ajout du parseur rss externe: magpierss qui est un projet sous gnu/gpl
This commit is contained in:
parent
c1055c4292
commit
d573200393
184
htdocs/includes/magpierss/rss_cache.inc
Normal file
184
htdocs/includes/magpierss/rss_cache.inc
Normal file
@ -0,0 +1,184 @@
|
||||
<?php
|
||||
/*
|
||||
* Project: MagpieRSS: a simple RSS integration tool
|
||||
* File: rss_cache.inc, a simple, rolling(no GC), cache
|
||||
* for RSS objects, keyed on URL.
|
||||
* Author: Kellan Elliott-McCrea <kellan@protest.net>
|
||||
* Version: 0.51
|
||||
* 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:
|
||||
* http://lists.sourceforge.net/lists/listinfo/magpierss-general
|
||||
*
|
||||
*/
|
||||
|
||||
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);
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
?>
|
||||
439
htdocs/includes/magpierss/rss_fetch.inc
Normal file
439
htdocs/includes/magpierss/rss_fetch.inc
Normal file
@ -0,0 +1,439 @@
|
||||
<?php
|
||||
/*
|
||||
* Project: MagpieRSS: a simple RSS integration tool
|
||||
* File: rss_fetch.inc, a simple functional interface
|
||||
to fetching and parsing RSS files, via the
|
||||
function fetch_rss()
|
||||
* Author: Kellan Elliott-McCrea <kellan@protest.net>
|
||||
* Version: 0.51
|
||||
* 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);
|
||||
}
|
||||
|
||||
require_once( MAGPIE_DIR . 'rss_parse.inc' );
|
||||
require_once( MAGPIE_DIR . 'rss_cache.inc' );
|
||||
|
||||
// for including 3rd party libraries
|
||||
define('MAGPIE_EXTLIB', MAGPIE_DIR . 'extlib' . DIR_SEP);
|
||||
require_once( MAGPIE_EXTLIB . 'Snoopy.class.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', '0.51');
|
||||
|
||||
$MAGPIE_ERROR = "";
|
||||
|
||||
function fetch_rss ($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;
|
||||
}
|
||||
|
||||
?>
|
||||
338
htdocs/includes/magpierss/rss_parse.inc
Normal file
338
htdocs/includes/magpierss/rss_parse.inc
Normal file
@ -0,0 +1,338 @@
|
||||
<?php
|
||||
/*
|
||||
* Project: MagpieRSS: a simple RSS integration tool
|
||||
* File: rss_parse.inc includes code for parsing
|
||||
* RSS, and returning an RSS object
|
||||
* Author: Kellan Elliott-McCrea <kellan@protest.net>
|
||||
* Version: 0.51
|
||||
* 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
|
||||
*
|
||||
*/
|
||||
|
||||
|
||||
/*
|
||||
* NOTES ON RSS PARSING PHILOSOPHY (moderately important):
|
||||
* MagpieRSS parse all versions of RSS with a few limitation (mod_content, and
|
||||
* mod_taxonomy support is shaky) into a simple object, with 2 fields,
|
||||
* the hash 'channel', and the array 'items'.
|
||||
*
|
||||
* MagpieRSS is a forgiving and inclusive parser. It currently makes no
|
||||
* attempt to enforce the validity on an RSS feed. It will include any
|
||||
* properly formatted tags it finds, allowing to you to mix RSS 0.93, with RSS
|
||||
* 1.0, with tags or your own imagining. This sort of witches brew is a bad
|
||||
* bad idea! But Magpie is less pendantic then I am.
|
||||
*
|
||||
* RSS validators are readily available on the web at:
|
||||
* http://feeds.archive.org/validator/
|
||||
* http://www.ldodds.com/rss_validator/1.0/validator.html
|
||||
*
|
||||
*/
|
||||
|
||||
/*
|
||||
* EXAMPLE PARSE RESULTS:
|
||||
*
|
||||
* Magpie tries to parse RSS into ease to use PHP datastructures.
|
||||
*
|
||||
* For example, Magpie on encountering RSS 1.0 item entry:
|
||||
*
|
||||
* <item rdf:about="http://protest.net/NorthEast/calendrome.cgi?span=event&ID=210257">
|
||||
* <title>Weekly Peace Vigil</title>
|
||||
* <link>http://protest.net/NorthEast/calendrome.cgi?span=event&ID=210257</link>
|
||||
* <description>Wear a white ribbon</description>
|
||||
* <dc:subject>Peace</dc:subject>
|
||||
* <ev:startdate>2002-06-01T11:00:00</ev:startdate>
|
||||
* <ev:location>Northampton, MA</ev:location>
|
||||
* <ev:enddate>2002-06-01T12:00:00</ev:enddate>
|
||||
* <ev:type>Protest</ev:type>
|
||||
* </item>
|
||||
*
|
||||
* Would transform it into the following associative array, and push it
|
||||
* onto the array $rss-items
|
||||
*
|
||||
* array(
|
||||
* title => 'Weekly Peace Vigil',
|
||||
* link =>
|
||||
* 'http://protest.net/NorthEast/calendrome.cgi?span=event&ID=210257',
|
||||
* description => 'Wear a white ribbon',
|
||||
* dc => array (
|
||||
* subject => 'Peace'
|
||||
* ),
|
||||
* ev => array (
|
||||
* startdate => '2002-06-01T11:00:00',
|
||||
* enddate => '2002-06-01T12:00:00',
|
||||
* type => 'Protest',
|
||||
* location => 'Northampton, MA'
|
||||
* )
|
||||
* )
|
||||
*
|
||||
*/
|
||||
|
||||
class MagpieRSS {
|
||||
/*
|
||||
* Hybrid parser, and object. (probably a bad idea! :)
|
||||
*
|
||||
* Useage Example:
|
||||
*
|
||||
* $some_rss = "<?xml version="1.0"......
|
||||
*
|
||||
* $rss = new MagpieRSS( $some_rss );
|
||||
*
|
||||
* // print rss chanel title
|
||||
* echo $rss->channel['title'];
|
||||
*
|
||||
* // print the title of each item
|
||||
* foreach ($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 $parent_field = array('RDF');
|
||||
var $current_field = '';
|
||||
var $current_namespace = false;
|
||||
|
||||
var $ERROR = "";
|
||||
|
||||
/*======================================================================*\
|
||||
Function: MagpieRSS
|
||||
Purpose: Constructor, sets up XML parser,parses source,
|
||||
and populates object..
|
||||
Input: String containing the RSS to be parsed
|
||||
\*======================================================================*/
|
||||
function MagpieRSS ($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, 'start_element', 'end_element');
|
||||
xml_set_character_data_handler( $this->parser, '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( $this->parser );
|
||||
}
|
||||
|
||||
function start_element ($p, $element, &$attrs) {
|
||||
$element = strtolower( $element );
|
||||
|
||||
# check for a namespace, and split if found
|
||||
#
|
||||
$namespace = false;
|
||||
if ( strpos( $element, ':' ) ) {
|
||||
list($namespace, $element) = split( ':', $element, 2);
|
||||
}
|
||||
$this->current_field = $element;
|
||||
if ( $namespace and $namespace != 'rdf' ) {
|
||||
$this->current_namespace = $namespace;
|
||||
}
|
||||
|
||||
if ( $element == 'channel' ) {
|
||||
array_unshift( $this->parent_field, 'channel' );
|
||||
}
|
||||
elseif ( $element == 'items' ) {
|
||||
array_unshift( $this->parent_field, 'items' );
|
||||
}
|
||||
elseif ( $element == 'item' ) {
|
||||
array_unshift( $this->parent_field, 'item' );
|
||||
}
|
||||
elseif ( $element == 'textinput' ) {
|
||||
array_unshift( $this->parent_field, 'textinput' );
|
||||
}
|
||||
elseif ( $element == 'image' ) {
|
||||
array_unshift( $this->parent_field, 'image' );
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
function end_element ($p, $element) {
|
||||
$element = strtolower($element);
|
||||
|
||||
if ( $element == 'item' ) {
|
||||
$this->items[] = $this->current_item;
|
||||
$this->current_item = array();
|
||||
array_shift( $this->parent_field );
|
||||
}
|
||||
elseif ( $element == 'channel' or $element == 'items' or
|
||||
$element == 'textinput' or $element == 'image' ) {
|
||||
array_shift( $this->parent_field );
|
||||
}
|
||||
|
||||
$this->current_field = '';
|
||||
$this->current_namespace = false;
|
||||
}
|
||||
|
||||
function cdata ($p, $text) {
|
||||
# skip item, channel, items first time we see them
|
||||
#
|
||||
if ( $this->parent_field[0] == $this->current_field or
|
||||
! $this->current_field ) {
|
||||
return;
|
||||
}
|
||||
elseif ( $this->parent_field[0] == 'channel') {
|
||||
if ( $this->current_namespace ) {
|
||||
$this->append(
|
||||
$this->channel[ $this->current_namespace ][ $this->current_field ],
|
||||
$text);
|
||||
}
|
||||
else {
|
||||
$this->append($this->channel[ $this->current_field ], $text);
|
||||
}
|
||||
|
||||
}
|
||||
elseif ( $this->parent_field[0] == 'item' ) {
|
||||
if ( $this->current_namespace ) {
|
||||
$this->append(
|
||||
$this->current_item[ $this->current_namespace ][$this->current_field ],
|
||||
$text);
|
||||
}
|
||||
else {
|
||||
$this->append(
|
||||
$this->current_item[ $this->current_field ],
|
||||
$text );
|
||||
}
|
||||
}
|
||||
elseif ( $this->parent_field[0] == 'textinput' ) {
|
||||
if ( $this->current_namespace ) {
|
||||
$this->append(
|
||||
$this->textinput[ $this->current_namespace ][ $this->current_field ],
|
||||
$text );
|
||||
}
|
||||
else {
|
||||
$this->append(
|
||||
$this->textinput[ $this->current_field ],
|
||||
$text );
|
||||
}
|
||||
}
|
||||
elseif ( $this->parent_field[0] == 'image' ) {
|
||||
if ( $this->current_namespace ) {
|
||||
$this->append(
|
||||
$this->image[ $this->current_namespace ][ $this->current_field ],
|
||||
$text );
|
||||
}
|
||||
else {
|
||||
$this->append(
|
||||
$this->image[ $this->current_field ],
|
||||
$text );
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
function append (&$str1, $str2="") {
|
||||
if (!isset($str1) ) {
|
||||
$str1="";
|
||||
}
|
||||
$str1 .= $str2;
|
||||
}
|
||||
|
||||
function error ($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( $errormsg, 0);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/*======================================================================*\
|
||||
EVERYTHING BELOW HERE IS FOR DEBUGGING PURPOSES
|
||||
\*======================================================================*/
|
||||
function show_list () {
|
||||
echo "<ol>\n";
|
||||
foreach ($this->items as $item) {
|
||||
echo "<li>", $this->show_item( $item );
|
||||
}
|
||||
echo "</ol>";
|
||||
}
|
||||
|
||||
function show_channel () {
|
||||
echo "channel:<br>";
|
||||
echo "<ul>";
|
||||
while ( list($key, $value) = each( $this->channel ) ) {
|
||||
echo "<li> $key: $value";
|
||||
}
|
||||
echo "</ul>";
|
||||
}
|
||||
|
||||
function show_item ($item) {
|
||||
echo "item: $item[title]";
|
||||
echo "<ul>";
|
||||
while ( list($key, $value) = each($item) ) {
|
||||
if ( is_array($value) ) {
|
||||
echo "<br><b>$key</b>";
|
||||
echo "<ul>";
|
||||
while ( list( $ns_key, $ns_value) = each( $value ) ) {
|
||||
echo "<li>$ns_key: $ns_value";
|
||||
}
|
||||
echo "</ul>";
|
||||
}
|
||||
else {
|
||||
echo "<li> $key: $value";
|
||||
}
|
||||
}
|
||||
echo "</ul>";
|
||||
}
|
||||
|
||||
/*======================================================================*\
|
||||
END DEBUGGING FUNCTIONS
|
||||
\*======================================================================*/
|
||||
|
||||
|
||||
|
||||
} # end class RSS
|
||||
?>
|
||||
67
htdocs/includes/magpierss/rss_utils.inc
Normal file
67
htdocs/includes/magpierss/rss_utils.inc
Normal file
@ -0,0 +1,67 @@
|
||||
<?php
|
||||
/*
|
||||
* Project: MagpieRSS: a simple RSS integration tool
|
||||
* File: rss_utils.inc, utility methods for working with RSS
|
||||
* Author: Kellan Elliott-McCrea <kellan@protest.net>
|
||||
* Version: 0.51
|
||||
* 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
|
||||
*/
|
||||
|
||||
|
||||
/*======================================================================*\
|
||||
Function: parse_w3cdtf
|
||||
Purpose: parse a W3CDTF date into unix epoch
|
||||
|
||||
NOTE: http://www.w3.org/TR/NOTE-datetime
|
||||
\*======================================================================*/
|
||||
|
||||
function parse_w3cdtf ( $date_str ) {
|
||||
|
||||
# regex to match wc3dtf
|
||||
$pat = "/(\d{4})-(\d{2})-(\d{2})T(\d{2}):(\d{2})(:(\d{2}))?(?:([-+])(\d{2}):?(\d{2})|(Z))?/";
|
||||
|
||||
if ( preg_match( $pat, $date_str, $match ) ) {
|
||||
list( $year, $month, $day, $hours, $minutes, $seconds) =
|
||||
array( $match[1], $match[2], $match[3], $match[4], $match[5], $match[6]);
|
||||
|
||||
# calc epoch for current date assuming GMT
|
||||
$epoch = gmmktime( $hours, $minutes, $seconds, $month, $day, $year);
|
||||
|
||||
$offset = 0;
|
||||
if ( $match[10] == 'Z' ) {
|
||||
# zulu time, aka GMT
|
||||
}
|
||||
else {
|
||||
list( $tz_mod, $tz_hour, $tz_min ) =
|
||||
array( $match[8], $match[9], $match[10]);
|
||||
|
||||
# zero out the variables
|
||||
if ( ! $tz_hour ) { $tz_hour = 0; }
|
||||
if ( ! $tz_min ) { $tz_min = 0; }
|
||||
|
||||
$offset_secs = (($tz_hour*60)+$tz_min)*60;
|
||||
|
||||
# is timezone ahead of GMT? then subtract offset
|
||||
#
|
||||
if ( $tz_mod == '+' ) {
|
||||
$offset_secs = $offset_secs * -1;
|
||||
}
|
||||
|
||||
$offset = $offset_secs;
|
||||
}
|
||||
$epoch = $epoch + $offset;
|
||||
return $epoch;
|
||||
}
|
||||
else {
|
||||
return -1;
|
||||
}
|
||||
}
|
||||
|
||||
?>
|
||||
Loading…
Reference in New Issue
Block a user