使用C#winform編寫滲透測試工具--子域名挖掘
這篇文章主要介紹使用C#winform編寫滲透測試工具--子域名挖掘。在滲透測試中，子域名的收集十分重要，通常一個網站的主站的防禦能力特別強，而他們的非主站相對較弱，我們便可以通過收集子站資訊從而擴大攻擊範圍，增大滲透的可能。
- 下面是使用C#winform編寫的滲透測試工具，前面我們已經完成了埠掃描、敏感目錄掃描和暴力破解的工作，這一部分將介紹如何實現子域名挖掘。
目錄
- 各種子域名挖掘技術
- 程式碼實現
- 使用步驟
一、各種子域名挖掘技術
字典爆破
- 字典爆破就是通過收集來的字典，拼接到頂級域名前面，然後通過自動化工具進行訪問，判斷返回結果，從而跑出子域名是否存在。比如ESD，subDomainsBrute。
證照SSL查詢
- 因為SSL證照支援證照透明度，而SSL裡包含子域名。證照SSL查詢就是通過HTTPS 證照，ssl證照等蒐集子域名記錄。比如網站cet就是從SSL證照收集子域名。
DNS資料
- DNS原理就是蒐集DNS的解析歷史，通過查詢dns記錄來獲取到對方的解析記錄，從而獲取到子域名，正常來說你的域名經DNS解析過一般就會搜到。比如virustotal執行DNS解析來構建資料庫，來檢索子域名。
爬蟲提取子域名(js檔案提取)
- 利用爬蟲從頁面原始碼中提取子域名，比如JSFinder。
二、程式碼實現
這裡分別使用兩種方式實現子域名的挖掘，即通過證照SSL查詢和js檔案提取。
1.使用證照SSL查詢方式
# !/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#呼叫指令碼
對於python指令碼中包含第三方模組的情況，同樣，通過直接建立Process程式，呼叫python指令碼，返回掃描結果。
- 建立按鈕按下事件button1_Click，執行“呼叫python指令碼”函式runPythonSubdomain_ssl()
private void button9_Click(object sender, EventArgs e)
{
richTextBox4.Clear();
runPythonSubdomain_ssl();//執行python函式
label22.Text = "開始掃描...";
}
- 例項化一個python程式 呼叫.py 指令碼
void runPythonSubdomain_ssl()
{
string url = textBox9.Text;
p = new Process();
string path = "Subdomain.py";//待處理python檔案的路徑，本例中放在debug資料夾下
string sArguments = path;
ArrayList arrayList = new ArrayList();
arrayList.Add(url);//需要挖掘的域名
foreach (var param in arrayList)//拼接引數
{
sArguments += " " + param;
}
p.StartInfo.FileName = @"D:\Anaconda\python.exe"; //沒有配環境變數的話，可以寫"xx\xx\python.exe"的絕對路徑。如果配了，直接寫"python"即可
p.StartInfo.Arguments = sArguments;//python命令的引數
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();//啟動程式
//MessageBox.Show("啟動成功");
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程式列印的字元資訊到文字顯示框
richTextBox4.AppendText(printedStr + "\n");
label22.Text = "掃描結束";
});
Invoke(at);
}
2.使用js檔案提取
#!/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]
# 傳送請求
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
# 處理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#呼叫指令碼
- 建立按鈕按下事件button1_Click，執行“呼叫python指令碼”函式runPythonSubdomain_js()
private void button10_Click(object sender, EventArgs e)
{
richTextBox5.Clear();
runPythonSubdomain_js();//執行python函式
label24.Text = "開始掃描...";
}
- 例項化一個python程式 呼叫.py 指令碼
void runPythonSubdomain_js()
{
string url = textBox9.Text;
p = new Process();
string path = "JSFinder.py";//待處理python檔案的路徑，本例中放在debug資料夾下
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)//拼接引數
{
sArguments += " " + param;
}
p.StartInfo.FileName = @"D:\Anaconda\python.exe"; //沒有配環境變數的話，可以寫"xx\xx\python.exe"的絕對路徑。如果配了，直接寫"python"即可
p.StartInfo.Arguments = sArguments;//python命令的引數
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();//啟動程式
//MessageBox.Show("啟動成功");
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程式列印的字元資訊到文字顯示框
richTextBox5.AppendText(printedStr + "\n");
label24.Text = "掃描結束";
});
Invoke(at);
}
}
}
三、使用步驟
- 首先在url欄中輸入地址，接著可以選擇是使用ssl證照提取或者Js檔案提取的方式進行挖掘，最後得到子域名資訊。