├── Common ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-38.pyc │ ├── GetProxies.cpython-38.pyc │ ├── LogOutput.cpython-38.pyc │ └── CustomException.cpython-38.pyc ├── CustomException.py ├── ProxyPool │ ├── DomesticProxyPool.txt │ └── ForeignProxyPool.txt ├── LogOutput.py ├── Exception结构.md └── GetProxies.py ├── Plugins ├── __init__.py ├── InfoSearch │ ├── __init__.py │ ├── Domain │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-38.pyc │ │ │ └── domainapi.cpython-38.pyc │ │ └── domainapi.py │ ├── Subdomain │ │ ├── __init__.py │ │ ├── IsCND │ │ │ ├── __init__.py │ │ │ ├── GeoLite2-ASN.mmdb │ │ │ ├── cdn-domain.conf │ │ │ └── CheckCDN.py │ │ ├── Spider │ │ │ ├── __init__.py │ │ │ ├── Baidu │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── baidu.cpython-38.pyc │ │ │ │ │ └── __init__.cpython-38.pyc │ │ │ │ └── baidu.py │ │ │ ├── Bing │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── bing.cpython-38.pyc │ │ │ │ │ └── __init__.cpython-38.pyc │ │ │ │ └── bing.py │ │ │ ├── Google │ │ │ │ ├── docs │ │ │ │ │ ├── .gitignore │ │ │ │ │ ├── index.rst │ │ │ │ │ ├── Makefile │ │ │ │ │ ├── make.bat │ │ │ │ │ └── conf.py │ │ │ │ ├── googlesearch │ │ │ │ │ ├── user_agents.txt.gz │ │ │ │ │ ├── __pycache__ │ │ │ │ │ │ └── __init__.cpython-38.pyc │ │ │ │ │ └── __init__.py │ │ │ │ ├── .google-cookie │ │ │ │ ├── .travis.yml │ │ │ │ ├── demo.py │ │ │ │ └── google.py │ │ │ └── __pycache__ │ │ │ │ └── __init__.cpython-38.pyc │ │ ├── JsFinder │ │ │ ├── __init__.py │ │ │ └── jsfinder.py │ │ ├── ESD │ │ │ ├── ESD-0.0.29.dist-info │ │ │ │ ├── REQUESTED │ │ │ │ ├── INSTALLER │ │ │ │ ├── top_level.txt │ │ │ │ ├── entry_points.txt │ │ │ │ ├── WHEEL │ │ │ │ ├── RECORD │ │ │ │ ├── METADATA │ │ │ │ └── LICENSE │ │ │ └── ESD │ │ │ │ ├── __pycache__ │ │ │ │ └── __init__.cpython-38.pyc │ │ │ │ ├── key.ini │ │ │ │ ├── subs-test.esd │ │ │ │ └── __init__.py │ │ ├── ThirdPartyPlatform │ │ │ ├── __init__.py │ │ │ ├── certificate.py │ │ │ └── netcraft.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-38.pyc │ │ │ └── subdomainapi.cpython-38.pyc │ │ └── subdomainapi.py │ ├── __pycache__ │ │ ├── __init__.cpython-38.pyc │ │ └── infosearchapi.cpython-38.pyc │ └── infosearchapi.py ├── __pycache__ │ └── __init__.cpython-38.pyc └── SaveToExcel.py ├── Reports ├── googleSpider.txt ├── tjzj.edu.cn-key-links └── tjzj.edu.cn-subdomains ├── config.ini ├── README.md ├── requirements.txt └── search_all.py /Common/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Plugins/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Domain/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/IsCND/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/JsFinder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Baidu/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Bing/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ESD/ESD-0.0.29.dist-info/REQUESTED: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ThirdPartyPlatform/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ESD/ESD-0.0.29.dist-info/INSTALLER: -------------------------------------------------------------------------------- 1 | pip 2 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Google/docs/.gitignore: -------------------------------------------------------------------------------- 1 | _build/ 2 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ESD/ESD-0.0.29.dist-info/top_level.txt: -------------------------------------------------------------------------------- 1 | ESD 2 | -------------------------------------------------------------------------------- /Reports/googleSpider.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Reports/googleSpider.txt -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ESD/ESD-0.0.29.dist-info/entry_points.txt: -------------------------------------------------------------------------------- 1 | [console_scripts] 2 | esd = ESD:main 3 | 4 | -------------------------------------------------------------------------------- /Common/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Common/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /Common/__pycache__/GetProxies.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Common/__pycache__/GetProxies.cpython-38.pyc -------------------------------------------------------------------------------- /Common/__pycache__/LogOutput.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Common/__pycache__/LogOutput.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /Common/CustomException.py: -------------------------------------------------------------------------------- 1 | '''自定义异常类''' 2 | 3 | class CustomException(Exception): 4 | pass 5 | 6 | class NetworkException(ValueError): 7 | -------------------------------------------------------------------------------- /Common/__pycache__/CustomException.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Common/__pycache__/CustomException.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/IsCND/GeoLite2-ASN.mmdb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Subdomain/IsCND/GeoLite2-ASN.mmdb -------------------------------------------------------------------------------- /Plugins/InfoSearch/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ESD/ESD-0.0.29.dist-info/WHEEL: -------------------------------------------------------------------------------- 1 | Wheel-Version: 1.0 2 | Generator: bdist_wheel (0.36.2) 3 | Root-Is-Purelib: true 4 | Tag: py3-none-any 5 | 6 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/__pycache__/infosearchapi.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/__pycache__/infosearchapi.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Domain/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Domain/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Domain/__pycache__/domainapi.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Domain/__pycache__/domainapi.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Subdomain/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/__pycache__/subdomainapi.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Subdomain/__pycache__/subdomainapi.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ESD/ESD/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Subdomain/ESD/ESD/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Bing/__pycache__/bing.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Subdomain/Spider/Bing/__pycache__/bing.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Subdomain/Spider/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Baidu/__pycache__/baidu.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Subdomain/Spider/Baidu/__pycache__/baidu.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Google/googlesearch/user_agents.txt.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Subdomain/Spider/Google/googlesearch/user_agents.txt.gz -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Baidu/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Subdomain/Spider/Baidu/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Bing/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Subdomain/Spider/Bing/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Google/googlesearch/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/urdr-gungnir/SearchAll/HEAD/Plugins/InfoSearch/Subdomain/Spider/Google/googlesearch/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /config.ini: -------------------------------------------------------------------------------- 1 | [fofa api] 2 | EMAIL = cnno.1@protonmail.com 3 | KEY = 86b1a3ae6a597782a0394041c7d1908c 4 | 5 | [shodan api] 6 | SHODAN_API_KEY = 7 | 8 | [github api] 9 | GITHUB_TOKEN = 10 | 11 | [quake api] 12 | X-QuakeToken = 13 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ESD/ESD/key.ini: -------------------------------------------------------------------------------- 1 | [shodan] 2 | shodan_key = 3 | 4 | [fofa] 5 | fofa_key = 6 | fofa_email = 7 | 8 | [zoomeye] 9 | zoomeye_username = 10 | zoomeye_password = 11 | 12 | [censys] 13 | uid = 14 | secret = 15 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ESD/ESD/subs-test.esd: -------------------------------------------------------------------------------- 1 | www 2 | h5 3 | wap 4 | _feei 5 | test 6 | dkim._domainkey 7 | _finger._tcp 8 | sso.cn 9 | dmarc.mail2 10 | f2.market 11 | market 12 | mail 13 | bn73 14 | passport 15 | djfowj 16 | video 17 | dkfowejf 18 | cnvhueq 19 | dhfowje 20 | clive 21 | echiu 22 | img 23 | inn 24 | et25 25 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 经过r师傅教诲，目前觉得这个项目造轮子无意义，已停止开发。 2 | 3 | # SearchAll 4 | 一款外网信息收集集合工具，包括对顶级域名、子域名、c段、敏感信息泄漏等等的收集 5 | 6 | 7 | 目前正在开发，功能还未完善 8 | 设计遇到问题，我会同步到我的博客https://urdr-gungnir.github.io/post/SearchAll%E8%AE%BE%E8%AE%A1%E9%97%AE%E9%A2%98.html 9 | ![image](https://user-images.githubusercontent.com/73213935/139377042-950135ce-c19a-478f-a943-6a9d14f234b1.png) 10 | -------------------------------------------------------------------------------- /Common/ProxyPool/DomesticProxyPool.txt: -------------------------------------------------------------------------------- 1 | 121.40.185.42:1080 2 | 123.60.93.108:1080 3 | 42.122.65.112:1080 4 | 114.117.206.230:1080 5 | 171.107.184.247:1080 6 | 123.59.211.39:45554 7 | 121.42.173.167:1080 8 | 39.103.199.2:1080 9 | 124.91.134.216:1080 10 | 123.60.224.72:1080 11 | 222.64.9.47:1080 12 | 115.239.213.75:1080 13 | 111.229.21.197:1080 14 | 59.61.161.66:1080 15 | 45.43.54.177:1080 16 | 39.103.199.2:1080 17 | 101.42.94.199:1080 18 | 113.107.166.125:1080 19 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Google/.google-cookie: -------------------------------------------------------------------------------- 1 | #LWP-Cookies-2.0 2 | Set-Cookie3: 1P_JAR="2021-10-01-12"; path="/"; domain=".google.com"; path_spec; domain_dot; secure; expires="2021-10-31 12:54:53Z"; version=0 3 | Set-Cookie3: NID="511=JTjC9CxK8SYPY3weJg-Aej42eHSD22u3_xTVIRYcfPecmhPzNd8tmOF42QmDwh3uJFXhZjB8utDi4nhu8xjmk8_Z6UDYKiRycBK-3u4H__Fo-U1toiaFgpQwY3D6rgETpjxChNhKfUaZZiaKmOS9zeC3g4llerzYVbVE3JOQILY"; path="/"; domain=".google.com"; path_spec; domain_dot; expires="2022-04-02 12:54:52Z"; HttpOnly=None; version=0 4 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Google/.travis.yml: -------------------------------------------------------------------------------- 1 | language: python 2 | 3 | # Supported CPython versions: 4 | # https://en.wikipedia.org/wiki/CPython#Version_history 5 | python: 6 | - pypy3 7 | - pypy 8 | - 2.7 9 | - 3.6 10 | - 3.5 11 | - 3.4 12 | 13 | # Use container-based infrastructure 14 | sudo: false 15 | 16 | install: 17 | - pip install pycodestyle pyflakes 18 | 19 | script: 20 | # Static analysis 21 | - pyflakes . 22 | - pycodestyle --statistics --count . 23 | 24 | matrix: 25 | fast_finish: true 26 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | aiodns==3.0.0 2 | aiohttp==3.7.4.post0 3 | async-timeout==3.0.1 4 | attrs==21.2.0 5 | backoff==1.11.1 6 | certifi==2021.5.30 7 | cffi==1.14.6 8 | chardet==4.0.0 9 | charset-normalizer==2.0.6 10 | colorama==0.4.4 11 | colorlog==6.4.1 12 | dnspython==2.1.0 13 | et-xmlfile==1.1.0 14 | idna==3.2 15 | multidict==5.1.0 16 | openpyxl==3.0.9 17 | pycares==4.0.0 18 | pycparser==2.20 19 | PySocks==1.7.1 20 | requests==2.26.0 21 | termcolor==1.1.0 22 | tqdm==4.62.3 23 | typing-extensions==3.10.0.2 24 | urllib3==1.26.7 25 | wincertstore==0.2 26 | yarl==1.6.3 27 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Google/docs/index.rst: -------------------------------------------------------------------------------- 1 | .. googlesearch documentation master file, created by 2 | sphinx-quickstart on Tue Nov 6 12:25:12 2018. 3 | You can adapt this file completely to your liking, but it should at least 4 | contain the root `toctree` directive. 5 | 6 | Welcome to googlesearch's documentation! 7 | ======================================== 8 | 9 | Indices and tables 10 | ================== 11 | 12 | * :ref:`genindex` 13 | * :ref:`modindex` 14 | * :ref:`search` 15 | 16 | Reference 17 | ========= 18 | 19 | .. automodule:: googlesearch 20 | :members: 21 | 22 | -------------------------------------------------------------------------------- /Common/ProxyPool/ForeignProxyPool.txt: -------------------------------------------------------------------------------- 1 | 123.59.120.247:1080 2 | 123.59.120.207:1080 3 | 123.59.120.38:45554 4 | 123.59.120.15:45554 5 | 123.59.211.123:45554 6 | 123.59.211.192:45554 7 | 123.59.120.40:45554 8 | 123.59.211.180:45554 9 | 120.244.127.254:1080 10 | 123.59.211.193:45554 11 | 183.45.77.126:1080 12 | 113.16.158.35:1080 13 | 123.59.120.61:45554 14 | 123.59.211.161:45554 15 | 123.59.120.112:45554 16 | 123.59.120.40:45554 17 | 123.59.211.123:45554 18 | 120.244.127.254:1080 19 | 123.59.211.213:45554 20 | 183.45.77.126:1080 21 | 123.59.120.38:45554 22 | 123.59.120.171:45554 23 | 123.59.211.193:45554 24 | 123.59.120.123:45554 25 | -------------------------------------------------------------------------------- /Reports/tjzj.edu.cn-key-links: -------------------------------------------------------------------------------- 1 | openportal服务后台 http://weixin.tjzj.edu.cn/ 2 | 腾讯企业邮箱-登录入口 http://mail.tjzj.edu.cn/ 3 | 同济大学浙江学院大门、公寓楼门口出入系统项目招标信息公告 |... https://www.tjzj.edu.cn/info/16183.html 4 | 浙江警官职业学院2014年招录省属监狱系统人民警察学员公告 | 同济大学浙 ... https://www.tjzj.edu.cn/info/13360.html 5 | 同济大学浙江学院安全态势感知系统和EDR招标信息公告 | 同济大学... https://www.tjzj.edu.cn/index.php/info/16194.html 6 | 同济大学浙江学院结构工程综合加载试验系统项目招标信息公告 |... https://www.tjzj.edu.cn/info/16252.html 7 | 喜报|我校代表队摘获市属教育系统红诗会比赛二等奖 | 同济大学浙江学院 https://www.tjzj.edu.cn/info/19831.html 8 | 吉讯大学生职业测评与规划系统 | 同济大学浙江学院 https://www.tjzj.edu.cn/info/13090.html 9 | 同济大学浙江学院银行系统软件测试仿真实验室招标信息公告 | 同济... https://www.tjzj.edu.cn/info/18640.html 10 | -------------------------------------------------------------------------------- /Plugins/SaveToExcel.py: -------------------------------------------------------------------------------- 1 | 2 | class saveToExcel: 3 | def __init__(self, excelSavePath, excel, title): 4 | self.excelSavePath = excelSavePath # excel的保存路径 5 | self.excel = excel # openpyxl.Workbook()的实例话 6 | self.sheet = self.excel.create_sheet(title=title) # 创建工作区 7 | self.Sheet_line = 1 # 表格的行 8 | 9 | # def CreatExcel(self): 10 | 11 | 12 | def SaveSpider(self, spiderName, key_links=[], subdomains=[]): 13 | 14 | def SaveKeyLinks(): 15 | cprint("*"*20+"存储spider关键词数据"+"*"*20, color="green") 16 | 17 | def SaveSubdomains(): 18 | cprint("*"*20+"存储spider子域名数据"+"*"*20, color="green") -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Google/docs/Makefile: -------------------------------------------------------------------------------- 1 | # Minimal makefile for Sphinx documentation 2 | # 3 | 4 | # You can set these variables from the command line. 5 | SPHINXOPTS = 6 | SPHINXBUILD = sphinx-build 7 | SPHINXPROJ = googlesearch 8 | SOURCEDIR = . 9 | BUILDDIR = _build 10 | 11 | # Put it first so that "make" without argument is like "make help". 12 | help: 13 | @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) 14 | 15 | .PHONY: help Makefile 16 | 17 | # Catch-all target: route all unknown targets to Sphinx using the new 18 | # "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS). 19 | %: Makefile 20 | @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Google/demo.py: -------------------------------------------------------------------------------- 1 | from googlesearch import search 2 | import sys 3 | from sys import version_info 4 | 5 | PY2, PY3 = (True, False) if version_info[0] == 2 else (False, True) 6 | 7 | if PY2: 8 | from urlparse import urlparse 9 | else: 10 | from urllib.parse import urlparse 11 | 12 | key = 'site:hbu.edu.cn 后台'# sys.argv[1] 13 | 14 | urls = [] 15 | 16 | for each_result in search(key, stop=4): 17 | parseRet = urlparse(each_result) 18 | print(each_result, parseRet) 19 | url = parseRet.scheme + '://' + parseRet.netloc 20 | if key in parseRet.netloc and url not in urls: 21 | print(url, each_result) 22 | urls.append(url) 23 | 24 | print('search {} Done!'.format(key)) 25 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Google/docs/make.bat: -------------------------------------------------------------------------------- 1 | @ECHO OFF 2 | 3 | pushd %~dp0 4 | 5 | REM Command file for Sphinx documentation 6 | 7 | if "%SPHINXBUILD%" == "" ( 8 | set SPHINXBUILD=sphinx-build 9 | ) 10 | set SOURCEDIR=. 11 | set BUILDDIR=_build 12 | set SPHINXPROJ=googlesearch 13 | 14 | if "%1" == "" goto help 15 | 16 | %SPHINXBUILD% >NUL 2>NUL 17 | if errorlevel 9009 ( 18 | echo. 19 | echo.The 'sphinx-build' command was not found. Make sure you have Sphinx 20 | echo.installed, then set the SPHINXBUILD environment variable to point 21 | echo.to the full path of the 'sphinx-build' executable. Alternatively you 22 | echo.may add the Sphinx directory to PATH. 23 | echo. 24 | echo.If you don't have Sphinx installed, grab it from 25 | echo.http://sphinx-doc.org/ 26 | exit /b 1 27 | ) 28 | 29 | %SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% 30 | goto end 31 | 32 | :help 33 | %SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% 34 | 35 | :end 36 | popd 37 | -------------------------------------------------------------------------------- /Reports/tjzj.edu.cn-subdomains: -------------------------------------------------------------------------------- 1 | sk.tjzj.edu.cn 122.225.92.218 2 | cxcy.tjzj.edu.cn 122.225.92.218 3 | h5.tjzj.edu.cn 122.225.92.218 4 | tcsf.tjzj.edu.cn 122.225.92.218 5 | kjx.tjzj.edu.cn 122.225.92.218 6 | dfl.tjzj.edu.cn 122.225.92.218 7 | jtx.tjzj.edu.cn 122.225.92.218 8 | message.tjzj.edu.cn 122.225.19.18 9 | tmx.tjzj.edu.cn 122.225.92.218 10 | weixin.tjzj.edu.cn 60.190.149.38 11 | oa.tjzj.edu.cn 192.168.100.16 12 | bwc.tjzj.edu.cn 122.225.60.2 13 | tyb.tjzj.edu.cn 122.225.92.218 14 | www.tjzj.edu.cn 122.225.92.218 15 | old.tjzj.edu.cn 122.225.92.218 16 | lxb.tjzj.edu.cn 122.225.92.218 17 | job.tjzj.edu.cn 121.41.227.53 18 | ns1.tjzj.edu.cn 121.192.40.100 19 | depart.tjzj.edu.cn 122.225.92.218 20 | mail.tjzj.edu.cn 157.255.173.155,61.241.49.119 21 | dem.tjzj.edu.cn 122.225.92.218 22 | daka.tjzj.edu.cn 60.190.149.38 23 | idm.tjzj.edu.cn 122.225.19.22 24 | ei.tjzj.edu.cn 122.225.92.218 25 | cdz.tjzj.edu.cn 122.225.92.218 26 | jxx.tjzj.edu.cn 122.225.92.218 27 | jzh.tjzj.edu.cn 122.225.92.218 28 | english.tjzj.edu.cn 122.225.92.218 29 | ns.tjzj.edu.cn 121.192.40.150 30 | sso.tjzj.edu.cn 122.225.19.22 31 | uc.tjzj.edu.cn 122.225.19.19 32 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ESD/ESD-0.0.29.dist-info/RECORD: -------------------------------------------------------------------------------- 1 | ../../Scripts/esd.exe,sha256=MixWaXi8KM3VLhimXNWmr4Y-fN-z09IqoTNbSDozYhY,106314 2 | ESD-0.0.29.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 3 | ESD-0.0.29.dist-info/LICENSE,sha256=_j7qbFmeI6AMCMX1yyMgwwrcj4aH21_OybeaZixT_2s,35120 4 | ESD-0.0.29.dist-info/METADATA,sha256=QpsUTykinvy5NmoN1Rfy0xEYUwv2csbmV-C_qiUxGDI,4297 5 | ESD-0.0.29.dist-info/RECORD,, 6 | ESD-0.0.29.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 7 | ESD-0.0.29.dist-info/WHEEL,sha256=OqRkF0eY5GHssMorFjlbTIq072vpHpF60fIQA6lS9xA,92 8 | ESD-0.0.29.dist-info/entry_points.txt,sha256=jACTsjKk3gdyl9UunxTSx1fgnzxDnZV3Q0omnUqY8Js,34 9 | ESD-0.0.29.dist-info/top_level.txt,sha256=Kl4w48552EuhLMDNoXD8LUUhnEzA-VOfGQHUdAtp2ig,4 10 | ESD/__init__.py,sha256=imNtmEteBLIjgnc4mH7zvwCmP2UIY0QyMKiQm6oUxhI,40162 11 | ESD/__pycache__/__init__.cpython-38.pyc,, 12 | ESD/cacert.pem,sha256=hmlbG-kiXDz4gtKD8FyUTjqrvB32QopEJCaak-mX3GU,209309 13 | ESD/key.ini,sha256=HLCG1J_EYjuFrrhKMRDN7rViJqJt2ZOH1fdJQiZzQCM,129 14 | ESD/subs-test.esd,sha256=KnXxbaeIBrV5U3DMk_JoCC4wWR6agyhSQjkJDgdsXWE,169 15 | ESD/subs.esd,sha256=jiSYlj4rlIZTOdrWaEr-SEiQvqt5qkJ2tRT9NRR46Mw,806655 16 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Google/google.py: -------------------------------------------------------------------------------- 1 | from Plugins.InfoSearch.Subdomain.Spider.Google.googlesearch import search 2 | from sys import version_info 3 | 4 | PY2, PY3 = (True, False) if version_info[0] == 2 else (False, True) 5 | 6 | if PY2: 7 | from urlparse import urlparse 8 | else: 9 | from urllib.parse import urlparse 10 | 11 | # 谷歌爬虫 12 | class GoogleSpider: 13 | def __init__(self, domain, save_fold_path): 14 | self.domain = domain 15 | # site:domain inurl:admin inurl:login inurl:system 后台 系统 16 | self.wds = ['inurl:admin|login|register|upload|editor', '后台|系统'] 17 | # print('Please wait a few time ...') 18 | self.STOP = 50 # 谷歌最多爬取20个结果 19 | self.save_fold_path = save_fold_path # \result\0ca9b508e31f 20 | self.googleSubdomains = [] 21 | 22 | def run(self): 23 | for wd in self.wds: 24 | with open('{}/googleSpider.txt'.format(self.save_fold_path), 'at') as f: 25 | key = 'site:*.{} {}'.format(self.domain, wd) 26 | f.writelines('[+] {} :\n'.format(key)) 27 | print('\t[+] google search -> [{}]'.format(key)) 28 | for each_result in search(key): 29 | f.writelines('{}\n'.format(each_result)) 30 | parseRet = urlparse(each_result) 31 | subdomain = parseRet.netloc 32 | if self.domain in subdomain and subdomain not in self.googleSubdomains: 33 | self.googleSubdomains.append(subdomain) 34 | 35 | return self.googleSubdomains 36 | -------------------------------------------------------------------------------- /Common/LogOutput.py: -------------------------------------------------------------------------------- 1 | ''' 2 | log output 3 | 4 | a = LogOutput() 5 | Logger_object = a.SetModuleName("Module_name") 6 | Looger_object.wrong("log_info") / Looger_object.error("log_info") / Looger_object.info("log_info") 7 | ''' 8 | 9 | import colorlog 10 | import logging 11 | 12 | 13 | class LogOutput(): 14 | _instance = None 15 | def __new__(cls, *args, **kwargs): 16 | if cls._instance is None: 17 | cls._instance = object.__new__(cls, *args, **kwargs) 18 | return cls._instance 19 | def __init__(self): 20 | self.mycolorlog = colorlog 21 | self.handler = self.mycolorlog.StreamHandler() 22 | formatter = self.mycolorlog.ColoredFormatter( 23 | '%(log_color)s[+] %(asctime)s [%(name)s] [%(levelname)s] %(message)s%(reset)s', 24 | datefmt=None, 25 | reset=True, 26 | log_colors={ 27 | 'DEBUG': 'cyan', 28 | 'INFO': 'green', 29 | 'WARNING': 'yellow', 30 | 'ERROR': 'red', 31 | 'CRITICAL': 'white,bg_red', 32 | 'Module': 'purple' 33 | }, 34 | secondary_log_colors={}, 35 | style='%' 36 | ) 37 | self.handler.setFormatter(formatter) 38 | 39 | 40 | def SetModuleName(self, module_name=''): 41 | if module_name == '': 42 | self.logger = self.mycolorlog.getLogger('Seach_all') 43 | else: 44 | self.logger = self.mycolorlog.getLogger('Seach_all {}'.format(module_name)) 45 | self.logger.addHandler(self.handler) 46 | self.logger.setLevel(self.mycolorlog.INFO) 47 | return self.logger -------------------------------------------------------------------------------- /Plugins/InfoSearch/infosearchapi.py: -------------------------------------------------------------------------------- 1 | ''' 2 | InfoSearchApi 3 | 4 | :return 5 | type : json 6 | ''' 7 | import random 8 | 9 | from Common.LogOutput import LogOutput 10 | logger_object = LogOutput() 11 | logger = logger_object.SetModuleName("InfoSearch") 12 | import sys 13 | 14 | class InfoSearchApi(): 15 | def __init__(self): 16 | pass 17 | def GetSubdomain_ips(self, domain, proxies): 18 | if domain: 19 | from Plugins.InfoSearch.Subdomain.subdomainapi import SubdomainApi 20 | subdomainobject = SubdomainApi(proxies) 21 | return subdomainobject.Run(domain) 22 | else: 23 | logger.error("Need a target domain！") 24 | sys.exit() 25 | 26 | def GetDomains(self, domain): 27 | if domain: 28 | from Plugins.InfoSearch.Domain.domainapi import DomainApi 29 | domainobject = DomainApi() 30 | return domainobject.run_domain(domain) 31 | else: 32 | logger.error("Need a target domain！") 33 | sys.exit() 34 | 35 | def get_proxy(self): 36 | with open("./Common/ProxyPool/DomesticProxyPool.txt", "r") as f: 37 | proxies = [proxy.strip() for proxy in f.readlines()] 38 | # current_path = os.path.dirname(__file__) 39 | # f = open(current_path +"/", "r") 40 | # proxies = f.readlines() 41 | return proxies 42 | 43 | def Run(self, domain): 44 | # proxies = self.get_proxy() 45 | # proxy = random.choice(proxies) 46 | Domains, companyname = self.GetDomains(domain) 47 | 48 | for domain in Domains: 49 | subdomain_ips, key_links = self.GetSubdomain_ips(domain[0]) 50 | 51 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ThirdPartyPlatform/certificate.py: -------------------------------------------------------------------------------- 1 | from Common.LogOutput import LogOutput 2 | logger_object = LogOutput() 3 | logger = logger_object.SetModuleName("certificate") 4 | import sys 5 | 6 | import requests 7 | import re 8 | 9 | # crt.sh 10 | class Certificate(): 11 | def __init__(self): 12 | self.header = { 13 | "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36", 14 | } 15 | self.subdomains = [] 16 | 17 | # def Get_subdomain(self): 18 | 19 | def run(self, domain): 20 | try: 21 | res = requests.get("https://crt.sh/?q={}".format(domain), headers=self.header) 22 | before_subdomains = re.findall(r"(.*.{})*?".format(domain), res.text) 23 | before_subdomains = list(set(before_subdomains)) 24 | for subdomains in before_subdomains: 25 | if '
' in subdomains: 26 | subdomain_list = subdomains.split("
") 27 | for subdomain in subdomain_list: 28 | if '*' in subdomain or '@' in subdomain: 29 | continue 30 | self.subdomains.append(subdomain) 31 | continue 32 | if '*' in subdomains or '@' in subdomains: 33 | continue 34 | self.subdomains.append(subdomains) 35 | except: 36 | logger.error("There are too many exceptions requested, you need to check.") 37 | sys.exit() 38 | return list(set(self.subdomains)) 39 | 40 | # 测试成功 41 | # a = Certificate() 42 | # print(a.run('tjut.edu.cn')) -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ThirdPartyPlatform/netcraft.py: -------------------------------------------------------------------------------- 1 | import time 2 | 3 | from Common.LogOutput import LogOutput 4 | logger_object = LogOutput() 5 | logger = logger_object.SetModuleName("netcraft") 6 | import sys 7 | from urllib.parse import urlparse 8 | import requests 9 | import re 10 | 11 | 12 | # netcraft 13 | class Netcraft(): 14 | def __init__(self): 15 | self.header = { 16 | "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36", 17 | } 18 | self.subdomains = [] 19 | self.proxy = {"http": "socks5://171.107.184.247:1080/", "https": "socks5://171.107.184.247:1080/"} 20 | 21 | def GetSubdomains(self, url): 22 | res = requests.get(url, headers=self.header, proxies=self.proxy) 23 | if "Sorry, no results were found." in res.text: 24 | return 0 25 | links = re.findall(r'Next Page ', res.text) 30 | for hr in href: 31 | url = "https://searchdns.netcraft.com"+hr 32 | res = requests.get(url, headers=self.header, proxies=self.proxy) 33 | links = re.findall(r' 3.2 to run search_all.') 11 | sys.exit() 12 | 13 | 14 | 15 | def InfoSearch(domain): 16 | from Plugins.InfoSearch.infosearchapi import InfoSearchApi 17 | infosearchapi = InfoSearchApi() 18 | infosearchapi.Run(domain) 19 | 20 | def GetPorxies(): 21 | from Common import GetProxies 22 | GetProxies.run_getSocksProxy() 23 | 24 | 25 | def Banner(): 26 | banner = ''' 27 | ________ _______ ________ ________ ________ ___ ___ ________ ___ ___ 28 | |\ ____\|\ ___ \ |\ __ \|\ __ \|\ ____\|\ \|\ \|\ __ \|\ \ |\ \ 29 | \ \ \___|\ \ __/|\ \ \|\ \ \ \|\ \ \ \___|\ \ \\\\\ \ \ \|\ \ \ \ \ \ \ 30 | \ \_____ \ \ \_|/_\ \ __ \ \ _ _\ \ \ \ \ __ \ \ __ \ \ \ \ \ \ 31 | \|____|\ \ \ \_|\ \ \ \ \ \ \ \\\\ \\\\ \ \____\ \ \ \ \ \ \ \ \ \ \____\ \ \____ 32 | ____\_\ \ \_______\ \__\ \__\ \__\\\\ _\\\\ \_______\ \__\ \__\ \__\ \__\ \_______\ \_______\\ 33 | |\_________\|_______|\|__|\|__|\|__|\|__|\|_______|\|__|\|__|\|__|\|__|\|_______|\|_______| 34 | \|_________| author:Gungnir 35 | ''' 36 | print('\033[35m' + banner + '\033[0m') 37 | 38 | 39 | def Init_set(): 40 | Banner() 41 | 42 | global domain, WhetherRunInfoSearch, WhetherGetProxies 43 | 44 | import argparse 45 | 46 | parser = argparse.ArgumentParser(description=''' 47 | (￢︿̫̿￢☆)，哼，可恶! 竟然发现我了. 48 | (ˉ▽￣～) 既然发现我了，那就给你吧！ 49 | ''') 50 | parser.add_argument("-d", "--domain", help="Need a target domain", dest="domain") 51 | parser.add_argument("-i", "--InfoSearch", help="Conduct information collection", dest="WhetherRunInfoSearch", action="store_true") 52 | parser.add_argument("-p", "--Proxy", help="Get proxies", dest="WhetherGetProxies", action="store_true") 53 | 54 | args = parser.parse_args() 55 | options = vars(args) 56 | 57 | 58 | domain, WhetherRunInfoSearch, WhetherGetProxies = options['domain'], options['WhetherRunInfoSearch'], options['WhetherGetProxies'] 59 | 60 | # GetProxies 61 | if(WhetherGetProxies): 62 | GetPorxies() 63 | 64 | 65 | # 判断用户要不要信息收集 66 | if(WhetherRunInfoSearch): 67 | # GetSubdomains(domain) 68 | InfoSearch(domain) 69 | # else: 70 | # logger.error('At least one run command parameter is required, please use the --help or -h command for details') 71 | # sys.exit() 72 | 73 | if __name__ == '__main__': 74 | 75 | 76 | 77 | '''初始化参数''' 78 | Init_set() 79 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ESD/ESD-0.0.29.dist-info/METADATA: -------------------------------------------------------------------------------- 1 | Metadata-Version: 2.1 2 | Name: ESD 3 | Version: 0.0.29 4 | Summary: Enumeration Sub Domains(枚举子域名) 5 | Home-page: https://github.com/FeeiCN/ESD 6 | Author: Feei 7 | Author-email: feei@feei.cn 8 | License: UNKNOWN 9 | Platform: UNKNOWN 10 | Classifier: Topic :: Security 11 | Classifier: Programming Language :: Python :: 3 12 | Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) 13 | Description-Content-Type: text/markdown 14 | Requires-Dist: colorlog 15 | Requires-Dist: aiodns 16 | Requires-Dist: aiohttp 17 | Requires-Dist: async-timeout 18 | Requires-Dist: requests 19 | Requires-Dist: backoff 20 | Requires-Dist: dnspython 21 | Requires-Dist: pysocks 22 | Requires-Dist: tqdm 23 | Requires-Dist: colorama 24 | 25 | # ESD(Enumeration Sub Domain) 26 | 27 | [![PyPI](https://img.shields.io/pypi/v/ESD.svg)](https://pypi.org/project/ESD/) 28 | ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/ESD.svg) 29 | ![license](https://img.shields.io/github/license/FeeiCN/ESD.svg) 30 | 31 | [![asciicast](https://asciinema.org/a/15WhUe40eEhSbwAXZdf2RQdq9.png)](https://asciinema.org/a/15WhUe40eEhSbwAXZdf2RQdq9) 32 | 33 | ## 优势 34 | #### 支持泛解析域名 35 | > 基于`RSC`（响应相似度对比）技术对泛解析域名进行枚举（受网络质量、网站带宽等影响，速度会比较慢） 36 | 37 | 基于`aioHTTP`获取一个不存在子域名的响应内容，并将其和字典子域名响应进行相似度比对。 38 | 超过阈值则说明是同个页面，否则则为可用子域名，并对最终子域名再次进行响应相似度对比。 39 | 40 | #### 更快的速度 41 | > 基于`AsyncIO`异步协程技术对域名进行枚举（受网络和DNS服务器影响会导致扫描速度小幅波动，基本在250秒以内） 42 | 43 | 基于`AsyncIO`+`aioDNS`将比传统多进程/多线程/gevent模式快50%以上。 44 | 通过扫描`qq.com`，共`620328`条规则，找到`3421`个域名，耗时`15`分钟左右。 45 | 46 | 更新于2021年9月，经实测多个DNS Server做了请求数限制，大并发下存在大量连接超时和异常导致遗漏情况大幅增加，目前通过限制DNS服务器以及并发数来解决，因此建议不要过于追求速度，通过设计更合理的触发时间来解决速度变慢问题。 47 | 48 | #### 更全的字典 49 | > 融合各类字典，去重后共620328条子域名字典 50 | 51 | - 通用字典 52 | - 单字母、单字母+单数字、双字母、双字母+单数字、双字母+双数字、三字母、四字母 53 | - 单数字、双数字、三数字 54 | - 域名解析商公布使用最多的子域名 55 | - DNSPod: dnspod-top2000-sub-domains.txt 56 | - 其它域名爆破工具字典 57 | - subbrute: names_small.txt 58 | - subDomainsBrute: subnames_full.txt 59 | 60 | #### 更多的收集渠道 61 | - [X] 收集DNSPod接口泄露的子域名 62 | - [X] 收集页面响应内容中出现的子域名 63 | - [X] 收集跳转过程中的子域名 64 | - [X] 收集HTTPS证书透明度子域名 65 | - [X] 收集DNS域传送子域名 66 | 67 | #### DNS服务器 68 | - 解决各家DNS服务商对于网络线路出口判定不一致问题 69 | - 解决各家DNS服务商缓存时间不一致问题 70 | - 解决随机DNS问题，比如fliggy.com、plu.cn等 71 | - 根据网络情况自动剔除无效DNS，提高枚举成功率 72 | 73 | ## 使用 74 | 仅在macOS、Linux的Python3下验证过 75 | ```bash 76 | # 安装 77 | pip install esd 78 | 79 | # 升级 80 | pip install esd --upgrade 81 | ``` 82 | **CLI命令行使用** 83 | ```bash 84 | # 扫描单个域名 85 | esd -d qq.com 86 | 87 | # debug模式扫描单个域名 88 | esd=debug esd -d qq.com 89 | 90 | # 扫描多个域名（英文逗号分隔） 91 | esd --domain qq.com,tencent.com 92 | 93 | # 扫描单个域名且过滤子域名中单个特定响应内容 94 | esd --domain mogujie.com --filter 搜本店 95 | 96 | # 扫描单个域名且过滤子域名中多个特定响应内容 97 | esd --domain mogujie.com --filter 搜本店,收藏店铺 98 | 99 | # 扫描文件（文件中每行一个域名） 100 | esd --file targets.txt 101 | 102 | # 跳过相似度对比（开启这个选项会把所有泛解析的域名都过滤掉） 103 | esd --domain qq.com --skip-rsc 104 | 105 | # 平均分割字典，加快爆破 106 | esd --domain qq.com --split 1/4 107 | 108 | # 使用DNS域传送漏洞获取子域名 109 | esd --domain qq.com --dns-transfer 110 | 111 | # 使用HTTPS证书透明度获取子域名 112 | esd --domain qq.com --ca-info 113 | 114 | ``` 115 | 116 | **程序调用** 117 | ```python 118 | from ESD import EnumSubDomain 119 | domains = EnumSubDomain('feei.cn').run() 120 | ``` 121 | 122 | ## 后续 123 | - 提升扫描速度 124 | - 支持三级子域名，多种组合更多可能性 125 | 126 | ## 文档 127 | - https://github.com/FeeiCN/ESD/wiki 128 | 129 | 130 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/IsCND/cdn-domain.conf: -------------------------------------------------------------------------------- 1 | #蓝汛 2 | gslbsvc.net.cn 3 | chinacache.com.cn 4 | ccgslb.net 5 | gslbsvc.com.cn 6 | cdnsvc.cn 7 | ccgslb.cn 8 | cdn2cdn.net 9 | blueit.org.cn 10 | cc-1.com 11 | cdnsvc.net 12 | ccgslb.com.cn 13 | lxsvc.net 14 | lxsvc.cn 15 | chinacache.org 16 | gslbsvc.com 17 | ccgslb.com 18 | gslbsvc.cn 19 | chinacache.com 20 | igslb.net 21 | chinacache.net 22 | cdnsvc.net.cn 23 | ccgslb.net.cn 24 | hd-cdn.com 25 | cdnsvc.com.cn 26 | cdnsvc.com 27 | speedupchina.net 28 | b2r.com.cn 29 | blueit.com 30 | lxsvc.cn 31 | gslbsvc.net 32 | speedupchina.com 33 | cc-cps.com 34 | cc-cps.com.cn 35 | cc-cps.net 36 | cc-cps.mobi 37 | cc-cps.cn 38 | ccbench.com 39 | webluker.com 40 | ccindex.cn 41 | ccindex.com.cn 42 | ccmplus.com.cn 43 | ccmplus.net 44 | ccmplus.cn 45 | 46 | #Webluker 47 | xgslb.net 48 | 49 | #网宿 50 | wscdns.com 51 | ourglb0.com 52 | wsngb.com 53 | lxdns.com 54 | lxdns.net 55 | 51cdn.com 56 | chinanetcenter.com 57 | netcenter.com.cn 58 | wangsu.com 59 | ourwebat.com 60 | ourwebcdn.com 61 | 62 | #快网 63 | fastweb.com.cn 64 | fwdns.net 65 | hadns.net 66 | cachecn.net 67 | sz-dns.net 68 | cachecn.com 69 | cloudcdn.cn 70 | 1test.cn 71 | 5test.cn 72 | fsspace.com 73 | fsspace.com.cn 74 | fsspace.cn 75 | cloudcdn.net 76 | fastwebcdn.com 77 | hacdn.com 78 | fwcdn.com 79 | fwcdn.net 80 | hacdn.net 81 | cloudglb.com 82 | cloudxns.net 83 | cloudglb.net 84 | cloudxns.com 85 | cloudtcp.net 86 | myxns.cn 87 | newdefend.cn 88 | myxns.net.cn 89 | myxns.com.cn 90 | myxns.org 91 | newdefend.net 92 | newdefend.org 93 | newdefend.net.cn 94 | newdefend.com.cn 95 | newdefend.org.cn 96 | newdefend.com 97 | ffdns.net 98 | fwmob.com 99 | tlgslb.com 100 | fastcdn.com 101 | 102 | #阿里云CDN 103 | kunlunea.com 104 | kunlunso.com 105 | kunlunwe.com 106 | kunlunno.com 107 | kunlunaq.com 108 | kunlunpi.com 109 | kunlunra.com 110 | kunlungr.com 111 | kunlunhuf.com 112 | kunlunsl.com 113 | kunlunar.com 114 | kunlunta.com 115 | kunlungem.com 116 | kunluncan.com 117 | kunlunle.com 118 | kunlunvi.com 119 | kunlunli.com 120 | kunlunsc.com 121 | kunlunsa.com 122 | kunlunca.com 123 | alikunlun.net 124 | alikunlun.com 125 | 126 | #腾讯CDN 127 | qcloud.com 128 | myqcloud.com 129 | tcdn.qq.com 130 | cdntip.com 131 | 132 | #百度云CDN 133 | bdydns.net 134 | bcedns.net 135 | bcedns.com 136 | bcedns.cn 137 | bdydns.com 138 | baiduyundns.net 139 | bdydns.cn 140 | baiduyundns.com 141 | baiduyundns.cn 142 | 143 | #百度云加速 144 | yunjiasu-cdn.net 145 | 146 | #七牛 147 | qiniudn.com 148 | qbox.me 149 | clouddn.com 150 | qiniudns.com 151 | 152 | #又拍云 153 | aicdn.com 154 | 155 | #360网站卫士 156 | dnspao.com 157 | 360wzb.cn 158 | 159 | #同兴万点CDN 160 | cdngc.net 161 | cdnetworks.net 162 | gccdn.net 163 | 164 | #CDN联盟 165 | cdnudns.com 166 | 167 | #白山云 168 | qingcdn.com 169 | 170 | #CloudFlare 171 | cdn.cloudflare.net 172 | cloudflare 173 | 174 | #未知 175 | hdslb.com 176 | hdslb.net 177 | tbcache.com 178 | 21okglb.cn 179 | 21vianet.com.cn 180 | 21vokglb.cn 181 | 360wzb.com 182 | acadn.com 183 | akadns.net 184 | akamai-staging.net 185 | akamai.com 186 | akamai.net 187 | akamaitech.net 188 | akamaized.net 189 | alicloudlayer.com 190 | aliyun-inc.com 191 | alicloudsec.com 192 | aliyuncs.com 193 | amazonaws.com 194 | aodianyun.com 195 | aqb.so 196 | awsdns 197 | azureedge.net 198 | bitgravity.com 199 | cachefly.net 200 | chinaidns.net 201 | cloudfront.net 202 | dnion.com 203 | edgesuite.net 204 | ewcache.com 205 | fastcache.com 206 | fastly.net 207 | footprint.net 208 | fpbns.net 209 | hichina.com 210 | hichina.net 211 | incapdns.net 212 | jiashule.com 213 | okglb.com 214 | txnetworks.cn 215 | ucloud.cn 216 | unicache.com 217 | verygslb.com 218 | vo.llnwd.net 219 | cloudfront 220 | edgekey 221 | fastly 222 | akamai 223 | edgecast 224 | cachefly 225 | fpbns 226 | footprint 227 | llnwd 228 | netdna 229 | bitgravity 230 | azureedge 231 | telefonica 232 | dnsv1 233 | ngenix 234 | incapdns 235 | clients.turbobytes.net 236 | akamaiedge.net 237 | akamaitechnologies.com 238 | gslb.tbcache.com 239 | att-dsa.net 240 | bluehatnetwork.com 241 | c3cache.net 242 | cncssr.chinacache.net 243 | cloudflare.com 244 | fastlylb.net 245 | googlesyndication. 246 | googleusercontent.com 247 | l.doubleclick.net 248 | inscname.net 249 | insnw.net 250 | llnwd.net 251 | lldns.net 252 | netdna-ssl.com 253 | netdna.com 254 | stackpathdns.com 255 | instacontent.net 256 | mirror-image.net 257 | cap-mii.net 258 | swiftserve.com 259 | gslb.taobao.com 260 | vo.msecnd.net 261 | ay1.b.yahoo.com 262 | zenedge.net -------------------------------------------------------------------------------- /Common/GetProxies.py: -------------------------------------------------------------------------------- 1 | from Common.LogOutput import LogOutput 2 | logger_object = LogOutput() 3 | logger = logger_object.SetModuleName("GetProxies") 4 | 5 | import sys 6 | 7 | import requests 8 | import base64 9 | import json 10 | import configparser 11 | from threading import Thread 12 | from queue import Queue 13 | import random 14 | import urllib3 15 | import datetime 16 | 17 | urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning) 18 | 19 | cf = configparser.ConfigParser() 20 | cf.read("./config.ini") 21 | secs = cf.sections() 22 | email = cf.get('fofa api', 'EMAIL') 23 | key = cf.get('fofa api', 'KEY') 24 | 25 | headers = {'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36', 'Connection': 'close'} 26 | 27 | size = 10000 28 | page = 1 29 | today = datetime.date.today() 30 | oneday = datetime.timedelta(days=1) 31 | yesterday = today - oneday 32 | 33 | 34 | # 访问百度和谷歌 35 | 36 | def curlWeb(socks5_proxys_queue, socksProxysDict): 37 | while not socks5_proxys_queue.empty(): 38 | proxy = socks5_proxys_queue.get() 39 | requests_proxies = {"http": "socks5://{}".format(proxy), "https": "socks5://{}".format(proxy)} 40 | baidu_url = "https://www.baidu.com" 41 | google_url = "https://www.google.com" 42 | 43 | try: 44 | res2 = requests.get(url=google_url, headers=headers, timeout=10, verify=False, proxies=requests_proxies) 45 | if res2.status_code == 200: 46 | logger.info("{} 成功访问谷歌 [{}]".format(proxy, res2.status_code)) 47 | socksProxysDict["google"].append(proxy) 48 | continue 49 | except Exception as e: 50 | pass 51 | 52 | try: 53 | res = requests.get(url=baidu_url, headers=headers, timeout=10, verify=False, proxies=requests_proxies) 54 | if res.status_code == 200: 55 | logger.info("{} 成功访问百度 [{}]".format(proxy, res.status_code)) 56 | socksProxysDict["baidu"].append(proxy) 57 | except Exception as e: 58 | pass 59 | 60 | 61 | def query_socks5(yesterday): 62 | query_str = r'protocol=="socks5" && "Version:5 Method:No Authentication(0x00)" && after="{}" && country="CN"'.format(yesterday) 63 | qbase64 = str(base64.b64encode(query_str.encode(encoding='utf-8')), 'utf-8') 64 | url = r'https://fofa.so/api/v1/search/all?email={}&key={}&qbase64={}&size={}&page={}&fields=host,title,ip,domain,port,country,city,server,protocol'.format(email, key, qbase64, size, page) 65 | print(url) 66 | socks5_proxys = [] 67 | try: 68 | ret = json.loads(requests.get(url=url, headers=headers, timeout=10, verify=False).text) 69 | fofa_Results = ret['results'] 70 | for result in fofa_Results: 71 | host, title, ip, domain, port, country, city, server, protocol = result 72 | proxy = ip + ":" + port 73 | socks5_proxys.append(proxy) 74 | except Exception as e: 75 | logger.error('fofa inquire {} : {}'.format(query_str, e.args)) 76 | return socks5_proxys 77 | 78 | def SaveToProxyPool(baidu_proxies, google_proxies): 79 | try: 80 | with open("./Common/ProxyPool/DomesticProxyPool.txt", "a") as f: 81 | for baidu_proxy in baidu_proxies: 82 | f.write(baidu_proxy+'\n') 83 | logger.info("The domestic proxies is stored in the file path as Common/ProxyPool/DomesticProxyPool.txt") 84 | with open("./Common/ProxyPool/ForeignProxyPool.txt", "a") as f: 85 | for google_proxy in google_proxies: 86 | f.write(google_proxy+'\n') 87 | logger.info("The foreign proxies is stored in the file path as Common/ProxyPool/ForeignProxyPool.txt") 88 | except: 89 | logger.error("Error opening file") 90 | sys.exit() 91 | def run_getSocksProxy(): 92 | logger.info("Start Searching Proxies") 93 | socksProxysDict = {"baidu": [], "google": []} 94 | socks5_proxys = query_socks5(yesterday) 95 | socks5_proxys_queue = Queue(-1) 96 | if socks5_proxys: 97 | # 随机取1000个代理ip 98 | for eachSocks5 in random.sample(socks5_proxys, 50): 99 | socks5_proxys_queue.put(eachSocks5) 100 | 101 | threads = [] 102 | for num in range(100): 103 | t = Thread(target=curlWeb, args=(socks5_proxys_queue, socksProxysDict)) 104 | threads.append(t) 105 | t.start() 106 | for t in threads: 107 | t.join() 108 | 109 | baidu_proxies = socksProxysDict.get('baidu') 110 | google_proxies = socksProxysDict.get('google') 111 | SaveToProxyPool(baidu_proxies, google_proxies) 112 | logger.info("Find {} DomesticProxies and {} ForeignProxies".format(len(baidu_proxies), len(google_proxies))) 113 | logger.info("End Searching Proxies") 114 | # return baidu_proxies, google_proxies 115 | 116 | 117 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Bing/bing.py: -------------------------------------------------------------------------------- 1 | import requests 2 | import threading 3 | import re 4 | 5 | from urllib.parse import urlparse 6 | 7 | class BingSpider(): 8 | def __init__(self, page): 9 | self.header = { 10 | "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36", 11 | # "Cookie": "MUID=0D37497B3A146A9009A459B93B2C6B63; _EDGE_V=1; SRCHD=AF=NOFORM; SRCHUID=V=2&GUID=BBE8EF5D85544AFFABC19E151D05B49F&dmnchg=1; _SS=SID=14FD12E54B646094309102274AC8612F; MUIDB=0D37497B3A146A9009A459B93B2C6B63; _EDGE_S=SID=14FD12E54B646094309102274AC8612F&mkt=zh-cn&ui=zh-cn; SRCHUSR=DOB=20210930&T=1632976149000&TPC=1632961354000; ipv6=hit=1632979751088&t=4; SNRHOP=I=&TS=; SRCHHPGUSR=SRCHLANG=zh-Hans&BZA=0&BRW=NOTP&BRH=M&CW=724&CH=722&SW=1536&SH=864&DPR=1.25&UTC=480&DM=1&WTS=63768572949&HV=1632976747", 12 | } 13 | self.timeout = 5 14 | self.PAGES = page # 子域名要爬取的页数 15 | self.KEY_PAGES = 1 # 关键词要爬取的页数 16 | self.subdomains = [] 17 | self.key_links = [] 18 | self.keywords = ['inurl:admin', 'inurl:login', 'inurl:system', 'inurl:register', 'inurl:upload', 'intitle:后台', 'intitle:系统', 'intitle:登录'] 19 | self.errorurls = [] 20 | 21 | def info_processing(self, text): 22 | return re.findall(r'

(.*?)

', text) 23 | 24 | 25 | def get_info(self, domain, page ,real_page): 26 | url = r"https://cn.bing.com/search?q=site:{}&first={}".format(domain, page) 27 | print('[+]page:第{}页 关键词:[site:{}] Requesting:[{}] '.format(real_page, domain, url)) 28 | try: 29 | res = requests.get(url=url, headers=self.header, timeout=self.timeout) 30 | tmp_subdomains = self.info_processing(res.text) 31 | for tmp_subdomain in tmp_subdomains: 32 | self.subdomains += [urlparse(tmp_subdomain[0]).netloc] 33 | except Exception as e: 34 | self.subdomains += [] 35 | self.errorurls[url] = e 36 | 37 | def get_key_info(self, domain, keyword='', page=1, real_page=1): 38 | #https://cn.bing.com/search?q=site%3Atjut.edu.cn+inurl:upload&qs=n&form=QBRE&sp=-1&pq=sitetjut.edu.cn+inurl:upload&sc=1-16&sk=&cvid=6734767D90664B77800EA8092B6BB8DD&first=1 39 | #https://cn.bing.com/search?q=site%3Abaidu.com&qs=n&form=QBRE&sp=-1&pq=site%3Atjut.edu.cn&sc=1-16&sk=&cvid=6734767D90664B77800EA8092B6BB8DD 40 | url = r"https://cn.bing.com/search?q=site:{}{}&first={}".format(domain, '+'+keyword, page) 41 | print('[+]page:第{}页 关键词:[site:{} {}] Requesting:[{}] '.format(real_page, domain, keyword, url)) 42 | try: 43 | res = requests.get(url=url, headers=self.header, timeout=self.timeout) 44 | tmp_key_links = self.info_processing(res.text) 45 | for tmp_key_link in tmp_key_links: 46 | self.key_links += [(tmp_key_link[1], tmp_key_link[0])] 47 | self.subdomains.append(urlparse(tmp_key_link[0]).netloc) 48 | except Exception as e: 49 | self.key_links += [] 50 | self.errorurls[url] = e 51 | 52 | def run(self, domain): 53 | 54 | threads = [] 55 | # tmp_page = 1 56 | # self.get_key_info(domain, self.keyword, tmp_page) 57 | # self.get_info(domain, tmp_page) 58 | for keyword in self.keywords: 59 | for page in range(1, self.KEY_PAGES+1): 60 | if page == 1: 61 | tmp_page = 1 62 | elif page == 2: 63 | tmp_page = 2 64 | else: 65 | tmp_page = (page-2)*10+2 66 | t = threading.Thread(target=self.get_key_info, args=(domain, keyword, tmp_page, page)) 67 | t.start() 68 | threads.append(t) 69 | if(len(threads)>5): 70 | for t in threads: 71 | t.join() 72 | threads = [] 73 | 74 | for page in range(1, self.PAGES+1): 75 | if page == 1: 76 | tmp_page = 1 77 | elif page == 2: 78 | tmp_page = 2 79 | else: 80 | tmp_page = (page - 2) * 10 + 2 81 | t = threading.Thread(target=self.get_info, args=(domain, tmp_page, page)) 82 | t.start() 83 | threads.append(t) 84 | if (len(threads) > 5): 85 | for t in threads: 86 | t.join() 87 | threads = [] 88 | for t in threads: 89 | t.join() 90 | 91 | if len(self.errorurls) >= 3: 92 | cprint("[+]There are too many exceptions requested, you need to check.", "red") 93 | cprint("[+]The exception information is", "red") 94 | for key in self.errorurls.keys(): 95 | cprint("[+]url:{}\n>>Err:{}".format(key, self.errorurls[key]), "red") 96 | 97 | return list(set(self.subdomains)), list(set(self.key_links)) 98 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Domain/domainapi.py: -------------------------------------------------------------------------------- 1 | import requests 2 | import re 3 | from urllib.parse import quote 4 | import json 5 | import math 6 | 7 | from Common.LogOutput import LogOutput 8 | logger_object = LogOutput() 9 | 10 | logger = logger_object.SetModuleName('Domain') 11 | 12 | headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:46.0) Gecko/20100101 Firefox/46.0'} 13 | 14 | class DomainApi(): 15 | def __init__(self): 16 | # self.proxy = {"http": "http://{}".format(proxy), "https": "https://{}".format(proxy)} 17 | pass 18 | def chinazApi(self, domain): 19 | # 解析chinaz返回结果的json数据 20 | def parse_json(json_ret): 21 | chinazNewDomains = [] 22 | results = json_ret['data'] 23 | for result in results: 24 | companyName = result['webName'] 25 | newDomain = result['host'] 26 | time = result['verifyTime'] 27 | chinazNewDomains.append((companyName, newDomain, time)) 28 | chinazNewDomains = list(set(chinazNewDomains)) 29 | return chinazNewDomains 30 | 31 | 32 | chinazNewDomains = [] 33 | tempDict = {} 34 | tempList = [] 35 | 36 | # 获取域名的公司名字 37 | url = r'http://icp.chinaz.com/{}'.format(domain) 38 | try: 39 | res = requests.get(url=url, headers=headers, allow_redirects=False, verify=False, timeout=10) 40 | except Exception as e: 41 | logger.error(url+' '+e.args) 42 | return [], [] 43 | text = res.text 44 | 45 | companyName = re.search("var kw = '([\S]*)'", text) 46 | if companyName: 47 | companyName = companyName.group(1) 48 | logger.info('公司名: {}'.format(companyName)) 49 | companyNameUrlEncode = quote(str(companyName)) 50 | else: 51 | logger.warning('没有匹配到公司名') 52 | return [], [] 53 | 54 | # 备案反查域名 55 | headers['Content-Type'] = 'application/x-www-form-urlencoded; charset=UTF-8' 56 | url = 'http://icp.chinaz.com/Home/PageData' 57 | data = 'pageNo=1&pageSize=20&Kw=' + companyNameUrlEncode 58 | try: 59 | res = requests.post(url=url, headers=headers, data=data, allow_redirects=False, verify=False, timeout=10) 60 | except Exception as e: 61 | logger.error('{} {}'.format(url, e.args)) 62 | return [], [] 63 | 64 | json_ret = json.loads(res.text) 65 | if 'amount' not in json_ret.keys(): 66 | return chinazNewDomains, [] 67 | amount = json_ret['amount'] 68 | pages = math.ceil(amount / 20) 69 | logger.info('页数: {}'.format(pages)) 70 | tempList.extend(parse_json(json_ret)) 71 | 72 | # 继续获取后面页数 73 | for page in range(2, pages+1): 74 | logger.info('请求第{}页'.format(page)) 75 | data = 'pageNo={}&pageSize=20&Kw='.format(page) + companyNameUrlEncode 76 | try: 77 | res = requests.post(url=url, headers=headers, data=data, allow_redirects=False, verify=False, timeout=10) 78 | json_ret = json.loads(res.text) 79 | tempList.extend(parse_json(json_ret)) 80 | except Exception as e: 81 | logger.error('{} {}'.format(url, e.args)) 82 | 83 | for each in tempList: 84 | if each[1] not in tempDict: 85 | tempDict[each[1]] = each 86 | chinazNewDomains.append(each) 87 | 88 | return chinazNewDomains, companyName 89 | 90 | def run_domain(self, domain): 91 | beianNewDomains = [] 92 | chinazNewDomains, companyName = self.chinazApi(domain) 93 | 94 | tempDict = {} 95 | for each in chinazNewDomains: 96 | if each[1] not in tempDict: 97 | tempDict[each[1]] = each 98 | beianNewDomains.append(each) 99 | 100 | logger.info("去重后共计{}个顶级域名".format(len(beianNewDomains))) 101 | print("\033[33m"+"The top-level domain name is shown below"+"\033[0m") 102 | 103 | for _ in beianNewDomains: 104 | print(_) 105 | 106 | p = re.compile("[^0-9a-zA-Z.]+") 107 | judge = 'y' 108 | for _ in beianNewDomains: 109 | if p.match(_[1]): 110 | logger.critical("I’m not sure if [{}] is a top-level domain name, you need to judge. (y/n)".format(_[1])) 111 | judge = input() 112 | while(judge != 'y' and judge !='n'): 113 | logger.critical("I’m not sure if [{}] is a top-level domain name, you need to judge. (y/n)".format(_[1])) 114 | judge = input() 115 | if(judge == 'y'): 116 | continue 117 | else: 118 | beianNewDomains.remove(_) 119 | else: 120 | continue 121 | logger.info("A total of {} top-level domain name after screening".format(len(beianNewDomains))) 122 | for _ in beianNewDomains: 123 | print(_[1]) 124 | 125 | return beianNewDomains, companyName 126 | # [('同济大学浙江学院', 'tjzj.edu.cn', '2021-01-14')] 同济大学浙江学院 -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Google/docs/conf.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # 3 | # googlesearch documentation build configuration file, created by 4 | # sphinx-quickstart on Tue Nov 6 12:25:12 2018. 5 | # 6 | # This file is execfile()d with the current directory set to its 7 | # containing dir. 8 | # 9 | # Note that not all possible configuration values are present in this 10 | # autogenerated file. 11 | # 12 | # All configuration values have a default; values that are commented out 13 | # serve to show the default. 14 | 15 | # If extensions (or modules to document with autodoc) are in another directory, 16 | # add these directories to sys.path here. If the directory is relative to the 17 | # documentation root, use os.path.abspath to make it absolute, like shown here. 18 | # 19 | import os 20 | import sys 21 | sys.path.insert(0, os.path.abspath('..')) 22 | 23 | 24 | # -- General configuration ------------------------------------------------ 25 | 26 | # If your documentation needs a minimal Sphinx version, state it here. 27 | # 28 | # needs_sphinx = '1.0' 29 | 30 | # Add any Sphinx extension module names here, as strings. They can be 31 | # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom 32 | # ones. 33 | extensions = ['sphinx.ext.autodoc', 34 | 'sphinx.ext.viewcode', 35 | 'sphinx.ext.githubpages'] 36 | 37 | # Add any paths that contain templates here, relative to this directory. 38 | templates_path = ['_templates'] 39 | 40 | # The suffix(es) of source filenames. 41 | # You can specify multiple suffix as a list of string: 42 | # 43 | # source_suffix = ['.rst', '.md'] 44 | source_suffix = '.rst' 45 | 46 | # The master toctree document. 47 | master_doc = 'index' 48 | 49 | # General information about the project. 50 | project = u'googlesearch' 51 | copyright = u'2018, Mario Vilas' 52 | author = u'Mario Vilas' 53 | 54 | # The version info for the project you're documenting, acts as replacement for 55 | # |version| and |release|, also used in various other places throughout the 56 | # built documents. 57 | # 58 | # The short X.Y version. 59 | version = u'' 60 | # The full version, including alpha/beta/rc tags. 61 | release = u'' 62 | 63 | # The language for content autogenerated by Sphinx. Refer to documentation 64 | # for a list of supported languages. 65 | # 66 | # This is also used if you do content translation via gettext catalogs. 67 | # Usually you set "language" from the command line for these cases. 68 | language = None 69 | 70 | # List of patterns, relative to source directory, that match files and 71 | # directories to ignore when looking for source files. 72 | # This patterns also effect to html_static_path and html_extra_path 73 | exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store'] 74 | 75 | # The name of the Pygments (syntax highlighting) style to use. 76 | pygments_style = 'sphinx' 77 | 78 | # If true, `todo` and `todoList` produce output, else they produce nothing. 79 | todo_include_todos = False 80 | 81 | 82 | # -- Options for HTML output ---------------------------------------------- 83 | 84 | # The theme to use for HTML and HTML Help pages. See the documentation for 85 | # a list of builtin themes. 86 | # 87 | html_theme = 'alabaster' 88 | 89 | # Theme options are theme-specific and customize the look and feel of a theme 90 | # further. For a list of options available for each theme, see the 91 | # documentation. 92 | # 93 | # html_theme_options = {} 94 | 95 | # Add any paths that contain custom static files (such as style sheets) here, 96 | # relative to this directory. They are copied after the builtin static files, 97 | # so a file named "default.css" will overwrite the builtin "default.css". 98 | html_static_path = ['_static'] 99 | 100 | # Custom sidebar templates, must be a dictionary that maps document names 101 | # to template names. 102 | # 103 | # This is required for the alabaster theme 104 | # refs: http://alabaster.readthedocs.io/en/latest/installation.html#sidebars 105 | html_sidebars = { 106 | '**': [ 107 | 'relations.html', # needs 'show_related': True theme option to display 108 | 'searchbox.html', 109 | ] 110 | } 111 | 112 | 113 | # -- Options for HTMLHelp output ------------------------------------------ 114 | 115 | # Output file base name for HTML help builder. 116 | htmlhelp_basename = 'googlesearchdoc' 117 | 118 | 119 | # -- Options for LaTeX output --------------------------------------------- 120 | 121 | latex_elements = { 122 | # The paper size ('letterpaper' or 'a4paper'). 123 | # 124 | # 'papersize': 'letterpaper', 125 | 126 | # The font size ('10pt', '11pt' or '12pt'). 127 | # 128 | # 'pointsize': '10pt', 129 | 130 | # Additional stuff for the LaTeX preamble. 131 | # 132 | # 'preamble': '', 133 | 134 | # Latex figure (float) alignment 135 | # 136 | # 'figure_align': 'htbp', 137 | } 138 | 139 | # Grouping the document tree into LaTeX files. List of tuples 140 | # (source start file, target name, title, 141 | # author, documentclass [howto, manual, or own class]). 142 | latex_documents = [ 143 | (master_doc, 'googlesearch.tex', u'googlesearch Documentation', 144 | u'Mario Vilas', 'manual'), 145 | ] 146 | 147 | 148 | # -- Options for manual page output --------------------------------------- 149 | 150 | # One entry per manual page. List of tuples 151 | # (source start file, name, description, authors, manual section). 152 | man_pages = [ 153 | (master_doc, 'googlesearch', u'googlesearch Documentation', 154 | [author], 1) 155 | ] 156 | 157 | 158 | # -- Options for Texinfo output ------------------------------------------- 159 | 160 | # Grouping the document tree into Texinfo files. List of tuples 161 | # (source start file, target name, title, author, 162 | # dir menu entry, description, category) 163 | texinfo_documents = [ 164 | (master_doc, 'googlesearch', u'googlesearch Documentation', 165 | author, 'googlesearch', 'Python bindings to the Google search engine.', 166 | 'Miscellaneous'), 167 | ] 168 | 169 | 170 | # -- Options for Epub output ---------------------------------------------- 171 | 172 | # Bibliographic Dublin Core info. 173 | epub_title = project 174 | epub_author = author 175 | epub_publisher = author 176 | epub_copyright = copyright 177 | 178 | # The unique identifier of the text. This can be a ISBN number 179 | # or the project homepage. 180 | # 181 | # epub_identifier = '' 182 | 183 | # A unique identification for the text. 184 | # 185 | # epub_uid = '' 186 | 187 | # A list of files that should not be packed into the epub file. 188 | epub_exclude_files = ['search.html'] 189 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Baidu/baidu.py: -------------------------------------------------------------------------------- 1 | 2 | import random 3 | 4 | import requests 5 | import threading 6 | import re 7 | from urllib.parse import urlparse 8 | from Common.LogOutput import LogOutput 9 | logger_object = LogOutput() 10 | logger = logger_object.SetModuleName("BaiduSpider") 11 | 12 | class MyThread(threading.Thread): 13 | def __init__(self,func,args=()): 14 | super(MyThread,self).__init__() 15 | self.func = func 16 | self.args = args 17 | def run(self): 18 | self.result = self.func(*self.args) 19 | def get_result(self): 20 | try: 21 | return self.result 22 | except Exception: 23 | return None 24 | class BaiduSpider(): 25 | def __init__(self, proxies): 26 | self.header = { 27 | "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36", 28 | # "Cookie": "MUID=0D37497B3A146A9009A459B93B2C6B63; _EDGE_V=1; SRCHD=AF=NOFORM; SRCHUID=V=2&GUID=BBE8EF5D85544AFFABC19E151D05B49F&dmnchg=1; _SS=SID=14FD12E54B646094309102274AC8612F; MUIDB=0D37497B3A146A9009A459B93B2C6B63; _EDGE_S=SID=14FD12E54B646094309102274AC8612F&mkt=zh-cn&ui=zh-cn; SRCHUSR=DOB=20210930&T=1632976149000&TPC=1632961354000; ipv6=hit=1632979751088&t=4; SNRHOP=I=&TS=; SRCHHPGUSR=SRCHLANG=zh-Hans&BZA=0&BRW=NOTP&BRH=M&CW=724&CH=722&SW=1536&SH=864&DPR=1.25&UTC=480&DM=1&WTS=63768572949&HV=1632976747", 29 | } 30 | self.timeout = 5 31 | self.PAGES = 10000 # 子域名要爬取的页数 32 | self.KEY_PAGES = 2 # 关键词要爬取的页数 33 | self.subdomains = [] 34 | self.key_links = [] 35 | self.links = [] 36 | self.keywords = ['inurl:admin', 'inurl:login', 'inurl:system', 'inurl:register', 'inurl:upload', 'intitle:后台', 'intitle:系统', 'intitle:登录'] 37 | self.errorurls = {} # 存放第一次报异常的url，和异常原因， 3秒后重新进行请求。 38 | self.proxies = proxies 39 | 40 | def info_processing(self, text): 41 | return re.findall(r'
', text) 42 | 43 | 44 | 45 | def real_url(self, link): 46 | try: 47 | real_link = requests.get(link, allow_redirects=False, timeout=self.timeout).headers.get('Location') 48 | return real_link 49 | except: 50 | return link 51 | 52 | def get_proxy(self): 53 | return random.choice(self.proxies) 54 | 55 | 56 | def get_info(self, domain, page=0): 57 | url = r"https://www.baidu.com/s?wd=site:{}&pn={}0".format(domain, page) 58 | print('[+]page:第{}页 关键词:[site:{}] Requesting:[{}] '.format(page+1, domain, url)) 59 | # proxies = { 60 | # "http": "socks5://{}".format(proxy), 61 | # "https": "socks5://{}".format(proxy) 62 | # } 63 | try: 64 | res = requests.get(url=url, headers=self.header, timeout=self.timeout) 65 | if self.check_page(res.text, page+1) == 'Stop': 66 | return 'Stop' 67 | tmp_subdomains = self.info_processing(res.text) 68 | for tmp_subdomain in tmp_subdomains: 69 | tmp_real_link = self.real_url(tmp_subdomain[1]) 70 | self.subdomains += [urlparse(tmp_real_link).netloc] 71 | self.links.append(tmp_real_link) 72 | logger.info(urlparse(tmp_real_link).netloc) 73 | except Exception as e: 74 | self.subdomains += [] 75 | self.errorurls[url] = e 76 | 77 | 78 | 79 | def get_key_info(self, domain, keyword='', page=0): 80 | url = r"https://www.baidu.com/s?wd=site:{}{}&pn={}0".format(domain, '+'+keyword, page) 81 | print('[+]page:第{}页 关键词:[site:{} {}] Requesting:[{}] '.format(page+1, domain, keyword, url)) 82 | # proxies = { 83 | # "http": "socks5://{}".format(proxy), 84 | # "https": "socks5://{}".format(proxy) 85 | # } 86 | try: 87 | res = requests.get(url=url, headers=self.header, timeout=self.timeout) 88 | tmp_key_links = self.info_processing(res.text) 89 | for tmp_key_link in tmp_key_links: 90 | tmp_real_link = self.real_url(tmp_key_link[1]) 91 | self.key_links += [(tmp_key_link[0], tmp_real_link)] 92 | self.subdomains.append(urlparse(tmp_key_link[0]).netloc) 93 | logger.info(urlparse(tmp_real_link).netloc) 94 | except Exception as e: 95 | self.key_links += [] 96 | self.errorurls[url] = e 97 | 98 | 99 | def check_page(self, text, page): 100 | num = re.findall(r'(\d*?)', text) 101 | if (num != ['{}'.format(page)]) and (page != 1): 102 | return 'Stop' 103 | else: 104 | print("{}页没问题， num = {}".format(page, num)) 105 | return 'Contiune' 106 | 107 | 108 | ''' 109 | 返回一个子域名列表和一个包含title和连接的link列表 110 | ''' 111 | def run(self, domain): 112 | threads = [] 113 | num = 1 114 | flag = 1 115 | try: 116 | while flag != 0: 117 | # proxy = self.get_proxy() 118 | for page in range(0+(num-1)*5, 5+(num-1)*5): 119 | # t = MyThread(self.get_info, args=(domain, proxy, page)) 120 | t = MyThread(self.get_info, args=(domain, page)) 121 | t.start() 122 | threads.append(t) 123 | for t in threads: 124 | t.join() 125 | if(t.get_result() == 'Stop'): 126 | flag = 0 127 | num += 1 128 | 129 | 130 | for keyword in self.keywords: 131 | # proxy = self.get_proxy() 132 | for page in range(0, self.KEY_PAGES): 133 | t = threading.Thread(target=self.get_key_info, args=(domain, keyword, page)) 134 | # t = threading.Thread(target=self.get_key_info, args=(domain, proxy, keyword, page)) 135 | t.start() 136 | threads.append(t) 137 | for t in threads: 138 | t.join() 139 | 140 | # if len(self.errorurls)>=3: 141 | # cprint("[+]There are too many exceptions requested, you need to check.", "red") 142 | # cprint("[+]The exception information is", "red") 143 | # for key in self.errorurls.keys(): 144 | # cprint("[+]url:{}\n>>Err:{}".format(key, self.errorurls[key]), "red") 145 | except: 146 | return list(set(self.subdomains)), list(set(self.key_links)), list(set(self.links)) 147 | # # print(set(self.subdomains)), list(set(self.key_links)) 148 | return list(set(self.subdomains)), list(set(self.key_links)), list(set(self.links)) -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/subdomainapi.py: -------------------------------------------------------------------------------- 1 | ''' 2 | 得到subdomain的api 3 | ''' 4 | import sys 5 | import requests 6 | 7 | from Common.LogOutput import LogOutput 8 | 9 | logger_object = LogOutput() 10 | logger = logger_object.SetModuleName("subdomains") 11 | 12 | class SubdomainApi(): 13 | 14 | def __init__(self): 15 | self.global_subdomains = [] 16 | self.global_subdomains_ips = [] 17 | self.global_key_links = [] 18 | self.links = [] 19 | self.global_CDNSubdomainsDict = [] 20 | # self.proxies = proxies 21 | 22 | def WebSpiderSubdomains(self, domain): 23 | # proxies = self.proxies 24 | def BaiduSpider(domain): 25 | logger.info('Start Baidu Spider') 26 | 27 | from Plugins.InfoSearch.Subdomain.Spider.Baidu.baidu import BaiduSpider 28 | BaiduSpider = BaiduSpider() 29 | tmp_subdomains, tmp_key_links, tmp_links = BaiduSpider.run(domain) 30 | self.global_subdomains += tmp_subdomains 31 | self.global_key_links += tmp_key_links 32 | self.links += tmp_links 33 | logger.info('Baidu Spider Is Over') 34 | 35 | # bing的请求一直有问题 36 | def BingSpider(domain): 37 | logger.info('Start Bing Spider') 38 | 39 | from Plugins.InfoSearch.Subdomain.Spider.Bing.bing import BingSpider 40 | BingSpider = BingSpider() 41 | tmp_subdomains, tmp_key_links, tmp_links = BingSpider.run(domain) 42 | 43 | self.global_subdomains += tmp_subdomains 44 | self.global_key_links += tmp_key_links 45 | self.links += self.links 46 | logger.info('Bing Spider Is Over') 47 | 48 | 49 | logger.info("Start Spider Module") 50 | BaiduSpider(domain) 51 | # BingSpider(domain, proxies) 52 | logger.info("WebSpider is over") 53 | 54 | def ThirdPartyPlatform(self, domain): 55 | # proxies = self.proxies 56 | # proxy = random.choice(proxies) 57 | def Certificate(domain): 58 | 59 | from Plugins.InfoSearch.Subdomain.ThirdPartyPlatform.certificate import Certificate 60 | Certificate = Certificate() 61 | tmp_subdomains = Certificate.run(domain) 62 | 63 | self.global_subdomains += tmp_subdomains 64 | 65 | def Netcraft(domain): 66 | from Plugins.InfoSearch.Subdomain.ThirdPartyPlatform.netcraft import Netcraft 67 | Netcraft = Netcraft() 68 | tmp_subdomains = Netcraft.Run(domain) 69 | 70 | self.global_subdomains += tmp_subdomains 71 | logger.info("ThirdPartyPlatform start") 72 | Certificate(domain) 73 | Netcraft(domain) 74 | logger.info("ThirdPartyPlatform end") 75 | 76 | 77 | '''DNS解析''' 78 | def Dns_resolver(self): 79 | import dns.resolver 80 | dns_servers = [ 81 | # DNS对结果准确性影响非常大，部分DNS结果会和其它DNS结果不一致甚至没结果 82 | # '223.5.5.5', # AliDNS 83 | # '114.114.114.114', # 114DNS 84 | # '1.1.1.1', # Cloudflare 85 | '119.29.29.29', # DNSPod https://www.dnspod.cn/products/public.dns 86 | # '180.76.76.76', # BaiduDNS 87 | # '1.2.4.8', # sDNS 88 | # '11.1.1.1' # test DNS, not available 89 | # '8.8.8.8', # Google DNS, 延时太高了 90 | ] 91 | 92 | my_resolver = dns.resolver.Resolver() 93 | my_resolver.nameservers = dns_servers 94 | 95 | def DNS_Query(domain_name, domain_type): 96 | try: 97 | ips = '' 98 | A = my_resolver.resolve(domain_name, domain_type) 99 | for ip in A.rrset.items.keys(): 100 | ips = ips + str(ip) + ',' 101 | return ips.strip(",") 102 | except Exception as e: 103 | return 'null' 104 | 105 | 106 | logger.info("Dns_resolver start") 107 | for single_subdomain in self.global_subdomains: 108 | ips = DNS_Query(single_subdomain, "A") 109 | self.global_subdomains_ips += [(single_subdomain, ips)] 110 | 111 | logger.info("Dns_resolver end") 112 | 113 | 114 | def ESD_Run(self, domain): 115 | logger.info("ESD start") 116 | from Plugins.InfoSearch.Subdomain.ESD.ESD import EnumSubDomain 117 | self.global_subdomains_ips += EnumSubDomain(domain).run() 118 | logger.info("ESD end") 119 | 120 | def Check_network_connectivity(self): 121 | try: 122 | logger.info("Checking the network") 123 | if requests.get("https://www.baidu.com").status_code == 200: 124 | logger.info("Network status is good") 125 | except: 126 | logger.error("You need to check the network settings.Network problems") 127 | sys.exit() 128 | def JsFinderRun(self): 129 | from Plugins.InfoSearch.Subdomain.JsFinder import jsfinder 130 | for link in self.links: 131 | self.global_subdomains += jsfinder.RunJsFinder(link) 132 | 133 | 134 | # def Save_Subdomains(self, domain): 135 | # f = open('../../../Reports/{}-{}-{}-{}'.format(domain, datetime.datetime.now().year, datetime.datetime.now().month,datetime.datetime.now().day), 'w') 136 | # print(list(set(self.global_subdomains_ips))) 137 | # 138 | # print("The subdomain is stored in Reports/{}".format(f.name)) 139 | # 140 | # for i in self.global_subdomains_ips: 141 | # f.write(i[0] + ' ' + i[1] + '\n') 142 | # f.close() 143 | # logger.error("There is something wrong in network") 144 | 145 | 146 | def Data_Filtering(self, domain): 147 | logger.info("Data filtering start") 148 | if ('') in self.global_subdomains: 149 | self.global_subdomains.remove('') 150 | if (domain) in self.global_subdomains: 151 | self.global_subdomains.remove(domain) 152 | self.global_subdomains = list(set(self.global_subdomains)) 153 | logger.info("Data filtering end") 154 | 155 | 156 | def CheckCDN(self): 157 | from Plugins.InfoSearch.Subdomain.IsCND import CheckCDN 158 | self.subdomain_ips ,self.global_CDNSubdomainsDict = CheckCDN.run_checkCDN(self.global_subdomains) 159 | 160 | def Run(self, domain): 161 | logger.info("Subdomains start") 162 | 163 | 164 | 165 | # self.Check_network_connectivity() 166 | 167 | self.WebSpiderSubdomains(domain) 168 | self.JsFinderRun() 169 | self.ThirdPartyPlatform(domain) 170 | 171 | 172 | self.Data_Filtering(domain) 173 | self.CheckCDN() 174 | 175 | # self.Dns_resolver() 176 | 177 | # self.ESD_Run(domain) 178 | 179 | logger.info("Subdomains end") 180 | return list(set(self.global_subdomains_ips)), self.global_key_links 181 | 182 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/JsFinder/jsfinder.py: -------------------------------------------------------------------------------- 1 | 2 | import requests, argparse, sys, re 3 | from requests.packages import urllib3 4 | from urllib.parse import urlparse 5 | from bs4 import BeautifulSoup 6 | 7 | 8 | def extract_URL(JS): 9 | pattern_raw = r""" 10 | (?:"|') # Start newline delimiter 11 | ( 12 | ((?:[a-zA-Z]{1,10}://|//) # Match a scheme [a-Z]*1-10 or // 13 | [^"'/]{1,}\. # Match a domainname (any character + dot) 14 | [a-zA-Z]{2,}[^"']{0,}) # The domainextension and/or path 15 | | 16 | ((?:/|\.\./|\./) # Start with /,../,./ 17 | [^"'><,;| *()(%%$^/\\\[\]] # Next character can't be... 18 | [^"'><,;|()]{1,}) # Rest of the characters can't be 19 | | 20 | ([a-zA-Z0-9_\-/]{1,}/ # Relative endpoint with / 21 | [a-zA-Z0-9_\-/]{1,} # Resource name 22 | \.(?:[a-zA-Z]{1,4}|action) # Rest + extension (length 1-4 or action) 23 | (?:[\?|/][^"|']{0,}|)) # ? mark with parameters 24 | | 25 | ([a-zA-Z0-9_\-]{1,} # filename 26 | \.(?:php|asp|aspx|jsp|json| 27 | action|html|js|txt|xml) # . + extension 28 | (?:\?[^"|']{0,}|)) # ? mark with parameters 29 | ) 30 | (?:"|') # End newline delimiter 31 | """ 32 | pattern = re.compile(pattern_raw, re.VERBOSE) 33 | result = re.finditer(pattern, str(JS)) 34 | if result == None: 35 | return None 36 | js_url = [] 37 | return [match.group().strip('"').strip("'") for match in result 38 | if match.group() not in js_url] 39 | 40 | 41 | # Get the page source 42 | def Extract_html(URL): 43 | header = { 44 | "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", 45 | } 46 | try: 47 | raw = requests.get(URL, headers=header, timeout=3, verify=False) 48 | raw = raw.content.decode("utf-8", "ignore") 49 | return raw 50 | except: 51 | return None 52 | 53 | 54 | # Handling relative URLs 55 | def process_url(URL, re_URL): 56 | black_url = ["javascript:"] # Add some keyword for filter url. 57 | URL_raw = urlparse(URL) 58 | ab_URL = URL_raw.netloc 59 | host_URL = URL_raw.scheme 60 | if re_URL[0:2] == "//": 61 | result = host_URL + ":" + re_URL 62 | elif re_URL[0:4] == "http": 63 | result = re_URL 64 | elif re_URL[0:2] != "//" and re_URL not in black_url: 65 | if re_URL[0:1] == "/": 66 | result = host_URL + "://" + ab_URL + re_URL 67 | else: 68 | if re_URL[0:1] == ".": 69 | if re_URL[0:2] == "..": 70 | result = host_URL + "://" + ab_URL + re_URL[2:] 71 | else: 72 | result = host_URL + "://" + ab_URL + re_URL[1:] 73 | else: 74 | result = host_URL + "://" + ab_URL + "/" + re_URL 75 | else: 76 | result = URL 77 | return result 78 | 79 | 80 | def find_last(string, str): 81 | positions = [] 82 | last_position = -1 83 | while True: 84 | position = string.find(str, last_position + 1) 85 | if position == -1: break 86 | last_position = position 87 | positions.append(position) 88 | return positions 89 | 90 | 91 | def find_by_url(url, js=False): 92 | if js == False: 93 | try: 94 | print("url:" + url) 95 | except: 96 | print("Please specify a URL like https://www.baidu.com") 97 | html_raw = Extract_html(url) 98 | if html_raw == None: 99 | print("Fail to access " + url) 100 | return None 101 | # print(html_raw) 102 | html = BeautifulSoup(html_raw, "html.parser") 103 | html_scripts = html.findAll("script") 104 | script_array = {} 105 | script_temp = "" 106 | for html_script in html_scripts: 107 | script_src = html_script.get("src") 108 | if script_src == None: 109 | script_temp += html_script.get_text() + "\n" 110 | else: 111 | purl = process_url(url, script_src) 112 | script_array[purl] = Extract_html(purl) 113 | script_array[url] = script_temp 114 | allurls = [] 115 | for script in script_array: 116 | # print(script) 117 | temp_urls = extract_URL(script_array[script]) 118 | if len(temp_urls) == 0: continue 119 | for temp_url in temp_urls: 120 | allurls.append(process_url(script, temp_url)) 121 | result = [] 122 | for singerurl in allurls: 123 | url_raw = urlparse(url) 124 | domain = url_raw.netloc 125 | positions = find_last(domain, ".") 126 | miandomain = domain 127 | if len(positions) > 1: miandomain = domain[positions[-2] + 1:] 128 | # print(miandomain) 129 | suburl = urlparse(singerurl) 130 | subdomain = suburl.netloc 131 | # print(singerurl) 132 | if miandomain in subdomain or subdomain.strip() == "": 133 | if singerurl.strip() not in result: 134 | result.append(singerurl) 135 | return result 136 | return sorted(set(extract_URL(Extract_html(url)))) or None 137 | 138 | 139 | def find_subdomain(urls, mainurl): 140 | url_raw = urlparse(mainurl) 141 | domain = url_raw.netloc 142 | miandomain = domain 143 | positions = find_last(domain, ".") 144 | if len(positions) > 1: miandomain = domain[positions[-2] + 1:] 145 | subdomains = [] 146 | for url in urls: 147 | suburl = urlparse(url) 148 | subdomain = suburl.netloc 149 | # print(subdomain) 150 | if subdomain.strip() == "": continue 151 | if miandomain in subdomain: 152 | if subdomain not in subdomains: 153 | subdomains.append(subdomain) 154 | return subdomains 155 | 156 | 157 | def find_by_url_deep(url): 158 | html_raw = Extract_html(url) 159 | if html_raw == None: 160 | print("Fail to access " + url) 161 | return None 162 | html = BeautifulSoup(html_raw, "html.parser") 163 | html_as = html.findAll("a") 164 | links = [] 165 | for html_a in html_as: 166 | src = html_a.get("href") 167 | if src == "" or src == None: continue 168 | link = process_url(url, src) 169 | if link not in links: 170 | links.append(link) 171 | if links == []: return None 172 | print("ALL Find " + str(len(links)) + " links") 173 | urls = [] 174 | i = len(links) 175 | for link in links: 176 | temp_urls = find_by_url(link) 177 | if temp_urls == None: continue 178 | print("Remaining " + str(i) + " | Find " + str(len(temp_urls)) + " URL in " + link) 179 | for temp_url in temp_urls: 180 | if temp_url not in urls: 181 | urls.append(temp_url) 182 | i -= 1 183 | return urls 184 | 185 | 186 | # def find_by_file(file_path, js=False): 187 | # with open(file_path, "r") as fobject: 188 | # links = fobject.read().split("\n") 189 | # if links == []: return None 190 | # print("ALL Find " + str(len(links)) + " links") 191 | # urls = [] 192 | # i = len(links) 193 | # for link in links: 194 | # if js == False: 195 | # temp_urls = find_by_url(link) 196 | # else: 197 | # temp_urls = find_by_url(link, js=True) 198 | # if temp_urls == None: continue 199 | # print(str(i) + " Find " + str(len(temp_urls)) + " URL in " + link) 200 | # for temp_url in temp_urls: 201 | # if temp_url not in urls: 202 | # urls.append(temp_url) 203 | # i -= 1 204 | # return urls 205 | 206 | # 207 | # def giveresult(urls, domian): 208 | # if urls == None: 209 | # return None 210 | # print("Find " + str(len(urls)) + " URL:") 211 | # content_url = "" 212 | # content_subdomain = "" 213 | # for url in urls: 214 | # content_url += url + "\n" 215 | # print(url) 216 | # subdomains = find_subdomain(urls, domian) 217 | # print("\nFind " + str(len(subdomains)) + " Subdomain:") 218 | # for subdomain in subdomains: 219 | # content_subdomain += subdomain + "\n" 220 | # print(subdomain) 221 | # if args.outputurl != None: 222 | # with open(args.outputurl, "a", encoding='utf-8') as fobject: 223 | # fobject.write(content_url) 224 | # print("\nOutput " + str(len(urls)) + " urls") 225 | # print("Path:" + args.outputurl) 226 | # if args.outputsubdomain != None: 227 | # with open(args.outputsubdomain, "a", encoding='utf-8') as fobject: 228 | # fobject.write(content_subdomain) 229 | # print("\nOutput " + str(len(subdomains)) + " subdomains") 230 | # print("Path:" + args.outputsubdomain) 231 | 232 | # return content_url, content_subdomain 233 | 234 | def RunJsFinder(url): 235 | urllib3.disable_warnings() 236 | urls = find_by_url(url) 237 | subdomains = find_subdomain(urls, url) 238 | # return urls, subdomains 239 | return subdomains 240 | if __name__ == "__main__": 241 | print(RunJsFinder("https://www.tjut.edu.cn")) -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/IsCND/CheckCDN.py: -------------------------------------------------------------------------------- 1 | import ipaddress 2 | import re 3 | import dns.resolver 4 | import geoip2.database 5 | 6 | import dns.resolver 7 | from queue import Queue 8 | from threading import Thread 9 | from Common.LogOutput import LogOutput 10 | logger_object = LogOutput() 11 | logger = logger_object.SetModuleName("CheckCDN") 12 | 13 | 14 | 15 | 16 | # 通过查询pdns，然后排除国内外常见的cdn段，如果出现极有可能是真实ip 17 | cdns = [ 18 | '223.99.255.0/24', '71.152.0.0/17', '219.153.73.0/24', '125.39.46.0/24', '190.93.240.0/20', '14.0.113.0/24', 19 | '14.0.47.0/24', '113.20.148.0/22', '103.75.201.0/24', '1.32.239.0/24', '101.79.239.0/24', '52.46.0.0/18', 20 | '125.88.189.0/24', '150.138.248.0/24', '180.153.235.0/24', '205.251.252.0/23', '103.1.65.0/24', '115.127.227.0/24', 21 | '14.0.42.0/24', '109.199.58.0/24', '116.211.155.0/24', '112.253.3.0/24', '14.0.58.0/24', '223.112.227.0/24', 22 | '113.20.150.0/23', '61.182.141.0/24', '34.216.51.0/25', '124.95.188.0/24', '42.51.25.0/24', '183.136.133.0/24', 23 | '52.220.191.0/26', '119.84.93.0/24', '182.118.38.0/24', '13.59.250.0/26', '54.178.75.0/24', '119.84.92.0/24', 24 | '183.131.62.0/24', '111.32.136.0/24', '13.124.199.0/24', '111.47.227.0/24', '104.37.177.0/24', '14.0.50.0/24', 25 | '183.230.70.0/24', '114.111.59.0/24', '220.181.135.0/24', '112.140.32.0/19', '101.79.230.0/24', '14.0.115.0/24', 26 | '103.28.248.0/22', '117.34.72.0/24', '109.199.57.0/24', '101.79.149.0/24', '116.128.128.0/24', '115.231.186.0/24', 27 | '103.22.200.0/22', '61.155.165.0/24', '113.20.148.0/23', '185.254.242.0/24', '59.36.120.0/24', '70.132.0.0/18', 28 | '116.31.126.0/24', '119.147.134.0/24', '115.127.246.0/24', '52.47.139.0/24', '118.107.175.0/24', '52.78.247.128/26', 29 | '110.93.176.0/20', '54.240.128.0/18', '46.51.216.0/21', '119.31.251.0/24', '125.39.18.0/24', '108.175.33.0/24', 30 | '1.31.128.0/24', '61.151.163.0/24', '103.95.132.0/24', '58.215.118.0/24', '54.233.255.128/26', '120.52.113.0/24', 31 | '118.107.174.0/24', '1.32.242.0/24', '221.195.34.0/24', '101.79.228.0/24', '205.251.249.0/24', '113.200.91.0/24', 32 | '101.79.146.0/24', '221.238.22.0/24', '134.19.183.0/24', '110.93.160.0/20', '180.97.158.0/24', '115.127.251.0/24', 33 | '119.167.147.0/24', '115.127.238.0/24', '115.127.240.0/22', '14.0.48.0/24', '115.127.240.0/24', '113.7.183.0/24', 34 | '112.140.128.0/20', '115.127.255.0/24', '114.31.36.0/22', '101.79.232.0/24', '218.98.44.0/24', '106.119.182.0/24', 35 | '101.79.167.0/24', '125.39.5.0/24', '58.49.105.0/24', '124.202.164.0/24', '111.177.6.0/24', '61.133.127.0/24', 36 | '185.11.124.0/22', '150.138.150.0/24', '115.127.248.0/24', '103.74.80.0/22', '101.79.166.0/24', '101.71.55.0/24', 37 | '198.41.128.0/17', '117.21.219.0/24', '103.231.170.0/24', '221.204.202.0/24', '101.79.224.0/24', '112.25.16.0/24', 38 | '111.177.3.0/24', '204.246.168.0/22', '103.40.7.0/24', '134.226.0.0/16', '52.15.127.128/26', '122.190.2.0/24', 39 | '101.203.192.0/18', '1.32.238.0/24', '101.79.144.0/24', '176.34.28.0/24', '119.84.15.0/24', '18.216.170.128/25', 40 | '222.88.94.0/24', '101.79.150.0/24', '114.111.48.0/21', '124.95.168.0/24', '114.111.48.0/20', '110.93.176.0/21', 41 | '223.111.127.0/24', '117.23.61.0/24', '140.207.120.0/24', '157.255.26.0/24', '221.204.14.0/24', '183.222.96.0/24', 42 | '104.37.180.0/24', '42.236.93.0/24', '111.63.51.0/24', '114.31.32.0/20', '118.180.50.0/24', '222.240.184.0/24', 43 | '205.251.192.0/19', '101.79.225.0/24', '115.127.228.0/24', '113.20.148.0/24', '61.213.176.0/24', '112.65.75.0/24', 44 | '111.13.147.0/24', '113.20.145.0/24', '103.253.132.0/24', '52.222.128.0/17', '183.203.7.0/24', '27.221.27.0/24', 45 | '103.79.134.0/24', '123.150.187.0/24', '103.15.194.0/24', '162.158.0.0/15', '61.163.30.0/24', '182.140.227.0/24', 46 | '112.25.60.0/24', '117.148.161.0/24', '61.182.136.0/24', '114.31.56.0/22', '64.252.128.0/18', '183.61.185.0/24', 47 | '115.127.250.0/24', '150.138.138.0/24', '13.210.67.128/26', '211.162.64.0/24', '61.174.9.0/24', '14.0.112.0/24', 48 | '52.52.191.128/26', '27.221.124.0/24', '103.4.203.0/24', '103.14.10.0/24', '34.232.163.208/29', '114.31.48.0/20', 49 | '59.51.81.0/24', '183.60.235.0/24', '101.227.206.0/24', '125.39.174.0/24', '119.167.246.0/24', '118.107.160.0/21', 50 | '223.166.151.0/24', '110.93.160.0/19', '204.246.172.0/23', '119.31.253.0/24', '143.204.0.0/16', '14.0.60.0/24', 51 | '123.151.76.0/24', '116.193.80.0/24', '120.241.102.0/24', '180.96.20.0/24', '216.137.32.0/19', '223.94.95.0/24', 52 | '103.4.201.0/24', '14.0.56.0/24', '115.127.234.0/24', '113.20.144.0/23', '103.248.104.0/24', '122.143.15.0/24', 53 | '101.79.229.0/24', '101.79.163.0/24', '104.37.112.0/22', '115.127.253.0/24', '141.101.64.0/18', '113.20.144.0/22', 54 | '101.79.155.0/24', '117.148.160.0/24', '124.193.166.0/24', '109.94.168.0/24', '203.90.247.0/24', '101.79.208.0/21', 55 | '182.118.12.0/24', '114.31.58.0/23', '202.162.109.0/24', '101.79.164.0/24', '58.216.2.0/24', '222.216.190.0/24', 56 | '101.79.165.0/24', '111.6.191.0/24', '1.255.100.0/24', '52.84.0.0/15', '112.65.74.0/24', '183.250.179.0/24', 57 | '101.79.236.0/24', '119.31.252.0/24', '113.20.150.0/24', '60.12.166.0/24', '101.79.234.0/24', '113.17.174.0/24', 58 | '101.79.237.0/24', '61.54.46.0/24', '118.212.233.0/24', '183.110.242.0/24', '150.138.149.0/24', '117.34.13.0/24', 59 | '115.127.245.0/24', '14.0.102.0/24', '14.0.109.0/24', '61.130.28.0/24', '113.20.151.0/24', '219.159.84.0/24', 60 | '114.111.62.0/24', '172.64.0.0/13', '61.155.222.0/24', '120.52.29.0/24', '115.127.231.0/24', '14.0.49.0/24', 61 | '113.202.0.0/16', '103.248.104.0/22', '205.251.250.0/23', '103.216.136.0/22', '118.107.160.0/20', '109.87.0.0/21', 62 | '54.239.128.0/18', '115.127.224.0/19', '111.202.98.0/24', '109.94.169.0/24', '59.38.112.0/24', '204.246.176.0/20', 63 | '123.133.84.0/24', '103.4.200.0/24', '111.161.109.0/24', '112.84.34.0/24', '103.82.129.0/24', '183.3.254.0/24', 64 | '112.137.184.0/21', '122.227.237.0/24', '36.42.75.0/24', '13.35.0.0/16', '101.226.4.0/24', '116.140.35.0/24', 65 | '58.250.143.0/24', '13.54.63.128/26', '205.251.254.0/24', '173.245.48.0/20', '183.61.177.0/24', '113.20.144.0/24', 66 | '104.37.183.0/24', '35.158.136.0/24', '116.211.121.0/24', '42.236.94.0/24', '117.34.91.0/24', '123.6.13.0/24', 67 | '13.224.0.0/14', '113.20.146.0/24', '58.58.81.0/24', '52.124.128.0/17', '122.228.198.0/24', '197.234.240.0/22', 68 | '99.86.0.0/16', '144.220.0.0/16', '119.188.97.0/24', '36.27.212.0/24', '104.37.178.0/24', '114.31.52.0/22', 69 | '218.65.212.0/24', '1.255.41.0/24', '14.0.45.0/24', '1.32.243.0/24', '220.170.185.0/24', '122.190.3.0/24', 70 | '103.79.133.0/24', '220.181.55.0/24', '125.39.191.0/24', '115.127.226.0/24', '125.39.32.0/24', '61.120.154.0/24', 71 | '103.4.202.0/24', '103.79.134.0/23', '115.127.224.0/24', '113.20.147.0/24', '61.156.149.0/24', '210.209.122.0/24', 72 | '115.127.249.0/24', '104.37.179.0/24', '120.52.18.0/24', '54.192.0.0/16', '14.0.55.0/24', '61.160.224.0/24', 73 | '113.207.101.0/24', '101.79.157.0/24', '110.93.128.0/20', '58.251.121.0/24', '61.240.149.0/24', '130.176.0.0/16', 74 | '113.107.238.0/24', '112.65.73.0/24', '103.75.200.0/23', '199.83.128.0/21', '123.129.220.0/24', '54.230.0.0/16', 75 | '114.111.60.0/24', '199.27.128.0/21', '14.0.118.0/24', '101.79.158.0/24', '119.31.248.0/21', '54.182.0.0/16', 76 | '113.31.27.0/24', '14.17.69.0/24', '101.79.145.0/24', '113.20.144.0/21', '180.163.22.0/24', '104.37.176.0/21', 77 | '117.25.156.0/24', '115.127.252.0/24', '115.127.244.0/23', '14.0.46.0/24', '113.207.102.0/24', '52.199.127.192/26', 78 | '13.113.203.0/24', '64.252.64.0/18', '1.32.240.0/24', '123.129.232.0/24', '1.32.241.0/24', '180.163.189.0/24', 79 | '157.255.25.0/24', '1.32.244.0/24', '103.248.106.0/24', '121.48.95.0/24', '54.239.192.0/19', '113.20.146.0/23', 80 | '61.136.173.0/24', '35.162.63.192/26', '117.34.14.0/24', '183.232.29.0/24', '42.81.93.0/24', '122.228.238.0/24', 81 | '183.61.190.0/24', '125.39.239.0/24', '115.127.230.0/24', '103.140.200.0/23', '202.102.85.0/24', '14.0.32.0/21', 82 | '14.0.57.0/24', '112.25.90.0/24', '58.211.137.0/24', '210.22.63.0/24', '34.226.14.0/24', '13.32.0.0/15', 83 | '101.79.156.0/24', '103.89.176.0/24', '14.0.116.0/24', '106.42.25.0/24', '101.79.233.0/24', '101.79.231.0/24', 84 | '103.75.200.0/24', '119.188.9.0/24', '183.232.51.0/24', '149.126.72.0/21', '103.21.244.0/22', '115.127.233.0/24', 85 | '27.221.20.0/24', '198.143.32.0/19', '103.248.107.0/24', '101.79.227.0/24', '115.127.242.0/24', '119.31.250.0/24', 86 | '103.82.130.0/24', '99.84.0.0/16', '222.73.144.0/24', '103.79.132.0/22', '101.79.208.0/20', '104.37.182.0/24', 87 | '101.79.152.0/24', '36.99.18.0/24', '101.71.56.0/24', '36.250.5.0/24', '61.158.240.0/24', '119.188.14.0/24', 88 | '13.249.0.0/16', '183.214.156.0/24', '60.221.236.0/24', '58.30.212.0/24', '115.127.254.0/24', '188.114.96.0/20', 89 | '115.127.241.0/24', '103.4.200.0/22', '115.127.239.0/24', '115.127.243.0/24', '111.32.135.0/24', '120.221.29.0/24', 90 | '115.127.232.0/24', '14.0.43.0/24', '14.0.59.0/24', '183.61.236.0/24', '34.223.12.224/27', '103.24.120.0/24', 91 | '52.57.254.0/24', '113.207.100.0/24', '222.186.19.0/24', '113.20.149.0/24', '150.138.151.0/24', '115.231.110.0/24', 92 | '52.56.127.0/25', '104.37.176.0/24', '163.177.8.0/24', '163.53.89.0/24', '52.82.128.0/19', '114.111.63.0/24', 93 | '108.162.192.0/18', '14.136.130.0/24', '115.127.229.0/24', '14.17.71.0/24', '52.212.248.0/26', '180.163.188.0/24', 94 | '61.182.137.0/24', '119.161.224.0/21', '14.0.41.0/24', '202.162.108.0/24', '106.122.248.0/24', '52.66.194.128/26', 95 | '115.127.237.0/24', '220.170.186.0/24', '14.0.32.0/19', '14.0.114.0/24', '112.90.216.0/24', '115.127.236.0/24', 96 | '116.193.84.0/24', '113.207.76.0/24', '101.79.235.0/24', '101.79.224.0/20', '61.155.149.0/24', '101.79.148.0/24', 97 | '180.163.224.0/24', '204.246.174.0/23', '183.60.136.0/24', '101.227.207.0/24', '103.248.105.0/24', 98 | '119.188.35.0/24', '42.236.7.0/24', '116.193.88.0/21', '116.193.83.0/24', '120.199.69.0/24', '122.226.182.0/24', 99 | '58.20.204.0/24', '110.93.128.0/21', '115.231.187.0/24', '69.28.58.0/24', '114.31.32.0/19', '112.25.91.0/24', 100 | '59.52.28.0/24', '117.27.149.0/24', '61.147.92.0/24', '14.0.117.0/24', '14.0.40.0/24', '119.97.151.0/24', 101 | '103.199.228.0/22', '122.70.134.0/24', '115.127.244.0/24', '223.112.198.0/24', '115.127.225.0/24', '104.16.0.0/12', 102 | '121.12.98.0/24', '103.31.4.0/22', '204.246.164.0/22', '223.94.66.0/24', '35.167.191.128/26', '116.31.127.0/24', 103 | '101.79.226.0/24', '34.195.252.0/24', '115.127.247.0/24', '61.240.144.0/24', '108.175.32.0/20', '120.197.85.0/24', 104 | '183.232.53.0/24', '111.161.66.0/24', '117.34.28.0/24', '45.64.64.0/22', '14.0.44.0/24', '109.86.0.0/15', 105 | '182.23.211.0/24', '58.211.2.0/24', '119.36.164.0/24', '116.55.250.0/24', '101.227.163.0/24', '13.228.69.0/24', 106 | '120.221.136.0/24', '119.188.132.0/24', '115.127.235.0/24', '42.236.6.0/24', '125.88.190.0/24', '61.54.47.0/24', 107 | '103.27.12.0/22', '116.193.80.0/21', '101.79.159.0/24', '123.155.158.0/24', '111.47.226.0/24', '131.0.72.0/22', 108 | '192.230.64.0/18', '218.92.0.0/24' 109 | ] 110 | 111 | ASNS = [ 112 | '10576', '10762', '11748', '131099', '132601', '133496', '134409', '135295', '136764', '137187', '13777', '13890', 113 | '14103', '14520', '17132', '199251', '200013', '200325', '200856', '201263', '202294', '203075', '203139', '204248', 114 | '204286', '204545', '206227', '206734', '206848', '206986', '207158', '208559', '209403', '21030', '21257', '23327', 115 | '23393', '23637', '23794', '24997', '26492', '268843', '28709', '29264', '30282', '30637', '328126', '36408', 116 | '38107', '397192', '40366', '43303', '44907', '46071', '46177', '47542', '49287', '49689', '51286', '55082', 117 | '55254', '56636', '57363', '58127', '59730', '59776', '60068', '60626', '60922', '61107', '61159', '62026', '62229', 118 | '63062', '64232', '8868', '9053', '55770', '49846', '49249', '48163', '45700', '43639', '39836', '393560', '393234', 119 | '36183', '35994', '35993', '35204', '34850', '34164', '33905', '32787', '31377', '31110', '31109', '31108', '31107', 120 | '30675', '24319', '23903', '23455', '23454', '22207', '21399', '21357', '21342', '20940', '20189', '18717', '18680', 121 | '17334', '16702', '16625', '12222', '209101', '201585', '135429', '395747', '394536', '209242', '203898', '202623', 122 | '14789', '133877', '13335', '132892', '21859', '6185', '47823' 123 | ] 124 | 125 | cdnDict = {} 126 | with open(r'./cdn-domain.conf', 'rt', encoding='utf-8') as f: 127 | # with open(r'cdn-domain.conf', 'rt') as f: 128 | for eachline in f.readlines(): 129 | eachline = eachline.strip() 130 | if '#' in eachline: 131 | cdnName = eachline.replace('#', '') 132 | cdnDict[cdnName] = [] 133 | elif eachline: 134 | cdnDict[cdnName].append(eachline) 135 | 136 | # 解析域名获取IP 137 | def query_A(subdomain): 138 | # 根据domain得到ip 例如www.xxx.com 得到 x.x.x.x 139 | ips = [] 140 | try: 141 | dns_A_ips = [j for i in dns.resolver.resolve(subdomain, 'A').response.answer for j in i.items] 142 | ips = [] 143 | for each_ip in dns_A_ips: 144 | each_ip = str(each_ip) 145 | if re.compile('^((25[0-5]|2[0-4]\d|[01]?\d\d?)\.){3}(25[0-5]|2[0-4]\d|[01]?\d\d?)$').match(each_ip): # 正则匹配是否是IP 146 | ips.append(str(each_ip)) 147 | except Exception as e: 148 | pass 149 | 150 | return ips 151 | 152 | # 通过IP判断是否是CDN 153 | def ipASNSCheckCDN(subdomain): 154 | ips = query_A(subdomain) 155 | 156 | with geoip2.database.Reader('./GeoLite2-ASN.mmdb') as reader: 157 | # with geoip2.database.Reader('./GeoLite2-ASN.mmdb') as reader: 158 | for ip in ips: 159 | # 通过CDN的IP段判断 160 | for cdn in cdns: 161 | if ipaddress.ip_address(ip) in ipaddress.ip_network(cdn): 162 | return ['CDN IP段', cdn] 163 | 164 | # 通过ASN判断 165 | try: 166 | response = reader.asn(ip) 167 | asnsNum = response.autonomous_system_number 168 | if str(asnsNum) in ASNS: 169 | return ['CDN ASNS范围', asnsNum] 170 | except Exception as e: 171 | pass 172 | 173 | return [], ips 174 | 175 | # 查询cname 176 | def queryCname(subdomain): 177 | try: 178 | cname = dns.resolver.resolve(subdomain, 'CNAME') 179 | for i in cname.response.answer: 180 | for j in i.items: 181 | subdomain_cname = j.to_text() 182 | return subdomain_cname 183 | except Exception as e: 184 | return '' 185 | 186 | # 通过cname判断是否是CDN 187 | def cnameCheckCDN(subdomian): 188 | subdomain_cname = queryCname(subdomian) 189 | # print(subdomain_cname) 190 | for cdnName in cdnDict: 191 | cdnDomains = cdnDict[cdnName] 192 | for cdnDomain in cdnDomains: 193 | if cdnDomain in subdomain_cname: 194 | # print(subdomian, subdomain_cname, cdnName) 195 | return [cdnName, subdomain_cname] 196 | if 'cdn' in subdomain_cname: 197 | return ['CDN', subdomain_cname] 198 | return False 199 | 200 | 201 | def checkCDN(subdomains_queue, notCDNSubdomains, CDNSubdomainsDict): 202 | while not subdomains_queue.empty(): 203 | subdomain = subdomains_queue.get() 204 | cnameRet = cnameCheckCDN(subdomain) 205 | if not cnameRet: 206 | ipASNSRet, ips = ipASNSCheckCDN(subdomain) 207 | if not ipASNSRet: 208 | notCDNSubdomains.append((subdomain,ips)) 209 | CDNSubdomainsDict[subdomain] = 'NOT' 210 | else: 211 | logger.info('{}: {}'.format(subdomain, ipASNSRet)) 212 | # notCDNSubdomains.append(subdomain) 213 | CDNSubdomainsDict[subdomain] = ipASNSRet 214 | else: 215 | logger.info('{}: {}'.format(subdomain, cnameRet)) 216 | # notCDNSubdomains.append(subdomain) 217 | CDNSubdomainsDict[subdomain] = cnameRet 218 | 219 | 220 | def run_checkCDN(subdomains): 221 | query_A_threads = [] # 存放线程 222 | subdomains_queue = Queue(-1) 223 | 224 | for subdomain in subdomains: 225 | subdomains_queue.put(subdomain) 226 | 227 | # 没有CDN的子域名 228 | notCDNSubdomains = [] 229 | # CDN的子域名结果 230 | CDNSubdomainsDict = {} 231 | 232 | for t_id in range(50): # 对新增的子域名进行A记录查询获取IP 233 | t = Thread(target=checkCDN, args=(subdomains_queue, notCDNSubdomains, CDNSubdomainsDict)) 234 | query_A_threads.append(t) 235 | t.start() 236 | for t in query_A_threads: 237 | t.join() 238 | 239 | # print() 240 | return notCDNSubdomains, CDNSubdomainsDict 241 | 242 | 243 | if __name__ == "__main__": 244 | subdomains = ['www.tjut.edu.cn'] 245 | notCDNSubdomains, CDNSubdomainsDict = run_checkCDN(subdomains) 246 | print(CDNSubdomainsDict) 247 | 248 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/Spider/Google/googlesearch/__init__.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | 3 | # Python bindings to the Google search engine 4 | # Copyright (c) 2009-2018, Mario Vilas 5 | # All rights reserved. 6 | # 7 | # Redistribution and use in source and binary forms, with or without 8 | # modification, are permitted provided that the following conditions are met: 9 | # 10 | # * Redistributions of source code must retain the above copyright notice, 11 | # this list of conditions and the following disclaimer. 12 | # * Redistributions in binary form must reproduce the above copyright 13 | # notice,this list of conditions and the following disclaimer in the 14 | # documentation and/or other materials provided with the distribution. 15 | # * Neither the name of the copyright holder nor the names of its 16 | # contributors may be used to endorse or promote products derived from 17 | # this software without specific prior written permission. 18 | # 19 | # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" 20 | # AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 21 | # IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 22 | # ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE 23 | # LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR 24 | # CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF 25 | # SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS 26 | # INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN 27 | # CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) 28 | # ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 29 | # POSSIBILITY OF SUCH DAMAGE. 30 | 31 | import os 32 | import random 33 | import sys 34 | import time 35 | import math 36 | from urllib.error import HTTPError 37 | 38 | if sys.version_info[0] > 2: 39 | from http.cookiejar import LWPCookieJar 40 | from urllib.request import Request, urlopen 41 | from urllib.parse import quote_plus, urlparse, parse_qs 42 | else: 43 | from cookielib import LWPCookieJar 44 | from urllib import quote_plus 45 | from urllib2 import Request, urlopen 46 | from urlparse import urlparse, parse_qs 47 | 48 | try: 49 | from bs4 import BeautifulSoup 50 | is_bs4 = True 51 | except ImportError: 52 | from BeautifulSoup import BeautifulSoup 53 | is_bs4 = False 54 | 55 | __all__ = [ 56 | 57 | # Main search function. 58 | 'search', 59 | 60 | # Specialized search functions. 61 | 'search_images', 'search_news', 62 | 'search_videos', 'search_shop', 63 | 'search_books', 'search_apps', 64 | 65 | # Shortcut for "get lucky" search. 66 | 'lucky', 67 | 68 | # Computations based on the number of Google hits. 69 | 'hits', 'ngd', 70 | 71 | # Miscellaneous utility functions. 72 | 'get_random_user_agent', 73 | ] 74 | 75 | # URL templates to make Google searches. 76 | url_home = "https://www.google.%(tld)s/" 77 | url_search = "https://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&" \ 78 | "btnG=Google+Search&tbs=%(tbs)s&safe=%(safe)s&tbm=%(tpe)s" 79 | url_next_page = "https://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&" \ 80 | "start=%(start)d&tbs=%(tbs)s&safe=%(safe)s&tbm=%(tpe)s" 81 | url_search_num = "https://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&" \ 82 | "num=%(num)d&btnG=Google+Search&tbs=%(tbs)s&safe=%(safe)s&" \ 83 | "tbm=%(tpe)s" 84 | url_next_page_num = "https://www.google.%(tld)s/search?hl=%(lang)s&" \ 85 | "q=%(query)s&num=%(num)d&start=%(start)d&tbs=%(tbs)s&" \ 86 | "safe=%(safe)s&tbm=%(tpe)s" 87 | 88 | # Cookie jar. Stored at the user's home folder. 89 | home_folder = os.getenv('HOME') 90 | if not home_folder: 91 | home_folder = os.getenv('USERHOME') 92 | if not home_folder: 93 | home_folder = '.' # Use the current folder on error. 94 | cookie_jar = LWPCookieJar(os.path.join(home_folder, '.google-cookie')) 95 | try: 96 | cookie_jar.load() 97 | except Exception: 98 | pass 99 | 100 | # Default user agent, unless instructed by the user to change it. 101 | USER_AGENT = 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0)' 102 | 103 | # Load the list of valid user agents from the install folder. 104 | try: 105 | install_folder = os.path.abspath(os.path.split(__file__)[0]) 106 | try: 107 | user_agents_file = os.path.join(install_folder, 'user_agents.txt.gz') 108 | import gzip 109 | fp = gzip.open(user_agents_file, 'rb') 110 | try: 111 | user_agents_list = [_.strip() for _ in fp.readlines()] 112 | finally: 113 | fp.close() 114 | del fp 115 | except Exception: 116 | user_agents_file = os.path.join(install_folder, 'user_agents.txt') 117 | with open(user_agents_file) as fp: 118 | user_agents_list = [_.strip() for _ in fp.readlines()] 119 | except Exception: 120 | user_agents_list = [USER_AGENT] 121 | 122 | 123 | # Get a random user agent. 124 | def get_random_user_agent(): 125 | """ 126 | Get a random user agent string. 127 | 128 | :rtype: str 129 | :return: Random user agent string. 130 | """ 131 | return random.choice(user_agents_list) 132 | 133 | 134 | # Request the given URL and return the response page, using the cookie jar. 135 | def get_page(url, user_agent=None): 136 | """ 137 | Request the given URL and return the response page, using the cookie jar. 138 | 139 | :param str url: URL to retrieve. 140 | :param str user_agent: User agent for the HTTP requests. 141 | Use None for the default. 142 | 143 | :rtype: str 144 | :return: Web page retrieved for the given URL. 145 | 146 | :raises IOError: An exception is raised on error. 147 | :raises urllib2.URLError: An exception is raised on error. 148 | :raises urllib2.HTTPError: An exception is raised on error. 149 | """ 150 | if user_agent is None: 151 | user_agent = USER_AGENT 152 | request = Request(url) 153 | request.add_header('User-Agent', USER_AGENT) 154 | cookie_jar.add_cookie_header(request) 155 | response = urlopen(request) 156 | cookie_jar.extract_cookies(response, request) 157 | html = response.read() 158 | response.close() 159 | try: 160 | cookie_jar.save() 161 | except Exception: 162 | pass 163 | return html 164 | 165 | 166 | # Filter links found in the Google result pages HTML code. 167 | # Returns None if the link doesn't yield a valid result. 168 | def filter_result(link): 169 | try: 170 | 171 | # Valid results are absolute URLs not pointing to a Google domain 172 | # like images.google.com or googleusercontent.com 173 | o = urlparse(link, 'http') 174 | if o.netloc and 'google' not in o.netloc: 175 | return link 176 | 177 | # Decode hidden URLs. 178 | if link.startswith('/url?'): 179 | link = parse_qs(o.query)['q'][0] 180 | 181 | # Valid results are absolute URLs not pointing to a Google domain 182 | # like images.google.com or googleusercontent.com 183 | o = urlparse(link, 'http') 184 | if o.netloc and 'google' not in o.netloc: 185 | return link 186 | 187 | # Otherwise, or on error, return None. 188 | except Exception: 189 | pass 190 | return None 191 | 192 | 193 | # Returns a generator that yields URLs. 194 | def search(query, tld='com', lang='en', tbs='0', safe='off', num=10, start=0, 195 | stop=None, domains=None, pause=2.0, only_standard=False, 196 | extra_params={}, tpe='', user_agent=None): 197 | """ 198 | Search the given query string using Google. 199 | 200 | :param str query: Query string. Must NOT be url-encoded. 201 | :param str tld: Top level domain. 202 | :param str lang: Language. 203 | :param str tbs: Time limits (i.e "qdr:h" => last hour, 204 | "qdr:d" => last 24 hours, "qdr:m" => last month). 205 | :param str safe: Safe search. 206 | :param int num: Number of results per page. 207 | :param int start: First result to retrieve. 208 | :param int or None stop: Last result to retrieve. 209 | Use None to keep searching forever. 210 | :param list of str or None domains: A list of web domains to constrain 211 | the search. 212 | :param float pause: Lapse to wait between HTTP requests. 213 | A lapse too long will make the search slow, but a lapse too short may 214 | cause Google to block your IP. Your mileage may vary! 215 | :param bool only_standard: If True, only returns the standard results from 216 | each page. If False, it returns every possible link from each page, 217 | except for those that point back to Google itself. Defaults to False 218 | for backwards compatibility with older versions of this module. 219 | :param dict of str to str extra_params: A dictionary of extra HTTP GET 220 | parameters, which must be URL encoded. For example if you don't want 221 | Google to filter similar results you can set the extra_params to 222 | {'filter': '0'} which will append '&filter=0' to every query. 223 | :param str tpe: Search type (images, videos, news, shopping, books, apps) 224 | Use the following values {videos: 'vid', images: 'isch', 225 | news: 'nws', shopping: 'shop', books: 'bks', applications: 'app'} 226 | :param str or None user_agent: User agent for the HTTP requests. 227 | Use None for the default. 228 | 229 | :rtype: generator of str 230 | :return: Generator (iterator) that yields found URLs. 231 | If the stop parameter is None the iterator will loop forever. 232 | """ 233 | # Set of hashes for the results found. 234 | # This is used to avoid repeated results. 235 | hashes = set() 236 | 237 | # Count the number of links yielded 238 | count = 0 239 | 240 | # Prepare domain list if it exists. 241 | if domains: 242 | query = query + ' ' + ' OR '.join( 243 | 'site:' + domain for domain in domains) 244 | 245 | # Prepare the search string. 246 | query = quote_plus(query) 247 | 248 | # Check extra_params for overlapping 249 | for builtin_param in ('hl', 'q', 'btnG', 'tbs', 'safe', 'tbm'): 250 | if builtin_param in extra_params.keys(): 251 | raise ValueError( 252 | 'GET parameter "%s" is overlapping with \ 253 | the built-in GET parameter', 254 | builtin_param 255 | ) 256 | 257 | # Grab the cookie from the home page. 258 | get_page(url_home % vars()) 259 | 260 | # Prepare the URL of the first request. 261 | if start: 262 | if num == 10: 263 | url = url_next_page % vars() 264 | else: 265 | url = url_next_page_num % vars() 266 | else: 267 | if num == 10: 268 | url = url_search % vars() 269 | else: 270 | url = url_search_num % vars() 271 | print('\tgoogle search : {}'.format(url)) 272 | # Loop until we reach the maximum result, if any (otherwise, loop forever). 273 | while not stop or start < stop: 274 | 275 | try: # Is it python<3? 276 | iter_extra_params = extra_params.iteritems() 277 | except AttributeError: # Or python>3? 278 | iter_extra_params = extra_params.items() 279 | # Append extra GET_parameters to URL 280 | for k, v in iter_extra_params: 281 | url += url + ('&%s=%s' % (k, v)) 282 | 283 | # Sleep between requests. 284 | time.sleep(pause) 285 | 286 | # Request the Google Search results page. 287 | # html = get_page(url) 288 | try: 289 | html = get_page(url) 290 | except HTTPError: 291 | print('\t[!] Error: Google probably now is blocking our requests.\n [-] Stop Google Search!') 292 | return False 293 | 294 | # Parse the response and process every anchored URL. 295 | if is_bs4: 296 | soup = BeautifulSoup(html, 'html.parser') 297 | else: 298 | soup = BeautifulSoup(html) 299 | anchors = soup.find(id='search').findAll('a') 300 | for a in anchors: 301 | 302 | # Leave only the "standard" results if requested. 303 | # Otherwise grab all possible links. 304 | if only_standard and ( 305 | not a.parent or a.parent.name.lower() != "h3"): 306 | continue 307 | 308 | # Get the URL from the anchor tag. 309 | try: 310 | link = a['href'] 311 | except KeyError: 312 | continue 313 | 314 | # Filter invalid links and links pointing to Google itself. 315 | link = filter_result(link) 316 | if not link: 317 | continue 318 | 319 | # Discard repeated results. 320 | h = hash(link) 321 | if h in hashes: 322 | continue 323 | hashes.add(h) 324 | 325 | # Yield the result. 326 | yield link 327 | 328 | count += 1 329 | if stop and count >= stop: 330 | return 331 | 332 | # End if there are no more results. 333 | if not soup.find(id='nav'): 334 | break 335 | 336 | # Prepare the URL for the next request. 337 | start += num 338 | if num == 10: 339 | url = url_next_page % vars() 340 | else: 341 | url = url_next_page_num % vars() 342 | 343 | 344 | # Shortcut to search images. 345 | # Beware, this does not return the image link. 346 | def search_images(query, tld='com', lang='en', tbs='0', safe='off', num=10, 347 | start=0, stop=None, pause=2.0, domains=None, 348 | only_standard=False, extra_params={}): 349 | """ 350 | Shortcut to search images. 351 | 352 | :note: Beware, this does not return the image link. 353 | 354 | :param str query: Query string. Must NOT be url-encoded. 355 | :param str tld: Top level domain. 356 | :param str lang: Language. 357 | :param str tbs: Time limits (i.e "qdr:h" => last hour, 358 | "qdr:d" => last 24 hours, "qdr:m" => last month). 359 | :param str safe: Safe search. 360 | :param int num: Number of results per page. 361 | :param int start: First result to retrieve. 362 | :param int or None stop: Last result to retrieve. 363 | Use None to keep searching forever. 364 | :param list of str or None domains: A list of web domains to constrain 365 | the search. 366 | :param float pause: Lapse to wait between HTTP requests. 367 | A lapse too long will make the search slow, but a lapse too short may 368 | cause Google to block your IP. Your mileage may vary! 369 | :param bool only_standard: If True, only returns the standard results from 370 | each page. If False, it returns every possible link from each page, 371 | except for those that point back to Google itself. Defaults to False 372 | for backwards compatibility with older versions of this module. 373 | :param dict of str to str extra_params: A dictionary of extra HTTP GET 374 | parameters, which must be URL encoded. For example if you don't want 375 | Google to filter similar results you can set the extra_params to 376 | {'filter': '0'} which will append '&filter=0' to every query. 377 | :param str tpe: Search type (images, videos, news, shopping, books, apps) 378 | Use the following values {videos: 'vid', images: 'isch', 379 | news: 'nws', shopping: 'shop', books: 'bks', applications: 'app'} 380 | :param str or None user_agent: User agent for the HTTP requests. 381 | Use None for the default. 382 | 383 | :rtype: generator of str 384 | :return: Generator (iterator) that yields found URLs. 385 | If the stop parameter is None the iterator will loop forever. 386 | """ 387 | return search(query, tld, lang, tbs, safe, num, start, stop, domains, 388 | pause, only_standard, extra_params, tpe='isch') 389 | 390 | 391 | # Shortcut to search news. 392 | def search_news(query, tld='com', lang='en', tbs='0', safe='off', num=10, 393 | start=0, stop=None, domains=None, pause=2.0, 394 | only_standard=False, extra_params={}): 395 | """ 396 | Shortcut to search news. 397 | 398 | :param str query: Query string. Must NOT be url-encoded. 399 | :param str tld: Top level domain. 400 | :param str lang: Language. 401 | :param str tbs: Time limits (i.e "qdr:h" => last hour, 402 | "qdr:d" => last 24 hours, "qdr:m" => last month). 403 | :param str safe: Safe search. 404 | :param int num: Number of results per page. 405 | :param int start: First result to retrieve. 406 | :param int or None stop: Last result to retrieve. 407 | Use None to keep searching forever. 408 | :param list of str or None domains: A list of web domains to constrain 409 | the search. 410 | :param float pause: Lapse to wait between HTTP requests. 411 | A lapse too long will make the search slow, but a lapse too short may 412 | cause Google to block your IP. Your mileage may vary! 413 | :param bool only_standard: If True, only returns the standard results from 414 | each page. If False, it returns every possible link from each page, 415 | except for those that point back to Google itself. Defaults to False 416 | for backwards compatibility with older versions of this module. 417 | :param dict of str to str extra_params: A dictionary of extra HTTP GET 418 | parameters, which must be URL encoded. For example if you don't want 419 | Google to filter similar results you can set the extra_params to 420 | {'filter': '0'} which will append '&filter=0' to every query. 421 | :param str tpe: Search type (images, videos, news, shopping, books, apps) 422 | Use the following values {videos: 'vid', images: 'isch', 423 | news: 'nws', shopping: 'shop', books: 'bks', applications: 'app'} 424 | :param str or None user_agent: User agent for the HTTP requests. 425 | Use None for the default. 426 | 427 | :rtype: generator of str 428 | :return: Generator (iterator) that yields found URLs. 429 | If the stop parameter is None the iterator will loop forever. 430 | """ 431 | return search(query, tld, lang, tbs, safe, num, start, stop, domains, 432 | pause, only_standard, extra_params, tpe='nws') 433 | 434 | 435 | # Shortcut to search videos. 436 | def search_videos(query, tld='com', lang='en', tbs='0', safe='off', num=10, 437 | start=0, stop=None, domains=None, pause=2.0, 438 | only_standard=False, extra_params={}): 439 | """ 440 | Shortcut to search videos. 441 | 442 | :param str query: Query string. Must NOT be url-encoded. 443 | :param str tld: Top level domain. 444 | :param str lang: Language. 445 | :param str tbs: Time limits (i.e "qdr:h" => last hour, 446 | "qdr:d" => last 24 hours, "qdr:m" => last month). 447 | :param str safe: Safe search. 448 | :param int num: Number of results per page. 449 | :param int start: First result to retrieve. 450 | :param int or None stop: Last result to retrieve. 451 | Use None to keep searching forever. 452 | :param list of str or None domains: A list of web domains to constrain 453 | the search. 454 | :param float pause: Lapse to wait between HTTP requests. 455 | A lapse too long will make the search slow, but a lapse too short may 456 | cause Google to block your IP. Your mileage may vary! 457 | :param bool only_standard: If True, only returns the standard results from 458 | each page. If False, it returns every possible link from each page, 459 | except for those that point back to Google itself. Defaults to False 460 | for backwards compatibility with older versions of this module. 461 | :param dict of str to str extra_params: A dictionary of extra HTTP GET 462 | parameters, which must be URL encoded. For example if you don't want 463 | Google to filter similar results you can set the extra_params to 464 | {'filter': '0'} which will append '&filter=0' to every query. 465 | :param str tpe: Search type (images, videos, news, shopping, books, apps) 466 | Use the following values {videos: 'vid', images: 'isch', 467 | news: 'nws', shopping: 'shop', books: 'bks', applications: 'app'} 468 | :param str or None user_agent: User agent for the HTTP requests. 469 | Use None for the default. 470 | 471 | :rtype: generator of str 472 | :return: Generator (iterator) that yields found URLs. 473 | If the stop parameter is None the iterator will loop forever. 474 | """ 475 | return search(query, tld, lang, tbs, safe, num, start, stop, domains, 476 | pause, only_standard, extra_params, tpe='vid') 477 | 478 | 479 | # Shortcut to search shop. 480 | def search_shop(query, tld='com', lang='en', tbs='0', safe='off', num=10, 481 | start=0, stop=None, domains=None, pause=2.0, 482 | only_standard=False, extra_params={}): 483 | """ 484 | Shortcut to search shop. 485 | 486 | :param str query: Query string. Must NOT be url-encoded. 487 | :param str tld: Top level domain. 488 | :param str lang: Language. 489 | :param str tbs: Time limits (i.e "qdr:h" => last hour, 490 | "qdr:d" => last 24 hours, "qdr:m" => last month). 491 | :param str safe: Safe search. 492 | :param int num: Number of results per page. 493 | :param int start: First result to retrieve. 494 | :param int or None stop: Last result to retrieve. 495 | Use None to keep searching forever. 496 | :param list of str or None domains: A list of web domains to constrain 497 | the search. 498 | :param float pause: Lapse to wait between HTTP requests. 499 | A lapse too long will make the search slow, but a lapse too short may 500 | cause Google to block your IP. Your mileage may vary! 501 | :param bool only_standard: If True, only returns the standard results from 502 | each page. If False, it returns every possible link from each page, 503 | except for those that point back to Google itself. Defaults to False 504 | for backwards compatibility with older versions of this module. 505 | :param dict of str to str extra_params: A dictionary of extra HTTP GET 506 | parameters, which must be URL encoded. For example if you don't want 507 | Google to filter similar results you can set the extra_params to 508 | {'filter': '0'} which will append '&filter=0' to every query. 509 | :param str tpe: Search type (images, videos, news, shopping, books, apps) 510 | Use the following values {videos: 'vid', images: 'isch', 511 | news: 'nws', shopping: 'shop', books: 'bks', applications: 'app'} 512 | :param str or None user_agent: User agent for the HTTP requests. 513 | Use None for the default. 514 | 515 | :rtype: generator of str 516 | :return: Generator (iterator) that yields found URLs. 517 | If the stop parameter is None the iterator will loop forever. 518 | """ 519 | return search(query, tld, lang, tbs, safe, num, start, stop, domains, 520 | pause, only_standard, extra_params, tpe='shop') 521 | 522 | 523 | # Shortcut to search books. 524 | def search_books(query, tld='com', lang='en', tbs='0', safe='off', num=10, 525 | start=0, stop=None, domains=None, pause=2.0, 526 | only_standard=False, extra_params={}): 527 | """ 528 | Shortcut to search books. 529 | 530 | :param str query: Query string. Must NOT be url-encoded. 531 | :param str tld: Top level domain. 532 | :param str lang: Language. 533 | :param str tbs: Time limits (i.e "qdr:h" => last hour, 534 | "qdr:d" => last 24 hours, "qdr:m" => last month). 535 | :param str safe: Safe search. 536 | :param int num: Number of results per page. 537 | :param int start: First result to retrieve. 538 | :param int or None stop: Last result to retrieve. 539 | Use None to keep searching forever. 540 | :param list of str or None domains: A list of web domains to constrain 541 | the search. 542 | :param float pause: Lapse to wait between HTTP requests. 543 | A lapse too long will make the search slow, but a lapse too short may 544 | cause Google to block your IP. Your mileage may vary! 545 | :param bool only_standard: If True, only returns the standard results from 546 | each page. If False, it returns every possible link from each page, 547 | except for those that point back to Google itself. Defaults to False 548 | for backwards compatibility with older versions of this module. 549 | :param dict of str to str extra_params: A dictionary of extra HTTP GET 550 | parameters, which must be URL encoded. For example if you don't want 551 | Google to filter similar results you can set the extra_params to 552 | {'filter': '0'} which will append '&filter=0' to every query. 553 | :param str tpe: Search type (images, videos, news, shopping, books, apps) 554 | Use the following values {videos: 'vid', images: 'isch', 555 | news: 'nws', shopping: 'shop', books: 'bks', applications: 'app'} 556 | :param str or None user_agent: User agent for the HTTP requests. 557 | Use None for the default. 558 | 559 | :rtype: generator of str 560 | :return: Generator (iterator) that yields found URLs. 561 | If the stop parameter is None the iterator will loop forever. 562 | """ 563 | return search(query, tld, lang, tbs, safe, num, start, stop, domains, 564 | pause, only_standard, extra_params, tpe='bks') 565 | 566 | 567 | # Shortcut to search apps. 568 | def search_apps(query, tld='com', lang='en', tbs='0', safe='off', num=10, 569 | start=0, stop=None, domains=None, pause=2.0, 570 | only_standard=False, extra_params={}): 571 | """ 572 | Shortcut to search apps. 573 | 574 | :param str query: Query string. Must NOT be url-encoded. 575 | :param str tld: Top level domain. 576 | :param str lang: Language. 577 | :param str tbs: Time limits (i.e "qdr:h" => last hour, 578 | "qdr:d" => last 24 hours, "qdr:m" => last month). 579 | :param str safe: Safe search. 580 | :param int num: Number of results per page. 581 | :param int start: First result to retrieve. 582 | :param int or None stop: Last result to retrieve. 583 | Use None to keep searching forever. 584 | :param list of str or None domains: A list of web domains to constrain 585 | the search. 586 | :param float pause: Lapse to wait between HTTP requests. 587 | A lapse too long will make the search slow, but a lapse too short may 588 | cause Google to block your IP. Your mileage may vary! 589 | :param bool only_standard: If True, only returns the standard results from 590 | each page. If False, it returns every possible link from each page, 591 | except for those that point back to Google itself. Defaults to False 592 | for backwards compatibility with older versions of this module. 593 | :param dict of str to str extra_params: A dictionary of extra HTTP GET 594 | parameters, which must be URL encoded. For example if you don't want 595 | Google to filter similar results you can set the extra_params to 596 | {'filter': '0'} which will append '&filter=0' to every query. 597 | :param str tpe: Search type (images, videos, news, shopping, books, apps) 598 | Use the following values {videos: 'vid', images: 'isch', 599 | news: 'nws', shopping: 'shop', books: 'bks', applications: 'app'} 600 | :param str or None user_agent: User agent for the HTTP requests. 601 | Use None for the default. 602 | 603 | :rtype: generator of str 604 | :return: Generator (iterator) that yields found URLs. 605 | If the stop parameter is None the iterator will loop forever. 606 | """ 607 | return search(query, tld, lang, tbs, safe, num, start, stop, domains, 608 | pause, only_standard, extra_params, tpe='app') 609 | 610 | 611 | # Shortcut to single-item search. 612 | # Evaluates the iterator to return the single URL as a string. 613 | def lucky(query, tld='com', lang='en', tbs='0', safe='off', 614 | only_standard=False, extra_params={}, tpe=''): 615 | """ 616 | Shortcut to single-item search. 617 | 618 | :param str query: Query string. Must NOT be url-encoded. 619 | :param str tld: Top level domain. 620 | :param str lang: Language. 621 | :param str tbs: Time limits (i.e "qdr:h" => last hour, 622 | "qdr:d" => last 24 hours, "qdr:m" => last month). 623 | :param str safe: Safe search. 624 | :param int num: Number of results per page. 625 | :param int start: First result to retrieve. 626 | :param int or None stop: Last result to retrieve. 627 | Use None to keep searching forever. 628 | :param list of str or None domains: A list of web domains to constrain 629 | the search. 630 | :param float pause: Lapse to wait between HTTP requests. 631 | A lapse too long will make the search slow, but a lapse too short may 632 | cause Google to block your IP. Your mileage may vary! 633 | :param bool only_standard: If True, only returns the standard results from 634 | each page. If False, it returns every possible link from each page, 635 | except for those that point back to Google itself. Defaults to False 636 | for backwards compatibility with older versions of this module. 637 | :param dict of str to str extra_params: A dictionary of extra HTTP GET 638 | parameters, which must be URL encoded. For example if you don't want 639 | Google to filter similar results you can set the extra_params to 640 | {'filter': '0'} which will append '&filter=0' to every query. 641 | :param str tpe: Search type (images, videos, news, shopping, books, apps) 642 | Use the following values {videos: 'vid', images: 'isch', 643 | news: 'nws', shopping: 'shop', books: 'bks', applications: 'app'} 644 | :param str or None user_agent: User agent for the HTTP requests. 645 | Use None for the default. 646 | 647 | :rtype: str 648 | :return: URL found by Google. 649 | """ 650 | gen = search(query, tld, lang, tbs, safe, 1, 0, 1, 0., only_standard, 651 | extra_params, tpe) 652 | return next(gen) 653 | 654 | 655 | # Returns only the number of Google hits for the given search query. 656 | # This is the number reported by Google itself, NOT by scraping. 657 | def hits(query, tld='com', lang='en', tbs='0', safe='off', 658 | domains=None, extra_params={}, tpe='', user_agent=None): 659 | """ 660 | Search the given query string using Google and return the number of hits. 661 | 662 | :note: This is the number reported by Google itself, NOT by scraping. 663 | 664 | :param str query: Query string. Must NOT be url-encoded. 665 | :param str tld: Top level domain. 666 | :param str lang: Language. 667 | :param str tbs: Time limits (i.e "qdr:h" => last hour, 668 | "qdr:d" => last 24 hours, "qdr:m" => last month). 669 | :param str safe: Safe search. 670 | :param int num: Number of results per page. 671 | :param int start: First result to retrieve. 672 | :param int or None stop: Last result to retrieve. 673 | Use None to keep searching forever. 674 | :param list of str or None domains: A list of web domains to constrain 675 | the search. 676 | :param float pause: Lapse to wait between HTTP requests. 677 | A lapse too long will make the search slow, but a lapse too short may 678 | cause Google to block your IP. Your mileage may vary! 679 | :param bool only_standard: If True, only returns the standard results from 680 | each page. If False, it returns every possible link from each page, 681 | except for those that point back to Google itself. Defaults to False 682 | for backwards compatibility with older versions of this module. 683 | :param dict of str to str extra_params: A dictionary of extra HTTP GET 684 | parameters, which must be URL encoded. For example if you don't want 685 | Google to filter similar results you can set the extra_params to 686 | {'filter': '0'} which will append '&filter=0' to every query. 687 | :param str tpe: Search type (images, videos, news, shopping, books, apps) 688 | Use the following values {videos: 'vid', images: 'isch', 689 | news: 'nws', shopping: 'shop', books: 'bks', applications: 'app'} 690 | :param str or None user_agent: User agent for the HTTP requests. 691 | Use None for the default. 692 | 693 | :rtype: int 694 | :return: Number of Google hits for the given search query. 695 | """ 696 | 697 | # Prepare domain list if it exists. 698 | if domains: 699 | domain_query = '+OR+'.join('site:' + domain for domain in domains) 700 | domain_query = '+' + domain_query 701 | else: 702 | domain_query = '' 703 | 704 | # Prepare the search string. 705 | query = quote_plus(query + domain_query) 706 | 707 | # Check extra_params for overlapping 708 | for builtin_param in ('hl', 'q', 'btnG', 'tbs', 'safe', 'tbm'): 709 | if builtin_param in extra_params.keys(): 710 | raise ValueError( 711 | 'GET parameter "%s" is overlapping with \ 712 | the built-in GET parameter', 713 | builtin_param 714 | ) 715 | 716 | # Grab the cookie from the home page. 717 | get_page(url_home % vars()) 718 | 719 | # Prepare the URL of the first (and in this cases ONLY) request. 720 | url = url_search % vars() 721 | 722 | try: # Is it python<3? 723 | iter_extra_params = extra_params.iteritems() 724 | except AttributeError: # Or python>3? 725 | iter_extra_params = extra_params.items() 726 | # Append extra GET_parameters to URL 727 | for k, v in iter_extra_params: 728 | url += url + ('&%s=%s' % (k, v)) 729 | 730 | # Request the Google Search results page. 731 | html = get_page(url) 732 | 733 | # Parse the response. 734 | if is_bs4: 735 | soup = BeautifulSoup(html, 'html.parser') 736 | else: 737 | soup = BeautifulSoup(html) 738 | 739 | # Get the number of hits. 740 | tag = soup.find_all(attrs={"class": "sd", "id": "resultStats"})[0] 741 | hits_text_parts = tag.text.split() 742 | if len(hits_text_parts) < 3: 743 | return 0 744 | return int(hits_text_parts[1].replace(',', '').replace('.', '')) 745 | 746 | 747 | def ngd(term1, term2): 748 | """ 749 | Return the Normalized Google distance between words. 750 | 751 | For more info, refer to: 752 | https://en.wikipedia.org/wiki/Normalized_Google_distance 753 | 754 | :param str term1: First term to compare. 755 | :param str term2: Second term to compare. 756 | 757 | :rtype: float 758 | :return: Normalized Google distance between words. 759 | """ 760 | 761 | lhits1 = math.log10(hits(term1)) 762 | lhits2 = math.log10(hits(term2)) 763 | lhits_mix = math.log10(hits('"' + term1 + '" "' + term2 + '"')) 764 | npages = hits('the') 765 | fix = 1000 766 | 767 | lN = math.log10(npages * fix) 768 | numerator = max([lhits1, lhits2]) - lhits_mix 769 | denomin = lN - min([lhits1, lhits2]) 770 | 771 | return numerator / denomin 772 | -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ESD/ESD-0.0.29.dist-info/LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | {one line to give the program's name and a brief idea of what it does.} 635 | Copyright (C) {year} {name of author} 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | {project} Copyright (C) {year} {fullname} 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . -------------------------------------------------------------------------------- /Plugins/InfoSearch/Subdomain/ESD/ESD/__init__.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | """ 5 | ESD 6 | ~~~ 7 | 8 | Implements enumeration sub domains 9 | 10 | :author: Feei 11 | :homepage: https://github.com/FeeiCN/ESD 12 | :license: GPL, see LICENSE for more details. 13 | :copyright: Copyright (c) 2018 Feei. All rights reserved 14 | """ 15 | import os 16 | import re 17 | import time 18 | import ssl 19 | import math 20 | import string 21 | import random 22 | import traceback 23 | import itertools 24 | import datetime 25 | import colorlog 26 | import asyncio 27 | import aiodns 28 | import aiohttp 29 | import logging 30 | import requests 31 | import backoff 32 | import socket 33 | import async_timeout 34 | import dns.query 35 | import dns.zone 36 | import dns.resolver 37 | from tqdm import tqdm 38 | from colorama import Fore 39 | from optparse import OptionParser 40 | from aiohttp.resolver import AsyncResolver 41 | from itertools import islice 42 | from difflib import SequenceMatcher 43 | 44 | __version__ = '0.0.29' 45 | 46 | handler = colorlog.StreamHandler() 47 | formatter = colorlog.ColoredFormatter( 48 | '%(log_color)s%(asctime)s [%(name)s] [%(levelname)s] %(message)s%(reset)s', 49 | datefmt=None, 50 | reset=True, 51 | log_colors={ 52 | 'DEBUG': 'cyan', 53 | 'INFO': 'green', 54 | 'WARNING': 'yellow', 55 | 'ERROR': 'red', 56 | 'CRITICAL': 'red,bg_white', 57 | }, 58 | secondary_log_colors={}, 59 | style='%' 60 | ) 61 | handler.setFormatter(formatter) 62 | 63 | logger = colorlog.getLogger('ESD') 64 | logger.addHandler(handler) 65 | logger.setLevel(logging.INFO) 66 | 67 | ssl.match_hostname = lambda cert, hostname: True 68 | 69 | 70 | # 只采用了递归，速度非常慢，在优化完成前不建议开启 71 | # TODO:优化DNS查询，递归太慢了 72 | class DNSQuery(object): 73 | def __init__(self, root_domain, subs, suffix): 74 | # root domain 75 | self.suffix = suffix 76 | self.sub_domains = [] 77 | if root_domain: 78 | self.sub_domains.append(root_domain) 79 | 80 | for sub in subs: 81 | sub = ''.join(sub.rsplit(suffix, 1)).rstrip('.') 82 | self.sub_domains.append('{sub}.{domain}'.format(sub=sub, domain=suffix)) 83 | 84 | def dns_query(self): 85 | """ 86 | soa,txt,mx,aaaa 87 | :param sub: 88 | :return: 89 | """ 90 | final_list = [] 91 | for subdomain in self.sub_domains: 92 | try: 93 | soa = [] 94 | q_soa = dns.resolver.resolve(subdomain, 'SOA') 95 | for a in q_soa: 96 | soa.append(str(a.rname).strip('.')) 97 | soa.append(str(a.mname).strip('.')) 98 | except Exception as e: 99 | logger.warning('Query failed. {e}'.format(e=str(e))) 100 | try: 101 | aaaa = [] 102 | q_aaaa = dns.resolver.resolve(subdomain, 'AAAA') 103 | aaaa = [str(a.address).strip('.') for a in q_aaaa] 104 | except Exception as e: 105 | logger.warning('Query failed. {e}'.format(e=str(e))) 106 | try: 107 | txt = [] 108 | q_txt = dns.resolver.resolve(subdomain, 'TXT') 109 | txt = [t.strings[0].decode('utf-8').strip('.') for t in q_txt] 110 | except Exception as e: 111 | logger.warning('Query failed. {e}'.format(e=str(e))) 112 | try: 113 | mx = [] 114 | q_mx = dns.resolver.resolve(subdomain, 'MX') 115 | mx = [str(m.exchange).strip('.') for m in q_mx] 116 | except Exception as e: 117 | logger.warning('Query failed. {e}'.format(e=str(e))) 118 | domain_set = soa + aaaa + txt + mx 119 | domain_list = [i for i in domain_set] 120 | for p in domain_set: 121 | re_domain = re.findall(r'^(([a-z0-9]+(-[a-z0-9]+)*\.)+[a-z]{2,}\.?)$', p) 122 | if len(re_domain) > 0 and subdomain in re_domain[0][0]: 123 | continue 124 | else: 125 | domain_list.remove(p) 126 | final_list = domain_list + final_list 127 | # 递归调用，在子域名的dns记录中查找新的子域名 128 | recursive = [] 129 | # print("before: {0}".format(final_list)) 130 | # print("self.sub_domain: {0}".format(self.sub_domains)) 131 | final_list = list(set(final_list).difference(set(self.sub_domains))) 132 | # print("after: {0}".format(final_list)) 133 | if final_list: 134 | d = DNSQuery('', final_list, self.suffix) 135 | recursive = d.dns_query() 136 | return final_list + recursive 137 | 138 | 139 | class DNSTransfer(object): 140 | def __init__(self, domain): 141 | self.domain = domain 142 | 143 | def transfer_info(self): 144 | ret_zones = list() 145 | try: 146 | nss = dns.resolver.resolve(self.domain, 'NS') 147 | nameservers = [str(ns) for ns in nss] 148 | ns_addr = dns.resolver.resolve(nameservers[0], 'A') 149 | # dnspython 的 bug，需要设置 lifetime 参数 150 | zones = dns.zone.from_xfr(dns.query.xfr(ns_addr, self.domain, relativize=False, timeout=2, lifetime=2), 151 | check_origin=False) 152 | names = zones.nodes.keys() 153 | for n in names: 154 | subdomain = '' 155 | for t in range(0, len(n) - 1): 156 | if subdomain != '': 157 | subdomain += '.' 158 | subdomain += str(n[t].decode()) 159 | if subdomain != self.domain: 160 | ret_zones.append(subdomain) 161 | return ret_zones 162 | except BaseException: 163 | return [] 164 | 165 | 166 | class CAInfo(object): 167 | def __init__(self, domain): 168 | self.domain = domain 169 | 170 | def dns_resolve(self): 171 | padding_domain = 'www.' + self.domain 172 | # loop = asyncio.get_event_loop() 173 | loop = asyncio.new_event_loop() 174 | asyncio.set_event_loop(loop) 175 | resolver = aiodns.DNSResolver(loop=loop) 176 | f = resolver.query(padding_domain, 'A') 177 | result = loop.run_until_complete(f) 178 | return result[0].host 179 | 180 | def get_cert_info_by_ip(self, ip): 181 | s = socket.socket() 182 | s.settimeout(2) 183 | base_dir = os.path.dirname(os.path.abspath(__file__)) 184 | cert_path = base_dir + '/cacert.pem' 185 | connect = ssl.wrap_socket(s, cert_reqs=ssl.CERT_REQUIRED, ca_certs=cert_path) 186 | connect.settimeout(2) 187 | connect.connect((ip, 443)) 188 | cert_data = connect.getpeercert().get('subjectAltName') 189 | return cert_data 190 | 191 | def get_ca_domain_info(self): 192 | domain_list = list() 193 | try: 194 | ip = self.dns_resolve() 195 | cert_data = self.get_cert_info_by_ip(ip) 196 | except Exception as e: 197 | return domain_list 198 | 199 | for domain_info in cert_data: 200 | hostname = domain_info[1] 201 | if not hostname.startswith('*') and hostname.endswith(self.domain): 202 | domain_list.append(hostname) 203 | 204 | return domain_list 205 | 206 | def get_subdomains(self): 207 | subs = list() 208 | subdomain_list = self.get_ca_domain_info() 209 | for sub in subdomain_list: 210 | subs.append(sub[:len(sub) - len(self.domain) - 1]) 211 | return subs 212 | 213 | 214 | class EnumSubDomain(object): 215 | def __init__(self, domain, response_filter=None, dns_servers=None, skip_rsc=False, debug=False, 216 | split=None, proxy={}, multiresolve=False): 217 | self.project_directory = os.path.abspath(os.path.dirname(__file__)) 218 | logger.info('Version: {v}'.format(v=__version__)) 219 | logger.info('----------') 220 | logger.info('Start domain: {d}'.format(d=domain)) 221 | self.proxy = proxy 222 | self.data = {} 223 | self.domain = domain 224 | self.skip_rsc = skip_rsc 225 | self.split = split 226 | self.multiresolve = multiresolve 227 | self.stable_dns_servers = ['119.29.29.29'] 228 | if dns_servers is None: 229 | # 除了DNSPod外，其它的都不适合作为稳定的DNS 230 | # 要么并发会显著下降，要么就完全不能用 231 | dns_servers = [ 232 | # DNS对结果准确性影响非常大，部分DNS结果会和其它DNS结果不一致甚至没结果 233 | # '223.5.5.5', # AliDNS 234 | # '114.114.114.114', # 114DNS 235 | # '1.1.1.1', # Cloudflare 236 | '119.29.29.29', # DNSPod https://www.dnspod.cn/products/public.dns 237 | # '180.76.76.76', # BaiduDNS 238 | # '1.2.4.8', # sDNS 239 | # '11.1.1.1' # test DNS, not available 240 | # '8.8.8.8', # Google DNS, 延时太高了 241 | ] 242 | 243 | random.shuffle(dns_servers) 244 | self.dns_servers = dns_servers 245 | self.resolver = None 246 | self.loop = asyncio.get_event_loop() 247 | self.general_dicts = [] 248 | # Mark whether the current domain name is a pan-resolved domain name 249 | self.is_wildcard_domain = False 250 | # Use a nonexistent domain name to determine whether 251 | # there is a pan-resolve based on the DNS resolution result 252 | self.wildcard_sub = 'feei-esd-{random}'.format(random=random.randint(0, 9999)) 253 | self.wildcard_sub3 = 'feei-esd-{random}.{random}'.format(random=random.randint(0, 9999)) 254 | # There is no domain name DNS resolution IP 255 | self.wildcard_ips = [] 256 | # No domain name response HTML 257 | self.wildcard_html = None 258 | self.wildcard_html_len = 0 259 | self.wildcard_html3 = None 260 | self.wildcard_html3_len = 0 261 | # Subdomains that are consistent with IPs that do not have domain names 262 | self.wildcard_subs = [] 263 | # Wildcard domains use RSC 264 | self.wildcard_domains = {} 265 | # Corotines count 266 | self.coroutine_count = None 267 | # 并发太高DNS Server的错误会大幅增加 268 | self.coroutine_count_dns = 1000 269 | self.coroutine_count_request = 100 270 | # dnsaio resolve timeout 271 | self.resolve_timeout = 3 272 | # RSC ratio 273 | self.rsc_ratio = 0.8 274 | self.remainder = 0 275 | self.count = 0 276 | # Request Header 277 | self.request_headers = { 278 | 'Connection': 'keep-alive', 279 | 'Pragma': 'no-cache', 280 | 'Cache-Control': 'no-cache', 281 | 'Upgrade-Insecure-Requests': '1', 282 | 'User-Agent': 'Baiduspider', 283 | 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', 284 | 'DNT': '1', 285 | 'Referer': 'http://www.baidu.com/', 286 | 'Accept-Encoding': 'gzip, deflate', 287 | 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8'} 288 | # Filter the domain's response(regex) 289 | self.response_filter = response_filter 290 | # debug mode 291 | self.debug = debug 292 | if self.debug: 293 | logger.setLevel(logging.DEBUG) 294 | # collect redirecting domains and response domains 295 | self.domains_rs = [] 296 | self.domains_rs_processed = [] 297 | self.dns_query_errors = 0 298 | 299 | def generate_general_dicts(self, line): 300 | """ 301 | Generate general subdomains dicts 302 | :param line: 303 | :return: 304 | """ 305 | letter_count = line.count('{letter}') 306 | number_count = line.count('{number}') 307 | letters = itertools.product(string.ascii_lowercase, repeat=letter_count) 308 | letters = [''.join(l) for l in letters] 309 | numbers = itertools.product(string.digits, repeat=number_count) 310 | numbers = [''.join(n) for n in numbers] 311 | for l in letters: 312 | iter_line = line.replace('{letter}' * letter_count, l) 313 | self.general_dicts.append(iter_line) 314 | number_dicts = [] 315 | for gd in self.general_dicts: 316 | for n in numbers: 317 | iter_line = gd.replace('{number}' * number_count, n) 318 | number_dicts.append(iter_line) 319 | if len(number_dicts) > 0: 320 | return number_dicts 321 | else: 322 | return self.general_dicts 323 | 324 | def load_sub_domain_dict(self): 325 | """ 326 | Load subdomains from files and dicts 327 | :return: 328 | """ 329 | dicts = [] 330 | if self.debug: 331 | path = '{pd}/subs-test.esd'.format(pd=self.project_directory) 332 | else: 333 | path = '{pd}/subs.esd'.format(pd=self.project_directory) 334 | with open(path, encoding='utf-8') as f: 335 | for line in f: 336 | line = line.strip().lower() 337 | # skip comments and space 338 | if '#' in line or line == '': 339 | continue 340 | if '{letter}' in line or '{number}' in line: 341 | self.general_dicts = [] 342 | dicts_general = self.generate_general_dicts(line) 343 | dicts += dicts_general 344 | else: 345 | # compatibility other dicts 346 | line = line.strip('.') 347 | dicts.append(line) 348 | dicts = list(set(dicts)) 349 | 350 | # split dict 351 | if self.split is not None: 352 | s = self.split.split('/') 353 | dicts_choose = int(s[0]) 354 | dicts_count = int(s[1]) 355 | dicts_every = int(math.ceil(len(dicts) / dicts_count)) 356 | dicts = [dicts[i:i + dicts_every] for i in range(0, len(dicts), dicts_every)][dicts_choose - 1] 357 | logger.info( 358 | 'Sub domain dict split {count} and get {choose}st'.format(count=dicts_count, choose=dicts_choose)) 359 | 360 | # root domain 361 | dicts.append('@') 362 | 363 | return dicts 364 | 365 | async def query(self, sub): 366 | """ 367 | Query domain 368 | :param sub: 369 | :return: 370 | """ 371 | ret = None 372 | # root domain 373 | if sub == '@' or sub == '': 374 | sub_domain = self.domain 375 | else: 376 | sub = ''.join(sub.rsplit(self.domain, 1)).rstrip('.') 377 | sub_domain = '{sub}.{domain}'.format(sub=sub, domain=self.domain) 378 | # 如果存在特定异常则进行重试 379 | for i in range(4): 380 | try: 381 | ret = await self.resolver.query(sub_domain, 'A') 382 | except aiodns.error.DNSError as e: 383 | err_code, err_msg = e.args[0], e.args[1] 384 | # 域名确实不存在 385 | # 4: Domain name not found 386 | # 1: DNS server returned answer with no data 387 | # 其它情况都需要重试，否则存在很高的遗漏 388 | # 11: Could not contact DNS servers 389 | # 12: Timeout while contacting DNS servers 390 | if err_code not in [1, 4]: 391 | if i == 2: 392 | logger.warning(f'Try {i + 1} times, but failed. {sub_domain} {e}') 393 | self.dns_query_errors = self.dns_query_errors + 1 394 | continue 395 | except Exception as e: 396 | logger.info(sub_domain) 397 | logger.warning(traceback.format_exc()) 398 | else: 399 | ret = [r.host for r in ret] 400 | domain_ips = [s for s in ret] 401 | # It is a wildcard domain name and 402 | # the subdomain IP that is burst is consistent with the IP 403 | # that does not exist in the domain name resolution, 404 | # the response similarity is discarded for further processing. 405 | if self.is_wildcard_domain and ( 406 | sorted(self.wildcard_ips) == sorted(domain_ips) or set(domain_ips).issubset( 407 | self.wildcard_ips)): 408 | if self.skip_rsc: 409 | logger.debug( 410 | '{sub} maybe wildcard subdomain, but it is --skip-rsc mode now, it will be drop this subdomain in results'.format( 411 | sub=sub_domain)) 412 | else: 413 | logger.debug( 414 | '{r} maybe wildcard domain, continue RSC {sub}'.format(r=self.remainder, sub=sub_domain, 415 | ips=domain_ips)) 416 | else: 417 | if sub != self.wildcard_sub: 418 | self.data[sub_domain] = sorted(domain_ips) 419 | print('', end='\n') 420 | self.count += 1 421 | logger.info('{r} {sub} {ips}'.format(r=self.remainder, sub=sub_domain, ips=domain_ips)) 422 | break 423 | self.remainder += -1 424 | return sub_domain, ret 425 | 426 | @staticmethod 427 | def limited_concurrency_coroutines(coros, limit): 428 | futures = [ 429 | asyncio.ensure_future(c) 430 | for c in islice(coros, 0, limit) 431 | ] 432 | 433 | async def first_to_finish(): 434 | while True: 435 | await asyncio.sleep(0) 436 | for f in futures: 437 | if f.done(): 438 | futures.remove(f) 439 | try: 440 | nf = next(coros) 441 | futures.append(asyncio.ensure_future(nf)) 442 | except StopIteration: 443 | pass 444 | return f.result() 445 | 446 | while len(futures) > 0: 447 | yield first_to_finish() 448 | 449 | async def start(self, tasks, tasks_num): 450 | """ 451 | Limit the number of coroutines for reduce memory footprint 452 | :param tasks: 453 | :return: 454 | """ 455 | for res in tqdm(self.limited_concurrency_coroutines(tasks, self.coroutine_count), 456 | bar_format="%s{l_bar}%s{bar}%s{r_bar}%s" % (Fore.YELLOW, Fore.YELLOW, Fore.YELLOW, Fore.RESET), 457 | total=tasks_num): 458 | await res 459 | 460 | @staticmethod 461 | def data_clean(data): 462 | try: 463 | html = re.sub(r'\s', '', data) 464 | html = re.sub(r'.*?', '', html) 465 | return html 466 | except BaseException: 467 | return data 468 | 469 | @staticmethod 470 | @backoff.on_exception(backoff.expo, TimeoutError, max_tries=3) 471 | async def fetch(session, url): 472 | """ 473 | Fetch url response with session 474 | :param session: 475 | :param url: 476 | :return: 477 | """ 478 | try: 479 | async with async_timeout.timeout(20): 480 | async with session.get(url) as response: 481 | return await response.text(), response.history 482 | except Exception as e: 483 | # TODO 当在随机DNS场景中只做响应相似度比对的话，如果域名没有Web服务会导致相似度比对失败从而丢弃 484 | logger.warning('fetch exception: {e} {u}'.format(e=type(e).__name__, u=url)) 485 | return None, None 486 | 487 | async def similarity(self, sub): 488 | """ 489 | Enumerate subdomains by responding to similarities 490 | :param sub: 491 | :return: 492 | """ 493 | # root domain 494 | if sub == '@' or sub == '': 495 | sub_domain = self.domain 496 | else: 497 | sub = ''.join(sub.rsplit(self.domain, 1)).rstrip('.') 498 | sub_domain = '{sub}.{domain}'.format(sub=sub, domain=self.domain) 499 | 500 | if sub_domain in self.domains_rs: 501 | self.domains_rs.remove(sub_domain) 502 | full_domain = 'http://{sub_domain}'.format(sub_domain=sub_domain) 503 | # 如果跳转中的域名是以下情况则不加入下一轮RSC 504 | skip_domain_with_history = [ 505 | # 跳到主域名了 506 | '{domain}'.format(domain=self.domain), 507 | 'www.{domain}'.format(domain=self.domain), 508 | # 跳到自己本身了，比如HTTP跳HTTPS 509 | '{domain}'.format(domain=sub_domain), 510 | ] 511 | try: 512 | regex_domain = r"((?!\/)(?:(?:[a-z\d-]*\.)+{d}))".format(d=self.domain) 513 | resolver = AsyncResolver(nameservers=self.dns_servers) 514 | conn = aiohttp.TCPConnector(resolver=resolver) 515 | async with aiohttp.ClientSession(connector=conn, headers=self.request_headers) as session: 516 | html, history = await self.fetch(session, full_domain) 517 | html = self.data_clean(html) 518 | if history is not None and len(history) > 0: 519 | location = str(history[-1].headers['location']) 520 | if '.' in location: 521 | location_split = location.split('/') 522 | if len(location_split) > 2: 523 | location = location_split[2] 524 | else: 525 | location = location 526 | try: 527 | location = re.match(regex_domain, location).group(0) 528 | except AttributeError: 529 | location = location 530 | status = history[-1].status 531 | if location in skip_domain_with_history and len(history) >= 2: 532 | logger.debug('domain in skip: {s} {r} {l}'.format(s=sub_domain, r=status, l=location)) 533 | return 534 | else: 535 | # cnsuning.com suning.com 536 | if location[-len(self.domain) - 1:] == '.{d}'.format(d=self.domain): 537 | # collect redirecting's domains 538 | if sub_domain != location and location not in self.domains_rs and location not in self.domains_rs_processed: 539 | print('', end='\n') 540 | logger.info( 541 | '[{sd}] add redirect domain: {l}({len})'.format(sd=sub_domain, l=location, 542 | len=len(self.domains_rs))) 543 | self.domains_rs.append(location) 544 | self.domains_rs_processed.append(location) 545 | else: 546 | print('', end='\n') 547 | logger.info('not same domain: {l}'.format(l=location)) 548 | else: 549 | print('', end='\n') 550 | logger.info('not domain(maybe path): {l}'.format(l=location)) 551 | if html is None: 552 | print('', end='\n') 553 | logger.warning('domain\'s html is none: {s}'.format(s=sub_domain)) 554 | return 555 | # collect response html's domains 556 | response_domains = re.findall(regex_domain, html) 557 | response_domains = list(set(response_domains) - set([sub_domain])) 558 | for rd in response_domains: 559 | rd = rd.strip().strip('.') 560 | if rd.count('.') >= sub_domain.count('.') and rd[-len(sub_domain):] == sub_domain: 561 | continue 562 | if rd not in self.domains_rs: 563 | if rd not in self.domains_rs_processed: 564 | print('', end='\n') 565 | logger.info('[{sd}] add response domain: {s}({l})'.format(sd=sub_domain, s=rd, 566 | l=len(self.domains_rs))) 567 | self.domains_rs.append(rd) 568 | self.domains_rs_processed.append(rd) 569 | 570 | if len(html) == self.wildcard_html_len: 571 | ratio = 1 572 | else: 573 | # SPEED 4 2 1, but here is still the bottleneck 574 | # real_quick_ratio() > quick_ratio() > ratio() 575 | # TODO bottleneck 576 | if sub.count('.') == 0: # secondary sub, ex: www 577 | ratio = SequenceMatcher(None, html, self.wildcard_html).real_quick_ratio() 578 | ratio = round(ratio, 3) 579 | else: # tertiary sub, ex: home.dev 580 | ratio = SequenceMatcher(None, html, self.wildcard_html3).real_quick_ratio() 581 | ratio = round(ratio, 3) 582 | self.remainder += -1 583 | if ratio > self.rsc_ratio: 584 | # passed 585 | logger.debug( 586 | '{r} RSC ratio: {ratio} (passed) {sub}'.format(r=self.remainder, sub=sub_domain, ratio=ratio)) 587 | else: 588 | # added 589 | # for def distinct func 590 | # self.wildcard_domains[sub_domain] = html 591 | if self.response_filter is not None: 592 | for resp_filter in self.response_filter.split(','): 593 | if resp_filter in html: 594 | logger.debug('{r} RSC filter in response (passed) {sub}'.format(r=self.remainder, 595 | sub=sub_domain)) 596 | return 597 | else: 598 | continue 599 | self.data[sub_domain] = self.wildcard_ips 600 | else: 601 | self.data[sub_domain] = self.wildcard_ips 602 | print('', end='\n') 603 | logger.info( 604 | '{r} RSC ratio: {ratio} (added) {sub}'.format(r=self.remainder, sub=sub_domain, ratio=ratio)) 605 | except Exception as e: 606 | logger.debug(traceback.format_exc()) 607 | return 608 | 609 | def distinct(self): 610 | for domain, html in self.wildcard_domains.items(): 611 | for domain2, html2 in self.wildcard_domains.items(): 612 | ratio = SequenceMatcher(None, html, html2).real_quick_ratio() 613 | if ratio > self.rsc_ratio: 614 | # remove this domain 615 | if domain2 in self.data: 616 | del self.data[domain2] 617 | m = 'Remove' 618 | else: 619 | m = 'Stay' 620 | logger.info('{d} : {d2} {ratio} {m}'.format(d=domain, d2=domain2, ratio=ratio, m=m)) 621 | 622 | def check(self, dns): 623 | logger.info("Checking if DNS server {dns} is available".format(dns=dns)) 624 | msg = b'\x5c\x6d\x01\x00\x00\x01\x00\x00\x00\x00\x00\x00\x03www\x05baidu\x03com\x00\x00\x01\x00\x01' 625 | sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM) 626 | sock.settimeout(3) 627 | repeat = { 628 | 1: 'first', 629 | 2: 'second', 630 | 3: 'third' 631 | } 632 | for i in range(3): 633 | logger.info("Sending message to DNS server a {times} time".format(times=repeat[i + 1])) 634 | sock.sendto(msg, (dns, 53)) 635 | try: 636 | sock.recv(4096) 637 | break 638 | except socket.timeout as e: 639 | logger.warning('check dns server timeout Failed!') 640 | if i == 2: 641 | return False 642 | return True 643 | 644 | def run(self): 645 | """ 646 | Run 647 | :return: 648 | """ 649 | start_time = time.time() 650 | subs = self.load_sub_domain_dict() 651 | logger.info('Sub domain dict count: {c}'.format(c=len(subs))) 652 | logger.info('Generate coroutines...') 653 | # Verify that all DNS server results are consistent 654 | stable_dns = [] 655 | wildcard_ips = None 656 | last_dns = [] 657 | only_similarity = False 658 | for dns in self.dns_servers: 659 | delay = self.check(dns) 660 | if not delay: 661 | logger.warning("@{dns} is not available, skip this DNS server".format(dns=dns)) 662 | continue 663 | self.resolver = aiodns.DNSResolver(loop=self.loop, nameservers=[dns], timeout=self.resolve_timeout) 664 | job = self.query(self.wildcard_sub) 665 | sub, ret = self.loop.run_until_complete(job) 666 | logger.info('@{dns} {sub} {ips}'.format(dns=dns, sub=sub, ips=ret)) 667 | if ret is None: 668 | ret = None 669 | else: 670 | ret = sorted(ret) 671 | 672 | if dns in self.stable_dns_servers: 673 | wildcard_ips = ret 674 | stable_dns.append(ret) 675 | 676 | if ret: 677 | equal = [False for r in ret if r not in last_dns] 678 | if len(last_dns) != 0 and False in equal: 679 | only_similarity = self.is_wildcard_domain = True 680 | logger.info('Is a random resolve subdomain.') 681 | break 682 | else: 683 | last_dns = ret 684 | 685 | is_all_stable_dns = stable_dns.count(stable_dns[0]) == len(stable_dns) 686 | if not is_all_stable_dns: 687 | logger.info('Is all stable dns: NO, use the default dns server') 688 | self.resolver = aiodns.DNSResolver(loop=self.loop, nameservers=self.stable_dns_servers, 689 | timeout=self.resolve_timeout) 690 | # Wildcard domain 691 | is_wildcard_domain = not (stable_dns.count(None) == len(stable_dns)) 692 | if is_wildcard_domain or self.is_wildcard_domain: 693 | if not self.skip_rsc: 694 | logger.info('This is a wildcard domain, will enumeration subdomains use by DNS+RSC.') 695 | else: 696 | logger.info( 697 | 'This is a wildcard domain, but it is --skip-rsc mode now, it will be drop all random resolve subdomains in results') 698 | self.is_wildcard_domain = True 699 | if wildcard_ips is not None: 700 | self.wildcard_ips = wildcard_ips 701 | else: 702 | self.wildcard_ips = stable_dns[0] 703 | logger.info('Wildcard IPS: {ips}'.format(ips=self.wildcard_ips)) 704 | if not self.skip_rsc: 705 | try: 706 | self.wildcard_html = requests.get( 707 | 'http://{w_sub}.{domain}'.format(w_sub=self.wildcard_sub, domain=self.domain), 708 | headers=self.request_headers, timeout=10, verify=False).text 709 | self.wildcard_html = self.data_clean(self.wildcard_html) 710 | self.wildcard_html_len = len(self.wildcard_html) 711 | self.wildcard_html3 = requests.get( 712 | 'http://{w_sub}.{domain}'.format(w_sub=self.wildcard_sub3, domain=self.domain), 713 | headers=self.request_headers, timeout=10, verify=False).text 714 | self.wildcard_html3 = self.data_clean(self.wildcard_html3) 715 | self.wildcard_html3_len = len(self.wildcard_html3) 716 | logger.info( 717 | 'Wildcard domain response html length: {len} 3length: {len2}'.format(len=self.wildcard_html_len, 718 | len2=self.wildcard_html3_len)) 719 | except requests.exceptions.SSLError: 720 | logger.warning('SSL Certificate Error!') 721 | except requests.exceptions.ConnectTimeout: 722 | logger.warning('Request response content failed, check network please!') 723 | except requests.exceptions.ReadTimeout: 724 | self.wildcard_html = self.wildcard_html3 = '' 725 | self.wildcard_html_len = self.wildcard_html3_len = 0 726 | logger.warning( 727 | 'Request response content timeout, {w_sub}.{domain} and {w_sub3}.{domain} maybe not a http service, content will be set to blank!'.format( 728 | w_sub=self.wildcard_sub, 729 | domain=self.domain, 730 | w_sub3=self.wildcard_sub3)) 731 | except requests.exceptions.ConnectionError: 732 | logger.error('ESD can\'t get the response text so the rsc will be skipped. ') 733 | self.skip_rsc = True 734 | else: 735 | logger.info('Not a wildcard domain') 736 | 737 | if not only_similarity: 738 | self.coroutine_count = self.coroutine_count_dns 739 | tasks = (self.query(sub) for sub in subs) 740 | self.loop.run_until_complete(self.start(tasks, len(subs))) 741 | logger.info("Brute Force subdomain count: {total}".format(total=self.count)) 742 | dns_time = time.time() 743 | time_consume_dns = int(dns_time - start_time) 744 | logger.info(f'DNS query errors: {self.dns_query_errors}') 745 | 746 | # CA subdomain info 747 | ca_subdomains = [] 748 | logger.info('Collect subdomains in CA...') 749 | ca_subdomains = CAInfo(self.domain).get_subdomains() 750 | if len(ca_subdomains): 751 | tasks = (self.query(sub) for sub in ca_subdomains) 752 | self.loop.run_until_complete(self.start(tasks, len(ca_subdomains))) 753 | logger.info('CA subdomain count: {c}'.format(c=len(ca_subdomains))) 754 | 755 | # DNS Transfer Vulnerability 756 | transfer_info = [] 757 | logger.info('Check DNS Transfer Vulnerability in {domain}'.format(domain=self.domain)) 758 | transfer_info = DNSTransfer(self.domain).transfer_info() 759 | if len(transfer_info): 760 | logger.warning('DNS Transfer Vulnerability found in {domain}!'.format(domain=self.domain)) 761 | tasks = (self.query(sub) for sub in transfer_info) 762 | self.loop.run_until_complete(self.start(tasks, len(transfer_info))) 763 | logger.info('DNS Transfer subdomain count: {c}'.format(c=len(transfer_info))) 764 | 765 | total_subs = set(subs + transfer_info + ca_subdomains) 766 | 767 | # Use TXT,SOA,MX,AAAA record to find sub domains 768 | if self.multiresolve: 769 | logger.info('Enumerating subdomains with TXT, SOA, MX, AAAA record...') 770 | dnsquery = DNSQuery(self.domain, total_subs, self.domain) 771 | record_info = dnsquery.dns_query() 772 | tasks = (self.query(record[:record.find('.')]) for record in record_info) 773 | self.loop.run_until_complete(self.start(tasks, len(record_info))) 774 | logger.info('DNS record subdomain count: {c}'.format(c=len(record_info))) 775 | 776 | if self.is_wildcard_domain and not self.skip_rsc: 777 | # Response similarity comparison 778 | total_subs = set(subs + transfer_info + ca_subdomains) 779 | self.wildcard_subs = list(set(subs).union(total_subs)) 780 | logger.info('Enumerates {len} sub domains by DNS mode in {tcd}.'.format(len=len(self.data), tcd=str( 781 | datetime.timedelta(seconds=time_consume_dns)))) 782 | logger.info( 783 | 'Will continue to test the distinct({len_subs}-{len_exist})={len_remain} domains used by RSC, the speed will be affected.'.format( 784 | len_subs=len(subs), len_exist=len(self.data), 785 | len_remain=len(self.wildcard_subs))) 786 | self.coroutine_count = self.coroutine_count_request 787 | self.remainder = len(self.wildcard_subs) 788 | tasks = (self.similarity(sub) for sub in self.wildcard_subs) 789 | self.loop.run_until_complete(self.start(tasks, len(self.wildcard_subs))) 790 | 791 | # Distinct last domains use RSC 792 | # Maybe misinformation 793 | # self.distinct() 794 | 795 | time_consume_request = int(time.time() - dns_time) 796 | logger.info('Requests time consume {tcr}'.format(tcr=str(datetime.timedelta(seconds=time_consume_request)))) 797 | # RS(redirect/response) domains 798 | while len(self.domains_rs) != 0: 799 | logger.info('RS(redirect/response) domains({l})...'.format(l=len(self.domains_rs))) 800 | tasks = (self.similarity(''.join(domain.rsplit(self.domain, 1)).rstrip('.')) for domain in self.domains_rs) 801 | 802 | self.loop.run_until_complete(self.start(tasks, len(self.domains_rs))) 803 | 804 | # write output 805 | # tmp_dir = '/tmp/esd' 806 | # if not os.path.isdir(tmp_dir): 807 | # os.mkdir(tmp_dir, 0o777) 808 | # output_path_with_time = '{td}/.{domain}_{time}.esd'.format(td=tmp_dir, domain=self.domain, 809 | # time=datetime.datetime.now().strftime( 810 | # "%Y-%m_%d_%H-%M")) 811 | # output_path = '{td}/.{domain}.esd'.format(td=tmp_dir, domain=self.domain) 812 | # if len(self.data): 813 | # max_domain_len = max(map(len, self.data)) + 2 814 | # else: 815 | # max_domain_len = 2 816 | # output_format = '%-{0}s%-s\n'.format(max_domain_len) 817 | # with open(output_path_with_time, 'w') as opt, open(output_path, 'w') as op: 818 | # for domain, ips in self.data.items(): 819 | # # The format is consistent with other scanners to ensure that they are 820 | # # invoked at the same time without increasing the cost of 821 | # # resolution 822 | # if ips is None or len(ips) == 0: 823 | # ips_split = '' 824 | # else: 825 | # ips_split = ','.join(ips) 826 | # con = output_format % (domain, ips_split) 827 | # op.write(con) 828 | # opt.write(con) 829 | 830 | # 自修改 831 | subdomains = [] 832 | for domain, ips in self.data.items(): 833 | # The format is consistent with other scanners to ensure that they are 834 | # invoked at the same time without increasing the cost of 835 | # resolution 836 | if ips is None or len(ips) == 0: 837 | ips_split = '' 838 | else: 839 | ips_split = ','.join(ips) 840 | subdomains += [(domain, ips_split)] 841 | 842 | 843 | # logger.info('Output: {op}'.format(op=output_path)) 844 | # logger.info('Output with time: {op}'.format(op=output_path_with_time)) 845 | logger.info('Total domain: {td}'.format(td=len(self.data))) 846 | time_consume = int(time.time() - start_time) 847 | logger.info('Time consume: {tc}'.format(tc=str(datetime.timedelta(seconds=time_consume)))) 848 | return subdomains 849 | 850 | 851 | def banner(): 852 | print("""\033[94m 853 | ______ _____ _____ 854 | | ____| / ____| | __ \ 855 | | |__ | (___ | | | | 856 | | __| \___ \ | | | | 857 | | |____ ____) | | |__| | 858 | |______| |_____/ |_____/\033[0m\033[93m 859 | Enumeration Sub Domains v%s\033[92m 860 | """ % __version__) 861 | 862 | 863 | def main(): 864 | banner() 865 | parser = OptionParser( 866 | 'Usage: esd -d feei.cn -F response_filter -p user:pass@host:port') 867 | parser.add_option('-d', '--domain', dest='domains', help='The domains that you want to enumerate') 868 | parser.add_option('-f', '--file', dest='input', help='Import domains from this file') 869 | parser.add_option('-F', '--filter', dest='filter', help='Response filter') 870 | parser.add_option('-s', '--skip-rsc', dest='skiprsc', help='Skip response similary compare', action='store_true', 871 | default=False) 872 | parser.add_option('-S', '--split', dest='split', help='Split the dict into several parts', default='1/1') 873 | parser.add_option('-p', '--proxy', dest='proxy', help='Use socks5 proxy to access Google and Yahoo') 874 | parser.add_option('-m', '--multi-resolve', dest='multiresolve', 875 | help='Use TXT, AAAA, MX, SOA record to find subdomains', action='store_true', default=False) 876 | (options, args) = parser.parse_args() 877 | 878 | domains = [] 879 | response_filter = options.filter 880 | skip_rsc = options.skiprsc 881 | split_list = options.split.split('/') 882 | split = options.split 883 | multiresolve = options.multiresolve 884 | 885 | try: 886 | if len(split_list) != 2 or int(split_list[0]) > int(split_list[1]): 887 | logger.error('Invaild split parameter,can not split the dict') 888 | split = None 889 | except: 890 | logger.error('Split validation failed: {d}'.format(d=split_list)) 891 | exit(0) 892 | 893 | if options.proxy: 894 | proxy = { 895 | 'http': 'socks5h://%s' % options.proxy, 896 | 'https': 'socks5h://%s' % options.proxy 897 | } 898 | else: 899 | proxy = {} 900 | 901 | if options.domains is not None: 902 | for p in options.domains.split(','): 903 | p = p.strip().lower() 904 | re_domain = re.findall(r'^(([a-z0-9]+(-[a-z0-9]+)*\.)+[a-z]{2,})$', p) 905 | if len(re_domain) > 0 and re_domain[0][0] == p: 906 | domains.append(p.strip()) 907 | else: 908 | logger.error('Domain validation failed: {d}'.format(d=p)) 909 | elif options.input and os.path.isfile(options.input): 910 | with open(options.input) as fh: 911 | for line_domain in fh: 912 | line_domain = line_domain.strip().lower() 913 | re_domain = re.findall(r'^(([a-z0-9]+(-[a-z0-9]+)*\.)+[a-z]{2,})$', line_domain) 914 | if len(re_domain) > 0 and re_domain[0][0] == line_domain: 915 | domains.append(line_domain) 916 | else: 917 | logger.error('Domain validation failed: {d}'.format(d=line_domain)) 918 | else: 919 | logger.error('Please input vaild parameter. ie: "esd -d feei.cn" or "esd -f /Users/root/domains.txt"') 920 | 921 | if 'esd' in os.environ: 922 | debug = os.environ['esd'] 923 | else: 924 | debug = False 925 | logger.info('Debug: {d}'.format(d=debug)) 926 | logger.info('--skip-rsc: {rsc}'.format(rsc=skip_rsc)) 927 | 928 | logger.info('Total target domains: {ttd}'.format(ttd=len(domains))) 929 | try: 930 | for d in domains: 931 | esd = EnumSubDomain(d, response_filter, skip_rsc=skip_rsc, debug=debug, split=split, 932 | proxy=proxy, 933 | multiresolve=multiresolve) 934 | esd.run() 935 | except KeyboardInterrupt: 936 | print('', end='\n') 937 | logger.info('Bye :)') 938 | exit(0) 939 | 940 | 941 | if __name__ == '__main__': 942 | main() 943 | --------------------------------------------------------------------------------