Extension:RSS Reader/wikiRSS

<?php
/*
 * wikiRSS 0.1 - PHP class to parse RSS files for MediaWiki
 * Copyright (C) 2007  Artem Kaznatcheev
 *
 * This program is free software: you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the
 * Free Software Foundation, either version 2 of the License, or (at your
 * option) any later version.
 *
 * This program 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
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License along
 * with this program.  If not, see <http://www.gnu.org/licenses/>.
 **************************************************************************
 *                        ACKNOWLEDGMENT
 *
 * This class is a modification of an existing RSS parser called:  lastRSS
 * 0.9.1. lasRSS was created by Vojtech Semecky who can be  contacted at 
 * webmaster @ oslab . net. The original lastRSS "Simple yet powerful PHP
 * class to parse RSS files" was licensed under GPL, and this product 
 * follows in its footsteps. Please visit http://lastrss.oslab.net/ for
 * more information about lastRSS
 **************************************************************************
 *                         WIKIRSS INFO
 *
 * wikiRSS provides a way to retrieve and parse RSS feeds. For retrieving 
 * and parsing it mostly relies on the code that made lastRSS work, however
 * instead of caching feeds in individual files in a  folder, it sticks
 * them in the database
 **************************************************************************
 */
 
# Not a valid entry point, skip unless MEDIAWIKI is defined
if (!defined('MEDIAWIKI')) {exit( 1 );} //uses MediaWiki database
 
/*
 * This is the wikiRSS class that does most the fetching and caching of RSS
 * feeds. Majority of it comes from lastRSS by Vojtech Semecky
 */
class wikiRSS {
  /*
   * Public properties
   */
  var $default_cp = 'UTF-8';
  var $CDATA = 'nochange';
  var $cp = '';
  var $items_limit = 0;
  var $stripHTML = False;
  var $date_format = '';
 
  /*
   Private variables
  */
  var $channeltags = array (
    'title', 'link', 'description', 'language', 'copyright',
    'managingEditor', 'webMaster', 'lastBuildDate', 'rating', 'docs'
  );
  var $itemtags = array(
    'title', 'link', 'description', 'author', 'category', 'comments',
    'enclosure', 'guid', 'pubDate', 'source'
  );
  var $imagetags = array('title', 'url', 'link', 'width', 'height');
  var $textinputtags = array('title', 'description', 'name', 'link');
 
  /* 
   * Parse RSS file and returns associative array.
   */
  function Get ($rss_url) {
    global $wgDBprefix; //get DBpreix
 
    if ($this->cache) { //cache enabled
      $dbr =& wfGetDB( DB_SLAVE ); //load the database object
 
      $res = $dbr->query("
        SELECT rss_content,rss_cacheTime FROM "
        .$wgDBprefix.'rss_cache
          WHERE rss_source="'.$rss_url.'"'
      ); //query for content and cacheTime of url
 
      $row = $dbr->fetchObject( $res );
      $dbr->close(); //close database
 
      if (!$row) { //no entry yet
        $result = $this->Parse($rss_url); //fetch the result
        if ($result) $result['cached'] = 0;
        $serialized = str_replace('"','\"', serialize($result)); //serialize and escape result
 
        $dbw =& wfGetDB( DB_MASTER ); //load the database object
 
        $res = $dbw->query('
          INSERT INTO '.$wgDBprefix.'rss_cache
            VALUES("'.$rss_url.'","'.$serialized.'",'.time().')
        ');
 
        $dbw->close(); //close database
      } else { //previous entry found
        if ((time() - $row->rss_cacheTime) < $this->cache_time) { //file is fresh enough
          $result = unserialize($row->rss_content); //unserialize old feed content
          if ($result) $result['cached'] = 1; // set 'cached' to 1 only if cached file is correct
        } else { //file is too old
          $result = $this->Parse($rss_url); //fetch the result
          if ($result) $result['cached'] = 0;
          $serialized = str_replace('"','\"', serialize($result)); //serialize and escape result
 
          $dbw =& wfGetDB( DB_MASTER ); //load the database object
 
          $res = $dbw->query('
            UPDATE '.$wgDBprefix.'rss_cache
              SET rss_content="'.$serialized.'",
                rss_cacheTime='.time().'
              WHERE rss_source="'.$rss_url.'"
          ');
          $dbw->close(); //close database
        }
      }
    } else { //cache disabled
      $result = $this->Parse($rss_url); //fetch the result
      if ($result) $result['cached'] = 0;
    }
 
    return $result; // return result
  }
 
  /*
   * Modification of preg_match(); return trimed field with index 1
   * from 'classic' preg_match() array output
   */
  function my_preg_match ($pattern, $subject) {
    // start regullar expression
    preg_match($pattern, $subject, $out);
 
    // if there is some result... process it and return it
    if(isset($out[1])) {
    // Process CDATA (if present)
      if ($this->CDATA == 'content') { // Get CDATA content (without CDATA tag)
        $out[1] = strtr($out[1], array('<![CDATA['=>'', ']]>'=>''));
      } elseif ($this->CDATA == 'strip') { // Strip CDATA
        $out[1] = strtr($out[1], array('<![CDATA['=>'', ']]>'=>''));
      }
 
      // If code page is set convert character encoding to required
      if ($this->cp != '')
        //$out[1] = $this->MyConvertEncoding($this->rsscp, $this->cp, $out[1]);
        $out[1] = iconv($this->rsscp, $this->cp.'//TRANSLIT', $out[1]);
      // Return result
      return trim($out[1]);
    } else {
      return ''; // if there is NO result, return empty string
    }
  }
 
  /*
   * Replace HTML entities &something; by real characters
   */
  function unhtmlentities ($string) {
    // Get HTML entities table
    $trans_tbl = get_html_translation_table (HTML_ENTITIES, ENT_QUOTES);
    // Flip keys<==>values
    $trans_tbl = array_flip ($trans_tbl);
    // Add support for &apos; entity (missing in HTML_ENTITIES)
    $trans_tbl += array('&apos;' => "'");
    // Replace entities by values
    return strtr ($string, $trans_tbl);
  }
 
  /*
   * Parse() is private method used by Get() to load and parse RSS file.
   * Don't use Parse() in your scripts - use Get($rss_file) instead.
   */
  function Parse ($rss_url) {
    // Open and load RSS file
    if ($f = @fopen($rss_url, 'r')) {
      $rss_content = '';
      while (!feof($f)) {
        $rss_content .= fgets($f, 4096);
      }
      fclose($f);
 
      // Parse document encoding
      $result['encoding'] = $this->my_preg_match("'encoding=[\'\"](.*?)[\'\"]'si", $rss_content);
      // if document codepage is specified, use it
      if ($result['encoding'] != '') { 
        $this->rsscp = $result['encoding']; // This is used in my_preg_match()
      } 
      // otherwise use the default codepage
      else { 
        $this->rsscp = $this->default_cp; // This is used in my_preg_match()
      }
 
      // Parse CHANNEL info
      preg_match("'<channel.*?>(.*?)</channel>'si", $rss_content, $out_channel);
      foreach($this->channeltags as $channeltag) {
        $temp = $this->my_preg_match("'<$channeltag.*?>(.*?)</$channeltag>'si", $out_channel[1]);
        if ($temp != '') $result[$channeltag] = $temp; // Set only if not empty
      }
      // If date_format is specified and lastBuildDate is valid
      if ($this->date_format != '' && ($timestamp = strtotime($result['lastBuildDate'])) !==-1) {
        // convert lastBuildDate to specified date format
        $result['lastBuildDate'] = date($this->date_format, $timestamp);
      }
 
      // Parse TEXTINPUT info
      preg_match("'<textinput(|[^>]*[^/])>(.*?)</textinput>'si", $rss_content, $out_textinfo);
      /* This a little strange regexp means:
       * Look for tag <textinput> with or without any attributes, but skip 
       * truncated version <textinput /> (it's not beggining tag)
       */
      if (isset($out_textinfo[2])) {
        foreach($this->textinputtags as $textinputtag) {
          $temp = $this->my_preg_match("'<$textinputtag.*?>(.*?)</$textinputtag>'si", $out_textinfo[2]);
          if ($temp != '') $result['textinput_'.$textinputtag] = $temp; // Set only if not empty
        }
      }
      // Parse IMAGE info
      preg_match("'<image.*?>(.*?)</image>'si", $rss_content, $out_imageinfo);
      if (isset($out_imageinfo[1])) {
        foreach($this->imagetags as $imagetag) {
          $temp = $this->my_preg_match("'<$imagetag.*?>(.*?)</$imagetag>'si", $out_imageinfo[1]);
          if ($temp != '') $result['image_'.$imagetag] = $temp; // Set only if not empty
        }
      }
      // Parse ITEMS
      preg_match_all("'<item(| .*?)>(.*?)</item>'si", $rss_content, $items);
      $rss_items = $items[2];
      $i = 0;
      $result['items'] = array(); // create array even if there are no items
      foreach($rss_items as $rss_item) {
        // If number of items is lower then limit: Parse one item
        if ($i < $this->items_limit || $this->items_limit == 0) {
          foreach($this->itemtags as $itemtag) {
            $temp = $this->my_preg_match("'<$itemtag.*?>(.*?)</$itemtag>'si", $rss_item);
            if ($temp != '') $result['items'][$i][$itemtag] = $temp; // Set only if not empty
          }
          // Strip HTML tags and other bullshit from DESCRIPTION
          if ($this->stripHTML && $result['items'][$i]['description'])
          $result['items'][$i]['description'] = strip_tags($this->unhtmlentities(strip_tags($result['items'][$i]['description'])));
          // Strip HTML tags and other bullshit from TITLE
          if ($this->stripHTML && $result['items'][$i]['title'])
          $result['items'][$i]['title'] = strip_tags($this->unhtmlentities(strip_tags($result['items'][$i]['title'])));
          // If date_format is specified and pubDate is valid
          if ($this->date_format != '' && ($timestamp = strtotime($result['items'][$i]['pubDate'])) !==-1) {
            // convert pubDate to specified date format
            $result['items'][$i]['pubDate'] = date($this->date_format, $timestamp);
          }
          // Item counter
          $i++;
          }
        }
 
      $result['items_count'] = $i;
      return $result;
    } else { // Error in opening return False
      return False;
    }
  }
}