Snoopy{} │ WP 1.0
No Hooks.
Usage
$Snoopy = new Snoopy(); // use class methods
Methods
- public _check_timeout($fp)
- public _connect(&$fp)
- public _disconnect($fp)
- public _expandlinks($links,$URI)
- public _httprequest($url,$fp,$URI,$http_method,$content_type="",$body="")
- public _httpsrequest($url,$URI,$http_method,$content_type="",$body="")
- public _prepare_post_body($formvars, $formfiles)
- public _stripform($document)
- public _striplinks($document)
- public _striptext($document)
- public fetch($URI)
- public fetchform($URI)
- public fetchlinks($URI)
- public fetchtext($URI)
- public set_submit_multipart()
- public set_submit_normal()
- public setcookies()
- public submit($URI, $formvars="", $formfiles="")
- public submitlinks($URI, $formvars="", $formfiles="")
- public submittext($URI, $formvars = "", $formfiles = "")
Snoopy{} Snoopy{} code WP 6.6.2
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 $proxy_user = ""; // proxy user to use var $proxy_pass = ""; // proxy password to use var $agent = "Snoopy v1.2.4"; // 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() // submitlinks(), and submittext() 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 $temp_dir = "/tmp"; // temporary directory that the webserver // has permission to write to. // under Windows, this should be C:\temp var $curl_path = "/usr/local/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. /**** 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 = $URI_PARTS["pass"]; if (empty($URI_PARTS["query"])) $URI_PARTS["query"] = ''; if (empty($URI_PARTS["path"])) $URI_PARTS["path"] = ''; switch(strtolower($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 = $URI_PARTS["path"].($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(); foreach ( $frameurls as $frameurl ) { if($this->_framedepth < $this->maxframes) { $this->fetch($frameurl); $this->_framedepth++; } else break; } } } else { return false; } return true; break; case "https": if(!$this->curl_path) return false; if(function_exists("is_executable")) if (!is_executable($this->curl_path)) 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(); foreach ( $frameurls as $frameurl ) { if($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; } /*======================================================================*\ Function: submit Purpose: submit an http form Input: $URI the location to post the data $formvars the formvars to use. format: $formvars["var"] = "val"; $formfiles an array of files to submit format: $formfiles["var"] = "/dir/filename.ext"; Output: $this->results the text output from the post \*======================================================================*/ function submit($URI, $formvars="", $formfiles="") { unset($postdata); $postdata = $this->_prepare_post_body($formvars, $formfiles); $URI_PARTS = parse_url($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"])) $URI_PARTS["query"] = ''; if (empty($URI_PARTS["path"])) $URI_PARTS["path"] = ''; switch(strtolower($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,$this->_submit_method,$this->_submit_type,$postdata); } else { $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : ""); // no proxy, send only the path $this->_httprequest($path, $fp, $URI, $this->_submit_method, $this->_submit_type, $postdata); } $this->_disconnect($fp); if($this->_redirectaddr) { /* url was redirected, check if we've hit the max depth */ if($this->maxredirs > $this->_redirectdepth) { if(!preg_match("|^".$URI_PARTS["scheme"]."://|", $this->_redirectaddr)) $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]); // 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; if( strpos( $this->_redirectaddr, "?" ) > 0 ) $this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get else $this->submit($this->_redirectaddr,$formvars, $formfiles); } } } if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) { $frameurls = $this->_frameurls; $this->_frameurls = array(); foreach ( $frameurls as $frameurl ) { if($this->_framedepth < $this->maxframes) { $this->fetch($frameurl); $this->_framedepth++; } else break; } } } else { return false; } return true; break; case "https": if(!$this->curl_path) return false; if(function_exists("is_executable")) if (!is_executable($this->curl_path)) 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->_submit_method, $this->_submit_type, $postdata); } else { $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : ""); // no proxy, send only the path $this->_httpsrequest($path, $URI, $this->_submit_method, $this->_submit_type, $postdata); } if($this->_redirectaddr) { /* url was redirected, check if we've hit the max depth */ if($this->maxredirs > $this->_redirectdepth) { if(!preg_match("|^".$URI_PARTS["scheme"]."://|", $this->_redirectaddr)) $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]); // 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; if( strpos( $this->_redirectaddr, "?" ) > 0 ) $this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get else $this->submit($this->_redirectaddr,$formvars, $formfiles); } } } if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) { $frameurls = $this->_frameurls; $this->_frameurls = array(); foreach ( $frameurls as $frameurl ) { if($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; } /*======================================================================*\ 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"; } /*======================================================================*\ 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 foreach ( $links[2] as $key => $val ) { if(!empty($val)) $match[] = $val; } foreach ( $links[3] as $key => $val ) { if(!empty($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);'", "'ß'i", ); $replace = array( "", "", "\\1", "\"", "&", "<", ">", " ", chr(161), chr(162), chr(163), chr(169), chr(174), chr(176), chr(39), chr(128), chr(0xE4), // ANSI ä chr(0xF6), // ANSI ö chr(0xFC), // ANSI ü chr(0xC4), // ANSI Ä chr(0xD6), // ANSI Ö chr(0xDC), // ANSI Ü chr(0xDF), // ANSI ß ); $text = preg_replace($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) && $this->port != 80) $headers .= ":".$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; foreach ( $this->rawheaders as $headerKey => $headerVal ) $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"; $headers .= "\r\n"; // set the read timeout if needed if ($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 a header begins with Location: or URI:, set the redirect if(preg_match("/^(Location:|URI:)/i",$currentHeader)) { // get URL portion of the redirect preg_match("/^(Location:|URI:)[ ]+(.*)/i",chop($currentHeader),$matches); // look for :// in the Location header to see if hostname is included if(!preg_match("|\:\/\/|",$matches[2])) { // no host in the path, so prepend $this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port; // eliminate double slash if(!preg_match("|^/|",$matches[2])) $this->_redirectaddr .= "/".$matches[2]; else $this->_redirectaddr .= $matches[2]; } else $this->_redirectaddr = $matches[2]; } if(preg_match("|^HTTP/|",$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)) { $this->status=-100; return false; } // check if there is a redirect meta tag if(preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match)) { $this->_redirectaddr = $this->_expandlinks($match[1],$URI); } // have we hit our frame depth and is there frame src to fetch? if(($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"]."://".$this->host); } // have we already fetched framed content? elseif(is_array($this->results)) $this->results[] = $results; // no framed content else $this->results = $results; return true; } /*======================================================================*\ Function: _httpsrequest Purpose: go get the https data from the server using curl Input: $url the url to fetch $URI the full URI $body body contents to send if any (POST) Output: \*======================================================================*/ function _httpsrequest($url,$URI,$http_method,$content_type="",$body="") { if($this->passcookies && $this->_redirectaddr) $this->setcookies(); $headers = array(); $URI_PARTS = parse_url($URI); if(empty($url)) $url = "/"; // GET ... header not needed for curl //$headers[] = $http_method." ".$url." ".$this->_httpversion; if(!empty($this->agent)) $headers[] = "User-Agent: ".$this->agent; if(!empty($this->host)) if(!empty($this->port)) $headers[] = "Host: ".$this->host.":".$this->port; else $headers[] = "Host: ".$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; foreach ( $this->rawheaders as $headerKey => $headerVal ) $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); $headerfile = tempnam( $this->temp_dir, "sno" ); $cmdline_params = '-k -D ' . escapeshellarg( $headerfile ); foreach ( $headers as $header ) { $cmdline_params .= ' -H ' . escapeshellarg( $header ); } if ( ! empty( $body ) ) { $cmdline_params .= ' -d ' . escapeshellarg( $body ); } if ( $this->read_timeout > 0 ) { $cmdline_params .= ' -m ' . escapeshellarg( $this->read_timeout ); } exec( $this->curl_path . ' ' . $cmdline_params . ' ' . escapeshellarg( $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); $currentHeader++) { // if a header begins with Location: or URI:, set the redirect if(preg_match("/^(Location: |URI: )/i",$result_headers[$currentHeader])) { // get URL portion of the redirect preg_match("/^(Location: |URI:)\s+(.*)/",chop($result_headers[$currentHeader]),$matches); // look for :// in the Location header to see if hostname is included if(!preg_match("|\:\/\/|",$matches[2])) { // no host in the path, so prepend $this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port; // eliminate double slash if(!preg_match("|^/|",$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]; } // check if there is a redirect meta tag if(preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match)) { $this->_redirectaddr = $this->_expandlinks($match[1],$URI); } // have we hit our frame depth and is there frame src to fetch? if(($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"]."://".$this->host); } // have we already fetched framed content? elseif(is_array($this->results)) $this->results[] = $results; // no framed content else $this->results = $results; unlink("$headerfile"); return true; } /*======================================================================*\ Function: setcookies() Purpose: set cookies for a redirection \*======================================================================*/ 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 Purpose: checks whether timeout has occurred Input: $fp file pointer \*======================================================================*/ function _check_timeout($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 Purpose: make a socket connection Input: $fp file pointer \*======================================================================*/ function _connect(&$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 )) { // socket connection succeeded return true; } else { // socket connection failed $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 Purpose: disconnect a socket connection Input: $fp file pointer \*======================================================================*/ function _disconnect($fp) { return(fclose($fp)); } /*======================================================================*\ Function: _prepare_post_body Purpose: Prepare post body according to encoding type Input: $formvars - form variables $formfiles - form upload files Output: post body \*======================================================================*/ function _prepare_post_body($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); foreach ( $formvars as $key => $val ) { if (is_array($val) || is_object($val)) { foreach ( $val as $cur_key => $cur_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); foreach ( $formvars as $key => $val ) { if (is_array($val) || is_object($val)) { foreach ( $val as $cur_key => $cur_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); foreach ( $formfiles as $field_name => $file_names ) { settype($file_names, "array"); foreach ( $file_names as $file_name ) { if (!is_readable($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; } }