[med-svn] r499 - in trunk/community/website: . inc
hanska-guest at alioth.debian.org
hanska-guest at alioth.debian.org
Tue Oct 2 11:30:24 UTC 2007
Author: hanska-guest
Date: 2007-10-02 11:30:24 +0000 (Tue, 02 Oct 2007)
New Revision: 499
Added:
trunk/community/website/inc/lastRSS.php
trunk/community/website/inc/rss-backup.php
Removed:
trunk/community/website/inc/rss.php
Modified:
trunk/community/website/index.php
Log:
Another implementation
Added: trunk/community/website/inc/lastRSS.php
===================================================================
--- trunk/community/website/inc/lastRSS.php (rev 0)
+++ trunk/community/website/inc/lastRSS.php 2007-10-02 11:30:24 UTC (rev 499)
@@ -0,0 +1,220 @@
+<?php
+/*
+ ======================================================================
+ 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 = '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);
+ $serialized = serialize($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->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;
+ }
+ }
+}
+
+?>
\ No newline at end of file
Copied: trunk/community/website/inc/rss-backup.php (from rev 498, trunk/community/website/inc/rss.php)
===================================================================
--- trunk/community/website/inc/rss-backup.php (rev 0)
+++ trunk/community/website/inc/rss-backup.php 2007-10-02 11:30:24 UTC (rev 499)
@@ -0,0 +1,34 @@
+<?php
+ $xml = "http://cia.vc/stats/project/Debian-Med/.rss";
+
+ phpinfo();
+// $xmlDoc = new DOMDocument();
+// $xmlDoc->load($xml);
+
+// echo $xmlDoc->saveXML();
+/*
+ // get elements from <channel>
+ $channel = $xmlDoc->getElementsByTagName("channel")->item(0);
+ $channel_title = $channel->getElementsByTagName("title")->item(0)->childNodes->item(0)->nodeValue;
+ $channel_link = $channel->getElementsByTagName("link")->item(0)->childNodes->item(0)->nodeValue;
+ $channel_desc = $channel->getElementsByTagName("description")->item(0)->childNodes->item(0)->nodeValue;
+
+ // output elements from <channel>
+ echo "<p><a href=\"$channel_link\">$channel_title</a>";
+ echo "<br />";
+ echo "$channel_desc</p>";
+
+ // get and output <item>s
+ $x = $xmlDoc->getElementsByTagName("item");
+ // show only last 10 messages
+ for ($i = 0; $i <= 9; $i++) {
+ $item_title = $x->item($i)->getElementsByTagName("title")->item(0)->childNodes->item(0)->nodeValue;
+ $item_link = $x->item($i)->getElementsByTagName("link")->item(0)->childNodes->item(0)->nodeValue;
+ $item_desc = $x->item($i)->getElementsByTagName("description")->item(0)->childNodes->item(0)->nodeValue;
+
+ echo "<p><a href=\"$item_link\">$item_title</a>";
+ echo "<br />";
+ echo "$item_desc</p>";
+ }
+*/
+?>
Deleted: trunk/community/website/inc/rss.php
===================================================================
--- trunk/community/website/inc/rss.php 2007-10-02 11:21:33 UTC (rev 498)
+++ trunk/community/website/inc/rss.php 2007-10-02 11:30:24 UTC (rev 499)
@@ -1,34 +0,0 @@
-<?php
- $xml = "http://cia.vc/stats/project/Debian-Med/.rss";
-
- phpinfo();
-// $xmlDoc = new DOMDocument();
-// $xmlDoc->load($xml);
-
-// echo $xmlDoc->saveXML();
-/*
- // get elements from <channel>
- $channel = $xmlDoc->getElementsByTagName("channel")->item(0);
- $channel_title = $channel->getElementsByTagName("title")->item(0)->childNodes->item(0)->nodeValue;
- $channel_link = $channel->getElementsByTagName("link")->item(0)->childNodes->item(0)->nodeValue;
- $channel_desc = $channel->getElementsByTagName("description")->item(0)->childNodes->item(0)->nodeValue;
-
- // output elements from <channel>
- echo "<p><a href=\"$channel_link\">$channel_title</a>";
- echo "<br />";
- echo "$channel_desc</p>";
-
- // get and output <item>s
- $x = $xmlDoc->getElementsByTagName("item");
- // show only last 10 messages
- for ($i = 0; $i <= 9; $i++) {
- $item_title = $x->item($i)->getElementsByTagName("title")->item(0)->childNodes->item(0)->nodeValue;
- $item_link = $x->item($i)->getElementsByTagName("link")->item(0)->childNodes->item(0)->nodeValue;
- $item_desc = $x->item($i)->getElementsByTagName("description")->item(0)->childNodes->item(0)->nodeValue;
-
- echo "<p><a href=\"$item_link\">$item_title</a>";
- echo "<br />";
- echo "$item_desc</p>";
- }
-*/
-?>
Modified: trunk/community/website/index.php
===================================================================
--- trunk/community/website/index.php 2007-10-02 11:21:33 UTC (rev 498)
+++ trunk/community/website/index.php 2007-10-02 11:30:24 UTC (rev 499)
@@ -15,7 +15,18 @@
<div id="rssOutput">div</div>
</p>
<?php
- include_once("inc/rss.php");
+ include_once("inc/lastRss.php");
+
+ $rss = new lastRSS;
+ $rss->cache_dir = "./cache";
+ $rss->cache_time = 3600;
+
+ if ($rs = $rss->get("http://cia.vc/stats/project/Debian-Med/.rss")) {
+ echo "<pre>"; print_r($rs); echo "</pre>";
+ }
+ else {
+ echo "Error: can't get RSS feed.<br />";
+ }
?>
<small>Please, note that this is a SVN export of our website. It might break during
SVN commits.</small>
More information about the debian-med-commit
mailing list