class-snoopy.php

Revision 1518, 36.6 kB (checked in by donncha, 3 weeks ago)
WP 2.6.3 security fix
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