#使用C#winform编写渗透测试工具--子域名挖掘

使用C#winform编写渗透测试工具--子域名挖掘

这篇文章主要介绍使用C#winform编写渗透测试工具--子域名挖掘。在渗透测试中，子域名的收集十分重要，通常一个网站的主站的防御能力特别强，而他们的非主站相对较弱，我们便可以通过收集子站信息从而扩大攻击范围，增大渗透的可能。

• 下面是使用C#winform编写的渗透测试工具，前面我们已经完成了端口扫描、敏感目录扫描和暴力破解的工作，这一部分将介绍如何实现子域名挖掘。

---

目录

1. 各种子域名挖掘技术
2. 代码实现
3. 使用步骤

---

一、各种子域名挖掘技术

字典爆破

• 字典爆破就是通过收集来的字典，拼接到顶级域名前面，然后通过自动化工具进行访问，判断返回结果，从而跑出子域名是否存在。比如ESD，subDomainsBrute。

证书SSL查询

• 因为SSL证书支持证书透明度，而SSL里包含子域名。证书SSL查询就是通过HTTPS 证书，ssl证书等搜集子域名记录。比如网站cet就是从SSL证书收集子域名。

DNS数据

• DNS原理就是搜集DNS的解析历史，通过查询dns记录来获取到对方的解析记录，从而获取到子域名，正常来说你的域名经DNS解析过一般就会搜到。比如virustotal执行DNS解析来构建数据库，来检索子域名。

爬虫提取子域名(js文件提取)

• 利用爬虫从页面源代码中提取子域名，比如JSFinder。

二、代码实现

这里分别使用两种方式实现子域名的挖掘，即通过证书SSL查询和js文件提取。

1.使用证书SSL查询方式

参考文章漏洞挖掘-子域名，从在线网站crt中直接提取相关的子域名。

# !/usr/bin/env python3
# -*- coding: utf-8 -*-
import sys
import urllib.request
import urllib.parse
import re
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
def crt_domain(domains):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'
    }
    with urllib.request.urlopen('https://crt.sh/?q=' + domains) as f:
        code = f.read().decode('utf-8')
        for cert, domain in re.findall('<tr>(?:\s|\S)*?href="\?id=([0-9]+?)"(?:\s|\S)*?<td>([*_a-zA-Z0-9.-]+?\.' + re.escape(domains) + ')</td>(?:\s|\S)*?</tr>', code, re.IGNORECASE):
            domain = domain.split('@')[-1]
            print(domain)
            with open('crt_result.txt', 'a+') as f:
                f.write(str(domain)+'\n')
if __name__ == '__main__':
    if len(sys.argv) == 2:
        domains=sys.argv[1]
        crt_domain(domains[11:])
    else:
        print('User: python3 crt_domain.py domain')

C#调用脚本

对于python脚本中包含第三方模块的情况，同样，通过直接创建Process进程，调用python脚本，返回扫描结果。

• 创建按钮按下事件button1_Click，运行“调用python脚本”函数runPythonSubdomain_ssl()

 private void button9_Click(object sender, EventArgs e)
        {
            richTextBox4.Clear();
            runPythonSubdomain_ssl();//运行python函数
            label22.Text = "开始扫描...";
        }

• 实例化一个python进程 调用.py 脚本

void runPythonSubdomain_ssl()
        {
            string url = textBox9.Text;
            p = new Process();
            string path = "Subdomain.py";//待处理python文件的路径，本例中放在debug文件夹下
            string sArguments = path;
            ArrayList arrayList = new ArrayList();
            arrayList.Add(url);//需要挖掘的域名
            foreach (var param in arrayList)//拼接参数
            {
                sArguments += " " + param;
            }
            p.StartInfo.FileName = @"D:\Anaconda\python.exe"; //没有配环境变量的话，可以写"xx\xx\python.exe"的绝对路径。如果配了，直接写"python"即可
            p.StartInfo.Arguments = sArguments;//python命令的参数
            p.StartInfo.UseShellExecute = false;
            p.StartInfo.RedirectStandardOutput = true;
            p.StartInfo.RedirectStandardInput = true;
            p.StartInfo.RedirectStandardError = true;
            p.StartInfo.CreateNoWindow = true;
            p.StartInfo.WindowStyle = ProcessWindowStyle.Hidden;
            p.Start();//启动进程
            //MessageBox.Show("启动成功");
            p.BeginOutputReadLine();
            p.OutputDataReceived += new DataReceivedEventHandler(p_OutputDataReceived_subdomain_ssl);
            Console.ReadLine();
            //p.WaitForExit();
        }
        void p_OutputDataReceived_subdomain_ssl(object sender, DataReceivedEventArgs e)
        {
            var printedStr = e.Data;
            Action at = new Action(delegate ()
            {
                //接受.py进程打印的字符信息到文本显示框
                richTextBox4.AppendText(printedStr + "\n");
                label22.Text = "扫描结束";
            });
            Invoke(at);
        }

2.使用js文件提取

#!/usr/bin/env python"
# coding: utf-8
import requests, argparse, sys, re
from requests.packages import urllib3
from urllib.parse import urlparse
from bs4 import BeautifulSoup
def parse_args():
    parser = argparse.ArgumentParser(epilog='\tExample: \r\npython ' + sys.argv[0] + " -u http://www.baidu.com")
    parser.add_argument("-u", "--url", help="The website")
    parser.add_argument("-c", "--cookie", help="The website cookie")
    parser.add_argument("-f", "--file", help="The file contains url or js")
    parser.add_argument("-ou", "--outputurl", help="Output file name. ")
    parser.add_argument("-os", "--outputsubdomain", help="Output file name. ")
    parser.add_argument("-j", "--js", help="Find in js file", action="store_true")
    parser.add_argument("-d", "--deep",help="Deep find", action="store_true")
    return parser.parse_args()
def extract_URL(JS):
	pattern_raw = r"""
	  (?:"|')                               # Start newline delimiter
	  (
	    ((?:[a-zA-Z]{1,10}://|//)           # Match a scheme [a-Z]*1-10 or //
	    [^"'/]{1,}\.                        # Match a domainname (any character + dot)
	    [a-zA-Z]{2,}[^"']{0,})              # The domainextension and/or path
	    |
	    ((?:/|\.\./|\./)                    # Start with /,../,./
	    [^"'><,;| *()(%%$^/\\\[\]]          # Next character can't be...
	    [^"'><,;|()]{1,})                   # Rest of the characters can't be
	    |
	    ([a-zA-Z0-9_\-/]{1,}/               # Relative endpoint with /
	    [a-zA-Z0-9_\-/]{1,}                 # Resource name
	    \.(?:[a-zA-Z]{1,4}|action)          # Rest + extension (length 1-4 or action)
	    (?:[\?|/][^"|']{0,}|))              # ? mark with parameters
	    |
	    ([a-zA-Z0-9_\-]{1,}                 # filename
	    \.(?:php|asp|aspx|jsp|json|
	         action|html|js|txt|xml)             # . + extension
	    (?:\?[^"|']{0,}|))                  # ? mark with parameters
	  )
	  (?:"|')                               # End newline delimiter
	"""
	pattern = re.compile(pattern_raw, re.VERBOSE)
	result = re.finditer(pattern, str(JS))
	if result == None:
		return None
	js_url = []
	return [match.group().strip('"').strip("'") for match in result
		if match.group() not in js_url]
# 发送请求
def Extract_html(URL):
	header = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36",
	"Cookie": args.cookie}
	try:
		raw = requests.get(URL, headers = header, timeout=3, verify=False)
		raw = raw.content.decode("utf-8", "ignore")
		return raw
	except:
		return None
# 处理url
def process_url(URL, re_URL):
	black_url = ["javascript:"]	# Add some keyword for filter url.
	URL_raw = urlparse(URL)
	ab_URL = URL_raw.netloc
	host_URL = URL_raw.scheme
	if re_URL[0:2] == "//":
		result = host_URL  + ":" + re_URL
	elif re_URL[0:4] == "http":
		result = re_URL
	elif re_URL[0:2] != "//" and re_URL not in black_url:
		if re_URL[0:1] == "/":
			result = host_URL + "://" + ab_URL + re_URL
		else:
			if re_URL[0:1] == ".":
				if re_URL[0:2] == "..":
					result = host_URL + "://" + ab_URL + re_URL[2:]
				else:
					result = host_URL + "://" + ab_URL + re_URL[1:]
			else:
				result = host_URL + "://" + ab_URL + "/" + re_URL
	else:
		result = URL
	return result
def find_last(string,str):
	positions = []
	last_position=-1
	while True:
		position = string.find(str,last_position+1)
		if position == -1:break
		last_position = position
		positions.append(position)
	return positions
def find_by_url(url, js = False):
	if js == False:
		try:
			print("url:" + url)
		except:
			print("Please specify a URL like https://www.baidu.com")
		html_raw = Extract_html(url)
		if html_raw == None:
			print("Fail to access " + url)
			return None
		#print(html_raw)
		html = BeautifulSoup(html_raw, "html.parser")
		html_scripts = html.findAll("script")
		script_array = {}
		script_temp = ""
		for html_script in html_scripts:
			script_src = html_script.get("src")
			if script_src == None:
				script_temp += html_script.get_text() + "\n"
			else:
				purl = process_url(url, script_src)
				script_array[purl] = Extract_html(purl)
		script_array[url] = script_temp
		allurls = []
		for script in script_array:
			#print(script)
			temp_urls = extract_URL(script_array[script])
			if len(temp_urls) == 0: continue
			for temp_url in temp_urls:
				allurls.append(process_url(script, temp_url))
		result = []
		for singerurl in allurls:
			url_raw = urlparse(url)
			domain = url_raw.netloc
			positions = find_last(domain, ".")
			miandomain = domain
			if len(positions) > 1:miandomain = domain[positions[-2] + 1:]
			#print(miandomain)
			suburl = urlparse(singerurl)
			subdomain = suburl.netloc
			#print(singerurl)
			if miandomain in subdomain or subdomain.strip() == "":
				if singerurl.strip() not in result:
					result.append(singerurl)
		return result
	return sorted(set(extract_URL(Extract_html(url)))) or None
def find_subdomain(urls, mainurl):
	url_raw = urlparse(mainurl)
	domain = url_raw.netloc
	miandomain = domain
	positions = find_last(domain, ".")
	if len(positions) > 1:miandomain = domain[positions[-2] + 1:]
	subdomains = []
	for url in urls:
		suburl = urlparse(url)
		subdomain = suburl.netloc
		#print(subdomain)
		if subdomain.strip() == "": continue
		if miandomain in subdomain:
			if subdomain not in subdomains:
				subdomains.append(subdomain)
	return subdomains
def find_by_url_deep(url):
	html_raw = Extract_html(url)
	if html_raw == None:
		print("Fail to access " + url)
		return None
	html = BeautifulSoup(html_raw, "html.parser")
	html_as = html.findAll("a")
	links = []
	for html_a in html_as:
		src = html_a.get("href")
		if src == "" or src == None: continue
		link = process_url(url, src)
		if link not in links:
			links.append(link)
	if links == []: return None
	print("ALL Find " + str(len(links)) + " links")
	urls = []
	i = len(links)
	for link in links:
		temp_urls = find_by_url(link)
		if temp_urls == None: continue
		print("Remaining " + str(i) + " | Find " + str(len(temp_urls)) + " URL in " + link)
		for temp_url in temp_urls:
			if temp_url not in urls:
				urls.append(temp_url)
		i -= 1
	return urls
def find_by_file(file_path, js=False):
	with open(file_path, "r") as fobject:
		links = fobject.read().split("\n")
	if links == []: return None
	print("ALL Find " + str(len(links)) + " links")
	urls = []
	i = len(links)
	for link in links:
		if js == False:
			temp_urls = find_by_url(link)
		else:
			temp_urls = find_by_url(link, js=True)
		if temp_urls == None: continue
		print(str(i) + " Find " + str(len(temp_urls)) + " URL in " + link)
		for temp_url in temp_urls:
			if temp_url not in urls:
				urls.append(temp_url)
		i -= 1
	return urls
def giveresult(urls, domian):
	if urls == None:
		return None
	print("Find " + str(len(urls)) + " URL:")
	content_url = ""
	content_subdomain = ""
	for url in urls:
		content_url += url + "\n"
		print(url)
	subdomains = find_subdomain(urls, domian)
	print("\nFind " + str(len(subdomains)) + " Subdomain:")
	for subdomain in subdomains:
		content_subdomain += subdomain + "\n"
		print(subdomain)
	if args.outputurl != None:
		with open(args.outputurl, "a", encoding='utf-8') as fobject:
			fobject.write(content_url)
		print("\nOutput " + str(len(urls)) + " urls")
		print("Path:" + args.outputurl)
	if args.outputsubdomain != None:
		with open(args.outputsubdomain, "a", encoding='utf-8') as fobject:
			fobject.write(content_subdomain)
		print("\nOutput " + str(len(subdomains)) + " subdomains")
		print("Path:" + args.outputsubdomain)
if __name__ == "__main__":
	urllib3.disable_warnings()
	args = parse_args()
	if args.file == None:
		if args.deep is not True:
			urls = find_by_url(args.url)
			giveresult(urls, args.url)
		else:
			urls = find_by_url_deep(args.url)
			giveresult(urls, args.url)
	else:
		if args.js is not True:
			urls = find_by_file(args.file)
			giveresult(urls, urls[0])
		else:
			urls = find_by_file(args.file, js = True)
			giveresult(urls, urls[0])

C#调用脚本

• 创建按钮按下事件button1_Click，运行“调用python脚本”函数runPythonSubdomain_js()

private void button10_Click(object sender, EventArgs e)
        {
            richTextBox5.Clear();
            runPythonSubdomain_js();//运行python函数
            label24.Text = "开始扫描...";
        }

• 实例化一个python进程 调用.py 脚本

void runPythonSubdomain_js()
        {
            string url = textBox9.Text;
            p = new Process();
            string path = "JSFinder.py";//待处理python文件的路径，本例中放在debug文件夹下
            string sArguments = path;
            ArrayList arrayList = new ArrayList();
            arrayList.Add("-u");
            arrayList.Add(url);//需要挖掘的域名
            foreach (var param in arrayList)//拼接参数
            {
                sArguments += " " + param;
            }
            p.StartInfo.FileName = @"D:\Anaconda\python.exe"; //没有配环境变量的话，可以写"xx\xx\python.exe"的绝对路径。如果配了，直接写"python"即可
            p.StartInfo.Arguments = sArguments;//python命令的参数
            p.StartInfo.UseShellExecute = false;
            p.StartInfo.RedirectStandardOutput = true;
            p.StartInfo.RedirectStandardInput = true;
            p.StartInfo.RedirectStandardError = true;
            p.StartInfo.CreateNoWindow = true;
            p.StartInfo.WindowStyle = ProcessWindowStyle.Hidden;
            p.Start();//启动进程
            //MessageBox.Show("启动成功");
            p.BeginOutputReadLine();
            p.OutputDataReceived += new DataReceivedEventHandler(p_OutputDataReceived_subdomain_js);
            Console.ReadLine();
            //p.WaitForExit();
        }
        void p_OutputDataReceived_subdomain_js(object sender, DataReceivedEventArgs e)
        {
            var printedStr = e.Data;
            Action at = new Action(delegate ()
            {
                //接受.py进程打印的字符信息到文本显示框
                richTextBox5.AppendText(printedStr + "\n");
                label24.Text = "扫描结束";
            });
            Invoke(at);
        }
    }
}

三、使用步骤

• 首先在url栏中输入地址，接着可以选择是使用ssl证书提取或者Js文件提取的方式进行挖掘，最后得到子域名信息。

github地址：https://github.com/Chenmengx/Penetration-testing-tool