summaryrefslogtreecommitdiffstats
path: root/modules/infotools/Snoopy.class.php
diff options
context:
space:
mode:
Diffstat (limited to 'modules/infotools/Snoopy.class.php')
-rw-r--r--modules/infotools/Snoopy.class.php268
1 files changed, 134 insertions, 134 deletions
diff --git a/modules/infotools/Snoopy.class.php b/modules/infotools/Snoopy.class.php
index 63198bbd..9c458797 100644
--- a/modules/infotools/Snoopy.class.php
+++ b/modules/infotools/Snoopy.class.php
@@ -33,7 +33,7 @@ http://snoopy.sourceforge.net/
class Snoopy
{
/**** Public variables ****/
-
+
/* user definable vars */
var $host = "www.php.net"; // host name we are connecting to
@@ -42,7 +42,7 @@ 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 v1.2.4"; // agent we masquerade as
var $referer = ""; // referer info to pass
var $cookies = array(); // array of cookies to pass
@@ -60,15 +60,15 @@ 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
@@ -94,11 +94,11 @@ 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
@@ -108,7 +108,7 @@ 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 $_fp_timeout = 30; // timeout for socket connection
@@ -123,7 +123,7 @@ class Snoopy
function fetch($URI)
{
-
+
//preg_match("|^([^:]+)://([^:/]+)(:[\d]+)*(.*)|",$URI,$URI_PARTS);
$URI_PARTS = parse_url($URI);
if (!empty($URI_PARTS["user"]))
@@ -134,7 +134,7 @@ class Snoopy
$URI_PARTS["query"] = '';
if (empty($URI_PARTS["path"]))
$URI_PARTS["path"] = '';
-
+
switch(strtolower($URI_PARTS["scheme"]))
{
case "http":
@@ -154,7 +154,7 @@ class Snoopy
// no proxy, send only the path
$this->_httprequest($path, $fp, $URI, $this->_httpmethod);
}
-
+
$this->_disconnect($fp);
if($this->_redirectaddr)
@@ -177,7 +177,7 @@ class Snoopy
{
$frameurls = $this->_frameurls;
$this->_frameurls = array();
-
+
while(list(,$frameurl) = each($frameurls))
{
if($this->_framedepth < $this->maxframes)
@@ -188,13 +188,13 @@ class Snoopy
else
break;
}
- }
+ }
}
else
{
return false;
}
- return true;
+ return true;
break;
case "https":
if(!$this->curl_path)
@@ -248,15 +248,15 @@ 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;
}
@@ -274,9 +274,9 @@ 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"];
@@ -306,17 +306,17 @@ 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)
{
@@ -335,9 +335,9 @@ class Snoopy
{
$frameurls = $this->_frameurls;
$this->_frameurls = array();
-
+
while(list(,$frameurl) = each($frameurls))
- {
+ {
if($this->_framedepth < $this->maxframes)
{
$this->fetch($frameurl);
@@ -346,14 +346,14 @@ class Snoopy
else
break;
}
- }
-
+ }
+
}
else
{
return false;
}
- return true;
+ return true;
break;
case "https":
if(!$this->curl_path)
@@ -380,9 +380,9 @@ class Snoopy
{
/* url was redirected, check if we've hit the max depth */
if($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)
@@ -404,7 +404,7 @@ class Snoopy
$this->_frameurls = array();
while(list(,$frameurl) = each($frameurls))
- {
+ {
if($this->_framedepth < $this->maxframes)
{
$this->fetch($frameurl);
@@ -413,16 +413,16 @@ 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;
}
@@ -436,7 +436,7 @@ class Snoopy
function fetchlinks($URI)
{
if ($this->fetch($URI))
- {
+ {
if($this->lastredirectaddr)
$URI = $this->lastredirectaddr;
if(is_array($this->results))
@@ -464,9 +464,9 @@ class Snoopy
function fetchform($URI)
{
-
+
if ($this->fetch($URI))
- {
+ {
if(is_array($this->results))
{
@@ -475,14 +475,14 @@ 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
@@ -493,7 +493,7 @@ class Snoopy
function fetchtext($URI)
{
if($this->fetch($URI))
- {
+ {
if(is_array($this->results))
{
for($x=0;$x<count($this->results);$x++)
@@ -517,7 +517,7 @@ class Snoopy
function submitlinks($URI, $formvars="", $formfiles="")
{
if($this->submit($URI,$formvars, $formfiles))
- {
+ {
if($this->lastredirectaddr)
$URI = $this->lastredirectaddr;
if(is_array($this->results))
@@ -551,7 +551,7 @@ class Snoopy
function submittext($URI, $formvars = "", $formfiles = "")
{
if($this->submit($URI,$formvars, $formfiles))
- {
+ {
if($this->lastredirectaddr)
$URI = $this->lastredirectaddr;
if(is_array($this->results))
@@ -575,7 +575,7 @@ class Snoopy
return false;
}
-
+
/*======================================================================*\
Function: set_submit_multipart
@@ -587,7 +587,7 @@ class Snoopy
$this->_submit_type = "multipart/form-data";
}
-
+
/*======================================================================*\
Function: set_submit_normal
Purpose: Set the form submission content type to
@@ -598,14 +598,14 @@ class Snoopy
$this->_submit_type = "application/x-www-form-urlencoded";
}
-
-
+
+
/*======================================================================*\
Private functions
\*======================================================================*/
-
-
+
+
/*======================================================================*\
Function: _striplinks
Purpose: strip the hyperlinks from an html document
@@ -614,13 +614,13 @@ class Snoopy
\*======================================================================*/
function _striplinks($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
@@ -628,14 +628,14 @@ class Snoopy
{
if(!empty($val))
$match[] = $val;
- }
-
+ }
+
while(list($key,$val) = each($links[3]))
{
if(!empty($val))
$match[] = $val;
- }
-
+ }
+
// return the links
return $match;
}
@@ -648,18 +648,18 @@ class Snoopy
\*======================================================================*/
function _stripform($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 $match;
}
-
-
+
+
/*======================================================================*\
Function: _striptext
Purpose: strip the text from an html document
@@ -669,11 +669,11 @@ class Snoopy
function _striptext($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("'<script[^>]*?>.*?</script>'si", // strip out javascript
"'<[\/\!]*?[^<>]*?>'si", // strip out html tags
"'([\r\n])[\s]+'", // strip out white space
@@ -722,9 +722,9 @@ class Snoopy
"Ü",
"ß",
);
-
+
$text = preg_replace($search,$replace,$document);
-
+
return $text;
}
@@ -738,7 +738,7 @@ class Snoopy
function _expandlinks($links,$URI)
{
-
+
preg_match("/^[^\?]+/",$URI,$match);
$match = preg_replace("|/[^\/\.]+\.[^\/\.]+$|","",$match[0]);
@@ -746,21 +746,21 @@ 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;
@@ -773,19 +773,19 @@ 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'])) {
@@ -799,10 +799,10 @@ 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: ';
@@ -810,7 +810,7 @@ class Snoopy
$cookie_headers .= $cookieKey."=".urlencode($cookieVal)."; ";
}
$headers .= substr($cookie_headers,0,-2) . "\r\n";
- }
+ }
}
if(!empty($this->rawheaders))
{
@@ -825,28 +825,28 @@ 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))
@@ -854,10 +854,10 @@ 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))
{
@@ -877,16 +877,16 @@ 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;
}
@@ -904,13 +904,13 @@ class Snoopy
$this->status=-100;
return false;
}
-
+
// check if there is a a redirect meta tag
-
+
if(preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match))
{
- $this->_redirectaddr = $this->_expandlinks($match[1],$URI);
+ $this->_redirectaddr = $this->_expandlinks($match[1],$URI);
}
// have we hit our frame depth and is there frame src to fetch?
@@ -926,7 +926,7 @@ class Snoopy
// no framed content
else
$this->results = $results;
-
+
return true;
}
@@ -936,21 +936,21 @@ 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($this->host))
@@ -963,10 +963,10 @@ class Snoopy
if(!empty($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: ';
@@ -989,43 +989,43 @@ 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");
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]))
{
@@ -1045,7 +1045,7 @@ class Snoopy
else
$this->_redirectaddr = $matches[2];
}
-
+
if(preg_match("|^HTTP/|",$result_headers[$currentHeader]))
$this->response_code = $result_headers[$currentHeader];
@@ -1053,10 +1053,10 @@ class Snoopy
}
// check if there is a 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);
+ $this->_redirectaddr = $this->_expandlinks($match[1],$URI);
}
// have we hit our frame depth and is there frame src to fetch?
@@ -1074,7 +1074,7 @@ class Snoopy
$this->results = $results;
unlink("$headerfile");
-
+
return true;
}
@@ -1082,7 +1082,7 @@ class Snoopy
Function: setcookies()
Purpose: set cookies for a redirection
\*======================================================================*/
-
+
function setcookies()
{
for($x=0; $x<count($this->headers); $x++)
@@ -1092,7 +1092,7 @@ class Snoopy
}
}
-
+
/*======================================================================*\
Function: _check_timeout
Purpose: checks whether timeout has occurred
@@ -1116,13 +1116,13 @@ 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;
}
@@ -1131,9 +1131,9 @@ class Snoopy
$host = $this->host;
$port = $this->port;
}
-
+
$this->status = 0;
-
+
if($fp = fsockopen(
$host,
$port,
@@ -1169,13 +1169,13 @@ 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
@@ -1183,7 +1183,7 @@ class Snoopy
$formfiles - form upload files
Output: post body
\*======================================================================*/
-
+
function _prepare_post_body($formvars, $formfiles)
{
settype($formvars, "array");
@@ -1192,7 +1192,7 @@ class Snoopy
if (count($formvars) == 0 && count($formfiles) == 0)
return;
-
+
switch ($this->_submit_type) {
case "application/x-www-form-urlencoded":
reset($formvars);
@@ -1208,7 +1208,7 @@ 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)) {
@@ -1223,7 +1223,7 @@ class Snoopy
$postdata .= "$val\r\n";
}
}
-
+
reset($formfiles);
while (list($field_name, $file_names) = each($formfiles)) {
settype($file_names, "array");
generated by cgit (git 2.34.1) at 2025-08-14 01:36:57 +0000