--- /dev/null
+kellan <kellan@protest.net>
--- /dev/null
+NAME
+
+ MagpieRSS - a simple RSS integration tool
+
+SYNOPSIS
+
+ require_once(rss_fetch.inc);
+ $url = $_GET['url'];
+ $rss = fetch_rss( $url );
+
+ echo "Channel Title: " . $rss->channel['title'] . "<p>";
+ echo "<ul>";
+ foreach ($rss->items as $item) {
+ $href = $item['link'];
+ $title = $item['title'];
+ echo "<li><a href=$href>$title</a></li>";
+ }
+ echo "</ul>";
+
+DESCRIPTION
+
+ MapieRSS is an XML-based RSS parser in PHP. It attempts to be "PHP-like",
+ and simple to use.
+
+ Some features include:
+
+ * supports RSS 0.9 - 1.0, with limited RSS 2.0 support
+ * supports namespaces, and modules, including mod_content and mod_event
+ * open minded [1]
+ * simple, functional interface, to object oriented backend parser
+ * automatic caching of parsed RSS objects makes its easy to integrate
+ * supports conditional GET with Last-Modified, and ETag
+ * uses constants for easy override of default behaviour
+ * heavily commented
+
+
+1. By open minded I mean Magpie will accept any tag it finds in good faith that
+ it was supposed to be here. For strict validation, look elsewhere.
+
+
+GETTING STARTED
+
+
+
+COPYRIGHT:
+ Copyright(c) 2002 kellan@protest.net. All rights reserved.
+ This software is released under the GNU General Public License.
+ Please read the disclaimer at the top of the Snoopy.class.inc file.
--- /dev/null
+This folder is the MagpieRSS news feed client library
+http://magpierss.sourceforge.net/
+Moodle's rss_client block uses these libraries to download, parse and cache remote new feeds.
--- /dev/null
+TROUBLESHOOTING
+
+
+Trouble Installing MagpieRSS:
+
+1. Fatal error: Failed opening required '/path/to/script/rss_fetch.inc'
+ (include_path='.:/usr/local/lib/php:/usr/local/lib/php/pear')
+
+2. Cache couldn't make dir './cache'.
+
+3. Fatal error: Failed to load PHP's XML Extension.
+ http://www.php.net/manual/en/ref.xml.php
+
+Trouble Using MagpieRSS
+
+4. Warning: MagpieRSS: Failed to fetch example.com/index.rdf.
+ (HTTP Error: Invalid protocol "")
+
+5. Warning: MagpieRSS: Failed to parse RSS file.
+ (not well-formed (invalid token) at line 19, column 98)
+
+6. Warning: MagpieRSS: Failed to fetch http://localhost/rss/features.1-0.rss.
+ (HTTP Response: HTTP/1.1 404 Not Found)
+
+If you would rather provide a custom error, see the COOKBOOK
+(http://magpierss.sf.net/cookbook.html) recipe 2.
+
+*************************************************************************
+1. Fatal error: Failed opening required '/path/to/script/rss_fetch.inc'
+ (include_path='.:/usr/local/lib/php:/usr/local/lib/php/pear')
+
+ This could mean that:
+
+ a) PHP can't find the MagpieRSS files.
+ b) PHP found them the MagpieRSS files, but can't read them.
+
+ a. Telling PHP where to look for MagpieRSS file.
+
+ This might mean your PHP program can't find the MagpieRSS libraries.
+ Magpie relies on 4 include files, rss_fetch.inc, rss_parse.inc,
+ rss_cache.inc, rss_util.inc, and for normal use you'll need all 4 (see the
+ cookbook for exceptions).
+
+ This can be fixed by making sure the MagpieRSS files are in your include
+ path.
+
+ If you can edit your include path (for example your on a shared host) then
+ you need to replace:
+
+ require_once('rss_fetch.inc');
+
+ -with-
+
+ define('MAGPIE_DIR', '/path/to/magpierss/');
+ require_once(MAGPIE_DIR.'rss_fetch.inc');
+
+ b. PHP can't read the MagpieRSS files
+
+ All PHP libraries need to be readable by your webserver.
+
+ On Unix you can accomplish this with:
+
+ chmod 755 rss_fetch.inc rss_parse.inc rss_cache.inc rss_util.inc
+
+*************************************************************************
+2. Cache couldn't make dir './cache'.
+
+ MagpieRSS caches the results of fetched and parsed RSS to reduce the load on
+ both your server, and the remote server providing the RSS. It does this by
+ writing files to a cache directory.
+
+ This error means the webserver doesn't have write access to the current
+ directory.
+
+ a. Make a webserver writeable cache directory
+
+ Find the webserver's group. (on my system it is 'www')
+
+ mkdir ./cache
+ chgrp www directory_name
+ chmod g+w directory_name
+
+ (this is the best, and desired solution)
+
+ b. Tell MagpieRSS to create the cache directory somewhere the webserver can
+ write to.
+
+ define('MAGPIE_CACHE_DIR', '/tmp/magpierss');
+
+ (this is not a great solution, and might have security considerations)
+
+ c. Turn off cacheing.
+
+ Magpie can work fine with cacheing, but it will be slower, and you might
+ become a nuiance to the RSS provider, but it is an option.
+
+ define('MAGPIE_CACHE_ON', 0);
+
+ d. And lastly, do NOT
+
+ chmod 777 ./cache
+
+ Any of the above solutions are better then this.
+
+ NOTE: If none of this works for you, let me know. I've got root, and a
+ custom compiled Apache on almost any box I ever touch, so I can be a little
+ out of touch with reality. But I won't know that if I don't feedback.
+
+************************************************************************* 3.
+3. Fatal error: Failed to load PHP's XML Extension.
+ http://www.php.net/manual/en/ref.xml.php
+
+ -or-
+
+ Fatal error: Failed to create an instance of PHP's XML parser.
+ http://www.php.net/manual/en/ref.xml.php
+
+ Make sure your PHP was built with --with-xml
+
+ This has been turned on by default for several versions of PHP, but it might
+ be turned off in your build.
+
+ See php.net for details on building and configuring PHP.
+
+
+*************************************************************************
+4. Warning: MagpieRSS: Failed to fetch index.rdf.
+ (HTTP Error: Invalid protocol "")
+
+ You need to put http:// in front of your the URL to your RSS feed
+
+*************************************************************************
+5. Warning: MagpieRSS: Failed to parse RSS file.
+ (not well-formed (invalid token) at line 19, column 98)
+
+ There is a problem with the RSS feed you are trying to read.
+ MagpieRSS is an XML parser, and therefore can't parse RSS feed with invalid
+ characters. Some RSS parser are based on regular expressions, and can
+ parse invalid RSS but they have their own problems.
+
+ You could try contacting the author of the RSS feed, and pointing them to
+ the online RSS validator at:
+
+ http://feeds.archive.org/validator/
+
+*************************************************************************
+6. Warning: MagpieRSS: Failed to fetch http://example.com/index.rdf
+ (HTTP Response: HTTP/1.1 404 Not Found)
+
+ Its a 404! The RSS file ain't there.
+
+
--- /dev/null
+MAGPIERSS RECIPES: Cooking with Corbies
+
+ "Four and twenty blackbirds baked in a pie."
+
+1. LIMIT THE NUMBER OF HEADLINES(AKA ITEMS) RETURNED.
+
+PROBLEM:
+
+You want to display the 10 (or 3) most recent headlines, but the RSS feed
+contains 15.
+
+SOLUTION:
+
+$num_items = 10;
+$rss = fetch_rss($url);
+
+$items = array_slice($rss->items, 0, $num_items);
+
+DISCUSSION:
+
+Rather then trying to limit the number of items Magpie parses, a much simpler,
+and more flexible approach is to take a "slice" of the array of items. And
+array_slice() is smart enough to do the right thing if the feed has less items
+then $num_items.
+
+See: http://www.php.net/array_slice
+
+
+2. DISPLAY A CUSTOM ERROR MESSAGE IF SOMETHING GOES WRONG
+
+PROBLEM:
+
+You don't want Magpie's error messages showing up if something goes wrong.
+
+SOLUTION:
+
+# Magpie throws USER_WARNINGS only
+# so you can cloak these, by only showing ERRORs
+error_reporting(E_ERROR);
+
+# check the return value of fetch_rss()
+
+$rss = fetch_rss($url);
+
+if ( $rss ) {
+...display rss feed...
+}
+else {
+ echo "An error occured! " .
+ "Consider donating more $$$ for restoration of services." .
+ "<br>Error Message: " . magpie_error();
+}
+
+DISCUSSION:
+
+MagpieRSS triggers a warning in a number of circumstances. The 2 most common
+circumstances are: if the specified RSS file isn't properly formed (usually
+because it includes illegal HTML), or if Magpie can't download the remote RSS
+file, and there is no cached version.
+
+If you don't want your users to see these warnings change your error_reporting
+settings to only display ERRORs. Another option is to turn off display_error,
+so that WARNINGs, and NOTICEs still go to the error_log but not to the webpages.
+
+You can do this with:
+
+ini_set('display_errors', 0);
+
+See: http://www.php.net/error_reporting,
+ http://www.php.net/ini_set,
+ http://www.php.net/manual/en/ref.errorfunc.php
+
+3. GENERATE A NEW RSS FEED
+
+PROBLEM:
+
+Create an RSS feed for other people to use.
+
+SOLUTION:
+
+Use Useful Inc's RSSWriter (http://usefulinc.com/rss/rsswriter/)
+
+DISCUSSION:
+
+An example of turning a Magpie parsed RSS object back into an RSS file is forth
+coming. In the meantime RSSWriter has great documentation.
+
+4. DISPLAY HEADLINES MORE RECENT THEN X DATE
+
+PROBLEM:
+
+You only want to display headlines that were published on, or after a certain
+date.
+
+
+SOLUTION:
+
+require 'rss_utils.inc';
+
+# get all headlines published today
+$today = getdate();
+
+# today, 12AM
+$date = mktime(0,0,0,$today['mon'], $today['mday'], $today['year']);
+
+$rss = fetch_rss($url);
+
+foreach ( $rss->items as $item ) {
+ $published = parse_w3cdtf($item['dc']['date']);
+ if ( $published >= $date ) {
+ echo "Title: " . $item['title'];
+ echo "Published: " . date("h:i:s A", $published);
+ echo "<p>";
+ }
+}
+
+DISCUSSION:
+
+This recipe only works for RSS 1.0 feeds that include the <dc:date> field.
+(which is very good RSS style)
+
+parse_w3cdtf is defined in rss_utils.inc, and parses RSS style dates into Unix
+epoch seconds.
+
+See: http://www.php.net/manual/en/ref.datetime.php
--- /dev/null
+<?php
+
+/*************************************************
+
+Snoopy - the PHP net client
+Author: Monte Ohrt <monte@ispi.net>
+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.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+
+You may contact the author of Snoopy by e-mail at:
+monte@ispi.net
+
+Or, write to:
+Monte Ohrt
+CTO, ispi
+237 S. 70th suite 220
+Lincoln, NE 68510
+
+The latest version of Snoopy can be obtained from:
+http://snoopy.sourceforge.com
+
+*************************************************/
+
+class Snoopy
+{
+ /**** Public variables ****/
+
+ /* user definable vars */
+
+ var $host = "www.php.net"; // host name we are connecting to
+ var $port = 80; // port we are connecting to
+ var $proxy_host = ""; // proxy host to use
+ var $proxy_port = ""; // proxy port to use
+ var $agent = "Snoopy v1.0"; // agent we masquerade as
+ var $referer = ""; // referer info to pass
+ var $cookies = array(); // array of cookies to pass
+ // $cookies["username"]="joe";
+ var $rawheaders = array(); // array of raw headers to send
+ // $rawheaders["Content-type"]="text/html";
+
+ var $maxredirs = 5; // http redirection depth maximum. 0 = disallow
+ var $lastredirectaddr = ""; // contains address of last redirected address
+ var $offsiteok = true; // allows redirection off-site
+ var $maxframes = 0; // frame content depth maximum. 0 = disallow
+ var $expandlinks = true; // expand links to fully qualified URLs.
+ // this only applies to fetchlinks()
+ // or submitlinks()
+ var $passcookies = true; // pass set cookies back through redirects
+ // NOTE: this currently does not respect
+ // dates, domains or paths.
+
+ var $user = ""; // user for http authentication
+ var $pass = ""; // password for http authentication
+
+ // http accept types
+ var $accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*";
+
+ var $results = ""; // where the content is put
+
+ var $error = ""; // error messages sent here
+ var $response_code = ""; // response code returned from server
+ var $headers = array(); // headers returned from server sent here
+ var $maxlength = 500000; // max return data length (body)
+ var $read_timeout = 0; // timeout on read operations, in seconds
+ // supported only since PHP 4 Beta 4
+ // set to 0 to disallow timeouts
+ var $timed_out = false; // if a read operation timed out
+ var $status = 0; // http request status
+
+ var $curl_path = "/usr/bin/curl";
+ // Snoopy will use cURL for fetching
+ // SSL content if a full system path to
+ // the cURL binary is supplied here.
+ // set to false if you do not have
+ // cURL installed. See http://curl.haxx.se
+ // for details on installing cURL.
+ // Snoopy does *not* use the cURL
+ // library functions built into php,
+ // as these functions are not stable
+ // as of this Snoopy release.
+
+ // 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))) {
+ $this->error = "Bad curl ($this->curl_path), can't fetch HTTPS \n";
+ return false;
+ }
+ $this->host = $URI_PARTS["host"];
+ if(!empty($URI_PARTS["port"]))
+ $this->port = $URI_PARTS["port"];
+ if($this->_isproxy)
+ {
+ // using proxy, send entire URI
+ $this->_httpsrequest($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;
+ }
+
+
+
+/*======================================================================*\
+ 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 <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
+
+ 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("'<script[^>]*?>.*?</script>'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")
+ if(preg_match("/^\r?\n$/", $currentHeader) )
+ break;
+
+ // if a header begins with Location: or URI:, set the redirect
+ if(preg_match("/^(Location:|URI:)/i",$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))
+ {
+ $this->status=-100;
+ return false;
+ }
+
+ // check if there is a a redirect meta tag
+
+ if(preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]+URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$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 < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i",$results,$match))
+ {
+ $this->results[] = $results;
+ for($x=0; $x<count($match[1]); $x++)
+ $this->_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());
+
+ # accept self-signed certs
+ $cmdline_params .= " -k";
+ exec($this->curl_path." -D \"/tmp/$headerfile\"".$cmdline_params." ".$URI,$results,$return);
+
+ if($return)
+ {
+ $this->error = "Error: cURL could not retrieve the document, error $return.";
+ return false;
+ }
+
+
+ $results = implode("\r\n",$results);
+
+ $result_headers = file("/tmp/$headerfile");
+
+ $this->_redirectaddr = false;
+ unset($this->headers);
+
+ for($currentHeader = 0; $currentHeader < count($result_headers); $currentHeader++)
+ {
+
+ // if a header begins with Location: or URI:, set the redirect
+ if(preg_match("/^(Location: |URI: )/i",$result_headers[$currentHeader]))
+ {
+ // get URL portion of the redirect
+ preg_match("/^(Location: |URI:)(.*)/",chop($result_headers[$currentHeader]),$matches);
+ // look for :// in the Location header to see if hostname is included
+ if(!preg_match("|\:\/\/|",$matches[2]))
+ {
+ // no host in the path, so prepend
+ $this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port;
+ // eliminate double slash
+ if(!preg_match("|^/|",$matches[2]))
+ $this->_redirectaddr .= "/".$matches[2];
+ else
+ $this->_redirectaddr .= $matches[2];
+ }
+ else
+ $this->_redirectaddr = $matches[2];
+ }
+
+ if(preg_match("|^HTTP/|",$result_headers[$currentHeader]))
+ {
+ $this->response_code = $result_headers[$currentHeader];
+ if(preg_match("|^HTTP/[^\s]*\s(.*?)\s|",$this->response_code, $match))
+ {
+ $this->status= $match[1];
+ }
+ }
+ $this->headers[] = $result_headers[$currentHeader];
+ }
+
+ // check if there is a a redirect meta tag
+
+ if(preg_match("'<meta[\s]*http-equiv[^>]*?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 < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i",$results,$match))
+ {
+ $this->results[] = $results;
+ for($x=0; $x<count($match[1]); $x++)
+ $this->_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; $x<count($this->headers); $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 $postdata;
+ }
+}
+
+?>
--- /dev/null
+<html>
+ <head>
+ <title>Magie RSS Recipes: Simple PHP RSS How To</title>
+ <style>
+ body {
+ font-family:trebuchet MS, trebuchet, verdana, arial, sans-serif;
+ font-size: 11px;
+
+ }
+
+ pre { font-family: "Courier New", monospace;
+ padding: 1em;
+ margin: 0.2em 2.5em 0.2em 3em;
+ background-color: #efeff5;
+ border: 1px solid #cfcfcf;
+ white-space: pre;
+ }
+
+ </style>
+ </head>
+ <body>
+<p>
+<h1>MagpieRSS Recipes: Cooking with Corbies</h1>
+
+<div align="center"><h3><em>"Four and twenty blackbirds baked in a
+pie."</em></h3></div>
+</p>
+<p>
+<ol>
+<li><a href="#limit">Limit the Number of Headlines(aka Items) Returned</a></li>
+<li><a href="#error_message">Display a Custom Error Message if Something Goes
+Wrong</a></li>
+<li><a href="#write_rss">Generate a New RSS Feed</a></li>
+<li><a href="#by_date">Display Headlines More Recent then X Date</a></li>
+<li><a href="#from_file">Parse a Local File Containing RSS</a></li>
+
+</ol>
+</p>
+
+<a name="limit"></a><h2>1. Limit the Number of Headlines(aka Items) Returned.</h2>
+
+<h3>Problem:</h3>
+
+You want to display the 10 (or 3 or whatever) most recent headlines, but the RSS feed
+contains 15.
+
+<h3>Solution:</h3>
+
+<pre>
+$num_items = 10;
+$rss = fetch_rss($url);
+
+$items = array_slice($rss->items, 0, $num_items);
+
+foreach ( $items as $item ) {
+</pre>
+<h3>Discussion:</h3>
+
+Rather then trying to limit the number of items Magpie parses, a much simpler,
+and more flexible approach is to take a "slice" of the array of items. And
+array_slice() is smart enough to do the right thing if the feed has less items
+then $num_items.
+
+<h3>See:</h3> <a href="http://www.php.net/array_slice">http://www.php.net/array_slice</a>
+</p>
+
+<a name="error_message"></a><h2>2. Display a Custom Error Message if Something Goes Wrong</h2>
+
+<h3>Problem:</h3>
+
+You don't want Magpie's error messages showing up if something goes wrong.
+
+<h3>Solution:</h3>
+<pre>
+# Magpie throws USER_WARNINGS only
+# so you can cloak these, by only showing ERRORs
+error_reporting(E_ERROR);
+
+# check the return value of fetch_rss()
+
+$rss = fetch_rss($url);
+
+if ( $rss ) {
+...display rss feed...
+}
+else {
+ echo "An error occured! " .
+ "Consider donating more $$$ for restoration of services." .
+ "<br>Error Message: " . magpie_error();
+}
+</pre>
+<h3>Discussion:</h3>
+
+MagpieRSS triggers a warning in a number of circumstances. The 2 most common
+circumstances are: if the specified RSS file isn't properly formed (usually
+because it includes illegal HTML), or if Magpie can't download the remote RSS
+file, and there is no cached version.
+
+If you don't want your users to see these warnings change your error_reporting
+settings to only display ERRORs.<br />
+Another option is to turn off display_error,
+so that WARNINGs, and NOTICEs still go to the error_log but not to the webpages.
+
+You can do this with:
+
+<pre>
+# you can also do this in your php.ini file
+ini_set('display_errors', 0);
+</pre>
+
+<h3>See:</h3>
+<a
+href="http://www.php.net/error_reporting">http://www.php.net/error_reporting</a>,<br
+/>
+<a href="http://www.php.net/ini_set">http://www.php.net/ini_set</a>, <br />
+<a
+href="http://www.php.net/manual/en/ref.errorfunc.php">http://www.php.net/manual/en/ref.errorfunc.php</a><br
+/>
+
+<a name="write_rss"></a><h2>3. Generate a New RSS Feed</h2>
+
+<h3>Problem:</h3>
+
+Create an RSS feed for other people to use.
+
+<h3>Solution:</h3>
+
+Use Useful Inc's <a href="http://usefulinc.com/rss/rsswriter/">RSSWriter</a>.
+
+<h3>Discussion:</h3>
+
+An example of turning a Magpie parsed RSS object back into an RSS file is
+forthcoming. In the meantime RSSWriter is well documented.
+
+<a name="by_date"></a><h2>4. Display Headlines More Recent then X Date</h2>
+
+<h3>Problem:</h3>
+
+You only want to display headlines that were published on, or after a certain
+date.
+
+
+<h3>Solution:</h3>
+<pre>
+require_once('rss_utils.inc');
+
+# get all headlines published today
+$today = getdate();
+
+# today, 12AM
+$date = mktime(0,0,0,$today['mon'], $today['mday'], $today['year']);
+
+$rss = fetch_rss($url);
+
+foreach ( $rss->items as $item ) {
+ $published = parse_w3cdtf($item['dc']['date']);
+ if ( $published >= $date ) {
+ echo "Title: " . $item['title'];
+ echo "Published: " . date("h:i:s A", $published);
+ echo "<p>";
+ }
+}
+</pre>
+<h3>Discussion:</h3>
+
+This recipe only works for RSS 1.0 feeds that include the <dc:date> field.
+(which is very good RSS style) <br />
+<code>parse_w3cdtf()</code> is defined in
+<code>rss_utils.inc</code>, and parses RSS style dates into Unix epoch
+seconds.
+
+<h3>See: </h3>
+<a
+href="http://www.php.net/manual/en/ref.datetime.php">http://www.php.net/manual/en/ref.datetime.php</a>
+
+<a name="from_file"></a>
+<h2>5. Parse a Local File Containing RSS</h2>
+<h3>Problem:</h3>
+MagpieRSS provides <code>fetch_rss()</code> which takes a URL and returns a
+parsed RSS object, but what if you want to parse a file stored locally that
+doesn't have a URL?
+
+<h3>Solution</h3>
+<pre>
+require_once('rss_parse.inc');
+
+$rss_file = 'some_rss_file.rdf';
+$rss_string = read_file($rss_file);
+$rss = new MagpieRSS( $rss_string );
+
+if ( $rss and !$rss->ERROR) {
+...display rss...
+}
+else {
+ echo "Error: " . $rss->ERROR;
+}
+
+# efficiently read a file into a string
+# in php >= 4.3.0 you can simply use file_get_contents()
+#
+function read_file($filename) {
+ $fh = fopen($filename, 'r') or die($php_errormsg);
+ $rss_string = fread($fh, filesize($filename) );
+ fclose($fh);
+ return $rss_string;
+}
+</pre>
+
+<h3>Discussion</h3>
+Here we are using MagpieRSS's RSS parser directly without the convience wrapper
+of <code>fetch_rss()</code>. We read the contents of the RSS file into a
+string, and pass it to the parser constructor. Notice also that error handling
+is subtly different.
+
+<h3>See: </h3>
+<a
+href="http://www.php.net/manual/en/ref.filesystem.php">http://www.php.net/manual/en/ref.filesystem.php</a>,<br
+/>
+<a
+href="http://www.php.net/manual/en/language.oop.php">http://www.php.net/manual/en/language.oop.php</a>
+
+<!--
+<a name="link"></a><h2>#. Recipe</h2>
+<h3>Problem:</h3>
+Problem description
+<h3>Solution</h3>
+<pre>
+code
+</pre>
+<h3>Discussion/h3>
+Discuss code
+<h3>See: </h3>
+Documentation links:
+-->
+
+</body>
+</html>
--- /dev/null
+<html>
+ <head>
+ <title>Magpie RSS - PHP RSS Parser</title>
+ <link rel="alternate" type="application/rss+xml" title="RSS"
+ href="http://laughingmeme.org/magpierss.rdf" />
+ <style>
+ body {
+ font-family:trebuchet MS, trebuchet, verdana, arial, sans-serif;
+ font-size: 11px;
+
+ }
+
+ pre { font-family: "Courier New", monospace;
+ padding: 1em;
+ margin: 0.2em 2.5em 0.2em 3em;
+ background-color: #efeff5;
+ border: 1px solid #cfcfcf;
+ white-space: pre;
+ }
+
+ li.news {
+ padding-bottom:15px;
+ }
+
+ a.nav { color: #FFFFFF; }
+
+ div.nav {
+ width: 2in;
+ float: right;
+ border: 2px solid #cfcfcf;
+ padding: 5px;
+ background-color: #996699;
+ }
+
+ </style>
+ </head>
+ <body>
+ <img src="magpie-photo.jpg">
+ <h1>MagpieRSS</h1>
+ <p>
+ <h2>MagpieRSS provides an XML-based (expat) RSS parser in PHP.</h2>
+ <p>
+ MagpieRSS is compatible with RSS .9 through RSS 1.0, and supports the
+ RSS 1.0's modules. (with a few exceptions)
+ <p>
+ <div class="nav">
+ <center><h3>Project Info</h3></center>
+ <ul>
+ <li><a class="nav"
+href="http://sourceforge.net/project/showfiles.php?group_id=55691">Download
+Magpie</a></li>
+ <li><a class="nav"
+href="http://sourceforge.net/mail/?group_id=55691">Mailing
+Lists</a></li>
+ <li><a class="nav" href="#news">News!</a></li>
+ <li><a class="nav" href="#why">Why?</a></li>
+ <li><a class="nav" href="#features">Features</a></li>
+ <li><a class="nav" href="#philosophy">Philosophy</a></li>
+ <li><a class="nav" href="#usage">Usage Examples</a></li>
+ <li><a class="nav" href="/cookbook.html">Cookbook</a></li>
+ <li><a class="nav" href="#todo">Todo</a></li>
+<li style="list-style: none; padding-top: 5px;"><a title="Keep up on MagpieRSS news via RSS" href="http://laughingmeme.org/magpierss.rdf"><img
+src="http://magpierss.sf.net/black_grey_magpie_news.gif" border="0"></a></li>
+</ul>
+</div>
+ <a name="news"></a>
+ <h3>News!</h3>
+ <ul>
+
+<li class="news">
+ <a
+href="http://sourceforge.net/project/showfiles.php?group_id=55691">MagpieRSS
+0.51 Released</a>
+<ul>
+<li> important bugfix!</li>
+<li> fix <a href="http://laughingmeme.org/archives/000811.html
+">"silent failure"</a> when PHP doesn't have zlib</li>
+</ul>
+
+</li>
+
+<li class="news">
+ <a href="http://minutillo.com/steve/feedonfeeds/">Feed On Feeds Uses Magpie</a>
+<ul>
+<li> server based PHP RSS aggregator built with MagpieRSS</li>
+<li> easy to install, easy to use.</li>
+</ul>
+
+</li>
+
+
+<li class="news">
+ <a
+href="http://sourceforge.net/project/showfiles.php?group_id=55691&release_id=158897">MagpieRSS
+0.5 Released</a>
+<ul>
+<li> supports transparent HTTP gzip content negotiation for reduced bandwidth usage</li>
+<li> quashed some undefined index notices</li>
+</ul>
+
+</li>
+
+
+<li class="news">
+ <a
+href="http://sourceforge.net/project/showfiles.php?group_id=55691&release_id=139643">MagpieRSS
+0.46 Released</a>
+<ul>
+<li> minor release, more error handling clean up</li>
+<li> documentation fixes, simpler example</li>
+<li> new <a href="/TROUBLESHOOTING">trouble shooting</a> guide for installation and usage problems</a>
+</ul>
+
+</li>
+
+<li class="news">
+ <a
+href="http://laughingmeme.org/magpierss.rdf">Magpie News as RSS</a>
+<ul>
+<li> releases, bug fixes, releated stories as an RSS feed</li>
+</ul>
+
+</li>
+
+
+<li class="news">
+ <a
+href="http://magpierss.sourceforge.net/cookbook.html">MagpieRSS
+Cookbook: Simple PHP RSS How Tos</a>
+<ul>
+<li> answers some of the most frequently asked Magpie questions</li>
+<li> feedback, suggestions, requests, recipes welcome</li>
+</ul>
+
+</li>
+
+<li clas="news">
+ <a href="http://sourceforge.net/project/showfiles.php?group_id=55691&release_id=134850">MagpieRSS 0.4 Released!</a>
+<ul>
+<li> improved error handling, more flexibility for script authors,
+backwards compatible</li>
+<li> new and better examples! including using MagpieRSS and <a
+href="http://smarty.php.net">Smarty</a></li>
+<li> new Smarty plugin for RSS date parsing</li>
+</ul>
+<br />
+</li>
+<!--
+<li class="news">
+<a href="http://www.infinitepenguins.net/rss/">Infinite Penguin now
+supports Magpie 0.3</a>
+<ul>
+<li> simple, sophisticated RSS viewer</li>
+<li> includes auto-generated javascript ticker from RSS feed</li>
+</ul>
+
+</li>
+
+
+<li class="news">
+<a
+href="http://traumwind.tierpfad.de/blog/magpie/magpie_alike.php">Traumwind
+releases REX backend for MagpieRSS</a>
+<ul>
+<li>drop in support using regex based XML parser</li>
+<li>parses improperly formed XML that chokes expat</li>
+</ul>
+
+</li>
+
+<li class="news">
+ <a
+href="http://sourceforge.net/project/showfiles.php?group_id=55691&release_id=118652">
+ MagpieRSS 0.3 Released!</a>
+ <ul>
+ <li>Support added for
+ <a href="http://fishbowl.pastiche.org/archives/001132.html">HTTP
+ Conditional GETs</a>.</li>
+ <li>See <a href="http://sourceforge.net/project/shownotes.php?group_id=55691&release_id=118652">ChangeLog</a>
+ for more info.</li>
+ </ul>
+ </li>
+ <li class="news">MagpieRSS 0.2!</a>
+ <ul>
+ <li>Major clean up of the code. Easier to use.</li>
+ <li>Simpler install on shared hosts.</li>
+ <li>Better documentation and comments.</li>
+ </ul>
+ </li>
+ <li class="news">We've <a href="http://sourceforge.net/projects/magpierss/">moved to
+ Sourceforge!</a></li>
+ -->
+ </ul>
+ </p>
+ <p>
+ <a name="why"></a>
+ <h3>Why?</h3>
+ I wrote MagpieRSS out of a frustration with the limitations of existing
+ solutions. In particular many of the existing PHP solutions seemed to:
+ <ul>
+ <li>use a parser based on regular expressions, making for an inherently
+ fragile solution
+ <li>only support early versions of RSS
+ <li>discard all the interesting information besides item title, description,
+ and link.
+ <li>not build proper separation between parsing the RSS and displaying it.
+ </ul>
+ In particular I failed to find any PHP RSS parsers that could sufficiently
+ parse RSS 1.0 feeds, to be useful on the RSS based event feeds we generate
+ at <a href="http://protest.net">Protest.net</a>.
+ </p>
+ <p>
+ <a name="features"></a>
+ <h3>Features</h3>
+
+<ul>
+ <li class="toplevel">
+ <h4>Easy to Use</h4>
+ As simple as:
+<pre>
+require('rss_fetch.inc');
+$rss = fetch_rss($url);
+</pre>
+
+ </li>
+ <li class="toplevel">
+ <h4>Parses RSS 0.9 - RSS 1.0</h4>
+
+ Parses most RSS formats, including support for
+ <a href="http://www.purl.org/rss/1.0/modules/">1.0 modules</a> and limited
+ namespace support. RSS is packed into convenient data structures; easy to
+ use in PHP, and appropriate for passing to a templating system, like
+ <a href="http://smarty.php.net">Smarty</a>.
+ </li>
+ <li>
+ <h4>Integrated Object Cache</h4>
+
+ Caching the parsed RSS means that the 2nd request is fast, and that
+including the rss_fetch call in your PHP page won't destroy your performance,
+and force you to reply on an external cron job. And it happens transparently.
+
+ </li>
+ <li>
+ <h4>HTTP Conditional GETs</h4>
+
+ Save bandwidth and speed up download times with intelligent use of
+ Last-Modified and ETag.<br /> See <a
+ href="http://fishbowl.pastiche.org/archives/001132.html">HTTP Conditional Get for RSS Hackers</a>
+ </li>
+
+ <li><h4>Configurable</h4>
+
+ Makes extensive use of constants to allow overriding default behaviour, and
+ installation on shared hosts.
+ </li>
+ <li><h4>Modular</h4>
+ <ul>
+ <li>rss_fetch.inc - wraps a simple interface (<code>fetch_rss()</code>)
+ around the library.
+ <li>rss_parse.inc - provides the RSS parser, and the RSS object
+ <li>rss_cache.inc - a simple (no GC) object cache, optimized for RSS objects
+ <li>rss_utils.inc - utility functions for working with RSS. currently
+ provides <code>parse_w3cdtf()</code>, for parsing <a
+ href="http://www.w3.org/TR/NOTE-datetime">W3CDTF</a> into epoch seconds.
+ </ul>
+</ul>
+
+
+ </p>
+<p>
+ <a name="philosophy"></a>
+ <h3>Magpie's approach to parsing RSS</h3>
+
+ Magpie takes a naive, and inclusive approach. Absolutely
+ non-validating, as long as the RSS feed is well formed, Magpie will
+ cheerfully parse new, and never before seen tags in your RSS feeds.
+ </p>
+ <p>
+ This makes it very simple support the varied versions of RSS simply, but
+ forces the consumer of a RSS feed to be cognizant of how it is
+ structured.(at least if you want to do something fancy)
+ </p>
+ <p>
+ Magpie parses a RSS feed into a simple object, with 4 fields:
+ <code>channel</code>, <code>items</code>, <code>image</code>, and
+ <code>textinput</code>.
+ </p>
+ <p>
+ <h4>channel</h4>
+ <code>$rss->channel</code> contains key-value pairs of all tags, without
+ nested tags, found between the root tag (<rdf:RDF>, or <rss>)
+ and the end of the document.
+ </p>
+ <p>
+ <h4>items</h4>
+ <code>$rss->items</code> is an array of associative arrays, each one
+ describing a single item. An example that looks like:
+ <pre>
+<item rdf:about="http://protest.net/NorthEast/calendrome.cgi?span=event&ID=210257">
+<title>Weekly Peace Vigil</title>
+<link>http://protest.net/NorthEast/calendrome.cgi?span=event&ID=210257</link>
+<description>Wear a white ribbon</description>
+<dc:subject>Peace</dc:subject>
+<ev:startdate>2002-06-01T11:00:00</ev:startdate>
+<ev:location>Northampton, MA</ev:location>
+<ev:enddate>2002-06-01T12:00:00</ev:enddate>
+<ev:type>Protest</ev:type>
+</item>
+ </pre><p>
+ Is parsed, and pushed on the <code>$rss->items</code> array as:
+ <p><pre>
+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'
+ )
+);
+</pre>
+</p>
+<p>
+<h4>image and textinput</h4>
+<code>$rss->image</code> and <code>$rss-textinput</code> are associative arrays
+including name-value pairs for anything found between the respective parent
+tags.
+</p>
+<p>
+<a name="usage"></a>
+<h3>Usage Examples:</h3>
+
+A very simple example would be:
+<pre>
+require_once 'rss_fetch.inc';
+
+$url = 'http://magpie.sf.net/samples/imc.1-0.rdf';
+$rss = fetch_rss($url);
+
+echo "Site: ", $rss->channel['title'], "<br>\n";
+foreach ($rss->items as $item ) {
+ $title = $item[title];
+ $url = $item[link];
+ echo "<a href=$url>$title</a></li><br>\n";
+}
+</pre>
+More soon....in the meantime you can check out a
+<a href="http://www.infinitepenguins.net/rss/">cool tool built with
+MagpieRSS</a>, version 0.1.
+</p>
+<p>
+<a name="todo"></a>
+<h3>Todos</h3>
+ <h4>RSS Parser</h4>
+ <ul>
+ <li>Swap in a smarter parser that includes optional
+ support for validation, and required fields.</li>
+
+ <li>Support RSS 2.0 (as much as I'm annoyed by it)</li>
+
+ <li>Improve support for modules that rely on attributes</li>
+ </ul>
+
+ <h4>RSS Cache</h4>
+ <ul>
+ <li>Light-weight garbage collection
+ </ul>
+
+ <h4>Fetch RSS</h4>
+ <ul>
+ <li>Attempt to <a
+ href="http://diveintomark.org/archives/2002/08/15.html">auto-detect an
+ RSS feed</a>, given a URL following, much like <a
+ href="http://diveintomark.org/projects/misc/rssfinder.py.txt">rssfinder.py</a>does.
+ </li>
+ </ul>
+ <h4>Misc</h4>
+ <ul>
+ <li>More examples</li>
+ <li>A test suite</li>
+ <li>RSS generation, perhaps with <a
+ href="http://usefulinc.com/rss/rsswriter/">RSSwriter</a>?
+ </li>
+ </ul>
+
+</p>
+<p>
+<h3>RSS Resources</h3>
+ <ul>
+ <li><a href="http://mnot.net/rss/tutorial/">RSS Tutorial for Content Publishers
+ and Webmasters</a> is a great place to start.
+ <li><a href="http://gils.utah.gov/rss/">RSS Workshop: Publish and Syndicate
+ Your News to the Web</a> is also a good introduction</li>
+ <li><a href="http://www.disobey.com/amphetadesk/finding_more.html">Finding
+ More Channels</a> on how to find RSS feeds.
+ <li>Hammersley's <a href="http://rss.benhammersley.com/">Content Syndication
+ with XML and RSS</a> is a blog covering RSS current events.
+ <li><a href="http://groups.yahoo.com/group/rss-dev/">RSS-DEV mailing
+ list</a> is generally a very helpful, informative space, with the occasional
+ heated debate
+ <li><a href="http://feeds.archive.org/validator/">RSS Validator</a>
+ </ul>.
+</p>
+<h3>License and Contact Info</h3>
+Magpie is distributed under the GPL license...
+<p>
+coded by: kellan (at) protest.net, feedback is always appreciated.
+<p>
+<a href="http://sourceforge.net"><img
+src="http://sourceforge.net/sflogo.php?group_id=55691&type=3"
+width="125" height="37" border="0" alt="SourceForge.net Logo"></a>
+<img src="http://laughingmeme.org/magpie_views.gif">
+</body>
+</html>
--- /dev/null
+<?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);
+ }
+ }
+
+}
+
+?>
--- /dev/null
+<?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>
+ * 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', '0.7');
+
+$MAGPIE_ERROR = "";
+
+function fetch_rss ($url) {
+ // initialize constants
+ init();
+
+ if ( !isset($url) ) {
+ do_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 {
+ do_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 $cache->ERROR) {
+ do_debug($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
+
+ // store parsed XML by desired output encoding
+ // as character munging happens at parse time
+ $cache_key = $url . MAGPIE_OUTPUT_ENCODING;
+
+ if (!$cache->ERROR) {
+ // return cache HIT, MISS, or STALE
+ $cache_status = $cache->check_cache( $cache_key);
+ }
+
+ // if object cached, and cache is fresh, return cached obj
+ if ( $cache_status == 'HIT' ) {
+ $rss = $cache->get( $cache_key );
+ if ( isset($rss) and $rss ) {
+ $rss->from_cache = 1;
+ if ( MAGPIE_DEBUG > 1) {
+ do_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) {
+ do_debug("Got 304 for $url");
+ }
+ // reset cache on 304 (at minutillo insistent prodding)
+ $cache->set($cache_key, $rss);
+ return $rss;
+ }
+ elseif ( is_success( $resp->status ) ) {
+ $rss = _response_to_rss( $resp );
+ if ( $rss ) {
+ if (MAGPIE_DEBUG > 1) {
+ do_debug("Fetch successful");
+ }
+ // add object to cache
+ $cache->set( $cache_key, $rss );
+ return $rss;
+ }
+ }
+ else {
+ $errormsg = "Failed to fetch $url. ";
+ if ( $resp->status == '-100' ) {
+ $errormsg .= "(Request timed out after " . MAGPIE_FETCH_TIME_OUT . " seconds)";
+ }
+ elseif ( $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 ) {
+ do_debug("Returning STALE object for $url");
+ }
+ return $rss;
+ }
+
+ // else we totally failed
+ do_error( $errormsg );
+
+ return false;
+
+ } // end if ( !MAGPIE_CACHE_ON ) {
+} // end fetch_rss()
+
+/*=======================================================================*\
+ Function: error
+ Purpose: set MAGPIE_ERROR, and trigger error
+\*=======================================================================*/
+//Daryl Hawes note: had to rename this function from error to do_error for moodle
+// due to conflict with existing moodle function name
+function do_error ($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, $lvl);
+ }
+}
+
+//Daryl Hawes note: renamed this function from debug to do_debug for moodle
+function do_debug ($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, MAGPIE_OUTPUT_ENCODING, MAGPIE_INPUT_ENCODING, MAGPIE_DETECT_ENCODING );
+
+ // 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 .= " (" . $rss->ERROR . ")";
+ }
+ do_error($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', true);
+ }
+
+ if ( !defined('MAGPIE_CACHE_ON') ) {
+ define('MAGPIE_CACHE_ON', true);
+ }
+
+ 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', false);
+ }
+
+ if ( !defined('MAGPIE_OUTPUT_ENCODING') ) {
+ define('MAGPIE_OUTPUT_ENCODING', 'ISO-8859-1');
+ }
+
+ if ( !defined('MAGPIE_INPUT_ENCODING') ) {
+ define('MAGPIE_INPUT_ENCODING', null);
+ }
+
+ if ( !defined('MAGPIE_DETECT_ENCODING') ) {
+ define('MAGPIE_DETECT_ENCODING', true);
+ }
+
+ 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;
+}
+
+?>
--- /dev/null
+<?php
+
+/**
+* Project: MagpieRSS: a simple RSS integration tool
+* File: rss_parse.inc - parse an RSS or Atom feed
+* return as a simple object.
+*
+* Handles RSS 0.9x, RSS 2.0, RSS 1.0, and Atom 0.3
+*
+* 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
+*
+* @author Kellan Elliott-McCrea <kellan@protest.net>
+* @version 0.7a
+* @license GPL
+*
+*/
+
+define('RSS', 'RSS');
+define('ATOM', 'Atom');
+
+require_once (MAGPIE_DIR . 'rss_utils.inc');
+
+/**
+* Hybrid parser, and object, takes RSS as a string and returns a simple object.
+*
+* see: rss_fetch.inc for a simpler interface with integrated caching support
+*
+*/
+class MagpieRSS {
+ 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;
+ var $encoding = ''; // output encoding of parsed rss
+
+ var $_source_encoding = ''; // only set if we have to parse xml prolog
+
+ var $ERROR = "";
+ var $WARNING = "";
+
+ // define some constants
+
+ var $_CONTENT_CONSTRUCTS = array('content', 'summary', 'info', 'title', 'tagline', 'copyright');
+ var $_KNOWN_ENCODINGS = array('UTF-8', 'US-ASCII', 'ISO-8859-1');
+
+ // parser variables, useless if you're not a parser, treat as private
+ var $stack = array(); // parser stack
+ var $inchannel = false;
+ var $initem = false;
+ var $incontent = false; // if in Atom <content mode="xml"> field
+ var $intextinput = false;
+ var $inimage = false;
+ var $current_field = '';
+ var $current_namespace = false;
+
+
+ /**
+ * Set up XML parser, parse source, and return populated RSS object..
+ *
+ * @param string $source string containing the RSS to be parsed
+ *
+ * NOTE: Probably a good idea to leave the encoding options alone unless
+ * you know what you're doing as PHP's character set support is
+ * a little weird.
+ *
+ * NOTE: A lot of this is unnecessary but harmless with PHP5
+ *
+ *
+ * @param string $output_encoding output the parsed RSS in this character
+ * set defaults to ISO-8859-1 as this is PHP's
+ * default.
+ *
+ * NOTE: might be changed to UTF-8 in future
+ * versions.
+ *
+ * @param string $input_encoding the character set of the incoming RSS source.
+ * Leave blank and Magpie will try to figure it
+ * out.
+ *
+ *
+ * @param bool $detect_encoding if false Magpie won't attempt to detect
+ * source encoding. (caveat emptor)
+ *
+ */
+ function MagpieRSS ($source, $output_encoding='ISO-8859-1',
+ $input_encoding=null, $detect_encoding=true)
+ {
+ # if PHP xml isn't compiled in, die
+ #
+ if (!function_exists('xml_parser_create')) {
+ $this->error( "Failed to load PHP's XML Extension. " .
+ "http://www.php.net/manual/en/ref.xml.php",
+ E_USER_ERROR );
+ }
+
+ list($parser, $source) = $this->create_parser($source,
+ $output_encoding, $input_encoding, $detect_encoding);
+
+
+ if (!is_resource($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 )
+ {
+ $this->append_content("</$el>");
+ }
+ 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['description'] = $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'];
+
+ $atom_date = (isset($item['issued']) ) ? $item['issued'] : $item['modified'];
+ if ( $atom_date ) {
+ $epoch = @parse_w3cdtf($item['modified']);
+ if ($epoch and $epoch > 0) {
+ $item['date_timestamp'] = $epoch;
+ }
+ }
+
+ $this->items[$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'];
+
+ if ( $this->is_rss() == '1.0' and isset($item['dc']['date']) ) {
+ $epoch = @parse_w3cdtf($item['dc']['date']);
+ if ($epoch and $epoch > 0) {
+ $item['date_timestamp'] = $epoch;
+ }
+ }
+ elseif ( isset($item['pubdate']) ) {
+ $epoch = @strtotime($item['pubdate']);
+ if ($epoch > 0) {
+ $item['date_timestamp'] = $epoch;
+ }
+ }
+
+ $this->items[$i] = $item;
+ }
+ }
+ }
+
+
+ function is_rss () {
+ if ( $this->feed_type == RSS ) {
+ return $this->feed_version;
+ }
+ else {
+ return false;
+ }
+ }
+
+ function is_atom() {
+ if ( $this->feed_type == ATOM ) {
+ return $this->feed_version;
+ }
+ else {
+ return false;
+ }
+ }
+
+ /**
+ * return XML parser, and possibly re-encoded source
+ *
+ */
+ function create_parser($source, $out_enc, $in_enc, $detect) {
+ if ( substr(phpversion(),0,1) == 5) {
+ $parser = $this->php5_create_parser($in_enc, $detect);
+ }
+ else {
+ list($parser, $source) = $this->php4_create_parser($source, $in_enc, $detect);
+ }
+ if ($out_enc) {
+ $this->encoding = $out_enc;
+ xml_parser_set_option($parser, XML_OPTION_TARGET_ENCODING, $out_enc);
+ }
+
+ return array($parser, $source);
+ }
+
+ /**
+ * Instantiate an XML parser under PHP5
+ *
+ * PHP5 will do a fine job of detecting input encoding
+ * if passed an empty string as the encoding.
+ *
+ * All hail libxml2!
+ *
+ */
+ function php5_create_parser($in_enc, $detect) {
+ // by default php5 does a fine job of detecting input encodings
+ if(!$detect && $in_enc) {
+ return xml_parser_create($in_enc);
+ }
+ else {
+ return xml_parser_create('');
+ }
+ }
+
+ /**
+ * Instaniate an XML parser under PHP4
+ *
+ * Unfortunately PHP4's support for character encodings
+ * and especially XML and character encodings sucks. As
+ * long as the documents you parse only contain characters
+ * from the ISO-8859-1 character set (a superset of ASCII,
+ * and a subset of UTF-8) you're fine. However once you
+ * step out of that comfy little world things get mad, bad,
+ * and dangerous to know.
+ *
+ * The following code is based on SJM's work with FoF
+ * @see http://minutillo.com/steve/weblog/2004/6/17/php-xml-and-character-encodings-a-tale-of-sadness-rage-and-data-loss
+ *
+ */
+ function php4_create_parser($source, $in_enc, $detect) {
+ if ( !$detect ) {
+ return array(xml_parser_create($in_enc), $source);
+ }
+
+ if (!$in_enc) {
+ if (preg_match('/<?xml.*encoding=[\'"](.*?)[\'"].*?>/m', $source, $m)) {
+ $in_enc = strtoupper($m[1]);
+ $this->source_encoding = $in_enc;
+ }
+ else {
+ $in_enc = 'UTF-8';
+ }
+ }
+
+ if ($this->known_encoding($in_enc)) {
+ return array(xml_parser_create($in_enc), $source);
+ }
+
+ // the dectected encoding is not one of the simple encodings PHP knows
+
+ // attempt to use the iconv extension to
+ // cast the XML to a known encoding
+ // @see http://php.net/iconv
+
+ if (function_exists('iconv')) {
+ $encoded_source = iconv($in_enc,'UTF-8', $source);
+ if ($encoded_source) {
+ return array(xml_parser_create('UTF-8'), $encoded_source);
+ }
+ }
+
+ // iconv didn't work, try mb_convert_encoding
+ // @see http://php.net/mbstring
+ if(function_exists('mb_convert_encoding')) {
+ $encoded_source = mb_convert_encoding($source, 'UTF-8', $in_enc );
+ if ($encoded_source) {
+ return array(xml_parser_create('UTF-8'), $encoded_source);
+ }
+ }
+
+ // else
+ $this->error("Feed is in an unsupported character encoding. ($in_enc) " .
+ "You may see strange artifacts, and mangled characters.",
+ E_USER_NOTICE);
+
+ return array(xml_parser_create(), $source);
+ }
+
+ function known_encoding($enc) {
+ $enc = strtoupper($enc);
+ if ( in_array($enc, $this->_KNOWN_ENCODINGS) ) {
+ return $enc;
+ }
+ else {
+ return false;
+ }
+ }
+
+ function error ($errormsg, $lvl=E_USER_WARNING) {
+ // append PHP's error message if track_errors enabled
+ if ( $php_errormsg ) {
+ $errormsg .= " ($php_errormsg)";
+ }
+ if ( MAGPIE_DEBUG ) {
+ trigger_error( $errormsg, $lvl);
+ }
+ else {
+ error_log( $errormsg, 0);
+ }
+
+ $notices = E_USER_NOTICE|E_NOTICE;
+ if ( $lvl&$notices ) {
+ $this->WARNING = $errormsg;
+ } else {
+ $this->ERROR = $errormsg;
+ }
+ }
+
+
+} // end class RSS
+
+function map_attrs($k, $v) {
+ return "$k=\"$v\"";
+}
+
+
+?>
--- /dev/null
+<?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;
+ }
+}
+
+?>
projects / moodle.git / commitdiff