revize
040f4da73d
1 změnil soubory, kde provedl 24 přidání a 30 odebrání
|
@ -11,42 +11,36 @@ class Rue89Bridge extends BridgeAbstract{
|
|||
|
||||
}
|
||||
|
||||
public function collectData(array $param){
|
||||
function Rue89StripCDATA($string) {
|
||||
$string = str_replace('<![CDATA[', '', $string);
|
||||
$string = str_replace(']]>', '', $string);
|
||||
return $string;
|
||||
}
|
||||
function Rue89ExtractContent($url) {
|
||||
$html2 = file_get_html($url);
|
||||
//$text = $html2->find('div[class=text]', 0)->innertext;
|
||||
private function rue89getDatas($url){
|
||||
|
||||
$url = "http://api.rue89.nouvelobs.com/export/mobile2/node/" . str_replace(" ", "", substr($url, -8)) . "/full";
|
||||
$datas = json_decode(file_get_contents($url), true);
|
||||
|
||||
return $datas["node"];
|
||||
|
||||
foreach($html2->find('img') as $image) {
|
||||
$src = $image->getAttribute('data-src');
|
||||
if($src) $image->src = $src;
|
||||
}
|
||||
$text = $html2->find('div.content', 0)->innertext;
|
||||
|
||||
public function collectData(array $param){
|
||||
|
||||
$html = file_get_html('http://api.rue89.nouvelobs.com/feed') or $this->returnError('Could not request Rue89.', 404);
|
||||
|
||||
$text = str_replace('href="/', 'href="http://rue89.nouvelobs.com/', $text);
|
||||
$text = str_replace('src="/', 'src="http://rue89.nouvelobs.com/', $text);
|
||||
$text = preg_replace('@<script[^>]*?>.*?</script>@si', '', $text);
|
||||
$text = strip_tags($text, '<h1><h2><strong><p><b><a><blockquote><img><em><ul><ol>');
|
||||
return $text;
|
||||
}
|
||||
$html = file_get_html('http://rue89.feedsportal.com/c/33822/f/608948/index.rss') or $this->returnError('Could not request Rue89.', 404);
|
||||
$limit = 0;
|
||||
foreach($html->find('item') as $element) {
|
||||
if($limit < 5) {
|
||||
$item = new \Item();
|
||||
$item->title = Rue89StripCDATA($element->find('title', 0)->innertext);
|
||||
$item->name = Rue89StripCDATA($element->find('dc:creator', 0)->innertext);
|
||||
$item->uri = str_replace('#commentaires', '', Rue89StripCDATA($element->find('comments', 0)->plaintext));
|
||||
$item->timestamp = strtotime($element->find('pubDate', 0)->plaintext);
|
||||
$item->content = Rue89ExtractContent($item->uri);
|
||||
$this->items[] = $item;
|
||||
$limit++;
|
||||
}
|
||||
|
||||
if($limit < 5) {
|
||||
|
||||
$datas = $this->rue89getDatas(str_replace('#commentaires', '', ($element->find('comments', 0)->plaintext)));
|
||||
|
||||
$item = new \Item();
|
||||
$item->title = $datas["title"];
|
||||
$item->author = $datas["author"][0]["name"];
|
||||
$item->timestamp = $datas["updated"];
|
||||
$item->content = $datas["body"];
|
||||
$item->uri = $datas["url"];
|
||||
|
||||
$this->items[] = $item;
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
|
Načítání…
Odkázat v novém problému