Python开发网站目录扫描器的实现

有人问为什么要去扫描网站目录：懂的人自然懂

这个python脚本的特点：

1.基本完善

2.界面美观（只是画了个图案）

3.可选参数增加了线程数

4.user agent细节处理

5.多线程显示进度

扫描目标：metasploitable linux

代码：webdirscanner.py：

# -*- coding:utf-8 -*-
__author__ = "yiqing"
import sys
import threading
import random
from queue import queue
from optparse import optionparser

try:
  import requests
except exception:
  print "[!] you need to install requests module!"
  print "[!] usage:pip install requests"
  exit()


class webdirscan:
  """
  web目录扫描器
  """

  def __init__(self, options):
    self.url = options.url
    self.file_name = options.file_name
    self.count = options.count

  class dirscan(threading.thread):
    """
    多线程
    """

    def __init__(self, queue, total):
      threading.thread.__init__(self)
      self._queue = queue
      self._total = total

    def run(self):
      while not self._queue.empty():
        url = self._queue.get()
        # 多线程显示进度
        threading.thread(target=self.msg).start()
        try:
          r = requests.get(url=url, headers=get_user_agent(), timeout=5)
          if r.status_code == 200:
            sys.stdout.write('\r' + '[+]%s\t\t\n' % url)
            # 保存到本地文件，以html的格式
            result = open('result.html', 'a+')
            result.write('<a href="' + url + '" rel="external nofollow" target="_blank">' + url + '</a>')
            result.write('\r\n</br>')
            result.close()
        except exception:
          pass

    def msg(self):
      """
      显示进度
      :return:none
      """
      per = 100 - float(self._queue.qsize()) / float(self._total) * 100
      percent = "%s finished| %s all| scan in %1.f %s" % (
        (self._total - self._queue.qsize()), self._total, per, '%')
      sys.stdout.write('\r' + '[*]' + percent)

  def start(self):
    result = open('result.html', 'w')
    result.close()
    queue = queue()
    f = open('dict.txt', 'r')
    for i in f.readlines():
      queue.put(self.url + "/" + i.rstrip('\n'))
    total = queue.qsize()
    threads = []
    thread_count = int(self.count)
    for i in range(thread_count):
      threads.append(self.dirscan(queue, total))
    for thread in threads:
      thread.start()
    for thread in threads:
      thread.join()


def get_user_agent():
  """
  user agent的细节处理
  :return:
  """
  user_agent_list = [
    {'user-agent': 'mozilla/4.0 (mozilla/4.0; msie 7.0; windows nt 5.1; fdm; sv1; .net clr 3.0.04506.30)'},
    {'user-agent': 'mozilla/4.0 (compatible; msie 8.0; windows nt 6.0; en) opera 11.00'},
    {
      'user-agent': 'mozilla/5.0 (x11; u; linux i686; de; rv:1.9.0.2) gecko/2008092313 ubuntu/8.04 (hardy) firefox/3.0.2'},
    {
      'user-agent': 'mozilla/5.0 (x11; u; linux i686; en-gb; rv:1.9.1.15) gecko/20101027 fedora/3.5.15-1.fc12 firefox/3.5.15'},
    {
      'user-agent': 'mozilla/5.0 (x11; u; linux i686; en-us) applewebkit/534.10 (khtml, like gecko) chrome/8.0.551.0 safari/534.10'},
    {'user-agent': 'mozilla/5.0 (x11; u; linux i686; en-us; rv:1.9.0.2) gecko/2008092809 gentoo firefox/3.0.2'},
    {
      'user-agent': 'mozilla/5.0 (x11; u; linux x86_64; en-us) applewebkit/534.10 (khtml, like gecko) chrome/7.0.544.0'},
    {'user-agent': 'opera/9.10 (windows nt 5.2; u; en)'},
    {
      'user-agent': 'mozilla/5.0 (iphone; u; cpu os 3_2 like mac os x; en-us) applewebkit/531.21.10 (khtml, like gecko)'},
    {'user-agent': 'opera/9.80 (x11; u; linux i686; en-us; rv:1.9.2.3) presto/2.2.15 version/10.10'},
    {
      'user-agent': 'mozilla/5.0 (windows; u; windows nt 5.1; ru-ru) applewebkit/533.18.1 (khtml, like gecko) version/5.0.2 safari/533.18.5'},
    {'user-agent': 'mozilla/5.0 (windows; u; windows nt 5.1; ru; rv:1.9b3) gecko/2008020514 firefox/3.0b3'},
    {
      'user-agent': 'mozilla/5.0 (macintosh; u; ppc mac os x 10_4_11; fr) applewebkit/533.16 (khtml, like gecko) version/5.0 safari/533.16'},
    {
      'user-agent': 'mozilla/5.0 (macintosh; u; intel mac os x 10_6_6; en-us) applewebkit/534.20 (khtml, like gecko) chrome/11.0.672.2 safari/534.20'},
    {
      'user-agent': 'mozilla/4.0 (compatible; msie 8.0; windows nt 6.1; wow64; trident/4.0; slcc2; .net clr 2.0.50727; infopath.2)'},
    {'user-agent': 'mozilla/4.0 (compatible; msie 6.0; x11; linux x86_64; en) opera 9.60'},
    {
      'user-agent': 'mozilla/5.0 (macintosh; u; intel mac os x 10_6_2; en-us) applewebkit/533.4 (khtml, like gecko) chrome/5.0.366.0 safari/533.4'},
    {'user-agent': 'mozilla/5.0 (windows nt 6.0; u; en; rv:1.8.1) gecko/20061208 firefox/2.0.0 opera 9.51'}
  ]

  return random.choice(user_agent_list)


def main():
  """
  主函数
  :return: none
  """
  print '''
   ____ _   ____         
  | _ \(_)_ __/ ___| ___ __ _ _ __ 
  | | | | | '__\___ \ / __/ _` | '_ \ 
  | |_| | | |  ___) | (_| (_| | | | |
  |____/|_|_| |____/ \___\__,_|_| |_|

  welcome to webdirscan
  version:1.0 author: %s
  ''' % __author__
  parser = optionparser('python webdirscanner.py -u <target url> -f <dictionary file name> [-t <thread_count>]')
  parser.add_option('-u', '--url', dest='url', type='string', help='target url for scan')
  parser.add_option('-f', '--file', dest='file_name', type='string', help='dictionary filename')
  parser.add_option('-t', '--thread', dest='count', type='int', default=10, help='scan thread count')
  (options, args) = parser.parse_args()
  if options.url and options.file_name:
    dirscan = webdirscan(options)
    dirscan.start()
    sys.exit(1)
  else:
    parser.print_help()
    sys.exit(1)


if __name__ == '__main__':
  main()

需要一个字典文件：

我存进去了一些，一部分是确定存在的目录

dict.txt

index.php
login
dvwa
phpmyadmin
dav
twiki
login.php

结果：得到一个html文件：

<a href="http://192.168.232.129/twiki" rel="external nofollow" target="_blank">http://192.168.232.129/twiki</a>

</br><a href="http://192.168.232.129/index.php" rel="external nofollow" target="_blank">http://192.168.232.129/index.php</a>

</br><a href="http://192.168.232.129/phpmyadmin" rel="external nofollow" target="_blank">http://192.168.232.129/phpmyadmin</a>

</br>

脚本的使用：

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。