{
237	$frameurls = $this->_frameurls;
238	$this->_frameurls = array();
239
240	while(list(,$frameurl) = each($frameurls))
241	{
242	if($this->_framedepth < $this->maxframes)
243	{
244	$this->fetch($frameurl);
245	$this->_framedepth++;
246	}
247	else
248	break;
249	}
250	}
251	return true;
252	break;
253	default:
254	// not a valid protocol
255	$this->error = 'Invalid protocol "'.$URI_PARTS["scheme"].'"\n';
256	return false;
257	break;
258	}
259	return true;
260	}
261
262	/======================================================================\
263	Function: submit
264	Purpose: submit an http form
265	Input: $URI the location to post the data
266	$formvars the formvars to use.
267	format: $formvars["var"] = "val";
268	$formfiles an array of files to submit
269	format: $formfiles["var"] = "/dir/filename.ext";
270	Output: $this->results the text output from the post
271	\======================================================================/
272
273	function submit($URI, $formvars="", $formfiles="")
274	{
275	unset($postdata);
276
277	$postdata = $this->_prepare_post_body($formvars, $formfiles);
278
279	$URI_PARTS = parse_url($URI);
280	if (!empty($URI_PARTS["user"]))
281	$this->user = $URI_PARTS["user"];
282	if (!empty($URI_PARTS["pass"]))
283	$this->pass = $URI_PARTS["pass"];
284	if (empty($URI_PARTS["query"]))
285	$URI_PARTS["query"] = '';
286	if (empty($URI_PARTS["path"]))
287	$URI_PARTS["path"] = '';
288
289	switch(strtolower($URI_PARTS["scheme"]))
290	{
291	case "http":
292	$this->host = $URI_PARTS["host"];
293	if(!empty($URI_PARTS["port"]))
294	$this->port = $URI_PARTS["port"];
295	if($this->_connect($fp))
296	{
297	if($this->_isproxy)
298	{
299	// using proxy, send entire URI
300	$this->_httprequest($URI,$fp,$URI,$this->_submit_method,$this->_submit_type,$postdata);
301	}
302	else
303	{
304	$path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
305	// no proxy, send only the path
306	$this->_httprequest($path, $fp, $URI, $this->_submit_method, $this->_submit_type, $postdata);
307	}
308
309	$this->_disconnect($fp);
310
311	if($this->_redirectaddr)
312	{
313	/* url was redirected, check if we've hit the max depth */
314	if($this->maxredirs > $this->_redirectdepth)
315	{
316	if(!preg_match("\|^".$URI_PARTS["scheme"]."://\|", $this->_redirectaddr))
317	$this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]);
318
319	// only follow redirect if it's on this site, or offsiteok is true
320	if(preg_match("\|^http://".preg_quote($this->host)."\|i",$this->_redirectaddr) \|\| $this->offsiteok)
321	{
322	/* follow the redirect */
323	$this->_redirectdepth++;
324	$this->lastredirectaddr=$this->_redirectaddr;
325	if( strpos( $this->_redirectaddr, "?" ) > 0 )
326	$this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get
327	else
328	$this->submit($this->_redirectaddr,$formvars, $formfiles);
329	}
330	}
331	}
332
333	if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0)
334	{
335	$frameurls = $this->_frameurls;
336	$this->_frameurls = array();
337
338	while(list(,$frameurl) = each($frameurls))
339	{
340	if($this->_framedepth < $this->maxframes)
341	{
342	$this->fetch($frameurl);
343	$this->_framedepth++;
344	}
345	else
346	break;
347	}
348	}
349
350	}
351	else
352	{
353	return false;
354	}
355	return true;
356	break;
357	case "https":
358	if(!$this->curl_path)
359	return false;
360	if(function_exists("is_executable"))
361	if (!is_executable($this->curl_path))
362	return false;
363	$this->host = $URI_PARTS["host"];
364	if(!empty($URI_PARTS["port"]))
365	$this->port = $URI_PARTS["port"];
366	if($this->_isproxy)
367	{
368	// using proxy, send entire URI
369	$this->_httpsrequest($URI, $URI, $this->_submit_method, $this->_submit_type, $postdata);
370	}
371	else
372	{
373	$path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
374	// no proxy, send only the path
375	$this->_httpsrequest($path, $URI, $this->_submit_method, $this->_submit_type, $postdata);
376	}
377
378	if($this->_redirectaddr)
379	{
380	/* url was redirected, check if we've hit the max depth */
381	if($this->maxredirs > $this->_redirectdepth)
382	{
383	if(!preg_match("\|^".$URI_PARTS["scheme"]."://\|", $this->_redirectaddr))
384	$this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]);
385
386	// only follow redirect if it's on this site, or offsiteok is true
387	if(preg_match("\|^http://".preg_quote($this->host)."\|i",$this->_redirectaddr) \|\| $this->offsiteok)
388	{
389	/* follow the redirect */
390	$this->_redirectdepth++;
391	$this->lastredirectaddr=$this->_redirectaddr;
392	if( strpos( $this->_redirectaddr, "?" ) > 0 )
393	$this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get
394	else
395	$this->submit($this->_redirectaddr,$formvars, $formfiles);
396	}
397	}
398	}
399
400	if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0)
401	{
402	$frameurls = $this->_frameurls;
403	$this->_frameurls = array();
404
405	while(list(,$frameurl) = each($frameurls))
406	{
407	if($this->_framedepth < $this->maxframes)
408	{
409	$this->fetch($frameurl);
410	$this->_framedepth++;
411	}
412	else
413	break;
414	}
415	}
416	return true;
417	break;
418
419	default:
420	// not a valid protocol
421	$this->error = 'Invalid protocol "'.$URI_PARTS["scheme"].'"\n';
422	return false;
423	break;
424	}
425	return true;
426	}
427
428	/======================================================================\
429	Function: fetchlinks
430	Purpose: fetch the links from a web page
431	Input: $URI where you are fetching from
432	Output: $this->results an array of the URLs
433	\======================================================================/
434
435	function fetchlinks($URI)
436	{
437	if ($this->fetch($URI))
438	{
439	if($this->lastredirectaddr)
440	$URI = $this->lastredirectaddr;
441	if(is_array($this->results))
442	{
443	for($x=0;$x<count($this->results);$x++)
444	$this->results[$x] = $this->_striplinks($this->results[$x]);
445	}
446	else
447	$this->results = $this->_striplinks($this->results);
448
449	if($this->expandlinks)
450	$this->results = $this->_expandlinks($this->results, $URI);
451	return true;
452	}
453	else
454	return false;
455	}
456
457	/======================================================================\
458	Function: fetchform
459	Purpose: fetch the form elements from a web page
460	Input: $URI where you are fetching from
461	Output: $this->results the resulting html form
462	\======================================================================/
463
464	function fetchform($URI)
465	{
466
467	if ($this->fetch($URI))
468	{
469
470	if(is_array($this->results))
471	{
472	for($x=0;$x<count($this->results);$x++)
473	$this->results[$x] = $this->_stripform($this->results[$x]);
474	}
475	else
476	$this->results = $this->_stripform($this->results);
477
478	return true;
479	}
480	else
481	return false;
482	}
483
484
485	/======================================================================\
486	Function: fetchtext
487	Purpose: fetch the text from a web page, stripping the links
488	Input: $URI where you are fetching from
489	Output: $this->results the text from the web page
490	\======================================================================/
491
492	function fetchtext($URI)
493	{
494	if($this->fetch($URI))
495	{
496	if(is_array($this->results))
497	{
498	for($x=0;$x<count($this->results);$x++)
499	$this->results[$x] = $this->_striptext($this->results[$x]);
500	}
501	else
502	$this->results = $this->_striptext($this->results);
503	return true;
504	}
505	else
506	return false;
507	}
508
509	/======================================================================\
510	Function: submitlinks
511	Purpose: grab links from a form submission
512	Input: $URI where you are submitting from
513	Output: $this->results an array of the links from the post
514	\======================================================================/
515
516	function submitlinks($URI, $formvars="", $formfiles="")
517	{
518	if($this->submit($URI,$formvars, $formfiles))
519	{
520	if($this->lastredirectaddr)
521	$URI = $this->lastredirectaddr;
522	if(is_array($this->results))
523	{
524	for($x=0;$x<count($this->results);$x++)
525	{
526	$this->results[$x] = $this->_striplinks($this->results[$x]);
527	if($this->expandlinks)
528	$this->results[$x] = $this->_expandlinks($this->results[$x],$URI);
529	}
530	}
531	else
532	{
533	$this->results = $this->_striplinks($this->results);
534	if($this->expandlinks)
535	$this->results = $this->_expandlinks($this->results,$URI);
536	}
537	return true;
538	}
539	else
540	return false;
541	}
542
543	/======================================================================\
544	Function: submittext
545	Purpose: grab text from a form submission
546	Input: $URI where you are submitting from
547	Output: $this->results the text from the web page
548	\======================================================================/
549
550	function submittext($URI, $formvars = "", $formfiles = "")
551	{
552	if($this->submit($URI,$formvars, $formfiles))
553	{
554	if($this->lastredirectaddr)
555	$URI = $this->lastredirectaddr;
556	if(is_array($this->results))
557	{
558	for($x=0;$x<count($this->results);$x++)
559	{
560	$this->results[$x] = $this->_striptext($this->results[$x]);
561	if($this->expandlinks)
562	$this->results[$x] = $this->_expandlinks($this->results[$x],$URI);
563	}
564	}
565	else
566	{
567	$this->results = $this->_striptext($this->results);
568	if($this->expandlinks)
569	$this->results = $this->_expandlinks($this->results,$URI);
570	}
571	return true;
572	}
573	else
574	return false;
575	}
576
577
578
579	/======================================================================\
580	Function: set_submit_multipart
581	Purpose: Set the form submission content type to
582	multipart/form-data
583	\======================================================================/
584	function set_submit_multipart()
585	{
586	$this->_submit_type = "multipart/form-data";
587	}
588
589
590	/======================================================================\
591	Function: set_submit_normal
592	Purpose: Set the form submission content type to
593	application/x-www-form-urlencoded
594	\======================================================================/
595	function set_submit_normal()
596	{
597	$this->_submit_type = "application/x-www-form-urlencoded";
598	}
599
600
601
602
603	/======================================================================\
604	Private functions
605	\======================================================================/
606
607
608	/======================================================================\
609	Function: _striplinks
610	Purpose: strip the hyperlinks from an html document
611	Input: $document document to strip.
612	Output: $match an array of the links
613	\======================================================================/
614
615	function _striplinks($document)
616	{
617	preg_match_all("'<\sa\s.?href\s=\s # find <a href=
618	([\"\'])? # find single or double quote
619	(?(1) (.*?)\\1 \| ([^\s\>]+)) # if quote found, match up to next matching
620	# quote, otherwise match up to next space
621	'isx",$document,$links);
622
623
624	// catenate the non-empty matches from the conditional subpattern
625
626	while(list($key,$val) = each($links[2]))
627	{
628	if(!empty($val))
629	$match[] = $val;
630	}
631
632	while(list($key,$val) = each($links[3]))
633	{
634	if(!empty($val))
635	$match[] = $val;
636	}
637
638	// return the links
639	return $match;
640	}
641
642	/======================================================================\
643	Function: _stripform
644	Purpose: strip the form elements from an html document
645	Input: $document document to strip.
646	Output: $match an array of the links
647	\======================================================================/
648
649	function _stripform($document)
650	{
651	preg_match_all("'<\/?(FORM\|INPUT\|SELECT\|TEXTAREA\|(OPTION))[^<>]>(?(2)(.(?=<\/?(option\|select)[^<>]>[\r\n])\|(?=[\r\n]))\|(?=[\r\n]))'Usi",$document,$elements);
652
653	// catenate the matches
654	$match = implode("\r\n",$elements[0]);
655
656	// return the links
657	return $match;
658	}
659
660
661
662	/======================================================================\
663	Function: _striptext
664	Purpose: strip the text from an html document
665	Input: $document document to strip.
666	Output: $text the resulting text
667	\======================================================================/
668
669	function _striptext($document)
670	{
671
672	// I didn't use preg eval (//e) since that is only available in PHP 4.0.
673	// so, list your entities one by one here. I included some of the
674	// more common ones.
675
676	$search = array("'<script[^>]?>.?</script>'si", // strip out javascript
677	"'<[\/\!]?[^<>]?>'si", // strip out html tags
678	"'([\r\n])[\s]+'", // strip out white space
679	"'&(quot\|#34\|#034\|#x22);'i", // replace html entities
680	"'&(amp\|#38\|#038\|#x26);'i", // added hexadecimal values
681	"'&(lt\|#60\|#060\|#x3c);'i",
682	"'&(gt\|#62\|#062\|#x3e);'i",
683	"'&(nbsp\|#160\|#xa0);'i",
684	"'&(iexcl\|#161);'i",
685	"'&(cent\|#162);'i",
686	"'&(pound\|#163);'i",
687	"'&(copy\|#169);'i",
688	"'&(reg\|#174);'i",
689	"'&(deg\|#176);'i",
690	"'&(#39\|#039\|#x27);'",
691	"'&(euro\|#8364);'i", // europe
692	"'&a(uml\|UML);'", // german
693	"'&o(uml\|UML);'",
694	"'&u(uml\|UML);'",
695	"'&A(uml\|UML);'",
696	"'&O(uml\|UML);'",
697	"'&U(uml\|UML);'",
698	"'ß'i",
699	);
700	$replace = array( "",
701	"",
702	"\\1",
703	"\"",
704	"&",
705	"<",
706	">",
707	" ",
708	chr(161),
709	chr(162),
710	chr(163),
711	chr(169),
712	chr(174),
713	chr(176),
714	chr(39),
715	chr(128),
716	"�
717	"� "� "�,
718	"�,
719	"�,
720	"�,
721	);
722
723	$text = preg_replace($search,$replace,$document);
724
725	return $text;
726	}
727
728	/======================================================================\
729	Function: _expandlinks
730	Purpose: expand each link into a fully qualified URL
731	Input: $links the links to qualify
732	$URI the full URI to get the base from
733	Output: $expandedLinks the expanded links
734	\======================================================================/
735
736	function _expandlinks($links,$URI)
737	{
738
739	preg_match("/^[^Warning: Unexpected character in input: '\' (ASCII=92) state=1 in Unknown on line 0?]+/",$URI,$match);
740
741	$match = preg_replace("\|/[^Warning: Unexpected character in input: '\' (ASCII=92) state=1 in Unknown on line 0/Warning: Unexpected character in input: '\' (ASCII=92) state=1 in Unknown on line 0.]+Warning: Unexpected character in input: '\' (ASCII=92) state=1 in Unknown on line 0.[^Warning: Unexpected character in input: '\' (ASCII=92) state=1 in Unknown on line 0/Warning: Unexpected character in input: '\' (ASCII=92) state=1 in Unknown on line 0.]+$\|","",$match[0]);
742	$match = preg_replace("\|/$\|","",$match);
743	$match_part = parse_url($match);
744	$match_root =
745	$match_part["scheme"]."://".$match_part["host"];
746
747	$search = array( "\|^http://".preg_quote($this->host)."\|i",
748	"\|^(\/)\|i",
749	"\|^(?!http://)(?!mailto:)\|i",
750	"\|/\./\|",
751	"\|/[^\/]+/\.\./\|"
752	);
753
754	$replace = array( "",
755	$match_root."/",
756	$match."/",
757	"/",
758	"/"
759	);
760
761	$expandedLinks = preg_replace($search,$replace,$links);
762
763	return $expandedLinks;
764	}
765
766	/======================================================================\
767	Function: _httprequest
768	Purpose: go get the http data from the server
769	Input: $url the url to fetch
770	$fp the current open file pointer
771	$URI the full URI
772	$body body contents to send if any (POST)
773	Output:
774	\======================================================================/
775
776	function _httprequest($url,$fp,$URI,$http_method,$content_type="",$body="")
777	{
778	$cookie_headers = '';
779	if($this->passcookies && $this->_redirectaddr)
780	$this->setcookies();
781
782	$URI_PARTS = parse_url($URI);
783	if(empty($url))
784	$url = "/";
785	$headers = $http_method." ".$url." ".$this->_httpversion."\r\n";
786	if(!empty($this->agent))
787	$headers .= "User-Agent: ".$this->agent."\r\n";
788	if(!empty($this->host) && !isset($this->rawheaders['Host'])) {
789	$headers .= "Host: ".$this->host;
790	if(!empty($this->port) && $this->port != 80)
791	$headers .= ":".$this->port;
792	$headers .= "\r\n";
793	}
794	if(!empty($this->accept))
795	$headers .= "Accept: ".$this->accept."\r\n";
796	if(!empty($this->referer))
797	$headers .= "Referer: ".$this->referer."\r\n";
798	if(!empty($this->cookies))
799	{
800	if(!is_array($this->cookies))
801	$this->cookies = (array)$this->cookies;
802
803	reset($this->cookies);
804	if ( count($this->cookies) > 0 ) {
805	$cookie_headers .= 'Cookie: ';
806	foreach ( $this->cookies as $cookieKey => $cookieVal ) {
807	$cookie_headers .= $cookieKey."=".urlencode($cookieVal)."; ";
808	}
809	$headers .= substr($cookie_headers,0,-2) . "\r\n";
810	}
811	}
812	if(!empty($this->rawheaders))
813	{
814	if(!is_array($this->rawheaders))
815	$this->rawheaders = (array)$this->rawheaders;
816	while(list($headerKey,$headerVal) = each($this->rawheaders))
817	$headers .= $headerKey.": ".$headerVal."\r\n";
818	}
819	if(!empty($content_type)) {
820	$headers .= "Content-type: $content_type";
821	if ($content_type == "multipart/form-data")
822	$headers .= "; boundary=".$this->_mime_boundary;
823	$headers .= "\r\n";
824	}
825	if(!empty($body))
826	$headers .= "Content-length: ".strlen($body)."\r\n";
827	if(!empty($this->user) \|\| !empty($this->pass))
828	$headers .= "Authorization: Basic ".base64_encode($this->user.":".$this->pass)."\r\n";
829
830	//add proxy auth headers
831	if(!empty($this->proxy_user))
832	$headers .= 'Proxy-Authorization: ' . 'Basic ' . base64_encode($this->proxy_user . ':' . $this->proxy_pass)."\r\n";
833
834
835	$headers .= "\r\n";
836
837	// set the read timeout if needed
838	if ($this->read_timeout > 0)
839	socket_set_timeout($fp, $this->read_timeout);
840	$this->timed_out = false;
841
842	fwrite($fp,$headers.$body,strlen($headers.$body));
843
844	$this->_redirectaddr = false;
845	unset($this->headers);
846
847	while($currentHeader = fgets($fp,$this->_maxlinelen))
848	{
849	if ($this->read_timeout > 0 && $this->_check_timeout($fp))
850	{
851	$this->status=-100;
852	return false;
853	}
854
855	if($currentHeader == "\r\n")
856	break;
857
858	// if a header begins with Location: or URI:, set the redirect
859	if(preg_match("/^(Location:\|URI:)/i",$currentHeader))
860	{
861	// get URL portion of the redirect
862	preg_match("/^(Location:\|URI:)[ ]+(.*)/i",chop($currentHeader),$matches);
863	// look for :// in the Location header to see if hostname is included
864	if(!preg_match("\|\:\/\/\|",$matches[2]))
865	{
866	// no host in the path, so prepend
867	$this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port;
868	// eliminate double slash
869	if(!preg_match("\|^/\|",$matches[2]))
870	$this->_redirectaddr .= "/".$matches[2];
871	else
872	$this->_redirectaddr .= $matches[2];
873	}
874	else
875	$this->_redirectaddr = $matches[2];
876	}
877
878	if(preg_match("\|^HTTP/\|",$currentHeader))
879	{
880	if(preg_match("\|^HTTP/[^\s]\s(.?)\s\|",$currentHeader, $status))
881	{
882	$this->status= $status[1];
883	}
884	$this->response_code = $currentHeader;
885	}
886
887	$this->headers[] = $currentHeader;
888	}
889
890	$results = '';
891	do {
892	$_data = fread($fp, $this->maxlength);
893	if (strlen($_data) == 0) {
894	break;
895	}
896	$results .= $_data;
897	} while(true);
898
899	if ($this->read_timeout > 0 && $this->_check_timeout($fp))
900	{
901	$this->status=-100;
902	return false;
903	}
904
905	// check if there is a a redirect meta tag
906
907	if(preg_match("'<meta[\s]http-equiv[^>]?content[\s]=[\s][\"\']?\d+;[\s]URL[\s]=[\s]([^\"\']?)[\"\']?>'i",$results,$match))
908
909	{
910	$this->_redirectaddr = $this->_expandlinks($match[1],$URI);
911	}
912
913	// have we hit our frame depth and is there frame src to fetch?
914	if(($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.src[\s]=[\'\"]?([^\'\"\>]+)'i",$results,$match))
915	{
916	$this->results[] = $results;
917	for($x=0; $x<count($match[1]); $x++)
918	$this->_frameurls[] = $this->_expandlinks($match[1][$x],$URI_PARTS["scheme"]."://".$this->host);
919	}
920	// have we already fetched framed content?
921	elseif(is_array($this->results))
922	$this->results[] = $results;
923	// no framed content
924	else
925	$this->results = $results;
926
927	return true;
928	}
929
930	/======================================================================\
931	Function: _httpsrequest
932	Purpose: go get the https data from the server using curl
933	Input: $url the url to fetch
934	$URI the full URI
935	$body body contents to send if any (POST)
936	Output:
937	\======================================================================/
938
939	function _httpsrequest($url,$URI,$http_method,$content_type="",$body="")
940	{
941	if($this->passcookies && $this->_redirectaddr)
942	$this->setcookies();
943
944	$headers = array();
945
946	$URI_PARTS = parse_url($URI);
947	if(empty($url))
948	$url = "/";
949	// GET ... header not needed for curl
950	//$headers[] = $http_method." ".$url." ".$this->_httpversion;
951	if(!empty($this->agent))
952	$headers[] = "User-Agent: ".$this->agent;
953	if(!empty($this->host))
954	if(!empty($this->port))
955	$headers[] = "Host: ".$this->host.":".$this->port;
956	else
957	$headers[] = "Host: ".$this->host;
958	if(!empty($this->accept))
959	$headers[] = "Accept: ".$this->accept;
960	if(!empty($this->referer))
961	$headers[] = "Referer: ".$this->referer;
962	if(!empty($this->cookies))
963	{
964	if(!is_array($this->cookies))
965	$this->cookies = (array)$this->cookies;
966
967	reset($this->cookies);
968	if ( count($this->cookies) > 0 ) {
969	$cookie_str = 'Cookie: ';
970	foreach ( $this->cookies as $cookieKey => $cookieVal ) {
971	$cookie_str .= $cookieKey."=".urlencode($cookieVal)."; ";
972	}
973	$headers[] = substr($cookie_str,0,-2);
974	}
975	}
976	if(!empty($this->rawheaders))
977	{
978	if(!is_array($this->rawheaders))
979	$this->rawheaders = (array)$this->rawheaders;
980	while(list($headerKey,$headerVal) = each($this->rawheaders))
981	$headers[] = $headerKey.": ".$headerVal;
982	}
983	if(!empty($content_type)) {
984	if ($content_type == "multipart/form-data")
985	$headers[] = "Content-type: $content_type; boundary=".$this->_mime_boundary;
986	else
987	$headers[] = "Content-type: $content_type";
988	}
989	if(!empty($body))
990	$headers[] = "Content-length: ".strlen($body);
991	if(!empty($this->user) \|\| !empty($this->pass))
992	$headers[] = "Authorization: BASIC ".base64_encode($this->user.":".$this->pass);
993
994	for($curr_header = 0; $curr_header < count($headers); $curr_header++) {
995	$safer_header = strtr( $headers[$curr_header], "\"", " " );
996	$cmdline_params .= " -H \"".$safer_header."\"";
997	}
998
999	if(!empty($body))
1000	$cmdline_params .= " -d \"$body\"";
1001
1002	if($this->read_timeout > 0)
1003	$cmdline_params .= " -m ".$this->read_timeout;
1004
1005	$headerfile = tempnam($temp_dir, "sno");
1006
1007	exec($this->curl_path." -k -D \"$headerfile\"".$cmdline_params." \"".escapeshellcmd($URI)."\"",$results,$return);
1008
1009	if($return)
1010	{
1011	$this->error = "Error: cURL could not retrieve the document, error $return.";
1012	return false;
1013	}
1014
1015
1016	$results = implode("\r\n",$results);
1017
1018	$result_headers = file("$headerfile");
1019
1020	$this->_redirectaddr = false;
1021	unset($this->headers);
1022
1023	for($currentHeader = 0; $currentHeader < count($result_headers); $currentHeader++)
1024	{
1025
1026	// if a header begins with Location: or URI:, set the redirect
1027	if(preg_match("/^(Location: \|URI: )/i",$result_headers[$currentHeader]))
1028	{
1029	// get URL portion of the redirect
1030	preg_match("/^(Location: \|URI:)\s+(.*)/",chop($result_headers[$currentHeader]),$matches);
1031	// look for :// in the Location header to see if hostname is included
1032	if(!preg_match("\|\:\/\/\|",$matches[2]))
1033	{
1034	// no host in the path, so prepend
1035	$this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port;
1036	// eliminate double slash
1037	if(!preg_match("\|^/\|",$matches[2]))
1038	$this->_redirectaddr .= "/".$matches[2];
1039	else
1040	$this->_redirectaddr .= $matches[2];
1041	}
1042	else
1043	$this->_redirectaddr = $matches[2];
1044	}
1045
1046	if(preg_match("\|^HTTP/\|",$result_headers[$currentHeader]))
1047	$this->response_code = $result_headers[$currentHeader];
1048
1049	$this->headers[] = $result_headers[$currentHeader];
1050	}
1051
1052	// check if there is a a redirect meta tag
1053
1054	if(preg_match("'<meta[\s]http-equiv[^>]?content[\s]=[\s][\"\']?\d+;[\s]URL[\s]=[\s]([^\"\']?)[\"\']?>'i",$results,$match))
1055	{
1056	$this->_redirectaddr = $this->_expandlinks($match[1],$URI);
1057	}
1058
1059	// have we hit our frame depth and is there frame src to fetch?
1060	if(($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.src[\s]=[\'\"]?([^\'\"\>]+)'i",$results,$match))
1061	{
1062	$this->results[] = $results;
1063	for($x=0; $x<count($match[1]); $x++)
1064	$this->_frameurls[] = $this->_expandlinks($match[1][$x],$URI_PARTS["scheme"]."://".$this->host);
1065	}
1066	// have we already fetched framed content?
1067	elseif(is_array($this->results))
1068	$this->results[] = $results;
1069	// no framed content
1070	else
1071	$this->results = $results;
1072
1073	unlink("$headerfile");
1074
1075	return true;
1076	}
1077
1078	/======================================================================\
1079	Function: setcookies()
1080	Purpose: set cookies for a redirection
1081	\======================================================================/
1082
1083	function setcookies()
1084	{
1085	for($x=0; $x<count($this->headers); $x++)
1086	{
1087	if(preg_match('/^set-cookie:[\s]+([^=]+)=([^;]+)/i', $this->headers[$x],$match))
1088	$this->cookies[$match[1]] = urldecode($match[2]);
1089	}
1090	}
1091
1092
1093	/======================================================================\
1094	Function: _check_timeout
1095	Purpose: checks whether timeout has occurred
1096	Input: $fp file pointer
1097	\======================================================================/
1098
1099	function _check_timeout($fp)
1100	{
1101	if ($this->read_timeout > 0) {
1102	$fp_status = socket_get_status($fp);
1103	if ($fp_status["timed_out"]) {
1104	$this->timed_out = true;
1105	return true;
1106	}
1107	}
1108	return false;
1109	}
1110
1111	/======================================================================\
1112	Function: _connect
1113	Purpose: make a socket connection
1114	Input: $fp file pointer
1115	\======================================================================/
1116
1117	function _connect(&$fp)
1118	{
1119	if(!empty($this->proxy_host) && !empty($this->proxy_port))
1120	{
1121	$this->_isproxy = true;
1122
1123	$host = $this->proxy_host;
1124	$port = $this->proxy_port;
1125	}
1126	else
1127	{
1128	$host = $this->host;
1129	$port = $this->port;
1130	}
1131
1132	$this->status = 0;
1133
1134	if($fp = fsockopen(
1135	$host,
1136	$port,
1137	$errno,
1138	$errstr,
1139	$this->_fp_timeout
1140	))
1141	{
1142	// socket connection succeeded
1143
1144	return true;
1145	}
1146	else
1147	{
1148	// socket connection failed
1149	$this->status = $errno;
1150	switch($errno)
1151	{
1152	case -3:
1153	$this->error="socket creation failed (-3)";
1154	case -4:
1155	$this->error="dns lookup failure (-4)";
1156	case -5:
1157	$this->error="connection refused or timed out (-5)";
1158	default:
1159	$this->error="connection failed (".$errno.")";
1160	}
1161	return false;
1162	}
1163	}
1164	/======================================================================\
1165	Function: _disconnect
1166	Purpose: disconnect a socket connection
1167	Input: $fp file pointer
1168	\======================================================================/
1169
1170	function _disconnect($fp)
1171	{
1172	return(fclose($fp));
1173	}
1174
1175
1176	/======================================================================\
1177	Function: _prepare_post_body
1178	Purpose: Prepare post body according to encoding type
1179	Input: $formvars - form variables
1180	$formfiles - form upload files
1181	Output: post body
1182	\======================================================================/
1183
1184	function _prepare_post_body($formvars, $formfiles)
1185	{
1186	settype($formvars, "array");
1187	settype($formfiles, "array");
1188	$postdata = '';
1189
1190	if (count($formvars) == 0 && count($formfiles) == 0)
1191	return;
1192
1193	switch ($this->_submit_type) {
1194	case "application/x-www-form-urlencoded":
1195	reset($formvars);
1196	while(list($key,$val) = each($formvars)) {
1197	if (is_array($val) \|\| is_object($val)) {
1198	while (list($cur_key, $cur_val) = each($val)) {
1199	$postdata .= urlencode($key)."[]=".urlencode($cur_val)."&";
1200	}
1201	} else
1202	$postdata .= urlencode($key)."=".urlencode($val)."&";
1203	}
1204	break;
1205
1206	case "multipart/form-data":
1207	$this->_mime_boundary = "Snoopy".md5(uniqid(microtime()));
1208
1209	reset($formvars);
1210	while(list($key,$val) = each($formvars)) {
1211	if (is_array($val) \|\| is_object($val)) {
1212	while (list($cur_key, $cur_val) = each($val)) {
1213	$postdata .= "--".$this->_mime_boundary."\r\n";
1214	$postdata .= "Content-Disposition: form-data; name=\"$key\[\]\"\r\n\r\n";
1215	$postdata .= "$cur_val\r\n";
1216	}
1217	} else {
1218	$postdata .= "--".$this->_mime_boundary."\r\n";
1219	$postdata .= "Content-Disposition: form-data; name=\"$key\"\r\n\r\n";
1220	$postdata .= "$val\r\n";
1221	}
1222	}
1223
1224	reset($formfiles);
1225	while (list($field_name, $file_names) = each($formfiles)) {
1226	settype($file_names, "array");
1227	while (list(, $file_name) = each($file_names)) {
1228	if (!is_readable($file_name)) continue;
1229
1230	$fp = fopen($file_name, "r");
1231	$file_content = fread($fp, filesize($file_name));
1232	fclose($fp);
1233	$base_name = basename($file_name);
1234
1235	$postdata .= "--".$this->_mime_boundary."\r\n";
1236	$postdata .= "Content-Disposition: form-data; name=\"$field_name\"; filename=\"$base_name\"\r\n\r\n";
1237	$postdata .= "$file_content\r\n";
1238	}
1239	}
1240	$postdata .= "--".$this->_mime_boundary."--\r\n";
1241	break;
1242	}
1243
1244	return $postdata;
1245	}
1246	}
1247	endif;
1248	?>
1249

Note: See TracBrowser for help on using the browser.

root/branches/2.6/wp-includes/class-snoopy.php

Download in other formats: