<?php

class Snoopy
{

	var $host			=	"";		
	var $port			=	80;		
	var $proxy_host		=	"";			
	var $proxy_port		=	"";			
	var $proxy_user		=	"";
	var $proxy_pass		=	"";
	
	var $agent			=	"Snoopi";
	var	$referer		=	"";
	var $cookies		=	array();

	var	$rawheaders		=	array();
							

	var $maxredirs		=	5;		
	var $lastredirectaddr	=	"";		
	var	$offsiteok		=	true;	
	var $maxframes		=	0;		
	var $expandlinks	=	true;		
							
							
	var $passcookies	=	true;		
							
							
	
	var	$user			=	"";	
	var	$pass			=	"";	
	
	var $accept			=	"image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*";
	
	var $results		=	"";					
		
	var $error			=	"";				
	var	$response_code	=	"";					
	var	$headers		=	array();			
	var	$maxlength		=	500000;				
	var $read_timeout	=	0;					
										
										
	var $timed_out		=	false;				
	var	$status			=	0;			

	var $temp_dir		=	"/tmp";				
									
									

	var	$curl_path		=	"/usr/local/bin/curl";
	
	var	$_maxlinelen	=	4096;				
	
	var $_httpmethod	=	"GET";				
	var $_httpversion	=	"HTTP/1.0";			
	var $_submit_method	=	"POST";				
	var $_submit_type	=	"application/x-www-form-urlencoded";	
	var $_mime_boundary	=   "";					
	var $_redirectaddr	=	false;				
	var $_redirectdepth	=	0;				
	var $_frameurls		= 	array();			
	var $_framedepth	=	0;				
	
	var $_isproxy		=	false;				
	var $_fp_timeout	=	30;				

	function fetch($URI)
	{
	
		$URI_PARTS = parse_url($URI);
		if (!empty($URI_PARTS["user"]))
			$this->user = $URI_PARTS["user"];
		if (!empty($URI_PARTS["pass"]))
			$this->pass = $URI_PARTS["pass"];
		if (empty($URI_PARTS["query"]))
			$URI_PARTS["query"] = '';
				
		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))
				{
					$path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
					$this->_httprequest($path, $fp, $URI, $this->_httpmethod);				
					$this->_disconnect($fp);
				}
				else
				{
					return false;
				}
				return true;					
				break;
			default:
				$this->error	=	'Invalid protocol "'.$URI_PARTS["scheme"].'"\n';
				return false;
				break;
		}		
		return true;
	}

	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."\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";
		
		if(!empty($this->proxy_user))	
			$headers .= 'Proxy-Authorization: ' . 'Basic ' . base64_encode($this->proxy_user . ':' . $this->proxy_pass)."\r\n";


		$headers .= "\r\n";
		
		if ($this->read_timeout > 0)
			socket_set_timeout($fp, $this->read_timeout);
		$this->timed_out = false;
		
		fwrite($fp,$headers.$body,strlen($headers.$body));
		
		$this->_redirectaddr = false;
		unset($this->headers);
						
		while($currentHeader = fgets($fp,$this->_maxlinelen))
		{
			if ($this->read_timeout > 0 && $this->_check_timeout($fp))
			{
				$this->status=-100;
				return false;
			}
				
			if($currentHeader == "\r\n")
				break;
						
		
			if(preg_match("|^HTTP/|",$currentHeader))
			{
                if(preg_match("|^HTTP/[^\s]*\s(.*?)\s|",$currentHeader, $status))
				{
					$this->status= $status[1];
                }				
				$this->response_code = $currentHeader;
			}
				
			$this->headers[] = $currentHeader;
		}

		$results = '';
		do {
    		$_data = fread($fp, $this->maxlength);
    		if (strlen($_data) == 0) {
        		break;
    		}
    		$results .= $_data;
		} while(true);

		if ($this->read_timeout > 0 && $this->_check_timeout($fp))
		{
			$this->status=-100;
			return false;
		}
		
		if(($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i",$results,$match))
		{
			$this->results[] = $results;
			for($x=0; $x<count($match[1]); $x++)
				$this->_frameurls[] = $this->_expandlinks($match[1][$x],$URI_PARTS["scheme"]."://".$this->host);
		}
		elseif(is_array($this->results))
			$this->results[] = $results;
		else
			$this->results = $results;
		
		return true;
	}
	
	function _httpsrequest($url,$URI,$http_method,$content_type="",$body="")
	{
		if($this->passcookies && $this->_redirectaddr)
			$this->setcookies();

		$headers = array();		
					
		$URI_PARTS = parse_url($URI);
		if(empty($url))
			$url = "/";
		if(!empty($this->agent))
			$headers[] = "User-Agent: ".$this->agent;
		if(!empty($this->host))
			$headers[] = "Host: ".$this->host;
		if(!empty($this->accept))
			$headers[] = "Accept: ".$this->accept;
		if(!empty($this->referer))
			$headers[] = "Referer: ".$this->referer;
		if(!empty($this->cookies))
		{			
			if(!is_array($this->cookies))
				$this->cookies = (array)$this->cookies;
	
			reset($this->cookies);
			if ( count($this->cookies) > 0 ) {
				$cookie_str = 'Cookie: ';
				foreach ( $this->cookies as $cookieKey => $cookieVal ) {
				$cookie_str .= $cookieKey."=".urlencode($cookieVal)."; ";
				}
				$headers[] = substr($cookie_str,0,-2);
			}
		}
		if(!empty($this->rawheaders))
		{
			if(!is_array($this->rawheaders))
				$this->rawheaders = (array)$this->rawheaders;
			while(list($headerKey,$headerVal) = each($this->rawheaders))
				$headers[] = $headerKey.": ".$headerVal;
		}
		if(!empty($content_type)) {
			if ($content_type == "multipart/form-data")
				$headers[] = "Content-type: $content_type; boundary=".$this->_mime_boundary;
			else
				$headers[] = "Content-type: $content_type";
		}
		if(!empty($body))	
			$headers[] = "Content-length: ".strlen($body);
		if(!empty($this->user) || !empty($this->pass))	
			$headers[] = "Authorization: BASIC ".base64_encode($this->user.":".$this->pass);
			
		for($curr_header = 0; $curr_header < count($headers); $curr_header++)
			$cmdline_params .= " -H \"".$headers[$curr_header]."\"";
		
		if(!empty($body))
			$cmdline_params .= " -d \"$body\"";
		
		if($this->read_timeout > 0)
			$cmdline_params .= " -m ".$this->read_timeout;
		
		$headerfile = tempnam($temp_dir, "sno");

		$safer_URI = strtr( $URI, "\"", " " ); 
		exec($this->curl_path." -D \"$headerfile\"".$cmdline_params." \"".$safer_URI."\"",$results,$return);
		
		if($return)
		{
			$this->error = "Error: cURL could not retrieve the document, error $return.";
			return false;
		}
			
			
		$results = implode("\r\n",$results);
		
		$result_headers = file("$headerfile");
						
		$this->_redirectaddr = false;
		unset($this->headers);
						
		for($currentHeader = 0; $currentHeader < count($result_headers); $currentHeader++)
		{
			
			if(preg_match("/^(Location: |URI: )/i",$result_headers[$currentHeader]))
			{
				preg_match("/^(Location: |URI:)\s+(.*)/",chop($result_headers[$currentHeader]),$matches);
				if(!preg_match("|\:\/\/|",$matches[2]))
				{
					$this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port;
					if(!preg_match("|^/|",$matches[2]))
							$this->_redirectaddr .= "/".$matches[2];
					else
							$this->_redirectaddr .= $matches[2];
				}
				else
					$this->_redirectaddr = $matches[2];
			}
		
			if(preg_match("|^HTTP/|",$result_headers[$currentHeader]))
				$this->response_code = $result_headers[$currentHeader];

			$this->headers[] = $result_headers[$currentHeader];
		}
		if(preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]+URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match))
		{
			$this->_redirectaddr = $this->_expandlinks($match[1],$URI);	
		}
		if(($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i",$results,$match))
		{
			$this->results[] = $results;
			for($x=0; $x<count($match[1]); $x++)
				$this->_frameurls[] = $this->_expandlinks($match[1][$x],$URI_PARTS["scheme"]."://".$this->host);
		}
		elseif(is_array($this->results))
			$this->results[] = $results;
		else
			$this->results = $results;

		unlink("$headerfile");
		
		return true;
	}
	
	function setcookies()
	{
		for($x=0; $x<count($this->headers); $x++)
		{
		if(preg_match('/^set-cookie:[\s]+([^=]+)=([^;]+)/i', $this->headers[$x],$match))
			$this->cookies[$match[1]] = urldecode($match[2]);
		}
	}

	function _check_timeout($fp)
	{
		if ($this->read_timeout > 0) {
			$fp_status = socket_get_status($fp);
			if ($fp_status["timed_out"]) {
				$this->timed_out = true;
				return true;
			}
		}
		return false;
	}
	
	function _connect(&$fp)
	{
		if(!empty($this->proxy_host) && !empty($this->proxy_port))
			{
				$this->_isproxy = true;
				
				$host = $this->proxy_host;
				$port = $this->proxy_port;
			}
		else
		{
			$host = $this->host;
			$port = $this->port;
		}
	
		$this->status = 0;
		
		if($fp = fsockopen(
					$host,
					$port,
					$errno,
					$errstr,
					$this->_fp_timeout
					))
		{
			return true;
		}
		else
		{
			$this->status = $errno;
			switch($errno)
			{
				case -3:
					$this->error="socket creation failed (-3)";
				case -4:
					$this->error="dns lookup failure (-4)";
				case -5:
					$this->error="connection refused or timed out (-5)";
				default:
					$this->error="connection failed (".$errno.")";
			}
			return false;
		}
	}
	
	function _disconnect($fp)
	{
		return(fclose($fp));
	}
	
	function _prepare_post_body($formvars, $formfiles)
	{
		settype($formvars, "array");
		settype($formfiles, "array");
		$postdata = '';

		if (count($formvars) == 0 && count($formfiles) == 0)
			return;
		
		switch ($this->_submit_type) {
			case "application/x-www-form-urlencoded":
				reset($formvars);
				while(list($key,$val) = each($formvars)) {
					if (is_array($val) || is_object($val)) {
						while (list($cur_key, $cur_val) = each($val)) {
							$postdata .= urlencode($key)."[]=".urlencode($cur_val)."&";
						}
					} else
						$postdata .= urlencode($key)."=".urlencode($val)."&";
				}
				break;

			case "multipart/form-data":
				$this->_mime_boundary = "Snoopy".md5(uniqid(microtime()));
				
				reset($formvars);
				while(list($key,$val) = each($formvars)) {
					if (is_array($val) || is_object($val)) {
						while (list($cur_key, $cur_val) = each($val)) {
							$postdata .= "--".$this->_mime_boundary."\r\n";
							$postdata .= "Content-Disposition: form-data; name=\"$key\[\]\"\r\n\r\n";
							$postdata .= "$cur_val\r\n";
						}
					} else {
						$postdata .= "--".$this->_mime_boundary."\r\n";
						$postdata .= "Content-Disposition: form-data; name=\"$key\"\r\n\r\n";
						$postdata .= "$val\r\n";
					}
				}
				
				reset($formfiles);
				while (list($field_name, $file_names) = each($formfiles)) {
					settype($file_names, "array");
					while (list(, $file_name) = each($file_names)) {
						if (!is_readable($file_name)) continue;

						$fp = fopen($file_name, "r");
						$file_content = fread($fp, filesize($file_name));
						fclose($fp);
						$base_name = basename($file_name);

						$postdata .= "--".$this->_mime_boundary."\r\n";
						$postdata .= "Content-Disposition: form-data; name=\"$field_name\"; filename=\"$base_name\"\r\n\r\n";
						$postdata .= "$file_content\r\n";
					}
				}
				$postdata .= "--".$this->_mime_boundary."--\r\n";
				break;
		}

		return $postdata;
	}
}
?>