*
* 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 3 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 .
*/
/**
* This script "cleans" a MySpace blog feed by fixing unencoded and double
* encoded entities, as well as converting "fancy" entities to plain text, where
* "fancy" for the purposes of this script is basically any entities that
* Facebook Notes doesn't like.
*
* It's a big hack. Suggestions welcome.
*
* @author Blaise Alleyne
* @version 0.1
*/
// Retrive the contents of the feed
$feed = file_get_contents('http://blog.myspace.com/blog/rss.cfm?friendID=105852723');
// A list of tags to "clean"
$tags = '(title|description|itunes\:author|itunes\:summary|itunes\:keywords|itunes\:name|itunes\:subtitle)';
// Clean up the HTML entities in the contents of these tags
echo preg_replace_callback("/(<$tags>)([^<]+)(<\/$tags>)/", cleanEntities, $feed);
/**
* Undo double encoding, encode unencoded characters, convert any "fancy"
* character entities to plain text, return the result.
*
* @param $match - the result returned from the regular expression
* @return the tag with its "cleaned" contents
**/
function cleanEntities($match){
$tag_open = $match[1];
$tag_close = $match[4];
// The contents of the tag
$_0 = $match[3];
// Reverse any double encoding (e.g. ’)
$_1 = html_entity_decode($_0, ENT_QUOTES, 'utf-8');
// Encode any unencoded characters (ignoring existing entities)
$_2 = htmlentities($_1, ENT_QUOTES, 'utf-8', false);
$contents = $_2;
// Replace any "fancy" unicode character entities with plain text
// Using list from: http://www.chuggnutt.com/html2text-source.php
$contents = preg_replace('/&(quot|rdquo|ldquo|#8220|#8221|#147|#148);/i', '"', $contents);
$contents = preg_replace('/&(apos|rsquo|lsquo|#8216|#8217);/i', "'", $contents);
return $tag_open . $contents . $tag_close;
}
?>