From 816cdfb7ee28912908557e07741a2cd803252159 Mon Sep 17 00:00:00 2001 From: Andrew Dolgov Date: Thu, 22 Jan 2009 14:33:02 +0100 Subject: move magpie to lib/ --- lib/magpierss/extlib/Snoopy.class.inc | 1001 +++++++++++++++++++++++++++++++++ 1 file changed, 1001 insertions(+) create mode 100644 lib/magpierss/extlib/Snoopy.class.inc (limited to 'lib/magpierss/extlib') diff --git a/lib/magpierss/extlib/Snoopy.class.inc b/lib/magpierss/extlib/Snoopy.class.inc new file mode 100644 index 000000000..17e6a952d --- /dev/null +++ b/lib/magpierss/extlib/Snoopy.class.inc @@ -0,0 +1,1001 @@ + +Copyright (c): 1999-2000 ispi, all rights reserved +Version: 1.0 (plus - see SJM comments below) + + * 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: +monte@ispi.net + +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 + + + +SJM - alpha-grade changes based on the version of Snoopy released with MagpieRSS 0.7 + +comments to steve@minutillo.com + +Two additions: + +1) If this is PHP 4.3 or greater, and 'openssl' is available, + use the PHP built in SSL support for "https" instead of calling curl externally. + Use of external curl can still be forced by setting $use_curl = true. + + ref: http://us2.php.net/fsockopen + +2) HTTP Digest Authentication. If you set a username and password, basic auth + will be tried first. If that fails, and the server sends back an + WWW-Authenticate: Digest header, the request will be retried with the appropriate + digest response. Only qop=auth is supported, with MD5 as the algorithm. + I realize that sending basic auth first, and then following up with a digest + challenge-response kind of defeats the purpose in terms of security. + + ref: http://www.faqs.org/rfcs/rfc2617.html + +*************************************************/ + +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. + + // SJM - always use curl for HTTPS requests? + var $use_curl = false; + + + // send Accept-encoding: gzip? + var $use_gzip = true; + + /**** Private variables ****/ + + var $_maxlinelen = 4096; // max line length (headers) + + var $_scheme = "http"; // default scheme + 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 $_trieddigest = false; // have we tried Digest auth yet? + 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"])) + $this->user = urldecode($URI_PARTS["user"]); + if (!empty($URI_PARTS["pass"])) + $this->pass = urldecode($URI_PARTS["pass"]); + + $this->_scheme = $URI_PARTS["scheme"]; + + switch($URI_PARTS["scheme"]) + { + case "http": + case "https": + break; + + default: + // not a valid protocol + $this->error = 'Invalid protocol "'.$URI_PARTS["scheme"].'"\n'; + return false; + } + + if($URI_PARTS["scheme"] == "https") + { + // SJM - if they really want curl, or it isn't PHP 4.3 yet, or openssl extension isn't loaded + + if($use_curl || !function_exists('file_get_contents') || !extension_loaded('openssl')) + { + 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 + $this->_curlrequest($URI,$URI,$this->_httpmethod); + } + else + { + $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : ""); + // no proxy, send only the path + $this->_curlrequest($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; + } + } + + // SJM - else drop through and treat https as http + + $this->host = $URI_PARTS["host"]; + if(!empty($URI_PARTS["port"])) + $this->port = $URI_PARTS["port"]; + + // SJM - if it's https, default the port to 443 + if($URI_PARTS["scheme"] == "https") + { + if(empty($URI_PARTS["port"])) + { + $this->port = 443; + } + } + + if($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; + } + + + +/*======================================================================*\ + 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 ]+)) # 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("']*?>.*?'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"; + } + } + 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)) { + $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"; + + $headers .= "\r\n"; + + // set the read timeout if needed + if ($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); + + // content was returned gzip encoded? + $is_gzipped = false; + + while($currentHeader = fgets($fp,$this->_maxlinelen)) + { + if ($this->read_timeout > 0 && $this->_check_timeout($fp)) + { + $this->status=-100; + return false; + } + + // if($currentHeader == "\r\n") + if(preg_match("/^\r?\n$/", $currentHeader) ) + break; + + if(!$this->_tried_digest && preg_match("/^WWW-Authenticate: Digest (.*)/", $currentHeader, $matches)) + { + // SJM - we got a Digest challenge. Try to respond... + + $digestheader = $matches[1]; + + preg_match("/nonce=\"(.*?)\"/", $digestheader, $matches); + $nonce = $matches[1]; + + preg_match("/realm=\"(.*?)\"/", $digestheader, $matches); + $realm = $matches[1]; + + $cnonce = md5(microtime()); + + $a1 = $this->user . ":" . $realm . ":" . $this->pass; + $a2 = $http_method . ":" . $url; + + $ha1 = md5($a1); + $ha2 = md5($a2); + + $response = md5($ha1 . ":" . $nonce . ":00000001:" . $cnonce . ":auth:" . $ha2); + + $auth = 'Digest username="' . $this->user . '", '; + $auth .= 'realm="' . $realm . '", '; + $auth .= 'nonce="' . $nonce . '", '; + $auth .= 'uri="' . $url . '", '; + $auth .= 'response="' . $response . '", '; + $auth .= 'algorithm="MD5", '; + $auth .= 'cnonce="' . $cnonce . '", '; + $auth .= 'nc=00000001, '; + $auth .= 'qop="auth"'; + + // SJM - treat Digest challenge as a redirect. set flag so we don't keep retrying. + + $this->_tried_digest = true; + + $this->rawheaders["Authorization"]=$auth . "\r\n"; + $this->user = ""; + $this->pass = ""; + + $this->_redirectaddr = $URI_PARTS['scheme'] . '://' . $this->host . $url; + } + + // if a header begins with Location: or URI:, set the redirect + if(preg_match("/^(Location:|URI:)/i",$currentHeader)) + { + // get URL portion of the redirect + preg_match("/^(Location:|URI:)\s+(.*)/",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; + } + + if (preg_match("/Content-Encoding: gzip/", $currentHeader) ) { + $is_gzipped = true; + } + + $this->headers[] = $currentHeader; + } + + # $results = fread($fp, $this->maxlength); + $results = ""; + while ( $data = fread($fp, $this->maxlength) ) { + $results .= $data; + if ( + strlen($results) > $this->maxlength ) { + break; + } + } + + // gunzip + if ( $is_gzipped ) { + // per http://www.php.net/manual/en/function.gzencode.php + $results = substr($results, 10); + $results = gzinflate($results); + } + + if ($this->read_timeout > 0 && $this->_check_timeout($fp)) + { + $this->status=-100; + return false; + } + + // check if there is a a redirect meta tag + + if(preg_match("']*?content[\s]*=[\s]*[\"\']?\d+;[\s]+URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match)) + { + $this->_redirectaddr = $this->_expandlinks($match[1],$URI); + } + + // have we hit our frame depth and is there frame src to fetch? + if(($this->_framedepth < $this->maxframes) && preg_match_all("']+)'i",$results,$match)) + { + $this->results[] = $results; + for($x=0; $x_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: _curlrequest + Purpose: go get the https data from the server using curl + Input: $url the url to fetch + $URI the full URI + $body body contents to send if any (POST) + Output: +\*======================================================================*/ + + function _curlrequest($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)) + $headers[] = "Host: ".$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; + + $headerfile = uniqid(time()); + + # accept self-signed certs + + // mbi: removed, as it breaks on older cURL's + //$cmdline_params .= " -k"; + + exec($this->curl_path." -D \"/tmp/$headerfile\"".$cmdline_params." ".$URI,$results,$return); + + if($return) + { + $this->error = "Error: cURL could not retrieve the document, error $return."; + return false; + } + + + $results = implode("\r\n",$results); + + $result_headers = file("/tmp/$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[$currentHeader])) + { + // get URL portion of the redirect + preg_match("/^(Location: |URI:)(.*)/",chop($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]; + if(preg_match("|^HTTP/[^\s]*\s(.*?)\s|",$this->response_code, $match)) + { + $this->status= $match[1]; + } + } + $this->headers[] = $result_headers[$currentHeader]; + } + + // 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],$URI); + } + + // have we hit our frame depth and is there frame src to fetch? + if(($this->_framedepth < $this->maxframes) && preg_match_all("']+)'i",$results,$match)) + { + $this->results[] = $results; + for($x=0; $x_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 = $results; + + unlink("/tmp/$headerfile"); + + return true; + } + +/*======================================================================*\ + Function: setcookies() + Purpose: set cookies for a redirection +\*======================================================================*/ + + function setcookies() + { + for($x=0; $xheaders); $x++) + { + if(preg_match("/^set-cookie:[\s]+([^=]+)=([^;]+)/i", $this->headers[$x],$match)) + $this->cookies[$match[1]] = $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; + } + + $this->status = 0; + + if($this->_scheme == "https") + { + $host = "ssl://" . $host; + } + + if($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($formfiles, "array"); + + if (count($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; + } +} + +?> -- cgit v1.2.3