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

[NiceMatinBridge] code simplification

Browse source 
Signed-off-by: Pierre Mazière <pierre.maziere@gmx.com>
This commit is contained in:
Pierre Mazière 2016-08-29 14:03:17 +02:00
parent 3fb8c5b916
commit 57fd0255ff
1 changed files with 19 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
bridges/NiceMatinBridge.php
View file

@ -9,11 +9,11 @@ class NiceMatinBridge extends BridgeAbstract{
private function NiceMatinExtractContent($url) {
$html = $this->getSimpleHTMLDOM($url);
if(!$html)
$this->returnServerError('Could not acquire content from url: ' . $url . '!');
return 'Could not acquire content from url: ' . $url . '!';
$content = $html->find('article', 0);
if(!$content)
$this->returnServerError('Could not find \'section\'!');
return 'Could not find \'section\'!';
$text = preg_replace('#<script(.*?)>(.*?)</script>#is', '', $content->innertext);
$text = strip_tags($text, '<p><a><img>');
@ -21,25 +21,27 @@ class NiceMatinBridge extends BridgeAbstract{
}
public function collectData(){
$html = $this->getSimpleHTMLDOM('http://www.nicematin.com/derniere-minute/rss') or $this->returnServerError('Could not request NiceMatin.');
$html = $this->getSimpleHTMLDOM($this->uri.'derniere-minute/rss')
or $this->returnServerError('Could not request NiceMatin.');
$limit = 0;
foreach($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);
if($limit >= 10) {
break;
}
// 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 = array();
$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++;
}
$item = array();
$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++;
}
}
}