Web应用指纹识别

perl FingerPrint.pl url.txt<uri 文件路径 必选> tanjiti.json[指纹规则文件，可选]

结果输出到 url.txt__fingerprint 文件里

指纹规则文件编写示例：

more tanjiti.json

"apps": {
                "Discuz!":{
               	 "website": "www.discuz.net/forum.php",
               	 "cats": [ 1 ],
                 "meta": { "generator": "Discuz"},
                 "headers": {"Set-Cookie": "_lastact.*_sid|_sid.*_lastact|_sid.*smile|smile.*_sid"},
                 "url": "/uc_server[/$]|uc_client[/$]",
                 "html": "Powered by (?:Discuz!|<a href=\"http://www\\.discuz\\.net/\"|UCenter)",
                 "implies": "php"
                },
        	"PHP": {
                "website": "php.net",
                "cats": [ 27 ],
                "headers": { "Server": "php/?([\\d.]+)?\\;confidence:40\\;version:\\1", "X-Powered-By": "php/?([\\d.]+)?\\;confidence:40\\;version:\\1", "Set-Cookie": "PHPSESSID" },
                "url": "\\.php(?:$|\\?)"
                }

 }

vim testCurl.php 

<?php

if ( php_sapi_name() !== 'cli' ) {
        exit('Run me from the command line');
}

$url = !empty($argv[1]) ? $argv[1] : '';

if ( !$url ) {
        echo "Usage: php {$argv[0]} <url>\n";

        exit(0);
}

$result = curl($url); 
var_dump($result);

function curl($url)
        {
                echo 'cURL request: ' . $url . "\n";

                $ch = curl_init($url); //初始化

                curl_setopt_array($ch, array(//设置选项
                        CURLOPT_SSL_VERIFYPEER => false,
                        CURLOPT_HEADER         => true,
                        CURLOPT_RETURNTRANSFER => true,
                        CURLOPT_FOLLOWLOCATION => true,
                        CURLOPT_MAXREDIRS      => 3, //重定向
                        CURLOPT_TIMEOUT        => 5, //超时时间，单位s
                        CURLOPT_USERAGENT      => 'Mozilla/5.0 (X11; Linux x86_64; rv:15.0) Gecko/20100101 Firefox/15.0.1' //User-Agent
                        ));

                $response = curl_exec($ch);

                if ( curl_errno($ch) !== 0 ) {
                        throw new Exception('cURL error: ' . curl_error($ch));
                }

                $httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);

                if ( $httpCode != 200 ) {
                        throw new Exception('cURL request returned HTTP code ' . $httpCode);
                }

                $result = new stdClass();

                $result->url = curl_getinfo($ch, CURLINFO_EFFECTIVE_URL);

                $result->host = parse_url($result->url, PHP_URL_HOST);

                $headerSize = curl_getinfo($ch, CURLINFO_HEADER_SIZE);
                
                $result->html = substr($response, $headerSize);

                $result->html = mb_check_encoding($result->html, 'UTF-8') ? $result->html : utf8_encode($result->html);

                $headers = trim(substr($response, 0, $headerSize));
                $headers = preg_split('/^\s*$/m', $headers);
                $headers = end($headers);
                $lines = array_slice(explode("\r\n", $headers), 1);

                foreach ( $lines as $line ) {
                        if ( strpos(trim($line), ': ') !== false ) {
                                list($key, $value) = explode(': ', $line);

                                $result->headers[strtolower($key)] = $value;
                        }
                }

                return $result;
        }
?>

php testCurl.php www.tanjiti.com/xss.php?a=lala   
cURL request: www.tanjiti.com/xss.php?a=lala
object(stdClass)#1 (4) {
  ["url"]=>
  string(37) "HTTP://www.tanjiti.com/xss.php?a=lala"
  ["host"]=>
  string(15) "www.tanjiti.com"
  ["html"]=>
  string(4) "lala"
  ["headers"]=>
  array(11) {
    ["date"]=>
    string(29) "Fri, 31 Oct 2014 10:08:50 GMT"
    ["content-type"]=>
    string(9) "text/html"
    ["transfer-encoding"]=>
    string(7) "chunked"
    ["connection"]=>
    string(10) "keep-alive"
    ["set-cookie"]=>
    string(133) "__cfduid=db05b3ccf4d2b4db66bb46b1058c616831414750130574; expires=Mon, 23-Dec-2019 23:50:00 GMT; path=/; domain=.tanjiti.com; HttpOnly"
    ["x-powered-by"]=>
    string(20) "PHP/5.5.9-1ubuntu4.4"
    ["x-content-type-options"]=>
    string(7) "nosniff"
    ["x-frame-options"]=>
    string(10) "sameorigin"
    ["x-xss-protection"]=>
    string(12) "1;mode=block"
    ["server"]=>
    string(16) "cloudflare-nginx"
    ["cf-ray"]=>
    string(20) "181f0dbc131a036e-LAX"
  }
}

NFA引擎正则优化TIPS、Perl正则技巧及正则性能评测方法