1
0
Fork 0
forked from blallo/rss-bridge
rss-bridge/bridges/NiceMatinBridge.php

49 lines
1.7 KiB
PHP
Raw Normal View History

<?php
class NiceMatinBridge extends BridgeAbstract{
2015-11-04 10:47:21 +01:00
public function loadMetadatas() {
$this->maintainer = "pit-fgfjiudghdf";
$this->name = "NiceMatin";
$this->uri = "http://www.nicematin.com/";
$this->description = "Returns the 10 newest posts from NiceMatin (full text)";
$this->update = '2016-08-17';
2016-08-03 22:39:03 +02:00
}
2015-11-04 10:47:21 +01:00
private function NiceMatinExtractContent($url) {
$html = $this->getSimpleHTMLDOM($url);
2016-08-03 22:39:03 +02:00
if(!$html)
$this->returnServerError('Could not acquire content from url: ' . $url . '!');
2016-08-03 22:39:03 +02:00
$content = $html->find('article', 0);
if(!$content)
$this->returnServerError('Could not find \'section\'!');
2016-08-03 22:39:03 +02:00
$text = preg_replace('#<script(.*?)>(.*?)</script>#is', '', $content->innertext);
$text = strip_tags($text, '<p><a><img>');
return $text;
2015-11-04 10:47:21 +01:00
}
2016-08-03 22:39:03 +02:00
public function collectData(array $param){
$html = $this->getSimpleHTMLDOM('http://www.nicematin.com/derniere-minute/rss') or $this->returnServerError('Could not request NiceMatin.');
2016-08-03 22:39:03 +02:00
$limit = 0;
foreach($html->find('item') as $element) {
if($limit < 10) {
// We need to fix the 'link' tag as simplehtmldom cannot parse it (just rename it and load back as dom)
$element_text = $element->outertext;
$element_text = str_replace('<link>', '<url>', $element_text);
$element_text = str_replace('</link>', '</url>', $element_text);
$element = str_get_html($element_text);
$item = new \Item();
$item->title = $element->find('title', 0)->innertext;
$item->uri = $element->find('url', 0)->innertext;
$item->timestamp = strtotime($element->find('pubDate', 0)->plaintext);
$item->content = $this->NiceMatinExtractContent($item->uri);
$this->items[] = $item;
$limit++;
}
}
}
}