.*?'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))
{
$this->status=-100;
return false;
}
// check if there is a redirect meta tag
if(preg_match("']*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$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: _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("']*?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 = $results;
unlink("$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]] = 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;
}
}
endif;
?>