rssfilter.php

for news RSS to HTML as ASP

<?php
//
// rssFilter.php Filter RSS feeds
//
// Copyright 2007 NotePage, Inc.
// http://www.feedforall.com
//
// NotePage, Inc. grants registerd users of our FeedForAll and/or
// FeedForAll Mac product(s) the right to install and use the
// rssFilter.php script free of charge.
// Please refer to the EULA included in the download for full license
// terms and conditions.
//
// $Id: rssFilter.php,v 3.3 2007/04/27 17:32:12 housley Exp $
//
// $Log: rssFilter.php,v $
// Revision 3.3  2007/04/27 17:32:12  housley
// Some versions of PHP, on windows at least, want the rssFilter_useItem() 
// function before the include in the script.
//
// Revision 3.2  2007/04/26 23:40:40  housley
// * Properly read "matchType" from a configuration file
// * Add UTF-8 characterset to the buildScript pages
//
// Revision 3.1  2007/04/24 18:29:55  housley
// Parse the iTunes Music Store namespace
//
// Revision 3.0  2007/04/16 14:23:04  housley
// Release version 3.0 of the scripts
//
// Revision 1.25  2007/04/11 18:38:08  housley
// Update the user agent to be 3.0
//
// Revision 1.24  2007/04/09 01:25:50  housley
// Fix the commented out code for enabling the extensions
//
// Revision 1.23  2007/04/06 11:08:58  housley
// Add support for the Dublin Core (dc) namespace
//
// Revision 1.22  2007/04/04 20:55:46  housley
// Add the ability to set CURLOPT_CONNECTTIMEOUT
//
// Revision 1.21  2007/04/04 14:53:27  housley
// * Remove the ...OrOnTime compares because of TZ they are too hard
// * Move the BeforeTime/AfterTime to the bottom to encourage ...Date compares
//
// Revision 1.20  2007/03/31 12:29:42  housley
// When working with an existing script, don't define the useItem() function
//
// Revision 1.19  2007/03/31 12:28:41  housley
// Add filters that include the current time/date
//
// Revision 1.18  2007/03/30 01:34:12  housley
// Move the very specific rssFilter code to rssFilter.php
//
// Revision 1.17  2007/03/27 23:16:31  housley
// Add support for Atom 1.0 atom:updated date field
//
// Revision 1.16  2007/03/26 20:51:48  housley
// Create a method to update the channel level date to the most recent
// item date
//
// Revision 1.15  2007/03/14 18:15:39  housley
// Get the top and bottom properly for Atom and RDF feeds
//
// Revision 1.14  2007/03/12 23:25:48  housley
// Set the caching variable when no script is defined
//
// Revision 1.13  2007/03/07 03:01:22  housley
// Add the flag to not parse TrackBack
//
// Revision 1.12  2007/03/07 00:22:26  housley
// Change the order of the filter builder fields, to make the operation
// easier to understand
//
// Revision 1.11  2007/03/06 14:27:41  housley
// Fix typo that prevented any output with a valid cache
//
// Revision 1.9  2007/03/05 21:13:11  housley
// * Add support for working with pubDate as a date or time
// * Show which items will and won't be used
//
// Revision 1.8  2007/03/05 18:23:58  housley
// Don't abort processing on XML parse error, just don't do anything else
//
// Revision 1.7  2007/03/05 17:29:46  housley
// Add a simple way to block parsing extensions
//
// Revision 1.6  2007/03/05 17:28:54  housley
// Remove some config variables that aren't used
//
// Revision 1.5  2007/03/05 15:10:33  housley
// Allow testing of the current script
//
// Revision 1.4  2007/03/05 01:19:45  housley
// Rename FeedForAll_rss2html_readFile() to FeedForAll_scripts_readFile()
//
// Revision 1.3  2007/03/05 01:12:16  housley
// Move FeedForAll_scripts_convertEncoding and FeedForAll_scripts_readFile
// into FeedForAll_XMLParser.inc.php, because they are used in every file
//
// Revision 1.2  2007/03/05 00:43:49  housley
// Allow the setting the type of joining of the statements
//
// Revision 1.1  2007/03/04 22:54:30  housley
// Program to filter rss feeds
//
//
//


//
// ==========================================================================
// Configuration options
// ==========================================================================
//
// Set the following variable useFopenURL to one if you want/need to use
// fopen() instead of CURL
if (!isset($useFopenURL)) {
  $useFopenURL = 0;
}

//
// Destination Encoding:  By default rssFilter.php converts all feeds to UTF-8
// and then produces webpages in UTF-8 because UTF-8 is capable of displaying
// all possible characters.
if (!isset($destinationEncoding)) {
  $destinationEncoding = "UTF-8";
}

//
// Missing Encoding Default:  Some feeds do not specify the character set 
// they are encoded in.  The XML specification states that if there is no
// encoding specified the XML file, all RSS feeds are XML, must be encoded
// in UTF-8, but experience has show differently.  This specifies the 
// encoding that will be used for feeds that don't specify the encoding.
//$missingEncodingDefault = "UTF-8";
if (!isset($missingEncodingDefault)) {
  $missingEncodingDefault = "ISO-8859-1";
}

//
// Enable the caching for the resulting XML file.  Since it may take time to 
// process multiple RSS feeds and may be noticed by visitors to your
// website this is highly recommended.  During development and testing set 
// this to 0 so you can see the results of your changes.
if (!isset($useOutputCaching)) {
  $useOutputCaching = 0;
}

//
// The variable $outputCacheTTL controls how many seconds a cached copy of
// resulting RSS feed can be used before it must be recreated.
if (!isset($outputCacheTTL)) {
  // $outputCacheTTL = 60;      //cache files for 1 minute
  $outputCacheTTL = 3600;    //cache files for 1 hour
  // $outputCacheTTL = 86400;   //cache files for 1 day
}

//
// The variable $outputCacheFolder specifies the name of the directory, relative to
// the location of rssFilter.php, where the cached files are stored.  It not
// recommened you change this with out a very good reason.
if (!isset($outputCacheFolder)) {
  $outputCacheFolder = "rssFilterCacheFiles";
}

//
// $connectTimeoutLimit allows the limiting the amount of time cURL will
// wait to successfully connect to a remote server.  Use with caution,
// a value too small will cause all connections to fail.
//$connectTimeoutLimit = 30;

//
// To prevent parsing of the iTunes(R) XML namespace extension, uncomment the
// following line.
//$Dont_Parse_iTunes == TRUE;
//
// To prevent parsing of the TrackBack XML namespace extension, uncomment the
// following line.
//$Dont_Parse_TrackBack == TRUE;
//
// To prevent parsing of the DublinCore XML namespace extension, uncomment the
// following line.
//$Dont_Parse_DublinCore == TRUE;
//
// To prevent parsing of the ITMS XML namespace extension, uncomment the
// following line.
//$Dont_Parse_ITMS == TRUE;
  

// ==========================================================================
// Below this point of the file there are no user editable options.  Your
// are welcome to make any modifications that you wish to any of the code
// below, but that is not necessary for normal use.
// ==========================================================================

//
// If using cURL, make sure it exists
if (($useFopenURL == 0) && !function_exists("curl_init")) {
  $useFopenURL = 1;
}

if ($useFopenURL) {
  ini_set("allow_url_fopen", "1");
  ini_set("user_agent", 'FeedForAll rssFilter.php v3');
}

// Since the output is cached it is not recommended to cache the XML in input
$allowCachingXMLFiles = 0;

@include_once("FeedForAll_Scripts_CachingExtension.php");

//
// Read in the configuration file
$config = Array();

@include_once("FeedForAll_parse_Extensions.inc.php");
if (function_exists("FeedForAll_parseExtensions") === FALSE) {
  Function FeedForAll_parseExtensions() {
    return FALSE;
  }
}

Function rssFilter_extendClass($className) {
  $newClassName = $className."_rssFilter";
  eval('class ' . $newClassName . ' extends ' . $className . ' {
    Function getArrayOfFilters() {
      $result = Array();
  
      $result[] = "contains//Conatins";
      $result[] = "notContains//Does not contain";
      $result[] = "equal//Equal with";
      $result[] = "notEqual//Not equal with";
      $result[] = "beginsWith//Begins with";
      $result[] = "notBeginsWith//Does not begin with";
      $result[] = "endsWith//Ends with";
      $result[] = "notEndsWith//Does not end with";
      $result[] = "isEmpty//Is Empty";
      $result[] = "notEmpty//Is Not Empty";
      $result[] = "alphaBefore//Alphabetically Before";
      $result[] = "alphaAfter//Alphabetically After";
      $result[] = "beforeDate//Before Date";
      $result[] = "beforeOrOnDate//Before or On Date";
      $result[] = "onDate//On Date";
      $result[] = "afterDate//After Date";
      $result[] = "afterOrOnDate//After or On Date";
      $result[] = "beforeTime//Before Time";
      $result[] = "afterTime//After Time";
      
      return $result;
    }
    
    Function contains($elementName, $value, $matchCase = 0) {
      if (($currentValue = $this->getValueOf($elementName)) == NULL) return FALSE;
  
      if ($matchCase) {
        if ((strstr($currentValue, $value)) !== FALSE) {
          return TRUE;
        }
      } else {
        if ((stristr($currentValue, $value)) !== FALSE) {
          return TRUE;
        }
      }
      return FALSE;
    }
  
    Function notContains($elementName, $value, $matchCase = 0) {
      return !$this->contains($elementName, $value, $matchCase);
    }
    
    Function equal($elementName, $value, $matchCase = 0) {
      if (($currentValue = $this->getValueOf($elementName)) == NULL) return FALSE;
  
      if ($matchCase) {
        if ((strcmp($currentValue, $value)) == 0) {
          return TRUE;
        }
      } else {
        if ((strcasecmp($currentValue, $value)) == 0) {
          return TRUE;
        }
      }
      return FALSE;
    }
  
    Function notEqual($elementName, $value, $matchCase = 0) {
      return !$this->equal($elementName, $value, $matchCase);
    }