模拟百度蜘蛛抓取页面(模拟百度蜘蛛抓取页面怎么设置)
时间:2022-11-15 22:44:52 阅读:295
ch = curl_init(); $ip = rand(0,255).'.'.rand(0,255).'.'.rand(0,255).'.'.rand(0,255) ; // 百度 蜘蛛 $this->timeout = 15; curl_setopt($this->ch,CURLOPT_URL,$url); curl_setopt($this->ch,CURLOPT_TIMEOUT,0); //伪造百度蜘蛛IP curl_setopt($this->ch,CURLOPT_HTTPHEADER,array('X-FORWARDED-FOR:'.$this->ip.'','CLIENT-IP:'.$this->ip.'')); //伪造百度蜘蛛头部 curl_setopt($this->ch,CURLOPT_USERAGENT,"Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)"); curl_setopt($this->ch,CURLOPT_RETURNTRANSFER,1); curl_setopt($this->ch,CURLOPT_HEADER,0); curl_setopt($this->ch,CURLOPT_CONNECTTIMEOUT,$this->timeout); curl_setopt($this->ch,CURLOPT_SSL_VERIFYPEER,false); $content = curl_exec($this->ch); if($content === false) {//输出错误信息 $no = curl_errno($this->ch); switch(trim($no)) { case 28 : $this->error = '访问目标地址超时'; break; default : $this->error = curl_error($this->ch); break; } echo $this->error; } else { $this->succ = true; return $content; } } public function getcurl($url){ return $this->_GetContent($url); } } $api = "https://www.whqmjs.cn"; $Curlcontent = new Curlcontent(); $data = $Curlcontent->getcurl($api); ?>
网友评论