snoopy.class.inc

下载系统 # 汉化：Fising # 邮箱：[e-mail] # 网址：http://www.fising.cn # 声明：本人水平有限

<?php

/*************************************************

Snoopy - the PHP net client
Author: Monte Ohrt <[e-mail]>
Copyright (c): 1999-2000 ispi, all rights reserved
Version: 1.0

 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA

You may contact the author of Snoopy by e-mail at:
[e-mail]

Or, write to:
Monte Ohrt
CTO, ispi
237 S. 70th suite 220
Lincoln, NE 68510

The latest version of Snoopy can be obtained from:
http://snoopy.sourceforge.com

*************************************************/

class Snoopy
{
	/**** Public variables ****/
	
	/* user definable vars */

	var $host			=	"www.php.net";		// host name we are connecting to
	var $port			=	80;					// port we are connecting to
	var $proxy_host		=	"";					// proxy host to use
	var $proxy_port		=	"";					// proxy port to use
	var $agent			=	"Snoopy v1.0";		// agent we masquerade as
	var	$referer		=	"";					// referer info to pass
	var $cookies		=	array();			// array of cookies to pass
												// $cookies["username"]="joe";
	var	$rawheaders		=	array();			// array of raw headers to send
												// $rawheaders["Content-type"]="text/html";

	var $maxredirs		=	5;					// http redirection depth maximum. 0 = disallow
	var $lastredirectaddr	=	"";				// contains address of last redirected address
	var	$offsiteok		=	true;				// allows redirection off-site
	var $maxframes		=	0;					// frame content depth maximum. 0 = disallow
	var $expandlinks	=	true;				// expand links to fully qualified URLs.
												// this only applies to fetchlinks()
												// or submitlinks()
	var $passcookies	=	true;				// pass set cookies back through redirects
												// NOTE: this currently does not respect
												// dates, domains or paths.
	
	var	$user			=	"";					// user for http authentication
	var	$pass			=	"";					// password for http authentication
	
	// http accept types
	var $accept			=	"image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*";
	
	var $results		=	"";					// where the content is put
		
	var $error			=	"";					// error messages sent here
	var	$response_code	=	"";					// response code returned from server
	var	$headers		=	array();			// headers returned from server sent here
	var	$maxlength		=	500000;				// max return data length (body)
	var $read_timeout	=	0;					// timeout on read operations, in seconds
												// supported only since PHP 4 Beta 4
												// set to 0 to disallow timeouts
	var $timed_out		=	false;				// if a read operation timed out
	var	$status			=	0;					// http request status
	
	var	$curl_path		=	"/usr/bin/curl";
												// Snoopy will use cURL for fetching
												// SSL content if a full system path to
												// the cURL binary is supplied here.
												// set to false if you do not have
												// cURL installed. See http://curl.haxx.se
												// for details on installing cURL.
												// Snoopy does *not* use the cURL
												// library functions built into php,
												// as these functions are not stable
												// as of this Snoopy release.
	
	// send Accept-encoding: gzip?
	var $use_gzip		= true;	
	
	/**** Private variables ****/	
	
	var	$_maxlinelen	=	4096;				// max line length (headers)
	
	var $_httpmethod	=	"GET";				// default http request method
	var $_httpversion	=	"HTTP/1.0";			// default http request version
	var $_submit_method	=	"POST";				// default submit method
	var $_submit_type	=	"application/x-www-form-urlencoded";	// default submit type
	var $_mime_boundary	=   "";					// MIME boundary for multipart/form-data submit type
	var $_redirectaddr	=	false;				// will be set if page fetched is a redirect
	var $_redirectdepth	=	0;					// increments on an http redirect
	var $_frameurls		= 	array();			// frame src urls
	var $_framedepth	=	0;					// increments on frame depth
	
	var $_isproxy		=	false;				// set if using a proxy server
	var $_fp_timeout	=	30;					// timeout for socket connection

/*======================================================================*\
	Function:	fetch
	Purpose:	fetch the contents of a web page
				(and possibly other protocols in the
				future like ftp, nntp, gopher, etc.)
	Input:		$URI	the location of the page to fetch
	Output:		$this->results	the output text from the fetch
\*======================================================================*/

	function fetch($URI)
	{
	
		//preg_match("|^([^:]+)://([^:/]+)(:[\d]+)*(.*)|",$URI,$URI_PARTS);
		$URI_PARTS = parse_url($URI);
		if (!empty($URI_PARTS["user"]))
			$this->user = $URI_PARTS["user"];
		if (!empty($URI_PARTS["pass"]))
			$this->pass = $URI_PARTS["pass"];
				
		switch($URI_PARTS["scheme"])
		{
			case "http":
				$this->host = $URI_PARTS["host"];
				if(!empty($URI_PARTS["port"]))
					$this->port = $URI_PARTS["port"];
				if($this->_connect($fp))
				{
					if($this->_isproxy)
					{
						// using proxy, send entire URI
						$this->_httprequest($URI,$fp,$URI,$this->_httpmethod);
					}
					else
					{
						$path = $URI_PARTS["path"].(isset($URI_PARTS["query"]) ? "?".$URI_PARTS["query"] : "");
						// no proxy, send only the path
						$this->_httprequest($path, $fp, $URI, $this->_httpmethod);
					}
					
					$this->_disconnect($fp);

					if($this->_redirectaddr)
					{
						/* url was redirected, check if we've hit the max depth */
						if($this->maxredirs > $this->_redirectdepth)
						{
							// only follow redirect if it's on this site, or offsiteok is true
							if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok)
							{
								/* follow the redirect */
								$this->_redirectdepth++;
								$this->lastredirectaddr=$this->_redirectaddr;
								$this->fetch($this->_redirectaddr);
							}
						}
					}

					if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0)
					{
						$frameurls = $this->_frameurls;
						$this->_frameurls = array();
						
						while(list(,$frameurl) = each($frameurls))
						{
							if($this->_framedepth < $this->maxframes)
							{
								$this->fetch($frameurl);
								$this->_framedepth++;
							}
							else
								break;
						}
					}					
				}
				else
				{
					return false;
				}
				return true;					
				break;
			case "https":
				if(!$this->curl_path || (!is_executable($this->curl_path))) {
					$this->error = "Bad curl ($this->curl_path), can't fetch HTTPS \n";
					return false;
				}
				$this->host = $URI_PARTS["host"];
				if(!empty($URI_PARTS["port"]))
					$this->port = $URI_PARTS["port"];
				if($this->_isproxy)
				{
					// using proxy, send entire URI
					$this->_httpsrequest($URI,$URI,$this->_httpmethod);
				}
				else
				{
					$path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
					// no proxy, send only the path
					$this->_httpsrequest($path, $URI, $this->_httpmethod);
				}

				if($this->_redirectaddr)
				{
					/* url was redirected, check if we've hit the max depth */
					if($this->maxredirs > $this->_redirectdepth)
					{
						// only follow redirect if it's on this site, or offsiteok is true
						if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok)
						{
							/* follow the redirect */
							$this->_redirectdepth++;
							$this->lastredirectaddr=$this->_redirectaddr;
							$this->fetch($this->_redirectaddr);
						}
					}
				}

				if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0)
				{
					$frameurls = $this->_frameurls;
					$this->_frameurls = array();

					while(list(,$frameurl) = each($frameurls))
					{
						if($this->_framedepth < $this->maxframes)
						{
							$this->fetch($frameurl);
							$this->_framedepth++;
						}
						else
							break;
					}
				}					
				return true;					
				break;
			default:
				// not a valid protocol
				$this->error	=	'Invalid protocol "'.$URI_PARTS["scheme"].'"\n';
				return false;
				break;
		}		
		return true;
	}



/*======================================================================*\
	Private functions
\*======================================================================*/
	
	
/*======================================================================*\
	Function:	_striplinks
	Purpose:	strip the hyperlinks from an html document
	Input:		$document	document to strip.
	Output:		$match		an array of the links
\*======================================================================*/

	function _striplinks($document)
	{	
		preg_match_all("'<\s*a\s+.*href\s*=\s*			# find <a href=
						([\"\'])?					# find single or double quote
						(?(1) (.*?)\\1 | ([^\s\>]+))		# if quote found, match up to next matching
													# quote, otherwise match up to next space
						'isx",$document,$links);
						

		// catenate the non-empty matches from the conditional subpattern

		while(list($key,$val) = each($links[2]))
		{
			if(!empty($val))
				$match[] = $val;
		}				
		
		while(list($key,$val) = each($links[3]))
		{
			if(!empty($val))
				$match[] = $val;
		}		
		
		// return the links
		return $match;
	}

/*======================================================================*\
	Function:	_stripform
	Purpose:	strip the form elements from an html document
	Input:		$document	document to strip.
	Output:		$match		an array of the links
\*======================================================================*/

	function _stripform($document)
	{	
		preg_match_all("'<\/?(FORM|INPUT|SELECT|TEXTAREA|(OPTION))[^<>]*>(?(2)(.*(?=<\/?(option|select)[^<>]*>[\r\n]*)|(?=[\r\n]*))|(?=[\r\n]*))'Usi",$document,$elements);
		
		// catenate the matches
		$match = implode("\r\n",$elements[0]);
				
		// return the links
		return $match;
	}

	
	
/*======================================================================*\
	Function:	_striptext
	Purpose:	strip the text from an html document
	Input:		$document	document to strip.
	Output:		$text		the resulting text
\*======================================================================*/

	function _striptext($document)
	{
		
		// I didn't use preg eval (//e) since that is only available in PHP 4.0.
		// so, list your entities one by one here. I included some of the
		// more common ones.
								
		$search = array("'<script[^>]*?>.*?</script>'si",	// strip out javascript
						"'<[\/\!]*?[^<>]*?>'si",			// strip out html tags
						"'([\r\n])[\s]+'",					// strip out white space
						"'&(quote|#34);'i",					// replace html entities
						"'&(amp|#38);'i",
						"'&(lt|#60);'i",
						"'&(gt|#62);'i",
						"'&(nbsp|#160);'i",
						"'&(iexcl|#161);'i",
						"'&(cent|#162);'i",
						"'&(pound|#163);'i",
						"'&(copy|#169);'i"
						);				
		$replace = array(	"",
							"",
							"\\1",
							"\"",
							"&",
							"<",
							">",
							" ",
							chr(161),
							chr(162),
							chr(163),
							chr(169));
					
		$text = preg_replace($search,$replace,$document);
								
		return $text;
	}

/*======================================================================*\
	Function:	_expandlinks
	Purpose:	expand each link into a fully qualified URL
	Input:		$links			the links to qualify
				$URI			the full URI to get the base from
	Output:		$expandedLinks	the expanded links
\*======================================================================*/

	function _expandlinks($links,$URI)
	{
		
		preg_match("/^[^\?]+/",$URI,$match);

		$match = preg_replace("|/[^\/\.]+\.[^\/\.]+$|","",$match[0]);
				
		$search = array( 	"|^http://".preg_quote($this->host)."|i",
							"|^(?!http://)(\/)?(?!mailto:)|i",
							"|/\./|",
							"|/[^\/]+/\.\./|"
						);
						
		$replace = array(	"",
							$match."/",
							"/",
							"/"
						);			
				
		$expandedLinks = preg_replace($search,$replace,$links);

		return $expandedLinks;
	}

/*======================================================================*\
	Function:	_httprequest
	Purpose:	go get the http data from the server
	Input:		$url		the url to fetch
				$fp			the current open file pointer
				$URI		the full URI
				$body		body contents to send if any (POST)
	Output:		
\*======================================================================*/
	
	function _httprequest($url,$fp,$URI,$http_method,$content_type="",$body="")
	{
		if($this->passcookies && $this->_redirectaddr)
			$this->setcookies();
			
		$URI_PARTS = parse_url($URI);
		if(empty($url))
			$url = "/";
		$headers = $http_method." ".$url." ".$this->_httpversion."\r\n";		
		if(!empty($this->agent))
			$headers .= "User-Agent: ".$this->agent."\r\n";
		if(!empty($this->host) && !isset($this->rawheaders['Host']))
			$headers .= "Host: ".$this->host."\r\n";
		if(!empty($this->accept))
			$headers .= "Accept: ".$this->accept."\r\n";
		
		if($this->use_gzip) {
			// make sure PHP was built with --with-zlib
			// and we can handle gzipp'ed data
			if ( function_exists(gzinflate) ) {
			   $headers .= "Accept-encoding: gzip\r\n";
			}
			else {
			   trigger_error(
			   	"use_gzip is on, but PHP was built without zlib support.".
				"  Requesting file(s) without gzip encoding.", 
				E_USER_NOTICE);
			}
		}
		
		if(!empty($this->referer))
			$headers .= "Referer: ".$this->referer."\r\n";
		if(!empty($this->cookies))
		{			
			if(!is_array($this->cookies))
				$this->cookies = (array)$this->cookies;
	
			reset($this->cookies);
			if ( count($this->cookies) > 0 ) {
				$cookie_headers .= 'Cookie: ';
				foreach ( $this->cookies as $cookieKey => $cookieVal ) {
				$cookie_headers .= $cookieKey."=".urlencode($cookieVal)."; ";
				}
				$headers .= substr($cookie_headers,0,-2) . "\r\n";
			}