php的curl携带header请求头信息实现http访问

 导读：

curl请求时添加请求头信息可以模拟真人操作，不容易被当成是爬虫机器人（采集），从而可以绕过Incapsula等安全验证机制。

1、首先使用浏览器（示例使用的是火狐浏览器）访问接口网址，使用F12调试，查看请求头信息，如下：

2、实现代码：

  

   

    

     

    
    

     

      <?php
     
    
   

    

     

    
    

     

      /**
     
    
   

    

     

    
    

     

       * 开始访问请求
     
    
   

    

     

    
    

     

       * @param $url
     
    
   

    

     

    
    

     

       * @return bool|string
     
    
   

    

     

    
    

     

       */
     
    
   

    

     

    
    

     

      function fetch_url($url) {
     
    
   

    

     

    
    

     

      	$header = FormatHeader($url);
     
    
   

    

     

    
    

     

      	$useragent = 
      'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:83.0) Gecko/20100101 Firefox/83.0';
     
    
   

    

     

    
    

     

      	$timeout= 
      120;
     
    
   

    

     

    
    

     

      	$ch = curl_init($url);
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_FAILONERROR, 
      true);
     
    
   

    

     

    
    

     
	
      //设置请求头信息
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_HTTPHEADER, $header);
     
    
   

    

     

    
    

     
	
      //不取得返回头信息 
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_HEADER, 
      0);
     
    
   

    

     

    
    

     
	
      // 关闭https验证
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, 
      false);
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 
      false);
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 
      true );
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_ENCODING, 
      "" );
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_RETURNTRANSFER, 
      true );
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_AUTOREFERER, 
      true );
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout );
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_TIMEOUT, $timeout );
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_MAXREDIRS, 
      10 );
     
    
   

    

     

    
    

     

      	curl_setopt($ch, CURLOPT_USERAGENT, $useragent);
     
    
   

    

     

    
    

     

      	$content = curl_exec($ch);
     
    
   

    

     

    
    

     
	
      if(curl_errno($ch))
     
    
   

    

     

    
    

     

      	{
     
    
   

    

     

    
    

     
		
      echo 
      'Error:' . curl_error($ch);
     
    
   

    

     

    
    

     

      	}
     
    
   

    

     

    
    

     
	
      else
     
    
   

    

     

    
    

     

      	{
     
    
   

    

     

    
    

     
		
      return $content;        
     
    
   

    

     

    
    

     

      	}
     
    
   

    

     

    
    

     

      	curl_close($ch);
     
    
   

    

     

    
    

     

      }
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      //添加请求头
     
    
   

    

     

    
    

     

      function FormatHeader($url)
     
    
   

    

     

    
    

     

      {
     
    
   

    

     

    
    

     
 
      // 解析url
     
    
   

    

     

    
    

     

       $temp = parse_url($url);
     
    
   

    

     

    
    

     

       $query = 
      isset($temp[
      'query']) ? $temp[
      'query'] : 
      ''; 
     
    
   

    

     

    
    

     

       $path = 
      isset($temp[
      'path']) ? $temp[
      'path'] : 
      '/'; 
     
    
   

    

     

    
    

     

       $header = 
      array (
     
    
   

    

     

    
    

     
 
      "POST {$path}?{$query} HTTP/1.1",
     
    
   

    

     

    
    

     
 
      "Host: {$temp['host']}",
     
    
   

    

     

    
    

     
 
      "Referer: http://{$temp['host']}/",
     
    
   

    

     

    
    

     
 
      "Content-Type: text/xml; charset=utf-8",
     
    
   

    

     

    
    

     
 
      'Accept: application/json, text/javascript, */*; q=0.01',
     
    
   

    

     

    
    

     
 
      'Accept-Encoding:gzip, deflate, br',
     
    
   

    

     

    
    

     
 
      'Accept-Language:zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
     
    
   

    

     

    
    

     
 
      'Connection:keep-alive',
     
    
   

    

     

    
    

     
 
      'User-Agent: Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:83.0) Gecko/20100101 Firefox/83.0',
     
    
   

    

     

    
    

     
 
      'X-Requested-With: XMLHttpRequest',
     
    
   

    

     

    
    

     

       );
     
    
   

    

     

    
    

     
 
      return $header;
     
    
   

    

     

    
    

     

      }
     
    
   

    

     

    
    

     

      ?>
     
    
  

3、调用示例：

  

   

    

     

    
    

     

      <?php
     
    
   

    

     

    
    

     

      //lcg_value() 返回范围为 (0, 1) 的一个伪随机数
     
    
   

    

     

    
    

     

      $url=
      "http://www.xxx.com/getdata.php?v=".lcg_value();
     
    
   

    

     

    
    

     

      //访问网址
     
    
   

    

     

    
    

     

      $html = fetch_url($url);