|
 view all services 
* License: GPL
*
* The lastest version of MagpieRSS can be obtained from:
* http://magpierss.sourceforge.net
*
* For questions, help, comments, discussion, etc., please join the
* Magpie mailing list:
* magpierss-general@lists.sourceforge.net
*
*/
// Setup MAGPIE_DIR for use on hosts that don't include
// the current path in include_path.
// with thanks to rajiv and smarty
if (!defined('DIR_SEP')) {
define('DIR_SEP', DIRECTORY_SEPARATOR);
}
if (!defined('MAGPIE_DIR')) {
define('MAGPIE_DIR', dirname(__FILE__) . DIR_SEP);
}
/* start parse.inc */
define('RSS', 'RSS');
define('ATOM', 'Atom');
class MagpieRSS {
/*
* Hybrid parser, and object. (probably a bad idea! :)
*
* Useage Example:
*
* $some_rss = "channel['title'];
*
* // print the title of each item
* foreach ($rss->items as $item ) {
* echo $item[title];
* }
*
* see: rss_fetch.inc for a simpler interface
*/
var $parser;
var $current_item = array(); // item currently being parsed
var $items = array(); // collection of parsed items
var $channel = array(); // hash of channel fields
var $textinput = array();
var $image = array();
var $feed_type;
var $feed_version;
// parser variables
var $stack = array(); // parser stack
var $inchannel = false;
var $initem = false;
var $incontent = false; // if in Atom field
var $intextinput = false;
var $inimage = false;
var $current_field = '';
var $current_namespace = false;
var $ERROR = "";
var $_CONTENT_CONSTRUCTS = array('content', 'summary', 'info', 'title', 'tagline', 'copyright');
/*======================================================================*\
Function: MagpieRSS
Purpose: Constructor, sets up XML parser,parses source,
and populates object..
Input: String containing the RSS to be parsed
\*======================================================================*/
function MagpieRSS ($source) {
# if PHP xml isn't compiled in, die
#
if (!function_exists('xml_parser_create')) {
$this->error( "Failed to load PHP's XML Extension. " .
"http://www.php.net/manual/en/ref.xml.php",
E_USER_ERROR );
}
$parser = @xml_parser_create();
if (!is_resource($parser))
{
$this->error( "Failed to create an instance of PHP's XML parser. " .
"http://www.php.net/manual/en/ref.xml.php",
E_USER_ERROR );
}
$this->parser = $parser;
# pass in parser, and a reference to this object
# setup handlers
#
xml_set_object( $this->parser, $this );
xml_set_element_handler($this->parser,
'feed_start_element', 'feed_end_element' );
xml_set_character_data_handler( $this->parser, 'feed_cdata' );
$status = xml_parse( $this->parser, $source );
if (! $status ) {
$errorcode = xml_get_error_code( $this->parser );
if ( $errorcode != XML_ERROR_NONE ) {
$xml_error = xml_error_string( $errorcode );
$error_line = xml_get_current_line_number($this->parser);
$error_col = xml_get_current_column_number($this->parser);
$errormsg = "$xml_error at line $error_line, column $error_col";
$this->error( $errormsg );
}
}
xml_parser_free( $this->parser );
$this->normalize();
}
function feed_start_element($p, $element, &$attrs) {
$el = $element = strtolower($element);
$attrs = array_change_key_case($attrs, CASE_LOWER);
// check for a namespace, and split if found
$ns = false;
if ( strpos( $element, ':' ) ) {
list($ns, $el) = split( ':', $element, 2);
}
if ( $ns and $ns != 'rdf' ) {
$this->current_namespace = $ns;
}
# if feed type isn't set, then this is first element of feed
# identify feed from root element
#
if (!isset($this->feed_type) ) {
if ( $el == 'rdf' ) {
$this->feed_type = RSS;
$this->feed_version = '1.0';
}
elseif ( $el == 'rss' ) {
$this->feed_type = RSS;
$this->feed_version = $attrs['version'];
}
elseif ( $el == 'feed' ) {
$this->feed_type = ATOM;
$this->feed_version = $attrs['version'];
$this->inchannel = true;
}
return;
}
if ( $el == 'channel' )
{
$this->inchannel = true;
}
elseif ($el == 'item' or $el == 'entry' )
{
$this->initem = true;
if ( isset($attrs['rdf:about']) ) {
$this->current_item['about'] = $attrs['rdf:about'];
}
}
// if we're in the default namespace of an RSS feed,
// record textinput or image fields
elseif (
$this->feed_type == RSS and
$this->current_namespace == '' and
$el == 'textinput' )
{
$this->intextinput = true;
}
elseif (
$this->feed_type == RSS and
$this->current_namespace == '' and
$el == 'image' )
{
$this->inimage = true;
}
# handle atom content constructs
elseif ( $this->feed_type == ATOM and in_array($el, $this->_CONTENT_CONSTRUCTS) )
{
// avoid clashing w/ RSS mod_content
if ($el == 'content' ) {
$el = 'atom_content';
}
$this->incontent = $el;
}
// if inside an Atom content construct (e.g. content or summary) field treat tags as text
elseif ($this->feed_type == ATOM and $this->incontent )
{
// if tags are inlined, then flatten
$attrs_str = join(' ',
array_map('map_attrs',
array_keys($attrs),
array_values($attrs) ) );
$this->append_content( "<$element $attrs_str>" );
array_unshift( $this->stack, $el );
}
// Atom support many links per containging element.
// Magpie treats link elements of type rel='alternate'
// as being equivalent to RSS's simple link element.
//
elseif ($this->feed_type == ATOM and $el == 'link' )
{
if ( isset($attrs['rel']) and $attrs['rel'] == 'alternate' )
{
$link_el = 'link';
}
else {
$link_el = 'link_' . $attrs['rel'];
}
$this->append($link_el, $attrs['href']);
}
// set stack[0] to current element
else {
array_unshift($this->stack, $el);
}
}
function feed_cdata ($p, $text) {
if ($this->feed_type == ATOM and $this->incontent)
{
$this->append_content( $text );
}
else {
$current_el = join('_', array_reverse($this->stack));
$this->append($current_el, $text);
}
}
function feed_end_element ($p, $el) {
$el = strtolower($el);
if ( $el == 'item' or $el == 'entry' )
{
$this->items[] = $this->current_item;
$this->current_item = array();
$this->initem = false;
}
elseif ($this->feed_type == RSS and $this->current_namespace == '' and $el == 'textinput' )
{
$this->intextinput = false;
}
elseif ($this->feed_type == RSS and $this->current_namespace == '' and $el == 'image' )
{
$this->inimage = false;
}
elseif ($this->feed_type == ATOM and in_array($el, $this->_CONTENT_CONSTRUCTS) )
{
$this->incontent = false;
}
elseif ($el == 'channel' or $el == 'feed' )
{
$this->inchannel = false;
}
elseif ($this->feed_type == ATOM and $this->incontent ) {
// balance tags properly
// note: i don't think this is actually neccessary
if ( $this->stack[0] == $el )
{
$this->append_content("");
}
else {
$this->append_content("<$el />");
}
array_shift( $this->stack );
}
else {
array_shift( $this->stack );
}
$this->current_namespace = false;
}
function concat (&$str1, $str2="") {
if (!isset($str1) ) {
$str1="";
}
$str1 .= $str2;
}
function append_content($text) {
if ( $this->initem ) {
$this->concat( $this->current_item[ $this->incontent ], $text );
}
elseif ( $this->inchannel ) {
$this->concat( $this->channel[ $this->incontent ], $text );
}
}
// smart append - field and namespace aware
function append($el, $text) {
if (!$el) {
return;
}
if ( $this->current_namespace )
{
if ( $this->initem ) {
$this->concat(
$this->current_item[ $this->current_namespace ][ $el ], $text);
}
elseif ($this->inchannel) {
$this->concat(
$this->channel[ $this->current_namespace][ $el ], $text );
}
elseif ($this->intextinput) {
$this->concat(
$this->textinput[ $this->current_namespace][ $el ], $text );
}
elseif ($this->inimage) {
$this->concat(
$this->image[ $this->current_namespace ][ $el ], $text );
}
}
else {
if ( $this->initem ) {
$this->concat(
$this->current_item[ $el ], $text);
}
elseif ($this->intextinput) {
$this->concat(
$this->textinput[ $el ], $text );
}
elseif ($this->inimage) {
$this->concat(
$this->image[ $el ], $text );
}
elseif ($this->inchannel) {
$this->concat(
$this->channel[ $el ], $text );
}
}
}
function normalize () {
// if atom populate rss fields
if ( $this->is_atom() ) {
$this->channel['descripton'] = $this->channel['tagline'];
for ( $i = 0; $i < count($this->items); $i++) {
$item = $this->items[$i];
if ( isset($item['summary']) )
$item['description'] = $item['summary'];
if ( isset($item['atom_content']))
$item['content']['encoded'] = $item['atom_content'];
$this->items[$i] = $item;
}
}
elseif ( $this->is_rss() ) {
$this->channel['tagline'] = $this->channel['description'];
for ( $i = 0; $i < count($this->items); $i++) {
$item = $this->items[$i];
if ( isset($item['description']))
$item['summary'] = $item['description'];
if ( isset($item['content']['encoded'] ) )
$item['atom_content'] = $item['content']['encoded'];
$this->items[$i] = $item;
}
}
}
function error ($errormsg, $lvl=E_USER_WARNING) {
// append PHP's error message if track_errors enabled
if ( $php_errormsg ) {
$errormsg .= " ($php_errormsg)";
}
$this->ERROR = $errormsg;
if ( MAGPIE_DEBUG ) {
trigger_error( $errormsg, $lvl);
}
else {
error_log( $errormsg, 0);
}
}
function is_rss () {
if ( $this->feed_type == RSS ) {
return $this->feed_version;
}
else {
return false;
}
}
function is_atom() {
if ( $this->feed_type == ATOM ) {
return $this->feed_version;
}
else {
return false;
}
}
/*======================================================================*\
EVERYTHING BELOW HERE IS FOR DEBUGGING PURPOSES
\*======================================================================*/
function show_list () {
echo "\n";
foreach ($this->items as $item) {
echo "- ", $this->show_item( $item );
}
echo "
";
}
function show_channel () {
echo "channel:
";
echo "";
while ( list($key, $value) = each( $this->channel ) ) {
echo "- $key: $value";
}
echo "
";
}
function show_item ($item) {
echo "item: $item[title]";
echo "";
while ( list($key, $value) = each($item) ) {
if ( is_array($value) ) {
echo "
$key";
echo "";
while ( list( $ns_key, $ns_value) = each( $value ) ) {
echo "- $ns_key: $ns_value";
}
echo "
";
}
else {
echo "- $key: $value";
}
}
echo "
";
}
/*======================================================================*\
END DEBUGGING FUNCTIONS
\*======================================================================*/
} # end class RSS
function map_attrs($k, $v) {
return "$k=\"$v\"";
}
/* end cache.inc */
class RSSCache {
var $BASE_CACHE = './cache'; // where the cache files are stored
var $MAX_AGE = 3600; // when are files stale, default one hour
var $ERROR = ""; // accumulate error messages
function RSSCache ($base='', $age='') {
if ( $base ) {
$this->BASE_CACHE = $base;
}
if ( $age ) {
$this->MAX_AGE = $age;
}
// attempt to make the cache directory
if ( ! file_exists( $this->BASE_CACHE ) ) {
$status = @mkdir( $this->BASE_CACHE, 0755 );
// if make failed
if ( ! $status ) {
$this->error(
"Cache couldn't make dir '" . $this->BASE_CACHE . "'."
);
}
}
}
/*=======================================================================*\
Function: set
Purpose: add an item to the cache, keyed on url
Input: url from wich the rss file was fetched
Output: true on sucess
\*=======================================================================*/
function set ($url, $rss) {
$this->ERROR = "";
$cache_file = $this->file_name( $url );
$fp = @fopen( $cache_file, 'w' );
if ( ! $fp ) {
$this->error(
"Cache unable to open file for writing: $cache_file"
);
return 0;
}
$data = $this->serialize( $rss );
fwrite( $fp, $data );
fclose( $fp );
return $cache_file;
}
/*=======================================================================*\
Function: get
Purpose: fetch an item from the cache
Input: url from wich the rss file was fetched
Output: cached object on HIT, false on MISS
\*=======================================================================*/
function get ($url) {
$this->ERROR = "";
$cache_file = $this->file_name( $url );
if ( ! file_exists( $cache_file ) ) {
$this->debug(
"Cache doesn't contain: $url (cache file: $cache_file)"
);
return 0;
}
$fp = @fopen($cache_file, 'r');
if ( ! $fp ) {
$this->error(
"Failed to open cache file for reading: $cache_file"
);
return 0;
}
$data = fread( $fp, filesize($cache_file) );
$rss = $this->unserialize( $data );
return $rss;
}
/*=======================================================================*\
Function: check_cache
Purpose: check a url for membership in the cache
and whether the object is older then MAX_AGE (ie. STALE)
Input: url from wich the rss file was fetched
Output: cached object on HIT, false on MISS
\*=======================================================================*/
function check_cache ( $url ) {
$this->ERROR = "";
$filename = $this->file_name( $url );
if ( file_exists( $filename ) ) {
// find how long ago the file was added to the cache
// and whether that is longer then MAX_AGE
$mtime = filemtime( $filename );
$age = time() - $mtime;
if ( $this->MAX_AGE > $age ) {
// object exists and is current
return 'HIT';
}
else {
// object exists but is old
return 'STALE';
}
}
else {
// object does not exist
return 'MISS';
}
}
/*=======================================================================*\
Function: serialize
\*=======================================================================*/
function serialize ( $rss ) {
return serialize( $rss );
}
/*=======================================================================*\
Function: unserialize
\*=======================================================================*/
function unserialize ( $data ) {
return unserialize( $data );
}
/*=======================================================================*\
Function: file_name
Purpose: map url to location in cache
Input: url from wich the rss file was fetched
Output: a file name
\*=======================================================================*/
function file_name ($url) {
$filename = md5( $url );
return join( DIRECTORY_SEPARATOR, array( $this->BASE_CACHE, $filename ) );
}
/*=======================================================================*\
Function: error
Purpose: register error
\*=======================================================================*/
function error ($errormsg, $lvl=E_USER_WARNING) {
// append PHP's error message if track_errors enabled
if ( isset($php_errormsg) ) {
$errormsg .= " ($php_errormsg)";
}
$this->ERROR = $errormsg;
if ( MAGPIE_DEBUG ) {
trigger_error( $errormsg, $lvl);
}
else {
error_log( $errormsg, 0);
}
}
function debug ($debugmsg, $lvl=E_USER_NOTICE) {
if ( MAGPIE_DEBUG ) {
$this->error("MagpieRSS [debug] $debugmsg", $lvl);
}
}
}
/* end cache.inc */
/*
* CONSTANTS - redefine these in your script to change the
* behaviour of fetch_rss() currently, most options effect the cache
*
* MAGPIE_CACHE_ON - Should Magpie cache parsed RSS objects?
* For me a built in cache was essential to creating a "PHP-like"
* feel to Magpie, see rss_cache.inc for rationale
*
*
* MAGPIE_CACHE_DIR - Where should Magpie cache parsed RSS objects?
* This should be a location that the webserver can write to. If this
* directory does not already exist Mapie will try to be smart and create
* it. This will often fail for permissions reasons.
*
*
* MAGPIE_CACHE_AGE - How long to store cached RSS objects? In seconds.
*
*
* MAGPIE_CACHE_FRESH_ONLY - If remote fetch fails, throw error
* instead of returning stale object?
*
* MAGPIE_DEBUG - Display debugging notices?
*
*/
/*=======================================================================*\
Function: fetch_rss:
Purpose: return RSS object for the give url
maintain the cache
Input: url of RSS file
Output: parsed RSS object (see rss_parse.inc)
NOTES ON CACHEING:
If caching is on (MAGPIE_CACHE_ON) fetch_rss will first check the cache.
NOTES ON RETRIEVING REMOTE FILES:
If conditional gets are on (MAGPIE_CONDITIONAL_GET_ON) fetch_rss will
return a cached object, and touch the cache object upon recieving a
304.
NOTES ON FAILED REQUESTS:
If there is an HTTP error while fetching an RSS object, the cached
version will be return, if it exists (and if MAGPIE_CACHE_FRESH_ONLY is off)
\*=======================================================================*/
define('MAGPIE_VERSION', '0.61');
$MAGPIE_ERROR = "";
function fetch_rss ($url) {
// initialize constants
init();
if ( !isset($url) ) {
error("fetch_rss called without a url");
return false;
}
// if cache is disabled
if ( !MAGPIE_CACHE_ON ) {
// fetch file, and parse it
$resp = _fetch_remote_file( $url );
if ( is_success( $resp->status ) ) {
return _response_to_rss( $resp );
}
else {
error("Failed to fetch $url and cache is off");
return false;
}
}
// else cache is ON
else {
// Flow
// 1. check cache
// 2. if there is a hit, make sure its fresh
// 3. if cached obj fails freshness check, fetch remote
// 4. if remote fails, return stale object, or error
$cache = new RSSCache( MAGPIE_CACHE_DIR, MAGPIE_CACHE_AGE );
if (MAGPIE_DEBUG and $cache->ERROR) {
debug($cache->ERROR, E_USER_WARNING);
}
$cache_status = 0; // response of check_cache
$request_headers = array(); // HTTP headers to send with fetch
$rss = 0; // parsed RSS object
$errormsg = 0; // errors, if any
if (!$cache->ERROR) {
// return cache HIT, MISS, or STALE
$cache_status = $cache->check_cache( $url );
}
// if object cached, and cache is fresh, return cached obj
if ( $cache_status == 'HIT' ) {
$rss = $cache->get( $url );
if ( isset($rss) and $rss ) {
$rss->from_cache = 1;
if ( MAGPIE_DEBUG > 1) {
debug("MagpieRSS: Cache HIT", E_USER_NOTICE);
}
return $rss;
}
}
// else attempt a conditional get
// setup headers
if ( $cache_status == 'STALE' ) {
$rss = $cache->get( $url );
if ( $rss->etag and $rss->last_modified ) {
$request_headers['If-None-Match'] = $rss->etag;
$request_headers['If-Last-Modified'] = $rss->last_modified;
}
}
$resp = _fetch_remote_file( $url, $request_headers );
if (isset($resp) and $resp) {
if ($resp->status == '304' ) {
// we have the most current copy
if ( MAGPIE_DEBUG > 1) {
debug("Got 304 for $url");
}
// reset cache on 304 (at minutillo insistent prodding)
$cache->set($url, $rss);
return $rss;
}
elseif ( is_success( $resp->status ) ) {
$rss = _response_to_rss( $resp );
if ( $rss ) {
if (MAGPIE_DEBUG > 1) {
debug("Fetch successful");
}
// add object to cache
$cache->set( $url, $rss );
return $rss;
}
}
else {
$errormsg = "Failed to fetch $url. ";
if ( $resp->error ) {
# compensate for Snoopy's annoying habbit to tacking
# on '\n'
$http_error = substr($resp->error, 0, -2);
$errormsg .= "(HTTP Error: $http_error)";
}
else {
$errormsg .= "(HTTP Response: " . $resp->response_code .')';
}
}
}
else {
$errormsg = "Unable to retrieve RSS file for unknown reasons.";
}
// else fetch failed
// attempt to return cached object
if ($rss) {
if ( MAGPIE_DEBUG ) {
debug("Returning STALE object for $url");
}
return $rss;
}
// else we totally failed
error( $errormsg );
return false;
} // end if ( !MAGPIE_CACHE_ON ) {
} // end fetch_rss()
/*=======================================================================*\
Function: error
Purpose: set MAGPIE_ERROR, and trigger error
\*=======================================================================*/
function error ($errormsg, $lvl=E_USER_WARNING) {
global $MAGPIE_ERROR;
// append PHP's error message if track_errors enabled
if ( isset($php_errormsg) ) {
$errormsg .= " ($php_errormsg)";
}
if ( $errormsg ) {
$errormsg = "MagpieRSS: $errormsg";
$MAGPIE_ERROR = $errormsg;
trigger_error( $errormsg, $lvl);
}
}
function debug ($debugmsg, $lvl=E_USER_NOTICE) {
trigger_error("MagpieRSS [debug] $debugmsg", $lvl);
}
/*=======================================================================*\
Function: magpie_error
Purpose: accessor for the magpie error variable
\*=======================================================================*/
function magpie_error ($errormsg="") {
global $MAGPIE_ERROR;
if ( isset($errormsg) and $errormsg ) {
$MAGPIE_ERROR = $errormsg;
}
return $MAGPIE_ERROR;
}
/*=======================================================================*\
Function: _fetch_remote_file
Purpose: retrieve an arbitrary remote file
Input: url of the remote file
headers to send along with the request (optional)
Output: an HTTP response object (see Snoopy.class.inc)
\*=======================================================================*/
function _fetch_remote_file ($url, $headers = "" ) {
// Snoopy is an HTTP client in PHP
$client = new Snoopy();
$client->agent = MAGPIE_USER_AGENT;
$client->read_timeout = MAGPIE_FETCH_TIME_OUT;
$client->use_gzip = MAGPIE_USE_GZIP;
if (is_array($headers) ) {
$client->rawheaders = $headers;
}
@$client->fetch($url);
return $client;
}
/*=======================================================================*\
Function: _response_to_rss
Purpose: parse an HTTP response object into an RSS object
Input: an HTTP response object (see Snoopy)
Output: parsed RSS object (see rss_parse)
\*=======================================================================*/
function _response_to_rss ($resp) {
$rss = new MagpieRSS( $resp->results );
// if RSS parsed successfully
if ( $rss and !$rss->ERROR) {
// find Etag, and Last-Modified
foreach($resp->headers as $h) {
// 2003-03-02 - Nicola Asuni (www.tecnick.com) - fixed bug "Undefined offset: 1"
if (strpos($h, ": ")) {
list($field, $val) = explode(": ", $h, 2);
}
else {
$field = $h;
$val = "";
}
if ( $field == 'ETag' ) {
$rss->etag = $val;
}
if ( $field == 'Last-Modified' ) {
$rss->last_modified = $val;
}
}
return $rss;
} // else construct error message
else {
$errormsg = "Failed to parse RSS file.";
if ($rss) {
$errormsg .= " (" . $rss->ERROR . ")";
}
error($errormsg);
return false;
} // end if ($rss and !$rss->error)
}
/*=======================================================================*\
Function: init
Purpose: setup constants with default values
check for user overrides
\*=======================================================================*/
function init () {
if ( defined('MAGPIE_INITALIZED') ) {
return;
}
else {
define('MAGPIE_INITALIZED', 1);
}
if ( !defined('MAGPIE_CACHE_ON') ) {
define('MAGPIE_CACHE_ON', 1);
}
if ( !defined('MAGPIE_CACHE_DIR') ) {
define('MAGPIE_CACHE_DIR', './cache');
}
if ( !defined('MAGPIE_CACHE_AGE') ) {
define('MAGPIE_CACHE_AGE', 60*60); // one hour
}
if ( !defined('MAGPIE_CACHE_FRESH_ONLY') ) {
define('MAGPIE_CACHE_FRESH_ONLY', 0);
}
if ( !defined('MAGPIE_DEBUG') ) {
define('MAGPIE_DEBUG', 0);
}
if ( !defined('MAGPIE_USER_AGENT') ) {
$ua = 'MagpieRSS/'. MAGPIE_VERSION . ' (+http://magpierss.sf.net';
if ( MAGPIE_CACHE_ON ) {
$ua = $ua . ')';
}
else {
$ua = $ua . '; No cache)';
}
define('MAGPIE_USER_AGENT', $ua);
}
if ( !defined('MAGPIE_FETCH_TIME_OUT') ) {
define('MAGPIE_FETCH_TIME_OUT', 5); // 5 second timeout
}
// use gzip encoding to fetch rss files if supported?
if ( !defined('MAGPIE_USE_GZIP') ) {
define('MAGPIE_USE_GZIP', true);
}
}
// NOTE: the following code should really be in Snoopy, or at least
// somewhere other then rss_fetch!
/*=======================================================================*\
HTTP STATUS CODE PREDICATES
These functions attempt to classify an HTTP status code
based on RFC 2616 and RFC 2518.
All of them take an HTTP status code as input, and return true or false
All this code is adapted from LWP's HTTP::Status.
\*=======================================================================*/
/*=======================================================================*\
Function: is_info
Purpose: return true if Informational status code
\*=======================================================================*/
function is_info ($sc) {
return $sc >= 100 && $sc < 200;
}
/*=======================================================================*\
Function: is_success
Purpose: return true if Successful status code
\*=======================================================================*/
function is_success ($sc) {
return $sc >= 200 && $sc < 300;
}
/*=======================================================================*\
Function: is_redirect
Purpose: return true if Redirection status code
\*=======================================================================*/
function is_redirect ($sc) {
return $sc >= 300 && $sc < 400;
}
/*=======================================================================*\
Function: is_error
Purpose: return true if Error status code
\*=======================================================================*/
function is_error ($sc) {
return $sc >= 400 && $sc < 600;
}
/*=======================================================================*\
Function: is_client_error
Purpose: return true if Error status code, and its a client error
\*=======================================================================*/
function is_client_error ($sc) {
return $sc >= 400 && $sc < 500;
}
/*=======================================================================*\
Function: is_client_error
Purpose: return true if Error status code, and its a server error
\*=======================================================================*/
function is_server_error ($sc) {
return $sc >= 500 && $sc < 600;
}
/*************************************************
Snoopy - the PHP net client
Author: Monte Ohrt
Copyright (c): 1999-2000 ispi, all rights reserved
Version: 1.0
* 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.
*
*
The latest version of Snoopy can be obtained from:
http://snoopy.sourceforge.com
*************************************************/
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/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.
// send Accept-encoding: gzip?
var $use_gzip = true;
/**** 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 = $URI_PARTS["pass"];
switch($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 = $URI_PARTS["path"].(isset($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);
$this->_framedepth++;
}
else
break;
}
}
}
else
{
return false;
}
return true;
break;
case "https":
if(!$this->curl_path || (!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;
$this->_frameurls = array();
while(list(,$frameurl) = each($frameurls))
{
if($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";
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 = $URI_PARTS["pass"];
switch($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;
$this->submit($this->_redirectaddr,$formvars, $formfiles);
}
}
}
if($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);
$this->_framedepth++;
}
else
break;
}
}
}
else
{
return false;
}
return true;
break;
case "https":
if(!$this->curl_path || (!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;
$this->submit($this->_redirectaddr,$formvars, $formfiles);
}
}
}
if($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;
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(is_array($this->results))
{
for($x=0;$xresults);$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;$xresults);$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;$xresults);$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, $formfiles))
{
if(is_array($this->results))
{
for($x=0;$xresults);$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, $formfiles))
{
if(is_array($this->results))
{
for($x=0;$xresults);$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 ]+)) # 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."\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";
$headers .= "\r\n";
// set the read timeout if needed
if ($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")
break;
// if a header begins with Location: or URI:, set the redirect
if(preg_match("/^(Location:|URI:)/i",$currentHeader))
{
// get URL portion of the redirect
preg_match("/^(Location:|URI:)\s+(.*)/",chop($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: _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))
$headers[] = "Host: ".$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;
$headerfile = uniqid(time());
exec($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];
$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;
}
$this->status = 0;
if($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 $postdata;
}
}
//end
function gettags($style)
{
switch($style)
{
case "b":
$tagarr[]="";
$tagarr[]="";
return $tagarr;
break;
case "u":
$tagarr[]="";
$tagarr[]="";
return $tagarr;
break;
case "i":
$tagarr[]="";
$tagarr[]="";
return $tagarr;
break;
case "bu":
$tagarr[]="";
$tagarr[]="";
return $tagarr;
break;
case "bi":
$tagarr[]="";
$tagarr[]="";
return $tagarr;
break;
case "iu":
$tagarr[]="";
$tagarr[]="";
return $tagarr;
break;
}
}
if($tfont=="")$tfont="verdana";
if($tstyle=="")$tstyle="";
if($tsize=="")$tsize="2";
if($tcolor=="")$tcolor="#000000";
if($dfont=="")$dfont="verdana";
if($dstyle=="")$dstyle="";
if($dsize=="")$dsize="2";
if($dcolor=="")$dcolor="#000000";
$tagarr1=gettags($tstyle);
$tagarr2=gettags($dstyle);
?>
items as $item) {
$rssresults[]=array(link=>$item['link'],title=>$item['title'],description=>$item['description']);
}
}
shuffle($rssresults);
$numitems=rand($numminitems,$nummaxitems);
$rssresults=array_slice($rssresults,0,$numitems);
for($i=0;$i";
$link=$rssresults[$i]["link"];
echo $tagarr1[0].''.$rssresults[$i]["title"].''.$tagarr1[1];
echo("
");
echo $tagarr2[0].''.$rssresults[$i]["description"].''.$tagarr2[1];
echo " ";
}
}
?>
|
Search Portal Navigation
Art & Literature - bol.com ~ dk.com ~ greatmagazines.co.uk whsmiths.co.uk 
Business & Finance - americanexpress.com ~ directline.com loans.co.uk ~ insurance.co.uk ryman.co.uk ~ vistaprint.co.uk 
Computers - aol.com ~ applestore.co.uk ~ dell.co.uk ~ fasthosts.co.uk ~ hp.com pcworld.co.uk ~ toshiba.com 
