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

Merge pull request #321 from LogMANOriginal/NiceMatinBridge

Browse source 
Nice matin bridge
This commit is contained in:
Mitsu 2016-08-03 22:58:03 +02:00 committed by GitHub
commit 9495e830e7
1 changed files with 43 additions and 45 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

88
bridges/NiceMatinBridge.php
View file

@ -2,61 +2,59 @@
class NiceMatinBridge extends BridgeAbstract{
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 = "2014-05-26";
$this->update = "2016-08-03";
}
public function collectData(array $param){
function NiceMatinExtractContent($url) {
$html = $this->file_get_html($url);
if(!$html)
$this->returnError('Could not acquire content from url: ' . $url . '!', 404);
$content = $html->find('article', 0);
if(!$content)
$this->returnError('Could not find \'section\'!', 404);
$text = preg_replace('#<script(.*?)>(.*?)</script>#is', '', $content->innertext);
$text = strip_tags($text, '<p><a><img>');
return $text;
}
function NiceMatinUrl($string) {
$string = str_replace('</link>', '', $string);
//$string = str_replace('.+', '', $string);
$string = preg_replace('/html.*http.*/i','html',$string);
$string = preg_replace('/.*http/i','http',$string);
return $string;
}
public function collectData(array $param){
$html = $this->file_get_html('http://www.nicematin.com/derniere-minute/rss') or $this->returnError('Could not request NiceMatin.', 404);
$limit = 0;
function NiceMatinExtractContent($url) {
$html2 = $this->file_get_html($url);
$text = $html2->find('figure[itemprop=associatedMedia]', 0)->innertext;
$text .= $html2->find('div[id=content-article]', 0)->innertext;
return $text;
}
foreach($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);
$html = $this->file_get_html('http://www.nicematin.com/derniere-minute/rss') or $this->returnError('Could not request NiceMatin.', 404);
$limit = 0;
$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;
$limit++;
}
}
}
foreach($html->find('item') as $element) {
if($limit < 10) {
$item = new \Item();
//$item->title = NiceMatinStripCDATA($element->find('title', 0)->innertext);
$item->title = $element->find('title', 0)->innertext;
$item->uri = NiceMatinUrl($element->plaintext);
public function getName(){
return 'NiceMatin';
}
$item->timestamp = strtotime($element->find('pubDate', 0)->plaintext);
$item->content = NiceMatinExtractContent($item->uri);
$this->items[] = $item;
$limit++;
}
}
public function getURI(){
return 'http://www.nicematin.com/';
}
}
public function getName(){
return 'NiceMatin';
}
public function getURI(){
return 'http://www.nicematin.com/';
}
public function getCacheDuration(){
return 3600; // 1 hour
}
public function getCacheDuration(){
return 3600; // 1 hour
}
}