php爬虫curl获取某个class为content的内容

最新推荐文章于 2021-05-13 15:18:10 发布

weixin_42648409

最新推荐文章于 2021-05-13 15:18:10 发布

阅读量1.6k

点赞数

 header( "Content-type:text/html;Charset=utf-8" );
        $ch = curl_init();
        $url ='网址';
        curl_setopt ( $ch , CURLOPT_USERAGENT ,"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.113 Safari/537.36" );
        curl_setopt($ch,CURLOPT_URL,$url);
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
        $content=curl_exec($ch);
        $regex4="/<div class=\"content\".*?>.*?<\/div>/ism";//获取class为content的内容
        preg_match_all($regex4,$content,$matchs,PREG_SET_ORDER);//匹配该表所用的正则