PHP 小方法之 仿百度蜘蛛采集

if(!function_exists('_GetContent')){
     function _GetContent( $url ){
        $ch = curl_init();
        $ip = '220.181.108.91';  // 百度蜘蛛
        $timeout = 15;
        curl_setopt($ch,CURLOPT_URL,$url);
        curl_setopt($ch,CURLOPT_TIMEOUT,0);
        //伪造百度蜘蛛IP
        curl_setopt($ch,CURLOPT_HTTPHEADER,array('X-FORWARDED-FOR:'.$ip.'','CLIENT-IP:'.$ip.''));
        //伪造百度蜘蛛头部
        curl_setopt($ch,CURLOPT_USERAGENT,"Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)");
        curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
        curl_setopt($ch,CURLOPT_HEADER,0);
        curl_setopt($ch,CURLOPT_CONNECTTIMEOUT,$timeout);
        $content = curl_exec($ch);
        if($content === false)
        {//输出错误信息
            $no = curl_errno($ch);
            switch(trim($no))
            {
                case 28 : $error = '访问目标地址超时'; break;
                default : $error = curl_error($ch); break;
            }
            echo $error;
        }
        else
        {
            $succ = true;
            return $content;
        }
    }
}

 

转载于:https://www.cnblogs.com/zouzhe0/p/6202939.html