X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/0f29eadd474473203a1182f52af1aa82721cecbd..1c09677af04c9e37714e09b73eb9dbc5b2e3eb13:/wp-includes/class-snoopy.php diff --git a/wp-includes/class-snoopy.php b/wp-includes/class-snoopy.php index e1a9c23d..b1b32d2f 100644 --- a/wp-includes/class-snoopy.php +++ b/wp-includes/class-snoopy.php @@ -1,11 +1,11 @@ -Copyright (c): 1999-2000 ispi, all rights reserved -Version: 1.01 +Copyright (c): 1999-2008 New Digital Group, all rights reserved +Version: 1.2.4 * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public @@ -22,24 +22,17 @@ Version: 1.01 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA You may contact the author of Snoopy by e-mail at: -monte@ispi.net - -Or, write to: -Monte Ohrt -CTO, ispi -237 S. 70th suite 220 -Lincoln, NE 68510 +monte@ohrt.com The latest version of Snoopy can be obtained from: http://snoopy.sourceforge.net/ *************************************************/ -if ( !in_array('Snoopy', get_declared_classes() ) ) : class Snoopy { /**** Public variables ****/ - + /* user definable vars */ var $host = "www.php.net"; // host name we are connecting to @@ -48,8 +41,8 @@ class Snoopy var $proxy_port = ""; // proxy port to use var $proxy_user = ""; // proxy user to use var $proxy_pass = ""; // proxy password to use - - var $agent = "Snoopy v1.2.3"; // agent we masquerade as + + 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"; @@ -66,19 +59,19 @@ class Snoopy 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 = 8192; // max return data length (body) + 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 @@ -100,11 +93,11 @@ class Snoopy // library functions built into php, // as these functions are not stable // as of this Snoopy release. - - /**** Private variables ****/ - + + /**** 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 @@ -114,7 +107,7 @@ class Snoopy 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 $_fp_timeout = 30; // timeout for socket connection @@ -129,7 +122,7 @@ class Snoopy function fetch($URI) { - + //preg_match("|^([^:]+)://([^:/]+)(:[\d]+)*(.*)|",$URI,$URI_PARTS); $URI_PARTS = parse_url($URI); if (!empty($URI_PARTS["user"])) @@ -140,7 +133,7 @@ class Snoopy $URI_PARTS["query"] = ''; if (empty($URI_PARTS["path"])) $URI_PARTS["path"] = ''; - + switch(strtolower($URI_PARTS["scheme"])) { case "http": @@ -160,7 +153,7 @@ class Snoopy // no proxy, send only the path $this->_httprequest($path, $fp, $URI, $this->_httpmethod); } - + $this->_disconnect($fp); if($this->_redirectaddr) @@ -183,7 +176,7 @@ class Snoopy { $frameurls = $this->_frameurls; $this->_frameurls = array(); - + while(list(,$frameurl) = each($frameurls)) { if($this->_framedepth < $this->maxframes) @@ -194,13 +187,13 @@ class Snoopy else break; } - } + } } else { return false; } - return true; + return true; break; case "https": if(!$this->curl_path) @@ -254,15 +247,15 @@ class Snoopy else break; } - } - return true; + } + return true; break; default: // not a valid protocol $this->error = 'Invalid protocol "'.$URI_PARTS["scheme"].'"\n'; return false; break; - } + } return true; } @@ -280,9 +273,9 @@ class Snoopy 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"]; @@ -312,17 +305,17 @@ class Snoopy // 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"]); - + $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) { @@ -341,9 +334,9 @@ class Snoopy { $frameurls = $this->_frameurls; $this->_frameurls = array(); - + while(list(,$frameurl) = each($frameurls)) - { + { if($this->_framedepth < $this->maxframes) { $this->fetch($frameurl); @@ -352,14 +345,14 @@ class Snoopy else break; } - } - + } + } else { return false; } - return true; + return true; break; case "https": if(!$this->curl_path) @@ -386,9 +379,9 @@ class Snoopy { /* url was redirected, check if we've hit the max depth */ if($this->maxredirs > $this->_redirectdepth) - { + { if(!preg_match("|^".$URI_PARTS["scheme"]."://|", $this->_redirectaddr)) - $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]); + $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) @@ -410,7 +403,7 @@ class Snoopy $this->_frameurls = array(); while(list(,$frameurl) = each($frameurls)) - { + { if($this->_framedepth < $this->maxframes) { $this->fetch($frameurl); @@ -419,16 +412,16 @@ class Snoopy else break; } - } - return true; + } + return true; break; - + default: // not a valid protocol $this->error = 'Invalid protocol "'.$URI_PARTS["scheme"].'"\n'; return false; break; - } + } return true; } @@ -442,7 +435,7 @@ class Snoopy function fetchlinks($URI) { if ($this->fetch($URI)) - { + { if($this->lastredirectaddr) $URI = $this->lastredirectaddr; if(is_array($this->results)) @@ -470,9 +463,9 @@ class Snoopy function fetchform($URI) { - + if ($this->fetch($URI)) - { + { if(is_array($this->results)) { @@ -481,14 +474,14 @@ class Snoopy } 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 @@ -499,7 +492,7 @@ class Snoopy function fetchtext($URI) { if($this->fetch($URI)) - { + { if(is_array($this->results)) { for($x=0;$xresults);$x++) @@ -523,7 +516,7 @@ class Snoopy function submitlinks($URI, $formvars="", $formfiles="") { if($this->submit($URI,$formvars, $formfiles)) - { + { if($this->lastredirectaddr) $URI = $this->lastredirectaddr; if(is_array($this->results)) @@ -557,7 +550,7 @@ class Snoopy function submittext($URI, $formvars = "", $formfiles = "") { if($this->submit($URI,$formvars, $formfiles)) - { + { if($this->lastredirectaddr) $URI = $this->lastredirectaddr; if(is_array($this->results)) @@ -581,7 +574,7 @@ class Snoopy return false; } - + /*======================================================================*\ Function: set_submit_multipart @@ -593,7 +586,7 @@ class Snoopy $this->_submit_type = "multipart/form-data"; } - + /*======================================================================*\ Function: set_submit_normal Purpose: Set the form submission content type to @@ -604,14 +597,14 @@ class Snoopy $this->_submit_type = "application/x-www-form-urlencoded"; } - - + + /*======================================================================*\ Private functions \*======================================================================*/ - - + + /*======================================================================*\ Function: _striplinks Purpose: strip the hyperlinks from an html document @@ -620,13 +613,13 @@ class Snoopy \*======================================================================*/ function _striplinks($document) - { + { preg_match_all("'<\s*a\s.*?href\s*=\s* # find ]+)) # 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 @@ -634,14 +627,14 @@ class Snoopy { if(!empty($val)) $match[] = $val; - } - + } + while(list($key,$val) = each($links[3])) { if(!empty($val)) $match[] = $val; - } - + } + // return the links return $match; } @@ -654,18 +647,18 @@ class Snoopy \*======================================================================*/ function _stripform($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 $match; } - - + + /*======================================================================*\ Function: _striptext Purpose: strip the text from an html document @@ -675,11 +668,11 @@ class Snoopy function _striptext($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("']*?>.*?'si", // strip out javascript "'<[\/\!]*?[^<>]*?>'si", // strip out html tags "'([\r\n])[\s]+'", // strip out white space @@ -720,17 +713,17 @@ class Snoopy chr(176), chr(39), chr(128), - "ä", - "ö", - "ü", - "Ä", - "Ö", - "Ü", - "ß", + "ä", + "ö", + "ü", + "Ä", + "Ö", + "Ü", + "ß", ); - + $text = preg_replace($search,$replace,$document); - + return $text; } @@ -744,7 +737,7 @@ class Snoopy function _expandlinks($links,$URI) { - + preg_match("/^[^\?]+/",$URI,$match); $match = preg_replace("|/[^\/\.]+\.[^\/\.]+$|","",$match[0]); @@ -752,21 +745,21 @@ class Snoopy $match_part = parse_url($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; @@ -779,24 +772,24 @@ class Snoopy $fp the current open file pointer $URI the full URI $body body contents to send if any (POST) - Output: + Output: \*======================================================================*/ - + function _httprequest($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"; + $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($this->port)) + if(!empty($this->port) && $this->port != 80) $headers .= ":".$this->port; $headers .= "\r\n"; } @@ -805,10 +798,10 @@ class Snoopy if(!empty($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: '; @@ -816,7 +809,7 @@ class Snoopy $cookie_headers .= $cookieKey."=".urlencode($cookieVal)."; "; } $headers .= substr($cookie_headers,0,-2) . "\r\n"; - } + } } if(!empty($this->rawheaders)) { @@ -831,28 +824,28 @@ class Snoopy $headers .= "; boundary=".$this->_mime_boundary; $headers .= "\r\n"; } - if(!empty($body)) + if(!empty($body)) $headers .= "Content-length: ".strlen($body)."\r\n"; - if(!empty($this->user) || !empty($this->pass)) + 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)) + 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)) @@ -860,10 +853,10 @@ class Snoopy $this->status=-100; return false; } - + if($currentHeader == "\r\n") break; - + // if a header begins with Location: or URI:, set the redirect if(preg_match("/^(Location:|URI:)/i",$currentHeader)) { @@ -883,16 +876,16 @@ class Snoopy 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; } @@ -910,13 +903,13 @@ class Snoopy $this->status=-100; return false; } - + // check if there is a a redirect meta tag - + if(preg_match("']*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match)) { - $this->_redirectaddr = $this->_expandlinks($match[1],$URI); + $this->_redirectaddr = $this->_expandlinks($match[1],$URI); } // have we hit our frame depth and is there frame src to fetch? @@ -932,7 +925,7 @@ class Snoopy // no framed content else $this->results = $results; - + return true; } @@ -942,21 +935,21 @@ class Snoopy Input: $url the url to fetch $URI the full URI $body body contents to send if any (POST) - Output: + Output: \*======================================================================*/ - + function _httpsrequest($url,$URI,$http_method,$content_type="",$body="") { if($this->passcookies && $this->_redirectaddr) $this->setcookies(); - $headers = array(); - + $headers = array(); + $URI_PARTS = parse_url($URI); if(empty($url)) $url = "/"; // GET ... header not needed for curl - //$headers[] = $http_method." ".$url." ".$this->_httpversion; + //$headers[] = $http_method." ".$url." ".$this->_httpversion; if(!empty($this->agent)) $headers[] = "User-Agent: ".$this->agent; if(!empty($this->host)) @@ -969,10 +962,10 @@ class Snoopy if(!empty($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: '; @@ -995,44 +988,43 @@ class Snoopy else $headers[] = "Content-type: $content_type"; } - if(!empty($body)) + if(!empty($body)) $headers[] = "Content-length: ".strlen($body); - if(!empty($this->user) || !empty($this->pass)) + 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++) { $safer_header = strtr( $headers[$curr_header], "\"", " " ); $cmdline_params .= " -H \"".$safer_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( $URI, "\"", " " ); // strip quotes from the URI to avoid shell access - exec(escapeshellcmd($this->curl_path." -D \"$headerfile\"".$cmdline_params." \"".$safer_URI."\""),$results,$return); - + exec($this->curl_path." -k -D \"$headerfile\"".$cmdline_params." \"".escapeshellcmd($URI)."\"",$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])) { @@ -1052,7 +1044,7 @@ class Snoopy else $this->_redirectaddr = $matches[2]; } - + if(preg_match("|^HTTP/|",$result_headers[$currentHeader])) $this->response_code = $result_headers[$currentHeader]; @@ -1060,10 +1052,10 @@ class Snoopy } // check if there is a a redirect meta tag - + if(preg_match("']*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match)) { - $this->_redirectaddr = $this->_expandlinks($match[1],$URI); + $this->_redirectaddr = $this->_expandlinks($match[1],$URI); } // have we hit our frame depth and is there frame src to fetch? @@ -1081,7 +1073,7 @@ class Snoopy $this->results = $results; unlink("$headerfile"); - + return true; } @@ -1089,7 +1081,7 @@ class Snoopy Function: setcookies() Purpose: set cookies for a redirection \*======================================================================*/ - + function setcookies() { for($x=0; $xheaders); $x++) @@ -1099,7 +1091,7 @@ class Snoopy } } - + /*======================================================================*\ Function: _check_timeout Purpose: checks whether timeout has occurred @@ -1123,13 +1115,13 @@ class Snoopy 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; } @@ -1138,9 +1130,9 @@ class Snoopy $host = $this->host; $port = $this->port; } - + $this->status = 0; - + if($fp = fsockopen( $host, $port, @@ -1176,13 +1168,13 @@ class Snoopy 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 @@ -1190,7 +1182,7 @@ class Snoopy $formfiles - form upload files Output: post body \*======================================================================*/ - + function _prepare_post_body($formvars, $formfiles) { settype($formvars, "array"); @@ -1199,7 +1191,7 @@ class Snoopy if (count($formvars) == 0 && count($formfiles) == 0) return; - + switch ($this->_submit_type) { case "application/x-www-form-urlencoded": reset($formvars); @@ -1215,7 +1207,7 @@ class Snoopy 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)) { @@ -1230,7 +1222,7 @@ class Snoopy $postdata .= "$val\r\n"; } } - + reset($formfiles); while (list($field_name, $file_names) = each($formfiles)) { settype($file_names, "array"); @@ -1238,9 +1230,7 @@ class Snoopy if (!is_readable($file_name)) continue; $fp = fopen($file_name, "r"); - while (!feof($fp)) { - $file_content .= fread($fp, filesize($file_name)); - } + $file_content = fread($fp, filesize($file_name)); fclose($fp); $base_name = basename($file_name); @@ -1257,5 +1247,4 @@ class Snoopy } } endif; - ?>