自定义HTTP抓包跟过滤

程序员文章站 2022-06-08 16:50:30

...

自定义HTTP抓包和过滤
定义一个http抓包类，发送数据到一个自定义的接受脚本，可以发送成功，并收取数据，但是发送到外网，却不行，分析过在浏览器下发送HTTP请求时的request header 信息，通过模拟请求，但超时...


//定义一个HTTP抓包类，其实也可以用curl。。。。。

ini_set('error_reporting', E_ALL);
class Httpwrap
{
	private $hostInfo=null;

	private $requestLine=null;
	private $requestHeader=null;
	private $emptyLine="\r\n";
	private $requestBody=null;
	private $requestEntity=null;

	private $responseEntity=null;
	private $responseHeader=null;
	private $responseBody=null;
	private $emptyLinePos=null;

	private $connect=null;
	private $errNo=null;
	private $errStr=null;


	public function __construct($url)
	{
		$this->hostInfo=parse_url($url);
		$this->setRequestHeader(array('Host' => $this->hostInfo['host']));
		$this->setRequestHeader(array('Connection' => 'keep-alive'));
	}
	//设置HTTP请求行信息，例如： GET /resources  HTTP/1.1
	//但为了避免漏掉url中?开始的查询信息，有必要进行判断
	public function setRequestLine($method)
	{
		//如果是POST请求，则自动添加content-type头信息
		if(strtolower($method)=='post')
		{
			$this->setRequestHeader(array('Content-type' => 'application/x-www-form-urlencoded'));
		}
		if(!empty($this->hostInfo['query']))
		{
			$this->requestLine=strtoupper($method)."  ".$this->hostInfo['path']."?".$this->hostInfo['query']."  HTTP/1.1 \r\n";
		}
		else
		{
			$this->requestLine=strtoupper($method)."  ".$this->hostInfo['path']."  HTTP/1.1 \r\n";
		}
	}
	//设置HTTP请求头。
	//接收参数是数组类型，通过迭代拼接key:value，并换行
	public function setRequestHeader($header)
	{
		foreach($header as $key => $value)
		{
			$this->requestHeader .=$key.":".$value."\r\n";
		}
	}
	//设置HTTP请求体
	//接收参数是数组类型，通过迭代拼接key=value,因为最后一席拼接会有一个多余的&，所以有必要去掉
	public function setRequestBody($body)
	{
		foreach($body as $key => $value)
		{
			$this->requestBody .=$key.'='.$value.'&';
		}
		$offset=strrpos($this->requestBody, '&');
		$this->requestBody=substr($this->requestBody, 0, $offset);
	}
	//组装  请求行+请求头+请求体，并根据请求体的长度，自动填充请求头的content-length字段
	public function setRequestEntity()
	{
		if(!empty($this->requestBody))
		{
			$contentLength=strlen($this->requestBody);
			$this->setRequestHeader(array('Content-length' => $contentLength));

			$this->requestEntity=$this->requestLine.$this->requestHeader."\r\n".$this->requestBody;
		}
		else
		{
			$this->requestEntity=$this->requestLine.$this->requestHeader."\r\n";
		}
	}
	//解析主机名的函数，暂时没有用上.......
	public function parseHost($url)
	{
		$pat='#http://([^/]+)#i';
		if(preg_match($pat, $url, $match))
		{
			return $match[1];
		}
		else
		{
			echo '匹配主机信息失败
';
		}
	}
	//创建到主机的连接
	public function createConnect()
	{
		$this->connect=fsockopen($this->hostInfo['host'], 80, $this->errNo, $this->errStr) or die('连接主机失败'.$this->errStr);
	}
	//发送请求
	public function sendRequest()
	{
		$this->setRequestEntity();
		echo $this->requestEntity;
		exit();
		$this->createConnect();
		$entityLength=strlen($this->requestEntity);
		if($entityLength != fwrite($this->connect, $this->requestEntity, $entityLength))
		{
			die('写入数据失败
');
		}
		else
		{
			$this->receiveResponse();
		}
	}
	//接受请求，并依次拼接响应体
	public function receiveResponse()
	{
		while(!feof($this->connect))
		{
			$this->responseEntity .= fread($this->connect, 1024);
		}
	}
	//计算响应头与响应体之间的空行的位置
	public function calculateEmptyLinePos()
	{
		$this->emptyLinePos=strpos($this->responseEntity,"\r\n\r\n",0);
	}
	//接受响应体的头部....
	public function receiveResponseHeader()
	{
		$this->calculateEmptyLinePos();
		$this->responseHeader=substr($this->responseEntity, 0, $this->emptyLinePos);
		echo $this->responseHeader;
	}
	//接收响应体的body部分
	public function receiveResponseBody()
	{
		$this->calculateEmptyLinePos();
		$this->responseBody=substr($this->responseEntity, $this->emptyLinePos);
	}
	//返回请求结果
	public function getResponse()
	{
		return $this->responseEntity;
	}


	public function parseResponse()
	{}
	public function __destruct()
	{
		//fclose($this->connect);
	} 
}
set_time_limit(60);
$http=new Httpwrap("http://www.mmkao.com/Beautyleg/");
//设置HTTP请求行
$http->setRequestLine("get");
//设置HTTP头
$http->setRequestHeader(array("Accept" => "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"));
$http->setRequestHeader(array("Accept-Language" => "zh-cn,zh;q=0.8,en-us;q=0.5,en;q=0.3"));
$http->setRequestHeader(array("Accept-Encoding" => "gzip, deflate"));
$http->setRequestHeader(array("User-Agent" => "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.101 Safari/537.36"));
//$http->setRequestHeader(array("Cookie" => "BAIDU_DUP_lcr=http://www.baidu.com/s?wd=beautyleg&rsv_spt=1&issp=1&f=3&rsv_bp=0&rsv_idx=2&ie=utf-8&tn=baiduhome_pg&rsv_enter=1&rsv_sug3=6&rsv_sug4=415&rsv_sug1=3&oq=beauty&rsv_sug2=0&rsp=0&inputT=2363; safedog-flow-item=8471BA510DA33350ED344AC374D3044A; bdshare_firstime=1415165097782; cscpvrich_fidx=6; AJSTAT_ok_pages=2; AJSTAT_ok_times=2; CNZZDATA3811623=cnzz_eid%3D253823549-1415164312-http%253A%252F%252Fwww.baidu.com%252F%26ntime%3D1415169712"));
//发送数据
$http->sendRequest();
//$http->receiveResponseHeader();

?>

通过这个类给领一个自定义的脚本，可以发送和接收数据，领一个脚本如下：

if(!empty($_POST))
{
	$str=implode(',',$_POST);
	file_put_contents('./post.txt', $str,FILE_APPEND);
	echo $str;
}

?>
但是给这个网站发送请求时，却超时：网站是：
http://www.mmkao.com/Beautyleg/
通过chrome给这个网站首页发送请求时的header头信息：
Accept:text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8
Accept-Encoding:gzip,deflate,sdch
Accept-Language:zh,en;q=0.8,zh-TW;q=0.6,zh-CN;q=0.4,ja;q=0.2
Cache-Control:max-age=0
Connection:keep-alive
Cookie:BAIDU_DUP_lcr=http://www.baidu.com/s?wd=beautyleg&rsv_spt=1&issp=1&f=3&rsv_bp=0&rsv_idx=2&ie=utf-8&tn=baiduhome_pg&rsv_enter=1&rsv_sug3=6&rsv_sug4=415&rsv_sug1=3&oq=beauty&rsv_sug2=0&rsp=0&inputT=2363; safedog-flow-item=8471BA510DA33350ED344AC374D3044A; bdshare_firstime=1415165097782; cscpvrich_fidx=7; AJSTAT_ok_pages=3; AJSTAT_ok_times=2; CNZZDATA3811623=cnzz_eid%3D253823549-1415164312-http%253A%252F%252Fwww.baidu.com%252F%26ntime%3D1415169712
DNT:1
Host:www.mmkao.com
User-Agent:Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.101 Safari/537.36
Response Headersview source

//通过相同的包装，并调用Httpwrap发送请求时，却提示超时，是在不知道哪里出问题........

针对这个网站写了一个过滤出图片链接的类：

class Parseimage
{
	private $responseBody=null;
	private $imgLink=null;
	private $pageNum=null;
	private header=null;
	private body=null;

	public function __construct($body)
	{
		$this->responseBody=$body;
	}
	//匹配图片src开始的链接地址
	public function feedImage()
	{
		$pat='#		if(preg_match_all($pat, $body, $match))
		{
			foreach($match[2] as $link)
			{
				$this->imgLink[]=$link;
			}
		}
		else
		{
			echo '匹配失败图片链接地址失败'."
";
		}
	}
	//提取head部分
	public function filterHeader($body)
	{
		$pat='#[\s\S]+#im';
		if(preg_match($pat, $body, $match))
		{
			$this->header=$match[0];
		}
		else
		{
			echo '匹配head部分失败'."
";
		}
	}
	//提取body部分
	public function filterBody($body)
	{
		$pat='#[\s\S]+#im';
		if(preg_match($pat, $body, $match))
		{
			$this->body=$match[0];
		}
		else
		{
			echo '匹配body部分失败'."
";
		}
	}
	//提取分页信息，这个只能针对性的匹配，不能通用
	public function rollPage($body)
	{
		$pat='#[\x{4e00}-\x{9fa5}]+\s*\d\s+?/\s+?\d+\s*[\x{4e00}-\x{9fa5}]*#ui';
		if(preg_match($pat, $body, $match))
		{
			$patNum='#/\s*(\d\d*)#';
			if(preg_match($patNum, $match[0], $num))
			{
				$this->pageNum=$num[1];
			}
			else
			{
				echo '提取分页具体值失败'."
";
			}
		}
		else
		{
			echo '提取分页统计失败'."
";
		}
	}

?>



附注：  这两个类，，都通过了内网的测试，并成功过滤出图片的链接，但是给http://www.mmkao.com/Beautyleg/发送请求时，却提示超时，，不知道哪里出了问题。。。。。。

------解决思路----------------------

$url = 'http://www.mmkao.com/Beautyleg/';
print_r(get_headers($url));

Array
(
    [0] => HTTP/1.1 200 OK
    [1] => Connection: close
    [2] => Date: Wed, 05 Nov 2014 08:53:09 GMT
    [3] => Content-Length: 13889
    [4] => Content-Type: text/html
    [5] => Content-Location: http://www.mmkao.com/Beautyleg/index.html
    [6] => Last-Modified: Wed, 05 Nov 2014 05:39:09 GMT
    [7] => Accept-Ranges: bytes
    [8] => ETag: "e8939ad2baf8cf1:693"
    [9] => Server: IIS
    [10] => X-Powered-By: WAF/2.0
    [11] => Set-Cookie: safedog-flow-item=8471BA510DA33350ED344AC374D3044A; expires=Sat, 12-Dec-2150 10:26:25 GMT; domain=mmkao.com; path=/
)

声明：本文内容由网友自发贡献，版权归原作者所有，本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容，请联系admin@php.cn核实处理。

自定义HTTP抓包跟过滤

[日常] 使用TCPDUMP和Ethereal抓包分析HTTP请求中的异常情况

python调用tcpdump抓包过滤的方法

Flutter中http请求抓包的完美解决方案

GO语言实现的http抓包分析工具pproxy介绍

【HTTP】Fiddler（二） - 使用Fiddler做抓包分析

【HTTP】Fiddler（二） - 使用Fiddler做抓包分析

fiddler抓包小技巧之自动保存抓包数据的实现方法分析【可根据需求过滤】

自定义HTTP抓包跟过滤

Fiddler抓包使用教程-过滤

[日常] 使用TCPDUMP和Ethereal抓包分析HTTP请求中的异常情况