snoopy.php

讲的是网络编程

				$this->error	=	'Invalid protocol "'.$URI_PARTS["scheme"].'"\n';
				return false;
				break;
		}		
		return true;
	}

/*======================================================================*\
	Function:	fetchlinks
	Purpose:	fetch the links from a web page
	Input:		$URI	where you are fetching from
	Output:		$this->results	an array of the URLs
\*======================================================================*/

	function fetchlinks($URI)
	{
		if ($this->fetch($URI))
		{			
			if($this->lastredirectaddr)
				$URI = $this->lastredirectaddr;
			if(is_array($this->results))
			{
				for($x=0;$x<count($this->results);$x++)
					$this->results[$x] = $this->_striplinks($this->results[$x]);
			}
			else
				$this->results = $this->_striplinks($this->results);

			if($this->expandlinks)
				$this->results = $this->_expandlinks($this->results, $URI);
			return true;
		}
		else
			return false;
	}

/*======================================================================*\
	Function:	fetchform
	Purpose:	fetch the form elements from a web page
	Input:		$URI	where you are fetching from
	Output:		$this->results	the resulting html form
\*======================================================================*/

	function fetchform($URI)
	{
		
		if ($this->fetch($URI))
		{			

			if(is_array($this->results))
			{
				for($x=0;$x<count($this->results);$x++)
					$this->results[$x] = $this->_stripform($this->results[$x]);
			}
			else
				$this->results = $this->_stripform($this->results);
			
			return true;
		}
		else
			return false;
	}
	
	
/*======================================================================*\
	Function:	fetchtext
	Purpose:	fetch the text from a web page, stripping the links
	Input:		$URI	where you are fetching from
	Output:		$this->results	the text from the web page
\*======================================================================*/

	function fetchtext($URI)
	{
		if($this->fetch($URI))
		{			
			if(is_array($this->results))
			{
				for($x=0;$x<count($this->results);$x++)
					$this->results[$x] = $this->_striptext($this->results[$x]);
			}
			else
				$this->results = $this->_striptext($this->results);
			return true;
		}
		else
			return false;
	}

/*======================================================================*\
	Function:	submitlinks
	Purpose:	grab links from a form submission
	Input:		$URI	where you are submitting from
	Output:		$this->results	an array of the links from the post
\*======================================================================*/

	function submitlinks($URI, $formvars="", $formfiles="")
	{
		if($this->submit($URI,$formvars, $formfiles))
		{			
			if($this->lastredirectaddr)
				$URI = $this->lastredirectaddr;
			if(is_array($this->results))
			{
				for($x=0;$x<count($this->results);$x++)
				{
					$this->results[$x] = $this->_striplinks($this->results[$x]);
					if($this->expandlinks)
						$this->results[$x] = $this->_expandlinks($this->results[$x],$URI);
				}
			}
			else
			{
				$this->results = $this->_striplinks($this->results);
				if($this->expandlinks)
					$this->results = $this->_expandlinks($this->results,$URI);
			}
			return true;
		}
		else
			return false;
	}

/*======================================================================*\
	Function:	submittext
	Purpose:	grab text from a form submission
	Input:		$URI	where you are submitting from
	Output:		$this->results	the text from the web page
\*======================================================================*/

	function submittext($URI, $formvars = "", $formfiles = "")
	{
		if($this->submit($URI,$formvars, $formfiles))
		{			
			if($this->lastredirectaddr)
				$URI = $this->lastredirectaddr;
			if(is_array($this->results))
			{
				for($x=0;$x<count($this->results);$x++)
				{
					$this->results[$x] = $this->_striptext($this->results[$x]);
					if($this->expandlinks)
						$this->results[$x] = $this->_expandlinks($this->results[$x],$URI);
				}
			}
			else
			{
				$this->results = $this->_striptext($this->results);
				if($this->expandlinks)
					$this->results = $this->_expandlinks($this->results,$URI);
			}
			return true;
		}
		else
			return false;
	}

	

/*======================================================================*\
	Function:	set_submit_multipart
	Purpose:	Set the form submission content type to
				multipart/form-data
\*======================================================================*/
	function set_submit_multipart()
	{
		$this->_submit_type = "multipart/form-data";
	}

	
/*======================================================================*\
	Function:	set_submit_normal
	Purpose:	Set the form submission content type to
				application/x-www-form-urlencoded
\*======================================================================*/
	function set_submit_normal()
	{
		$this->_submit_type = "application/x-www-form-urlencoded";
	}


// XOOPS2 Hack begin
// Added on March 4, 2003 by [e-mail]
/*======================================================================*\
	Function:	set_submit_xml
	Purpose:	Set the submission content type to
				text/xml
\*======================================================================*/
	function set_submit_xml()
	{
		$this->_submit_type = "text/xml";
	}
// XOOPS2 Hack end


/*======================================================================*\
	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
						"'&(quot|#34|#034|#x22);'i",		// replace html entities
						"'&(amp|#38|#038|#x26);'i",			// added hexadecimal values
						"'&(lt|#60|#060|#x3c);'i",
						"'&(gt|#62|#062|#x3e);'i",
						"'&(nbsp|#160|#xa0);'i",
						"'&(iexcl|#161);'i",
						"'&(cent|#162);'i",
						"'&(pound|#163);'i",
						"'&(copy|#169);'i",
						"'&(reg|#174);'i",
						"'&(deg|#176);'i",
						"'&(#39|#039|#x27);'",
						"'&(euro|#8364);'i",				// europe
						"'&a(uml|UML);'",					// german
						"'&o(uml|UML);'",
						"'&u(uml|UML);'",
						"'&A(uml|UML);'",
						"'&O(uml|UML);'",
						"'&U(uml|UML);'",
						"'&szlig;'i",
						);
		$replace = array(	"",
							"",
							"\\1",
							"\"",
							"&",
							"<",
							">",
							" ",
							chr(161),
							chr(162),
							chr(163),
							chr(169),
							chr(174),
							chr(176),
							chr(39),
							chr(128),
							chr(228),
							chr(246),
							chr(252),
							chr(196),
							chr(214),
							chr(220),
							chr(223),
						);
					
		$text = preg_replace($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]);
		$match = preg_replace("|/$|","",$match);
		$match_part = parse_url($match);
		$match_root =
		$match_part["scheme"]."://".$match_part["host"];
				
		$search = array( 	"|^http://".preg_quote($this->host)."|i",
							"|^(\/)|i",
							"|^(?!http://)(?!mailto:)|i",
							"|/\./|",
							"|/[^\/]+/\.\./|"
						);
						
		$replace = array(	"",
							$match_root."/",
							$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="")
	{
		$cookie_headers = '';
		if($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;
			if(!empty($this->port))
				$headers .= ":".$this->port;
			$headers .= "\r\n";
		}
		if(!empty($this->accept))
			$headers .= "Accept: ".$this->accept."\r\n";
		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";
			} 
		}
		if(!empty($this->rawheaders))
		{
			if(!is_array($this->rawheaders))
				$this->rawheaders = (array)$this->rawheaders;
			while(list($headerKey,$headerVal) = each($this->rawheaders))
				$headers .= $headerKey.": ".$headerVal."\r\n";
		}
		if(!empty($content_type)) {
			$headers .= "Content-type: $content_type";
			if ($content_type == "multipart/form-data")
				$headers .= "; boundary=".$this->_mime_boundary;
			$headers .= "\r\n";
		}
		if(!empty($body))	
			$headers .= "Content-length: ".strlen($body)."\r\n";
		if(!empty($this->user) || !empty($this->pass))	
			$headers .= "Authorization: Basic ".base64_encode($this->user.":".$this->pass)."\r\n";
		
		//add proxy auth headers
		if(!empty($this->proxy_user))	
			$headers .= 'Proxy-Authorization: ' . 'Basic ' . base64_encode($this->proxy_user . ':' . $this->proxy_pass)."\r\n";