boyska/rss-bridge
1
0
Fork 0
forked from blallo/rss-bridge
Code Releases Activity

Add support for Zataz website.

Browse source 
It gets the last 5 articles available. The feed is missing images since hot-linking is impossible from host.
We might need a way to grab and store that content as well.
This commit is contained in:
Alexis Degrugillier 2015-02-07 14:25:38 -05:00
parent ade723f6a6
commit 5144c83c95
1 changed files with 55 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

55
bridges/ZatazBridge.php Normal file
View file

@ -0,0 +1,55 @@
<?php
/**
* @name Zataz
* @homepage http://www.zataz.com/
* @description ZATAZ Magazine - S'informer, c'est déjà se sécuriser
* @maintainer aledeg
* @update 07/02/2015
*/
class ZatazBridge extends BridgeAbstract {
public function collectData(array $param) {
$html = file_get_html($this->getURI()) or $this->returnError('Could not request ' . $this->getURI(), 404);
$recent_posts = $html->find('#recent-posts-3', 0)->find('ul', 0)->find('li');
foreach ($recent_posts as $article) {
if (count($this->items) < 5) {
$uri = $article->find('a', 0)->href;
$this->items[] = $this->getDetails($uri);
}
}
}
private function getDetails($uri) {
$html = file_get_html($uri) or exit;
$item = new \Item();
$article = $html->find('.gdl-blog-full', 0);
$item->uri = $uri;
$item->title = $article->find('.blog-title', 0)->find('a', 0)->innertext;
$item->content = $article->find('.blog-content', 0)->innertext;
$item->timestamp = $this->getTimestampFromDate($article->find('.blog-date', 0)->find('a', 0)->href);
return $item;
}
private function getTimestampFromDate($uri) {
preg_match('/\d{4}\/\d{2}\/\d{2}/', $uri, $matches);
$date = new \DateTime($matches[0]);
return $date->format('U');
}
public function getName() {
return 'Zataz Magazine';
}
public function getCacheDuration() {
return 7200; // 2h
}
public function getURI() {
return 'http://www.zataz.com';
}
}