<?php
/***********************************************************
* pmfeed.php, requires PmWiki 2.1 *
* This is an RSS feed display cookbook recipe for PmWiki. *
* *
* Uses (and includes) lastRSS which is a GPL'd php class *
* for handling RSS feeds. *
* See "copyright" after this boiler plate below... *
* *
* Copyright (c) 2006, Chris Cox ccox@airmail.net *
* All Rights, Reserved. *
* *
* 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. *
* *
* Installation: *
* *
* Place pmfeed.php (this file) into your cookbook *
* directory (e.g. /srv/www/htdocs/pmwiki/cookbook) *
* *
* Include the cookbook in your local/config.php *
* include_once('cookbook/pmfeed.php'); *
* *
* Create a cache directory at pub/pmfeed under your *
* your PmWiki base directory. Needs to be writable by *
* the web username. *
* *
* On a page include the markup with a feed url. *
* (:pmfeed feed='http://www.digg.com/rss/index.xml':) *
* *
* *
-<0.01: Initial release.
-<0.02: Attempt to interpret some HTML tags as PmWiki equivalents. Enabled for now.
-<0.03: Renamed banner to title and added several "show" options and added \
an unsafe option for some flexibility/risk.
-<0.04: Fixed bug regarding use of newwin=false resulting in bad output (space problem).
->Variables:
[@
feed= URL to RSS feed file. Defaults to pmwiki.org's
Site/AllRecentChanges.
cache_time= Time to cache data... be nice to the providers.
Defaults to 2000 seconds.
max_count= Number of items to read. Defaults to 0.
newwin= Open links to items in a new window. Defaults to true.
overrides= Set this to false to prevent URL line GET overrides to
these parameters.
showitems= Defaults to true. If false, don't show RSS items.
showitemdescr= Defaults to true. If false, don't include the description along with
the item.
showtitle= Defaults to true. If false, don't show the feed title.
title= Alternate title instead of using RSS title.
unsafe= Defaults to false. If true, allows setting of title and feed
from the URL line (_GET).
@]
***********************************************************/
/*
======================================================================
lastRSS 0.9.1
Simple yet powerfull 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 powerfull PHP class to parse RSS files.
*/
class lastRSS {
// -------------------------------------------------------------------
// Public properties
// -------------------------------------------------------------------
var $default_cp = 'UTF-8';
var $CDATA = 'content';
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);
$serialized = serialize($result);
if ($f = @fopen($cache_file, 'w')) {
fwrite ($f, $serialized, strlen($serialized));
fclose($f);
}
if ($result) $result['cached'] = 0;
}
}
// If CACHE DISABLED >> load and parse the file directly
else {
$result = $this->Parse($rss_url);
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 {
// 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 ' entity (missing in HTML_ENTITIES)
$trans_tbl += array(''' => "'");
// Replace entities by values
return strtr ($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 is used in my_preg_match()
$this->rsscp = $result['encoding'];
} else {
// This is used in my_preg_match()
// otherwise use the default codepage
$this->rsscp = $this->default_cp;
}
// 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 != '') {
// Set only if not empty
$result['textinput_'.$textinputtag] = $temp;
}
}
}
// 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 != '') {
// Set only if not empty
$result['image_'.$imagetag] = $temp;
}
}
}
// 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] = $temp; // Set only if not empty
}
// Strip HTML tags and other stuff from DESCRIPTION
if ($this->stripHTML && $result['items'][$i]['description'])
$result['items'][$i]['description'] = strip_tags($this->unhtmlentities(strip_tags($result['items'][$i]['description'])));
// Strip HTML tags and other stuff from TITLE
if ($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;
}
}
}
/**
* End lastRSS
*/
/* pmfeed */
Markup('pmfeed','directives',"/^\(:pmfeed[ ]*(.*?):\)\s*$/e",
"pmfeed('$1')");
// For users prior to PHP 4.3.0 you may do this:
function pmfeedunhtmlentities($string) {
// replace numeric entities
$string = preg_replace('~&#x([0-9a-f]+);~ei', 'chr(hexdec("\\1"))', $string);
$string = preg_replace('~&#([0-9]+);~e', 'chr(\\1)', $string);
// replace literal entities
$trans_tbl = get_html_translation_table(HTML_ENTITIES);
$trans_tbl = array_flip($trans_tbl);
return strtr($string, $trans_tbl);
}
function pmfeed($opts) {
global $FarmD, $pagename, $MaxIncludes, $HTMLHeaderFmt, $PmFeedCacheDir,
$PmFeedTitleMark, $PmFeedItemMark, $PmFeedDescrBold,
$PmFeedDescrItalic, $PmFeedDescrUnderline, $PmFeedDescrSmall,
$PmFeedDescrStrong, $PmFeedMarkupReplace;
SDV($PmFeedCacheDir, $FarmD.'/pub/pmfeed');
//Initial PmWiki markup for feed title
SDV($PmFeedTitleMark, '!!');
//Initial PmWiki markup for items
SDV($PmFeedItemMark, '*');
//Convert bold tags
SDV($PmFeedDescrBold, '\'\'\'$1\'\'\'');
//Convert italic tags
SDV($PmFeedDescrItalic, '\'\'$1\'\'');
//Convert underline tags
SDV($PmFeedDescrUnderline, '{+$1+}');
//Convert small tags
SDV($PmFeedDescrSmall, '[-$1-]');
//Convert strong tags: <strong>text</strong> to '''''text'''''
SDV($PmFeedDescrStrong, '\'\'\'\'\'$1\'\'\'\'\'');
//Attempt to escape markups special to PmWiki that might be found in description
SDV($PmFeedMarkupReplace, '/([#*])/');
// Determine this Group
//
$group = FmtPageName('$Group',$pagename);
$name = FmtPageName('$Name',$pagename);
// Process markup arguments first
//
$defaults = array(
'feed'=>'http://www.pmwiki.org/wiki/Site/AllRecentChanges?action=rss',
'title'=>'',
'cache_time'=>2000,
'max_count'=>0,
'showitems'=>'true',
'showitemdescr'=>'true',
'showtitle'=>'true',
'showfeedxmllink'=>'false',
'newwin'=>'true',
'overrides'=>'true',
'unsafe'=>'false'
);
$args = array_merge($defaults, ParseArgs($opts));
$urladd='';
// Allows overrides=false in the :pmfeed: markup to disallow
// settings on the URL line.
//
$overrides = $args['overrides'];
if ($overrides == 'false') {
$_GET = NULL;
}
$cache_time = isset($_GET['cache_time']) ? $_GET['cache_time'] :
$args['cache_time'];
if (isset($_GET['cache_time']))
$urladd.="&cache_time=".urlencode($_GET['cache_time']);
$showitemdescr = isset($_GET['showitemdescr']) ? $_GET['showitemdescr'] :
$args['showitemdescr'];
if (isset($_GET['showitemdescr']))
$urladd.="&showitemdescr=".urlencode($_GET['showitemdescr']);
$showitems = isset($_GET['showitems']) ? $_GET['showitems'] :
$args['showitems'];
if (isset($_GET['showitems']))
$urladd.="&showitems=".urlencode($_GET['showitems']);
$showtitle = isset($_GET['showtitle']) ? $_GET['showtitle'] :
$args['showtitle'];
if (isset($_GET['showtitle']))
$urladd.="&showtitle=".urlencode($_GET['showtitle']);
$showfeedxmllink = isset($_GET['showfeedxmllink']) ? $_GET['showfeedxmllink'] :
$args['showfeedxmllink'];
if (isset($_GET['showfeedxmllink']))
$urladd.="&showfeedxmllink=".urlencode($_GET['showfeedxmllink']);
$max_count = isset($_GET['max_count']) ? $_GET['max_count'] :
$args['max_count'];
if (isset($_GET['max_count']))
$urladd.="&max_count=".urlencode($_GET['max_count']);
$newwin= isset($_GET['newwin']) ? $_GET['newwin'] : $args['newwin'];
if (isset($_GET['newwin']))
$urladd.="&newwin=".urlencode($_GET['newwin']);
// For unsafe (?) things
// Enabling unsafe would allow you to create a totally user driven
// feed. It's possible that some "nasty" markup could come in via
// title if made user modifiable.
$unsafe=$args['unsafe'];
if ($unsafe == 'true') {
$feed= isset($_GET['feed']) ? $_GET['feed'] : $args['feed'];
if (isset($_GET['feed']))
$urladd.="&feed=".urlencode($_GET['feed']);
$title= isset($_GET['title']) ? $_GET['title'] : $args['title'];
if (isset($_GET['title']))
$urladd.="&title=".urlencode($_GET['title']);
} else {
$title=$args['title'];
$feed=$args['feed'];
}
$out='';
// Create lastRSS object
$rss = new lastRSS;
// $rss->stripHTML = True;
// Set cache dir and cache time limit
// (don't forget to chmod cache to allow writing)
$rss->cache_dir = $PmFeedCacheDir;
$rss->cache_time = $cache_time;
$out.="\n";
if ($newwin == 'true') {
$pmnewwin='newwin ';
} else {
$pmnewwin='';
}
// Try to load and parse RSS file
$feed=str_replace('&', '&', $feed);
if ($rs = $rss->get($feed)) {
// Show title or clickable website rss title if not supplied
if ($showtitle == 'true') {
if ($title != '') {
$out.="\n$PmFeedTitleMark %".$pmnewwin."class=pmfeedtitle%[[$rs[link]|$title\"$rs[title]\"]]";
} else {
$out.="\n$PmFeedTitleMark %".$pmnewwin."class=pmfeedtitle%[[$rs[link]|$rs[title]]]";
}
}
//Hack to convert destroyed german 'umlauts' (Ä, ä, Ü, ü, Ö, ö, ß(= double s in german)) back.
//Works on the original Feed name!
//(Axel)
$out=preg_replace('/ü/', 'ü', $out); //ü
$out=preg_replace('/Ä/', 'Ä', $out); //Ä
$out=preg_replace('/ä/', 'ä', $out); //ä
$out=preg_replace('/Ö/', 'Ö', $out); //Ö
$out=preg_replace('/ö/', 'ö', $out); //ö
$out=preg_replace('/ß/', 'ß', $out); //ß
// Display a link to the original feed xml
if ($showfeedxmllink == 'true') {
$out.="[[$feed|(XML)]]";
}
$out.="\n";
// Show last published articles (title, link, description)
if ($showitems == 'true') {
$i=0;
foreach($rs['items'] as $item) {
if ($max_count && $i >= $max_count) {
break;
}
$pmfeedtitle=preg_replace('/\n/','',strip_tags(pmfeedunhtmlentities($item['title'])));
$pmfeedlink=$item['link'];
if ($pmfeedlink == '') {
$pmfeeditem="$PmFeedItemMark %class=pmfeeditem%".$pmfeedtitle;
} else {
$pmfeeditem="$PmFeedItemMark %".$pmnewwin."class=pmfeeditem%[[$pmfeedlink|$pmfeedtitle]]";
}
//Hack to convert destroyed german 'umlauts' (Ä, ä, Ü, ü, Ö, ö, ß(= double s in german)) back.
//Works on the news headers!
//(Axel)
$pmfeeditem=preg_replace('/ü/', 'ü', $pmfeeditem); //ü
$pmfeeditem=preg_replace('/Ä/', 'Ä', $pmfeeditem); //Ä
$pmfeeditem=preg_replace('/ä/', 'ä', $pmfeeditem); //ä
$pmfeeditem=preg_replace('/Ö/', 'Ö', $pmfeeditem); //Ö
$pmfeeditem=preg_replace('/ö/', 'ö', $pmfeeditem); //ö
$pmfeeditem=preg_replace('/ß/', 'ß', $pmfeeditem); //ß
$out.="$pmfeeditem\n";
if ($showitemdescr == 'true') {
$d=pmfeedunhtmlentities($item['description']);
// Get rid of initial para or br
$d=preg_replace('/^<p>/i','', $d);
$d=preg_replace('/^<[bh]r \/>/i','', $d);
// Attempt to convert <a href="url">name</a> to [[url|name]]
$d=preg_replace('/<a\s+.*?href="([^"]+)"[^>]*>([^<]+)<\/a>/is', '[[$1|$2]]', $d);
//Convert bold tags
$d=preg_replace('/<b>(.*?)<\/b>/', $PmFeedDescrBold, $d);
//Convert italics tags
$d=preg_replace('/<i>(.*?)<\/i>/', $PmFeedDescrItalic, $d);
//Convert underline tags
$d=preg_replace('/<u>(.*?)<\/u>/', $PmFeedDescrUnderline, $d);
//Convert small tags
$d=preg_replace('/<small>(.*?)<\/small>/', $PmFeedDescrSmall, $d);
//Convert strong tags: <strong>text</strong> to '''''text'''''
////$d=preg_replace('/<strong>(.*?)<\/strong>/', $PmFeedDescrStrong, $d);
//Convert breaks and paragraphs
$d=preg_replace('/<hr \/>/', '\\\\\\\\'."\n", $d);
$d=preg_replace('/<br \>/', '\\\\'."\n", $d);
// $d=preg_replace('/<br>/', "\n".'\\\\\\', $d);
$d=preg_replace('/<p>/', '\\\\\\\\'."\n", $d);
//Hack to hide PmWiki Markup, pound and asterisk
//... sigh, there could be a ton of these.
$d=preg_replace($PmFeedMarkupReplace, '[=$1=]', $d);
// Slaughter the rest of the html tags
$d="%block class=indent ".$pmnewwin."%".ltrim(strip_tags($d))."%%\n";
$d=preg_replace('/^\s+/', '', $d);
//Hack to convert destroyed german 'umlauts' (Ä, ä, Ü, ü, Ö, ö, ß(= double s in german)) back.
//Works on new's bodies!
//(Axel)
$d=preg_replace('/ü/', 'ü', $d); //ü
$d=preg_replace('/Ä/', 'Ä', $d); //Ä
$d=preg_replace('/ä/', 'ä', $d); //ä
$d=preg_replace('/Ö/', 'Ö', $d); //Ö
$d=preg_replace('/ö/', 'ö', $d); //ö
$d=preg_replace('/ß/', 'ß', $d); //ß
$out.=$d;
}
$i++;
}
}
} else {
$out.="Error: It's not possible to reach RSS file $feed ...\n";
}
PRR(); return $out;
}