TorrentFlux-b4rt-PHP7/html/inc/classes/lastRSS.php

<?php

/* $Id: lastRSS.php 2907 2007-04-15 13:05:13Z b4rt $ */

/*
 ======================================================================
 lastRSS 0.9.1

 Simple yet powerful PHP class to parse RSS files.

 by Vojtech Semecky, webmaster @ webdot . cz

 Latest version, features, manual and examples:
 	http://lastrss.webdot.cz/

 ----------------------------------------------------------------------
 LICENSE

 This program is free software; you can redistribute it and/or
 modify it under the terms of the GNU General Public License (GPL)
 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.

 To read the license please visit http://www.gnu.org/copyleft/gpl.html
 ======================================================================
*/

/**
* lastRSS
* Simple yet powerful PHP class to parse RSS files.
*/
class lastRSS {

	// -------------------------------------------------------------------------
	// 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($rss_url) {
		// If CACHE ENABLED
		if ($this->cache_dir != '') {
			$cache_file = $this->cache_dir . '/rsscache_' . md5($rss_url);
			$timedif = @(time() - filemtime($cache_file));
			if ($timedif < $this->cache_time) {
				// cached file is fresh enough, return cached array
				$result = unserialize(join('', file($cache_file)));
				// set 'cached' to 1 only if cached file is correct
				if ($result) $result['cached'] = 1;
			} else {
				// cached file is too old, create new
				$result = $this->Parse($rss_url);
				if ($result !== false) {
					$serialized = serialize($result);
					if ($f = @fopen($cache_file, 'w')) {
						fwrite ($f, $serialized, strlen($serialized));
						fclose($f);
					}
					if ($result) $result['cached'] = 0;
				}
			}
		} else {
			// If CACHE DISABLED >> load and parse the file directly
			$result = $this->Parse($rss_url);
			if ($result) $result['cached'] = 0;
		}
		// return result
		return $result;
	}

	// -------------------------------------------------------------------
	// Modification of preg_match(); return trimmed field with index 1
	// from 'classic' preg_match() array output
	// -------------------------------------------------------------------
	function my_preg_match($pattern, $subject) {
		// start regular expression
		preg_match($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 != '')
				$out[1] = iconv($this->rsscp, $this->cp.'//TRANSLIT', $out[1]);
			// Return result
			return trim($out[1]);
		} else {
			// if there is NO result, return empty string
			return '';
		}
	}

	// -------------------------------------------------------------------
	// 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) {

		// Load RSS file
		require_once("inc/classes/SimpleHTTP.php");
		$rss_content = SimpleHTTP::getData($rss_url);
		if (SimpleHTTP::getState() != SIMPLEHTTP_STATE_OK) {
			// last op was not ok
			// log
			global $cfg;
			$msgs = SimpleHTTP::getMessages();
			AuditAction($cfg["constants"]["error"], "lastRSS: could not download feed-data from url ".$rss_url." (".implode("; ", $msgs).")");
			// return false
			return false;
		}

		// result-array
		$result = array();

		// 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()
		} else {
			// otherwise use the default codepage
			$this->rsscp = $this->default_cp; // This is used in my_preg_match()
		}

		// CHANNEL info
		if (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);
		}

		// TEXTINPUT info
		preg_match("'<textinput(|[^>]*[^/])>(.*?)</textinput>'si", $rss_content, $out_textinfo);
		// This a little strange regexp means:
		// Look for tag <textinput> with or without any attributes, but skip truncated version <textinput /> (it's not beginning tag)
		if (isset($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
			}
		}
		// 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
			}
		}
		// 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;
	}
}

?>