PHP爬虫类库“phpQuery”

364 阅读1分钟
		$url = "http://caibaojian.com/c/news/";
      
        $data = Http_Spider($url);
        Vendor('phpQuery.phpQuery');
        // var_dump($data,$url);die;
        \phpQuery::newDocumentHTML($data);


        $arr = array();
        $list = pq('#content article');
        foreach ($list as $li) {
            $title = pq($li)->find('.entry-title span')->text();
            $desc = pq($li)->find('.entry-content p')->text();
            $url = pq($li)->find('.entry-title a')->attr('href');
            $date = pq($li)->find('.entry-date')->text();
            $id = intval(preg_replace('/\D/s', '', $url));


            $tmp = array(
                'title' => $title,
                'date' => $date,
                'desc' => $desc,
                'daily_id' => $id,
                'url'=>$url
            );
            array_push($arr, $tmp);
        }