[乐意黎]php curl 以及refer设置

文章地址: http://blog.csdn.net/aerchi/article/details/51644423
set_time_limit(0);
// GET测试淘宝详情页抓取
$url  =  "http://item.taobao.com/item.htm?id=37530539791" ;
$url  =  "http://item.taobao.com/item.htm?id=14861616067" ;

//curl 伪造useragent
$useragent  =  array (
    'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0)' ,
    'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2)' ,
    'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)' ,
    'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1' ,
    'Opera/9.27 (Windows NT 5.2; U; zh-cn)' ,
    'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)' ,
    'Mozilla/5.0 (Windows; U; Windows NT 5.2) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13 ' ,
    'Mozilla/5.0 (Windows; U; Windows NT 5.2) AppleWebKit/525.13 (KHTML, like Gecko) Version/3.1 Safari/525.13'
);

header( "Content-type: text/html; charset=utf-8" );
$cookiefile  =  realpath ( "./" ). "/Application/Runtime/Temp/cookie.txt" ; //创建一个用于存放cookie信息的临时文件,
if  (! file_exists ( $cookiefile )){
    $file  = @ file_put_contents ( $cookiefile ,  "" );
}

$ch  = curl_init();
//设置选项，包括URL
curl_setopt( $ch , CURLOPT_URL,  $url );
curl_setopt( $ch , CURLOPT_TIMEOUT,  $timeout );
curl_setopt( $ch , CURLOPT_HEADER, 0);
curl_setopt( $ch , CURLOPT_NOBODY,0);
curl_setopt( $ch , CURLOPT_MAXREDIRS, 300);
curl_setopt( $ch , CURLOPT_RETURNTRANSFER, true);  //获取数据返回流形式
curl_setopt( $ch , CURLOPT_AUTOREFERER, true);  //重定向时，自动设置header中的Referer:信息
curl_setopt( $ch , CURLOPT_FOLLOWLOCATION, true);  //启用时会将服务器服务器返回的"Location: "放在header中递归的返回给服务器，使用CURLOPT_MAXREDIRS可以限定递归返回的数量

// 设置iP和useragent
/*curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)');
curl_setopt($ch, CURLOPT_HTTPHEADER, array('X-FORWARDED-FOR:28.58.88.'.$r, 'CLIENT-IP:225.28.58.'.$r));  //构造IP
curl_setopt($ch, CURLOPT_REFERER, "http://www.baidu.com");   //构造来路
curl_setopt($ch, CURLOPT_USERAGENT, array_rand($useragent));*/

// 设置代理
/*curl_setopt($ch, CURLOPT_HTTPPROXYTUNNEL, 1);
curl_setopt($ch, CURLOPT_PROXY, '218.213.168.131:80');*/
//curl_setopt($ch, CURLOPT_PROXYUSERPWD, 'user:password');

// 对于cookie保存
curl_setopt( $ch , CURLOPT_COOKIESESSION, true);
curl_setopt( $ch , CURLOPT_COOKIEFILE,  $cookiefile ); //关闭连接时，将服务器端返回的cookie保存在以下文件中
curl_setopt( $ch , CURLOPT_COOKIEJAR,  $cookiefile );

//执行并获取HTML文档内容
for  ( $i =0; $i <=5; $i ++){
    curl_setopt( $ch , CURLOPT_USERAGENT,  $useragent [ $i ]);
    $output  = curl_exec( $ch );
    if  (! empty ( $output )){
        break ;
    }
}
//释放curl句柄
$info  = curl_getinfo( $ch );
curl_close( $ch );

echo "

";print_r($info);die($output);
 
  
 
 
 
  
 
 
 
  
 
 
  
 
   
$url  =  "http://item.taobao.com/item.htm?id=14861616067" ;
echo  curl_get( $url );
 
  
 
  
 
  得到的数据中有 
  
 
   
  
 
  T浦力顿500g 成犬幼犬狗粮泰迪贵宾比熊金毛萨摩耶博美 批发散装 
  
 
  证明访问是没有问题的 
  
 
  
 
  
 
   
function  curl_get( $durl ,  $data = array ()) {
  $cookiejar  =  realpath ( 'cookie.txt' );
  $t  =  parse_url ( $durl );
  $ch  = curl_init();
  curl_setopt( $ch , CURLOPT_URL, $durl );
  curl_setopt( $ch , CURLOPT_TIMEOUT,5);
  curl_setopt( $ch , CURLOPT_SSL_VERIFYPEER, 0);
  curl_setopt( $ch , CURLOPT_USERAGENT,  $_SERVER [ 'HTTP_USER_AGENT' ]);
  curl_setopt( $ch , CURLOPT_REFERER,  "http://$t[host]/" );
  curl_setopt( $ch , CURLOPT_COOKIEFILE,  $cookiejar );
  curl_setopt( $ch , CURLOPT_COOKIEJAR,  $cookiejar );
  curl_setopt( $ch , CURLOPT_RETURNTRANSFER,1);
  curl_setopt( $ch , CURLOPT_FOLLOWLOCATION, true);
  if ( $data ) {
    curl_setopt( $ch , CURLOPT_POST, 1);
    curl_setopt( $ch , CURLOPT_POSTFIELDS,  $data );
  }
  $r  = curl_exec( $ch );
  curl_close( $ch );
  return  $r ;
}
 
  
 
  
 
  
 
  
 
 
  

    referer是php用来判断页面上级来源页面的一个超级变局变量了，我们可以使用referer来判断是从那个页面进入到此页面了，这样我们可以进行更好的跟踪了，下面我就来给各位朋友整理了几种伪造页面referer来源例子，希望例子能给各位朋友。 
  
 
  
 
   
file_get_contents方法
 
   
 
    
 
     
 
      
 代码如下
 
      
  
 
     
 
     
 
      
 
$opt=array('http'=>array('header'=>"Referer: $refer")); 
 $context=stream_context_create($opt); 
 $file_contents = file_get_contents($url,false, $context);
 
 
     
 
    
 
   
 
   
分析:
 
   
file_get_contents中stream_context_create就伪造来源的重要参数了，这个什么好说的非常的简单。
 
   
CURL方式
 
   
 
    
 
     
 
      
 代码如下
 
      
  
 
     
 
     
 
      
 
$ch = curl_init();
 curl_setopt ($ch, CURLOPT_URL, "http://www.111cn.net");
 curl_setopt ($ch, CURLOPT_REFERER, "http://www.111cn.net/");
 curl_exec ($ch);
 curl_close ($ch);
 
 
     
 
    
 
   
 
   
分析:
 
   
curl伪造来源页面非常的简单这是它的优点了，所以我们只要在页面加上curl_setopt ($ch, CURLOPT_REFERER, "http://www.111cn.net/");就可以了。
 
   
SOCKET方式
 
   
 
    
 
     
 
      
 代码如下
 
      
  
 
     
 
     
 
      
 
$server = 'www.111cn.net';
 $host = 'www.111cn.net';
 $target = 'index.php';
 $referer = 'http://www.111cn.net/'; // Referer
 $port = 80;
 $fp = fsockopen($server, $port, $errno, $errstr, 30);
 if (!$fp){
 echo "$errstr ($errno)＼n";
 }else{
 $out = "GET $target HTTP/1.1＼r＼n";
 $out .= "Host: $host＼r＼n";
 $out .= "Referer: $referer＼r＼n";
 $out .= "Connection: Close＼r＼n＼r＼n";
 fwrite($fp, $out);
 while (!feof($fp)){
 echo fgets($fp, 128);
 }
 fclose($fp);
 }
 
 
     
 
    
 
   
 
   
友情提示：三种性能比对fsockopen是最好的哦。
 
   
我们再使用
 
   
 
    
 
     
 
      
 代码如下
 
      
  
 
     
 
     
 
      
 
 echo "
";
 echo $_SERVER["HTTP_REFERER"];
 ?>
 
 
     
 
    
 
   
 
  
 ------------------------------------------------------------------- 
  
 
  
 
 
  

    php curl伪造referer与来源IP非常的简单，今天做一个图片采集的也有做过，下面我把两个例子都整理一下，供大家参考。 
  
 
  
 
   
例子1
 
   
 
    
 
     
 
      
 代码如下
 
      
  
 
     
 
     
 
      
 [one.php]
  $post_data = array (
 "user" => "gongwen",
 "pwd" => "123456"
 );
 $header_ip = array(
 'CLIENT-IP:88.88.88.88',
 'X-FORWARDED-FOR:88.88.88.88',
 );
 $referer='http://www.111cn.net';
 $ch = curl_init();
 curl_setopt ($ch, CURLOPT_URL, 'http://localhost/curl/two.PHP');
 //伪造来源referer
 curl_setopt ($ch,CURLOPT_REFERER,$referer);
 //伪造来源ip
 curl_setopt($ch, CURLOPT_HTTPHEADER, $header_ip);
 //提交post传参
 curl_setopt($ch, CURLOPT_POSTFIELDS, $post_data);
 //加上这个表示执行curl_exec是把输出做为返回值,不会输出到浏览器
 curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
 $out_put=curl_exec ($ch);
 curl_close ($ch);
 echo $out_put;
 [two.php]
  //请求来源referer
 echo '[HTTP_REFERER]
';
 echo $_SERVER['HTTP_REFERER'];
 //请求来源ip
 //[注]此处的IP打印顺序是目前很多开源系统的IP获取顺序 
 echo '
[IP]
';
 echo $_SERVER['HTTP_CLIENT_IP'];
 echo '
';
 echo $_SERVER['HTTP_X_FORWARDED_FOR'];
 echo '
';
 echo $_SERVER['REMOTE_ADDR'];
 //POST数据
 echo '
[POST]
';
 var_dump($_POST);
 echo '
';
 
     
 
    
 
   
 
   

 浏览器访问one.php。页面打印如下:
 例子2
 
   
 
    
 
     
 
      
 代码如下
 
      
  
 
     
 
     
 
      
 function getImagesUrl( $url,$userinfo,$header)
 {
 $ch = curl_init();
 $timeout = 1;
 curl_setopt ($ch, CURLOPT_URL, "$url");
 curl_setopt ($ch, CURLOPT_HTTPHEADER, $header);
 curl_setopt ($ch, CURLOPT_REFERER, "http://www.baidu.com/"); 
 curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
 curl_setopt ($ch, CURLOPT_USERAGENT, "$userinfo");
 curl_setopt ($ch, CURLOPT_CONNECTTIMEOUT, $timeout); 
 $contents = curl_exec($ch);
 curl_close($ch);
 //echo $contents;
 return $contents ;
 
 }
 function saveurl( $handle ,$filename)
 {
 $fp = fopen($filename,"w");
 fwrite($fp,$handle);
 unset($fp);
 unset($handle);
 }
 $binfo =array('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; InfoPath.2; AskTbPTV/5.17.0.25589; Alexa Toolbar)','Mozilla/5.0 (Windows NT 5.1; rv:22.0) Gecko/20100101 Firefox/22.0','Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET4.0C; Alexa Toolbar)','Mozilla/4.0(compatible; MSIE 6.0; Windows NT 5.1; SV1)',$_SERVER['HTTP_USER_AGENT']);
 //123.125.68.*
 //125.90.88.* 
 $cip = '123.125.68.'.mt_rand(0,254);
 $xip = '125.90.88.'.mt_rand(0,254);
 $header = array( 
 'CLIENT-IP:'.$cip, 
 'X-FORWARDED-FOR:'.$xip, 
 ); 
 $u = $binfo[mt_rand(0,3)];
 $get_file = getImagesUrl($value,$u,$header);
 saveurl($get_file,'a.jpg');
 
     
 
    
 
   
 
  
 文章地址: http://blog.csdn.net/aerchi/article/details/51644423