├── CREDITS
├── Wappalyzer
    ├── __init__.py
    ├── webpage
    │   ├── __init__.py
    │   ├── _bs4.py
    │   ├── _stdlib.py
    │   └── _common.py
    ├── __main__.py
    ├── fingerprint.py
    └── Wappalyzer.py
├── .gitignore
├── Makefile
├── .github
    └── workflows
    │   ├── docs.yml
    │   └── test.yml
├── tox.ini
├── setup.py
├── README.rst
├── tests
    └── test_wappalyzer.py
└── LICENSE


/CREDITS:
--------------------------------------------------------------------------------
1 | The code in this repository is based on
2 | Elbert Alias' Wappalyzer utility:
3 | 
4 |   https://github.com/ElbertF/Wappalyzer
5 | 


--------------------------------------------------------------------------------
/Wappalyzer/__init__.py:
--------------------------------------------------------------------------------
 1 | """
 2 | Welcome to ``python-Wappalyzer`` API documentation!
 3 | 
 4 | :see: `Wappalyzer` and `WebPage`.
 5 | """
 6 | 
 7 | from .Wappalyzer import Wappalyzer, analyze
 8 | from .webpage import WebPage
 9 | __all__ = ["Wappalyzer", 
10 |            "WebPage", 
11 |            "analyze"]
12 | 


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
 1 | # VScode
 2 | .vscode
 3 | 
 4 | # PyDoctor
 5 | apidocs
 6 | 
 7 | # Byte-compiled / optimized / DLL files
 8 | __pycache__/
 9 | *.py[cod]
10 | *$py.class
11 | 
12 | # C extensions
13 | *.so
14 | 
15 | # Distribution / packaging
16 | .Python
17 | env/
18 | venv/
19 | ENV/
20 | build/
21 | develop-eggs/
22 | dist/
23 | downloads/
24 | eggs/
25 | .eggs/
26 | lib/
27 | lib64/
28 | parts/
29 | sdist/
30 | var/
31 | *.egg-info/
32 | .installed.cfg
33 | *.egg
34 | 
35 | # Installer logs
36 | pip-log.txt
37 | 
38 | # Unit test / coverage reports
39 | .coverage
40 | .tox
41 | nosetests.xml
42 | .noseids
43 | 
44 | # Translations
45 | *.mo
46 | 
47 | # Mr Developer
48 | .mr.developer.cfg
49 | .project
50 | .pydevproject
51 | 


--------------------------------------------------------------------------------
/Makefile:
--------------------------------------------------------------------------------
 1 | .PHONY: tests
 2 | 
 3 | default: build
 4 | 
 5 | install:
 6 | 	wget -O Wappalyzer/data/technologies.json https://raw.githubusercontent.com/AliasIO/wappalyzer/master/src/technologies.json
 7 | 	pip install .
 8 | 
 9 | rebuild: clean install tests
10 | 
11 | build: install tests
12 | 
13 | clean:
14 | 	rm -f -r build/
15 | 	rm -f -r bin/
16 | 	rm -f -r dist/
17 | 	rm -f -r *.egg-info
18 | 	find . -name '*.pyc' -exec rm -f {} +
19 | 	find . -name '*.pyo' -exec rm -f {} +
20 | 	find . -name '*~' -exec rm -f  {} +
21 | 	find . -name '__pycache__' -exec rm -rf {} +
22 | 	find . -name '.pytest_cache' -exec rm -rf {} +
23 | 
24 | tests:
25 | 	flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
26 | 	python -m pytest
27 | 


--------------------------------------------------------------------------------
/Wappalyzer/webpage/__init__.py:
--------------------------------------------------------------------------------
 1 | """
 2 | `Wappalyzer.WebPage` uses BeautifulSoup4 by default and fallback to standard library if it's not available.
 3 | 
 4 | The following objects are importable form this module: `WebPage`, `IWebPage`, `ITag`.
 5 | 
 6 | :Note: You can directly use/subclass one of the ``WebPage`` classes provided 
 7 |     in modules `_bs4` and `_stdlib` if you'de like more control. 
 8 |     Alternatively, your can write your own ``WebPage`` from scratch by suclassing the `IWebPage` interface.
 9 | """
10 | from ._common import IWebPage, ITag
11 | try:
12 |     from ._bs4 import WebPage
13 | except Exception:
14 |     try:
15 |         from ._stdlib import WebPage # type: ignore
16 |     except Exception as e:
17 |         raise ImportError(
18 |         """Cannot use Wappalyzer, missing required parser libraries.
19 |         You can either install 'lxml' and 'beatifulsoup4' OR install 'dom_query'. 
20 |         The later option makes Wappalyzer use the standard library HTML parser.""") from e


--------------------------------------------------------------------------------
/.github/workflows/docs.yml:
--------------------------------------------------------------------------------
 1 | name: Publish API Docs
 2 | on:
 3 |   push:
 4 |     branches: [ master ]
 5 | 
 6 | jobs:
 7 |   deploy:
 8 |     runs-on: ubuntu-latest
 9 | 
10 |     steps:
11 |     - uses: actions/checkout@master
12 |     - name: Set up Python 3.8
13 |       uses: actions/setup-python@v2
14 |       with:
15 |         python-version: 3.8
16 | 
17 |     - name: Install package
18 |       run: |
19 |         python -m pip install --upgrade pip setuptools wheel
20 |         python -m pip install .[dev]
21 |         python -m pip install docutils pydoctor
22 | 
23 |         pydoctor --version
24 | 
25 |     - name: Generate API documentation with pydoctor
26 |       run: |
27 |         # Run pydoctor build
28 |         tox -e docs -- $(git rev-parse HEAD)
29 | 
30 |     - name: Publish API documentation to the gh-pages branch
31 |       uses: peaceiris/actions-gh-pages@v3
32 |       with:
33 |         github_token: ${{ secrets.GITHUB_TOKEN }}
34 |         publish_dir: ./apidocs
35 |         commit_message: "Generate API documentation"
36 | 


--------------------------------------------------------------------------------
/Wappalyzer/__main__.py:
--------------------------------------------------------------------------------
 1 | import argparse
 2 | import json
 3 | from .Wappalyzer import analyze
 4 | 
 5 | def get_parser() -> argparse.ArgumentParser:
 6 |     """Get the CLI `argparse.ArgumentParser`"""
 7 |     parser = argparse.ArgumentParser(description="python-Wappalyzer CLI", prog="python -m Wappalyzer")
 8 |     parser.add_argument('url', help='URL to analyze')
 9 |     parser.add_argument('--update', action='store_true', help='Use the latest technologies file downloaded from the internet')
10 |     parser.add_argument('--user-agent', help='Request user agent', dest='useragent')
11 |     parser.add_argument('--timeout', help='Request timeout', type=int, default=10)
12 |     parser.add_argument('--no-verify', action='store_true', help='Skip SSL cert verify', dest='noverify')
13 |     return parser
14 | 
15 | def main(args) -> None:
16 |     """Entrypoint
17 |     :param args: `Namespace` returned by `argparse.ArgumentParser.parse_args`. 
18 |     """
19 |     result = analyze(args.url, update=args.update, useragent=args.useragent, timeout=args.timeout, verify=not args.noverify)
20 |     print(json.dumps(result))
21 | 
22 | if __name__ == '__main__':
23 |     main(get_parser().parse_args())
24 | 


--------------------------------------------------------------------------------
/tox.ini:
--------------------------------------------------------------------------------
 1 | [tox]
 2 | minversion=3.20.1
 3 | requires=
 4 |     virtualenv>=20.0.35
 5 | envlist =
 6 |     test,mypy,docs
 7 | 
 8 | [testenv:test]
 9 | description = run tests (unittest)
10 | 
11 | passenv = *
12 | 
13 | extras = dev
14 | 
15 | commands =
16 |     pytest -vv
17 | 
18 | [testenv:mypy]
19 | description = run mypy (static type checker)
20 | 
21 | extras = dev
22 | 
23 | commands =
24 |     mypy                                       \
25 |         --cache-dir="{toxworkdir}/mypy_cache"  \
26 |         {tty:--pretty:}                        \
27 |         {posargs:Wappalyzer}
28 | 
29 | [testenv:docs]
30 | description = build the documentation
31 | 
32 | extras = docs
33 | 
34 | setenv =
35 |     TOX_INI_DIR = {toxinidir}
36 | 
37 | commands =
38 |     pydoctor \
39 |           ./Wappalyzer \
40 |           --project-name=python-Wappalyzer \
41 |             --project-url=https://github.com/chorsley/python-Wappalyzer/ \
42 |             --html-viewsource-base=https://github.com/chorsley/python-Wappalyzer/tree/{posargs:master}/ \
43 |             --make-html --quiet \
44 |             --html-output={toxinidir}/apidocs \
45 |             --project-base-dir={toxinidir} \
46 |             --docformat=restructuredtext \
47 |             --intersphinx=https://docs.python.org/3/objects.inv \
48 |             --intersphinx=https://docs.aiohttp.org/en/stable/objects.inv \
49 |             --intersphinx=https://requests.readthedocs.io/en/stable/objects.inv
50 | 


--------------------------------------------------------------------------------
/setup.py:
--------------------------------------------------------------------------------
 1 | from setuptools import setup, find_packages
 2 | import pathlib
 3 | 
 4 | setup(
 5 |     name                =   "python-Wappalyzer",
 6 |     version             =   "0.4.0",
 7 |     description         =   "Python implementation of the Wappalyzer web application "
 8 |                             "detection utility",
 9 |     long_description    =   (pathlib.Path(__file__).parent / "README.rst").read_text(),
10 |     long_description_content_type   =   "text/markdown",
11 |     author              =   "Chris Horsley (chorsley) and other contributors (See git history)",
12 |     url                 =   "https://github.com/chorsley/python-Wappalyzer",
13 |     classifiers         =   [
14 |                                 'Development Status :: 3 - Alpha',
15 |                                 'Intended Audience :: Developers',
16 |                                 'License :: OSI Approved :: GNU General Public License v3 (GPLv3)',
17 |                                 'Programming Language :: Python :: 3',
18 |                                 'Topic :: Internet :: WWW/HTTP',
19 |                             ],
20 |     packages            =   find_packages(exclude='tests'),
21 |     package_data        =   {'Wappalyzer': ['data/technologies.json']},
22 |     install_requires    =   [   'beautifulsoup4', 
23 |                                 'lxml',
24 |                                 'requests',
25 |                                 'aiohttp',
26 |                                 'cached_property', ],
27 |     extras_require      =   {
28 |                              # Pin pydoctor version until https://github.com/twisted/pydoctor/issues/513 is fixed
29 |                              'docs': ["pydoctor==21.2.2", "docutils"], 
30 |                              'dev': ["tox", "mypy>=0.902", "httpretty", "pytest", "pytest-asyncio", 
31 |                                      "types-requests", "types-pkg_resources", "aioresponses"]
32 |                             },
33 |     python_requires     =   '>=3.6',
34 | )


--------------------------------------------------------------------------------
/Wappalyzer/webpage/_bs4.py:
--------------------------------------------------------------------------------
 1 | """
 2 | Implementation of WebPage based on bs4, depends on lxml.
 3 | """
 4 | from typing import Iterator, Mapping
 5 | #Just to check if it's available
 6 | import lxml # type: ignore 
 7 | from bs4 import BeautifulSoup, Tag as bs4_Tag # type: ignore
 8 | from cached_property import cached_property # type: ignore
 9 | 
10 | from ._common import BaseWebPage, BaseTag
11 | 
12 | class Tag(BaseTag):
13 | 
14 |     def __init__(self, name: str, attributes: Mapping[str, str], soup: bs4_Tag) -> None:
15 |         super().__init__(name, attributes)
16 |         self._soup = soup
17 |     
18 |     @cached_property
19 |     def inner_html(self) -> str:
20 |         return self._soup.decode_contents()
21 | 
22 | class WebPage(BaseWebPage):
23 |     """
24 |     Simple representation of a web page, decoupled
25 |     from any particular HTTP library's API.
26 | 
27 |     Well, except for the class methods that use `requests`
28 |     or `aiohttp` to create the WebPage.
29 | 
30 |     This object is designed to be created for each website scanned
31 |     by python-Wappalyzer. 
32 |     It will parse the HTML with BeautifulSoup to find <script> and <meta> tags.
33 | 
34 |     You can create it from manually from HTML with the `WebPage()` method
35 |     or from the class methods. 
36 |     """
37 | 
38 |     def _parse_html(self):
39 |         """
40 |         Parse the HTML with BeautifulSoup to find <script> and <meta> tags.
41 |         """
42 |         self._parsed_html = soup = BeautifulSoup(self.html, 'lxml')
43 |         self.scripts.extend(script['src'] for script in
44 |                         soup.findAll('script', src=True))
45 |         self.meta = {
46 |             meta['name'].lower():
47 |                 meta['content'] for meta in soup.findAll(
48 |                     'meta', attrs=dict(name=True, content=True))
49 |         }
50 |     
51 |     def select(self, selector: str) -> Iterator[Tag]:
52 |         """Execute a CSS select and returns results as Tag objects."""
53 |         for item in self._parsed_html.select(selector):
54 |             yield Tag(item.name, item.attrs, item)
55 | 
56 | 
57 | 


--------------------------------------------------------------------------------
/.github/workflows/test.yml:
--------------------------------------------------------------------------------
 1 | name: Tests (and release on tags)
 2 | 
 3 | on:
 4 |   push:
 5 |     branches: [ master ]
 6 |     tags: 
 7 |       - '*'
 8 |   pull_request:
 9 |     branches: [ master ]
10 | 
11 | jobs:
12 |   unit_tests:
13 |     runs-on: ${{ matrix.os }}
14 | 
15 |     strategy:
16 |       matrix:
17 |         python-version: [3.6, 3.7, 3.8, 3.9, '3.10', pypy-3.6]
18 |         os: [ubuntu-20.04]
19 |         include:
20 |           - os: windows-latest
21 |             python-version: 3.6
22 |           - os: macos-latest
23 |             python-version: 3.6
24 | 
25 |     steps:
26 |     - uses: actions/checkout@v2
27 | 
28 |     - name: Set up Python
29 |       uses: actions/setup-python@v2
30 |       with:
31 |         python-version: ${{ matrix.python-version }}
32 | 
33 |     - name: Install tox
34 |       run: |
35 |         python -m pip install --upgrade pip tox
36 | 
37 |     - name: Run unit tests (CPython)
38 |       if: matrix.python-version != 'pypy-3.6'
39 |       run: |
40 |         tox -e test
41 | 
42 |         python3 -m pip install pytest pytest-asyncio httpretty aioresponses
43 |         python3 -m pip install requests aiohttp cached_property dom_query 
44 |         python3 -m pip install . --no-deps
45 |         pytest -vv
46 |     
47 |     - name: Run unit tests (PyPy)
48 |       if: matrix.python-version == 'pypy-3.6'
49 |       run: |
50 |         python3 -m pip install pytest pytest-asyncio httpretty aioresponses
51 |         python3 -m pip install requests aiohttp cached_property dom_query
52 |         python3 -m pip install . --no-deps
53 |         pytest -vv
54 | 
55 |     - name: Run static code checks
56 |       if: matrix.python-version != 'pypy-3.6' &&  matrix.python-version != '3.6'
57 |       run: |
58 |         tox -e mypy
59 | 
60 |   release:
61 | 
62 |     needs: [unit_tests]
63 |     runs-on: ubuntu-latest
64 | 
65 |     steps:
66 |       - uses: actions/checkout@v2
67 | 
68 |       - name: Set up Python 3.9
69 |         uses: actions/setup-python@v2
70 |         with:
71 |           python-version: 3.9
72 | 
73 |       - name: Install deps
74 |         run: |
75 |           python -m pip install --upgrade pip setuptools wheel
76 | 
77 |       - name: Build python-Wappalyzer
78 |         run: |
79 |           python setup.py --quiet build check sdist bdist_wheel
80 |           ls -alh ./dist/
81 | 
82 |       - name: Publish python-Wappalyzer to PyPI on tags
83 |         if: startsWith(github.ref, 'refs/tags')
84 |         uses: pypa/gh-action-pypi-publish@master
85 |         with:
86 |           user: __token__
87 |           password: ${{ secrets.PYPI_TOKEN }}
88 | 


--------------------------------------------------------------------------------
/Wappalyzer/webpage/_stdlib.py:
--------------------------------------------------------------------------------
 1 | """
 2 | Implementation of WebPage based on the standard library. 
 3 | """
 4 | import logging
 5 | from typing import Iterable, Mapping, Optional
 6 | 
 7 | from html.parser import HTMLParser
 8 | from xml.dom import minidom
 9 | from cached_property import cached_property # type: ignore
10 | 
11 | from ._common import BaseWebPage, BaseTag
12 | 
13 | from dom_query import select_all # type: ignore
14 | 
15 | # Parsing HTLM with built-in libraries is difficult, we should not reinvent the wheel here. 
16 | # We provide this module only as a backup for environments where lxml cannot be installed.
17 | # https://stackoverflow.com/questions/2676872/how-to-parse-malformed-html-in-python-using-standard-libraries
18 | 
19 | class Tag(BaseTag):
20 | 
21 |     def __init__(self, name: str, attributes: Mapping[str, str], elem: minidom.Element) -> None:
22 |         super().__init__(name, attributes)
23 |         self._elem = elem
24 |     
25 |     @cached_property
26 |     def inner_html(self) -> str:
27 |         return ''.join(d.toxml() for d in self._elem.childNodes)
28 | 
29 | class ScriptMetaParser(HTMLParser):
30 | 
31 |     def __init__(self):
32 |         super().__init__()
33 |         self.script_src = []
34 |         self.meta_info = {}
35 | 
36 |     def handle_starttag(self, tag, attrs):
37 |         attributes = dict(attrs)
38 |         if tag == 'script':
39 |             if attributes.get('src'):
40 |                 self.script_src.append(attributes.get('src'))
41 |         if tag == 'meta':
42 |             if attributes.get('name'):
43 |                 self.meta_info.update({attributes.get('name').lower(): attributes.get('content')})
44 | 
45 | class WebPage(BaseWebPage):
46 |     """
47 |     This is an alternative WebPage object that uses only the standard library to parse HTML.
48 |     It does require an extra dependency to parse CSS selectors, though.
49 |     """
50 | 
51 |     def _parse_html(self):
52 |         """
53 |         Parse the HTML with HTMLParser to find <script> and <meta> tags.
54 |         """
55 |         script_meta_parser = ScriptMetaParser()
56 |         script_meta_parser.feed(self.html)
57 |         self.scripts.extend(script_meta_parser.script_src)
58 |         self.meta = script_meta_parser.meta_info
59 |     
60 |     @cached_property
61 |     def _dom(self) -> Optional[minidom.Document]:
62 |         try:
63 |             dom = minidom.parseString(self.html)
64 |         except Exception as e:
65 |             logging.getLogger(name="python-Wappalyzer").error(
66 |                 f"Could not parse HTML of webpage {self.url}: {e}")
67 |             dom = None
68 |         return dom
69 | 
70 |     def select(self, selector: str) -> Iterable[Tag]:
71 |         """Execute a CSS select and returns results as Tag objects."""
72 |         dom = self._dom
73 |         if not dom:
74 |             return ()
75 |         for item in select_all(dom, selector):
76 |             yield Tag(item.tagName, dict(item._get_attributes().items()), item)
77 | 


--------------------------------------------------------------------------------
/README.rst:
--------------------------------------------------------------------------------
  1 | # This repo is no longer maintained and is archived. There are many forks available, however.
  2 | 
  3 | python-Wappalyzer
  4 | -----------------
  5 | 
  6 | .. image:: https://travis-ci.org/chorsley/python-Wappalyzer.svg?branch=master
  7 |   :target: https://travis-ci.org/chorsley/python-Wappalyzer
  8 | 
  9 | .. image:: https://badge.fury.io/py/python-Wappalyzer.svg
 10 |   :target: https://pypi.org/project/python-Wappalyzer/
 11 | 
 12 | .. image:: https://coveralls.io/repos/github/chorsley/python-Wappalyzer/badge.svg?branch=master
 13 |   :target: https://coveralls.io/github/chorsley/python-Wappalyzer?branch=master
 14 | 
 15 | 
 16 | 
 17 | Python implementation of the `Wappalyzer <https://github.com/AliasIO/wappalyzer>`_ web application detection utility.  
 18 | 
 19 | 
 20 | Install
 21 | -------
 22 | 
 23 | ::
 24 | 
 25 |     $ pip install python-Wappalyzer
 26 | 
 27 | Require Python3.6 or later. 
 28 | 
 29 | Usage
 30 | -----
 31 | 
 32 | The API exposes two objects: ``Wappalyzer.Wappalyzer`` and ``Wappalyzer.WebPage``. 
 33 | 
 34 | >>> from Wappalyzer import Wappalyzer, WebPage
 35 | 
 36 | First create a WebPage. The following code creates a webpage with the ``request`` module. 
 37 | 
 38 | >>> webpage = WebPage.new_from_url('http://example.com')
 39 | 
 40 | Then analyze it with Wappalyzer. 
 41 | 
 42 | >>> wappalyzer = Wappalyzer.latest()
 43 | >>> wappalyzer.analyze(webpage)
 44 | {'Docker', 'Azure CDN', 'Amazon Web Services', 'Amazon ECS'}
 45 | 
 46 | To download and use the latest technologies file from AliasIO/wappalyzer repository, 
 47 | create the Wappalyzer driver with the ``update=True`` parameter. 
 48 | 
 49 | >>> wappalyzer = Wappalyzer.latest(update=True)
 50 | 
 51 | The Wappalyzer object exposes more methods that returns metatada for the detected technologies. 
 52 | 
 53 | >>> wappalyzer.analyze_with_categories(webpage)
 54 | {'Amazon ECS': {'categories': ['IaaS']},
 55 |  'Amazon Web Services': {'categories': ['PaaS']},
 56 |  'Azure CDN': {'categories': ['CDN']},
 57 |  'Docker': {'categories': ['Containers']}}
 58 | 
 59 | >>> webpage = WebPage.new_from_url('http://wordpress-example.com')
 60 | >>> wappalyzer.analyze_with_versions_and_categories(webpage)
 61 | {'Font Awesome': {'categories': ['Font scripts'], 'versions': ['5.4.2']},
 62 |  'Google Font API': {'categories': ['Font scripts'], 'versions': []},
 63 |  'MySQL': {'categories': ['Databases'], 'versions': []},
 64 |  'Nginx': {'categories': ['Web servers', 'Reverse proxies'], 'versions': []},
 65 |  'PHP': {'categories': ['Programming languages'], 'versions': ['5.6.40']},
 66 |  'WordPress': {'categories': ['CMS', 'Blogs'], 'versions': ['5.4.2']},
 67 |  'Yoast SEO': {'categories': ['SEO'], 'versions': ['14.6.1']}}
 68 | 
 69 | Read the `API Reference <https://chorsley.github.io/python-Wappalyzer/Wappalyzer.html>`_ for more documentation.
 70 | 
 71 | CLI
 72 | ---
 73 | 
 74 | Additionnaly, there is now a CLI interface. It prints the analyzer results (with metatada) as JSON.
 75 | 
 76 | Call it with::
 77 | 
 78 |     python -m Wappalyzer
 79 | 
 80 | positional arguments:
 81 |   url                   URL to analyze
 82 | 
 83 | optional arguments:
 84 |   -h, --help            show this help message and exit
 85 |   --update              Use the latest technologies file downloaded from the internet
 86 |   --user-agent USERAGENT
 87 |                         Request user agent
 88 |   --timeout TIMEOUT     Request timeout
 89 |   --no-verify           Skip SSL cert verify
 90 | 
 91 | Cannot use lxml in your environment?
 92 | ------------------------------------
 93 | 
 94 | We provide a way to use python-Wappalyzer without ``lxml``.
 95 | This should only be used only lxml cannot be installed, 
 96 | the standard library DOM parser will fail on broken HTML,
 97 | resulting in incomplete results.
 98 | 
 99 | It can be used by installing ``python-Wappalyzer`` with ``pip`` 
100 | option ``--no-deps``. Then install the required packages manually 
101 | (``pip install requests aiohttp cached_property dom_query pytest``).
102 | 
103 | What's new
104 | ----------
105 | 
106 | in development
107 | ^^^^^^^^^^^^^^
108 | * Add support for the "dom" key in technologies JSON.
109 | * Fix case sensitivity of the WebPage headers.
110 | * Provide a fallback WebPage class that works without ``lxml``. 
111 | 
112 | python-Wappalyzer 0.4.0 (unreleased)
113 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
114 | * Add ``python -m Wappalyzer`` entrypoint.
115 | * Support list of regular expressions in technologies JSON.
116 | * Add auto-update feature (unstable).
117 | 
118 | python-Wappalyzer 0.3.x
119 | ^^^^^^^^^^^^^^^^^^^^^^^
120 | * Python 3 support.
121 | * Async support.
122 | * Add confidence and version parsing.
123 | 
124 | Note:
125 |     Last version to support Python2 was `0.2.2`.  
126 | 


--------------------------------------------------------------------------------
/Wappalyzer/webpage/_common.py:
--------------------------------------------------------------------------------
  1 | """
  2 | Containers for a Web page and it's components.
  3 | Wraps only the information strictly necessary to run the Wappalyzer engine.
  4 | """
  5 | 
  6 | import abc
  7 | from typing import Iterable, List, Mapping, Any
  8 | try:
  9 |     from typing import Protocol
 10 | except ImportError:
 11 |     Protocol = object # type: ignore
 12 | 
 13 | import aiohttp
 14 | import requests
 15 | from requests.structures import CaseInsensitiveDict
 16 | 
 17 | def _raise_not_dict(obj:Any, name:str) -> None:
 18 |     try:
 19 |         list(obj.keys())
 20 |     except AttributeError: 
 21 |         raise ValueError(f"{name} must be a dictionary-like object")
 22 | 
 23 | class ITag(Protocol):
 24 |     """
 25 |     A HTML tag, decoupled from any particular HTTP library's API.
 26 |     """
 27 |     name: str
 28 |     attributes: Mapping[str, str]
 29 |     inner_html: str
 30 | 
 31 | class BaseTag(ITag, abc.ABC):
 32 |     """
 33 |     Subclasses must implement inner_html().
 34 |     """
 35 |     def __init__(self, name:str, attributes:Mapping[str, str]) -> None:
 36 |         _raise_not_dict(attributes, "attributes")
 37 |         self.name = name
 38 |         self.attributes = attributes
 39 |     @property
 40 |     def inner_html(self) -> str: # type: ignore
 41 |         """Returns the inner HTML of an element as a UTF-8 encoded bytestring"""
 42 |         raise NotImplementedError()
 43 | 
 44 | class IWebPage(Protocol):
 45 |     """
 46 |     Interfacte declaring the required methods/attributes of a WebPage object.
 47 | 
 48 |     Simple representation of a web page, decoupled from any particular HTTP library's API.
 49 |     """
 50 |     url: str
 51 |     html: str
 52 |     headers: Mapping[str, str]
 53 |     scripts: List[str]
 54 |     meta: Mapping[str, str]
 55 |     def select(self, selector:str) -> Iterable[ITag]: 
 56 |         raise NotImplementedError()
 57 | 
 58 | class BaseWebPage(IWebPage):
 59 |     """
 60 |     Implements factory methods for a WebPage.
 61 | 
 62 |     Subclasses must implement _parse_html() and select(string).
 63 |     """
 64 |     def __init__(self, url:str, html:str, headers:Mapping[str, str]):
 65 |         """
 66 |         Initialize a new WebPage object manually.  
 67 | 
 68 |         >>> from Wappalyzer import WebPage
 69 |         >>> w = WebPage('exemple.com',  html='<strong>Hello World</strong>', headers={'Server': 'Apache', })
 70 | 
 71 |         :param url: The web page URL.
 72 |         :param html: The web page content (HTML)
 73 |         :param headers: The HTTP response headers
 74 |         """
 75 |         _raise_not_dict(headers, "headers")
 76 |         self.url = url
 77 |         self.html = html
 78 |         self.headers = CaseInsensitiveDict(headers)
 79 |         self.scripts: List[str] = []
 80 |         self.meta: Mapping[str, str] = {}
 81 |         self._parse_html()
 82 | 
 83 |     def _parse_html(self):
 84 |         raise NotImplementedError()
 85 |     
 86 |     @classmethod
 87 |     def new_from_url(cls, url: str, **kwargs:Any) -> IWebPage:
 88 |         """
 89 |         Constructs a new WebPage object for the URL,
 90 |         using the `requests` module to fetch the HTML.
 91 | 
 92 |         >>> from Wappalyzer import WebPage
 93 |         >>> page = WebPage.new_from_url('exemple.com', timeout=5)
 94 | 
 95 |         :param url: URL 
 96 |         :param headers: (optional) Dictionary of HTTP Headers to send.
 97 |         :param cookies: (optional) Dict or CookieJar object to send.
 98 |         :param timeout: (optional) How many seconds to wait for the server to send data before giving up. 
 99 |         :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy.
100 |         :param verify: (optional) Boolean, it controls whether we verify the SSL certificate validity. 
101 |         :param \*\*kwargs: Any other arguments are passed to `requests.get` method as well. 
102 |         """
103 |         response = requests.get(url, **kwargs)
104 |         return cls.new_from_response(response)
105 | 
106 |     @classmethod
107 |     def new_from_response(cls, response:requests.Response) -> IWebPage:
108 |         """
109 |         Constructs a new WebPage object for the response,
110 |         using the `BeautifulSoup` module to parse the HTML.
111 | 
112 |         :param response: `requests.Response` object
113 |         """
114 |         return cls(response.url, html=response.text, headers=response.headers)
115 | 
116 | 
117 |     @classmethod
118 |     async def new_from_url_async(cls, url: str, verify: bool = True,
119 |                                  aiohttp_client_session: aiohttp.ClientSession = None, **kwargs:Any) -> IWebPage:
120 |         """
121 |         Same as new_from_url only Async.
122 | 
123 |         Constructs a new WebPage object for the URL,
124 |         using the `aiohttp` module to fetch the HTML.
125 | 
126 |         >>> from Wappalyzer import WebPage
127 |         >>> from aiohttp import ClientSession
128 |         >>> async with ClientSession() as session:
129 |         ...     page = await WebPage.new_from_url_async(aiohttp_client_session=session)
130 |         
131 |         :param url: URL
132 |         :param aiohttp_client_session: `aiohttp.ClientSession` instance to use, optional.
133 |         :param verify: (optional) Boolean, it controls whether we verify the SSL certificate validity. 
134 |         :param headers: Dict. HTTP Headers to send with the request (optional).
135 |         :param cookies: Dict. HTTP Cookies to send with the request (optional).
136 |         :param timeout: Int. override the session's timeout (optional)
137 |         :param proxy: Proxy URL, `str` or `yarl.URL` (optional).
138 |         :param \*\*kwargs: Any other arguments are passed to `aiohttp.ClientSession.get` method as well. 
139 | 
140 |         """
141 | 
142 |         if not aiohttp_client_session:
143 |             connector = aiohttp.TCPConnector(ssl=verify)
144 |             aiohttp_client_session = aiohttp.ClientSession(connector=connector)
145 | 
146 |         async with aiohttp_client_session.get(url, **kwargs) as response:
147 |             return await cls.new_from_response_async(response)
148 | 
149 |     @classmethod
150 |     async def new_from_response_async(cls, response:aiohttp.ClientResponse) -> IWebPage:
151 |         """
152 |         Constructs a new WebPage object for the response,
153 |         using the `BeautifulSoup` module to parse the HTML.
154 | 
155 |         >>> from aiohttp import ClientSession
156 |         >>> wappalyzer = Wappalyzer.latest()
157 |         >>> async with ClientSession() as session:
158 |         ...     page = await session.get("http://example.com")
159 |         ...
160 |         >>> webpage = await WebPage.new_from_response_async(page)
161 | 
162 |         :param response: `aiohttp.ClientResponse` object
163 |         """
164 |         html = await response.text()
165 |         return cls(str(response.url), html=html, headers=response.headers)


--------------------------------------------------------------------------------
/Wappalyzer/fingerprint.py:
--------------------------------------------------------------------------------
  1 | """
  2 | Classes to load and prepare technology fingerprints. 
  3 | 
  4 | This module is an implementation detail and is not considered public API.
  5 | """
  6 | import sre_compile
  7 | import re
  8 | import logging
  9 | from typing import Optional, Optional, Union, Mapping, Dict, List, Any
 10 | 
 11 | logger = logging.getLogger(name="python-Wappalyzer")
 12 | 
 13 | class Pattern:
 14 |     def __init__(self, string:str, 
 15 |                  regex: Optional['re.Pattern']=None, 
 16 |                  version: Optional[str]=None, 
 17 |                  confidence: Optional[str] = None) -> None:
 18 |         self.string: str = string
 19 |         self.regex: 're.Pattern' = regex or sre_compile.compile('', 0)
 20 |         self.version: Optional[str] = version
 21 |         self.confidence: int = int(confidence) if confidence else 100
 22 | 
 23 | class DomSelector:
 24 |     def __init__(self, 
 25 |                  selector: str, 
 26 |                  exists: Optional[bool] = None, 
 27 |                  text: Optional[List['Pattern']] = None, 
 28 |                  attributes: Optional[Mapping[str, List['Pattern']]] = None,) -> None:
 29 |         self.selector: str = selector
 30 |         self.exists: bool = bool(exists)
 31 |         self.text: Optional[List['Pattern']] = text
 32 |         self.attributes: Optional[Mapping[str, List['Pattern']]] = attributes
 33 |         # self.properties Not supported
 34 | 
 35 | class Category:
 36 |     def __init__(self, name:str, 
 37 |                  groups: Optional[List[int]] = None,
 38 |                  priority: Optional[int] = None) -> None:
 39 |         self.name:str = name
 40 |         self.groups: List[int] = groups or []
 41 |         self.priority: int = priority or 0
 42 | 
 43 | class Technology:
 44 |     """
 45 |     A detected technology (not implied).
 46 |     """
 47 |     def __init__(self, name:str) -> None:
 48 |         self.name = name
 49 |         self.confidence: Dict[str, int] = {}
 50 |         self.versions: List[str] = []
 51 |     
 52 |     @property
 53 |     def confidenceTotal(self) -> int: 
 54 |         total = 0
 55 |         for v in self.confidence.values():
 56 |             total += v
 57 |         return total
 58 | 
 59 | # Prepare patterns for fields (TODO): 
 60 | # - "scriptSrc": "regex string"
 61 | # - "js": dict string contains ins file to string (with version extraction).
 62 | # - "requires" / "excludes" rules/
 63 | # - "text" field.
 64 | 
 65 | # Inspired by projectdiscovery/wappalyzergo (MIT License)
 66 | class Fingerprint:
 67 |     """
 68 |     A Fingerprint represent a single piece of information about a tech. 
 69 |     Validated, normalized and regex expressions complied.
 70 | 
 71 |     See https://github.com/AliasIO/wappalyzer#json-fields
 72 |     """
 73 |     
 74 |     def __init__(self, name:str, **attrs: Any) -> None:
 75 |         # Required infos
 76 |         self.name: str = name
 77 | 
 78 |         # Metadata
 79 |         self.website: str = attrs.get('website', '??')
 80 |         self.cats: List[int] = attrs.get('cats', [])
 81 |         self.description: Optional[str] = attrs.get('description') # type:ignore
 82 |         self.icon: Optional[str] = attrs.get('icon') # type:ignore
 83 |         self.cpe: Optional[str] = attrs.get('cpe') # type:ignore
 84 |         self.saas: Optional[bool] = attrs.get('saas') # type:ignore
 85 |         self.oss: Optional[bool] = attrs.get('oss') # type:ignore
 86 |         self.pricing: List[str] = self._prepare_list(attrs['princing']) if 'princing' in attrs else []
 87 | 
 88 |         # Implies and cie
 89 |         self.implies: List[str] = self._prepare_list(attrs['implies']) if 'implies' in attrs else []
 90 |         # self.requires: List[str] = self._prepare_list(attrs['requires']) if 'requires' in attrs else [] # Not supported
 91 |         # self.requiresCategory: List[str] = self._prepare_list(attrs['requiresCategory']) if 'requiresCategory' in attrs else [] # Not supported
 92 |         # self.excludes: List[str] = self._prepare_list(attrs['excludes']) if 'excludes' in attrs else [] # Not supported
 93 | 
 94 |         # Patterns
 95 |         self.dom: List[DomSelector] = self._prepare_dom(attrs['dom']) if 'dom' in attrs else []
 96 |         
 97 |         self.headers: Mapping[str, List[Pattern]] = self._prepare_headers(attrs['headers']) if 'headers' in attrs else {}
 98 |         self.meta: Mapping[str, List[Pattern]] = self._prepare_meta(attrs['meta']) if 'meta' in attrs else {}
 99 | 
100 |         self.html: List[Pattern] = self._prepare_pattern(attrs['html']) if 'html' in attrs else []
101 |         self.text: List[Pattern] = self._prepare_pattern(attrs['text']) if 'text' in attrs else []
102 |         self.url: List[Pattern] = self._prepare_pattern(attrs['url']) if 'url' in attrs else []
103 |         self.scriptSrc: List[Pattern] = self._prepare_pattern(attrs['scriptSrc']) if 'scriptSrc' in attrs else []
104 |         self.scripts: List[Pattern] = self._prepare_pattern(attrs['scripts']) if 'scripts' in attrs else []
105 | 
106 |         # self.cookies: Mapping[str, List[Pattern]] Not supported
107 |         # self.dns: Mapping[str, List[Pattern]] Not supported
108 |         # self.js: Mapping[str, List[Pattern]] Not supported
109 |         # self.css: List[Pattern] Not supported (yet)
110 |         # self.robots: List[Pattern] Not supported (yet)
111 |         # self.xhr: List[Pattern] Not supported
112 |     
113 |     @classmethod
114 |     def _prepare_list(cls, thing: Any) -> List[Any]:
115 |         if not isinstance(thing, list):
116 |             return [thing]
117 |         else:
118 |             return thing
119 | 
120 |     @classmethod
121 |     def _prepare_pattern(cls, pattern: Union[str, List[str]]) -> List[Pattern]:
122 |         """
123 |         Prepare regular expression patterns.
124 |         Strip out key:value pairs from the pattern and compile the regular
125 |         expression.
126 |         """
127 |         pattern_objects = []
128 |         if isinstance(pattern, list):
129 |             for p in pattern:
130 |                 pattern_objects.extend(cls._prepare_pattern(p))
131 |         else:
132 |             attrs = {}
133 |             patterns = pattern.split('\\;')
134 |             for index, expression in enumerate(patterns):
135 |                 if index == 0:
136 |                     attrs['string'] = expression
137 |                     try:
138 |                         attrs['regex'] = re.compile(expression, re.I) # type: ignore
139 |                     except re.error as err:
140 |                         # Wappalyzer is a JavaScript application therefore some of the regex wont compile in Python.
141 |                         logger.debug(
142 |                             "Caught '{error}' compiling regex: {regex}".format(
143 |                                 error=err, regex=patterns)
144 |                         )
145 |                         # regex that never matches:
146 |                         # http://stackoverflow.com/a/1845097/413622
147 |                         attrs['regex'] = re.compile(r'(?!x)x') # type: ignore
148 |                 else:
149 |                     attr = expression.split(':')
150 |                     if len(attr) > 1:
151 |                         key = attr.pop(0)
152 |                         # This adds pattern['version'] when specified with "\\;version:\\1"
153 |                         attrs[str(key)] = ':'.join(attr)
154 |             pattern_objects.append(Pattern(**attrs)) # type: ignore
155 | 
156 |         return pattern_objects
157 |     
158 |     @classmethod
159 |     def _prepare_pattern_dict(cls, thing: Dict[str, Union[str, List[str]]]) -> Mapping[str, List[Pattern]]:
160 |         for k in thing:
161 |             thing[k] = cls._prepare_pattern(thing[k]) # type: ignore
162 |         return thing # type: ignore
163 |     
164 |     @classmethod
165 |     def _prepare_meta(cls,  thing: Union[str, List[str], Dict[str, Union[str, List[str]]]]) -> Mapping[str, List[Pattern]]:
166 |         # Ensure dict
167 |         if not isinstance(thing, dict):
168 |             thing = {'generator': thing}
169 |         # Enure lowercase keys
170 |         return cls._prepare_pattern_dict({k.lower():v for k,v in thing.items()})
171 | 
172 |     @classmethod
173 |     def _prepare_headers(cls,  thing: Dict[str, Union[str, List[str]]]) -> Mapping[str, List[Pattern]]:
174 |         # Enure lowercase keys
175 |         return cls._prepare_pattern_dict({k.lower():v for k,v in thing.items()})
176 |     
177 |     @classmethod
178 |     def _prepare_dom(cls, thing: Union[str, List[str], 
179 |                                     Dict[str, Dict[str, 
180 |                                         Union[str, List[str]]]]]) -> List[DomSelector]:
181 |         selectors = []
182 |         if isinstance(thing, str):
183 |             selectors.append(DomSelector(thing, exists=True))
184 |         elif isinstance(thing, list):
185 |             for _o in thing: 
186 |                 selectors.append(DomSelector(_o, exists=True))
187 |         elif isinstance(thing, dict):
188 |             for cssselect, clause in thing.items():
189 |                 # prepare regexes
190 |                 _prep_text_patterns = None
191 |                 _prep_attr_patterns = None
192 |                 _exists = None
193 |                 if clause.get('exists') is not None:
194 |                     _exists = True
195 |                 if clause.get('text'):
196 |                     _prep_text_patterns = cls._prepare_pattern(clause['text'])
197 |                 if clause.get('attributes'):
198 |                     _prep_attr_patterns ={}
199 |                     for _key, pattern in clause['attributes'].items(): #type: ignore
200 |                         _prep_attr_patterns[_key] = cls._prepare_pattern(pattern)
201 |                 selectors.append(DomSelector(cssselect, exists=_exists, text=_prep_text_patterns, attributes=_prep_attr_patterns))
202 |         return selectors


--------------------------------------------------------------------------------
/tests/test_wappalyzer.py:
--------------------------------------------------------------------------------
  1 | import pytest
  2 | import requests
  3 | import json
  4 | import os
  5 | 
  6 | from pathlib import Path
  7 | from contextlib import redirect_stdout
  8 | from io import StringIO
  9 | 
 10 | from httpretty import HTTPretty, httprettified
 11 | from aioresponses import aioresponses
 12 | 
 13 | from Wappalyzer.fingerprint import Fingerprint
 14 | from Wappalyzer import WebPage, Wappalyzer
 15 | from Wappalyzer.__main__ import get_parser, main
 16 | 
 17 | @pytest.fixture
 18 | def async_mock():
 19 |     with aioresponses() as m:
 20 |         yield m
 21 | 
 22 | @httprettified
 23 | def test_new_from_url():
 24 |     HTTPretty.register_uri(HTTPretty.GET, 'http://example.com/',
 25 |                             body='snerble')
 26 | 
 27 |     webpage = WebPage.new_from_url('http://example.com/')
 28 | 
 29 |     assert webpage.html == 'snerble'
 30 | 
 31 | @pytest.mark.asyncio
 32 | async def test_new_from_url_async(async_mock):
 33 |     async_mock.get('http://example.com', status=200, body='snerble')
 34 | 
 35 |     webpage = await WebPage.new_from_url_async('http://example.com/')
 36 | 
 37 |     assert webpage.html == 'snerble'
 38 | 
 39 | def test_latest():
 40 |     analyzer = Wappalyzer.latest()
 41 | 
 42 |     print((analyzer.categories))
 43 |     assert analyzer.categories['1'].name == 'CMS'
 44 |     assert 'Apache' in analyzer.technologies
 45 | 
 46 | # Until https://github.com/chorsley/python-Wappalyzer/pull/66 is merged
 47 | @pytest.mark.xfail
 48 | def test_latest_update(tmp_path: Path):
 49 |     
 50 |     # Get the lastest file
 51 |     lastest_technologies_file=requests.get('https://raw.githubusercontent.com/AliasIO/wappalyzer/master/src/technologies.json')
 52 |     
 53 |     tmp_file = tmp_path.joinpath('technologies.json')
 54 |     # Write the content to a tmp file
 55 |     with tmp_file.open('w', encoding='utf-8') as t_file:
 56 |         t_file.write(lastest_technologies_file.text)
 57 | 
 58 |     # Create Wappalyzer with this file in argument
 59 |     wappalyzer1=Wappalyzer.latest(technologies_file=str(tmp_file))
 60 | 
 61 |     wappalyzer2=Wappalyzer.latest(update=True)
 62 | 
 63 |     assert wappalyzer1.technologies==wappalyzer2.technologies
 64 |     assert wappalyzer1.categories==wappalyzer2.categories
 65 | 
 66 | def test_analyze_no_technologies():
 67 |     analyzer = Wappalyzer(categories={}, technologies={})
 68 |     webpage = WebPage('http://example.com', '<html></html>', {})
 69 | 
 70 |     detected_technologies = analyzer.analyze(webpage)
 71 | 
 72 |     assert detected_technologies == set()
 73 | 
 74 | def test_get_implied_technologies():
 75 |     analyzer = Wappalyzer(categories={}, technologies={
 76 |         'a': {
 77 |             'implies': 'b',
 78 |         },
 79 |         'b': {
 80 |             'implies': 'c',
 81 |         },
 82 |         'c': {
 83 |             'implies': 'a',
 84 |         },
 85 |     })
 86 | 
 87 |     implied_technologies = analyzer._get_implied_technologies('a')
 88 | 
 89 |     assert implied_technologies == set(['a', 'b', 'c'])
 90 | 
 91 | def test_get_analyze_with_categories():
 92 |     webpage = WebPage('http://example.com', '<html>aaa</html>', {})
 93 |     categories = {
 94 |         "1": {
 95 |             "name": "cat1",
 96 |             "priority": 1
 97 |         },
 98 |         "2": {
 99 |             "name": "cat2",
100 |             "priority": 1
101 |         }
102 |     }
103 | 
104 |     technologies = {
105 |         'a': {
106 |             'html': 'aaa',
107 |             'cats': [1],
108 |         },
109 |         'b': {
110 |             'html': 'bbb',
111 |             'cats': [1, 2],
112 |         }
113 |     }
114 | 
115 |     analyzer = Wappalyzer(categories=categories, technologies=technologies)
116 |     result = analyzer.analyze_with_categories(webpage)
117 | 
118 |     assert result == {"a": {"categories": ["cat1"]}}
119 | 
120 | def test_get_analyze_with_versions():
121 | 
122 |     webpage = WebPage('http://wordpress-example.com', '<html><head><meta name="generator" content="WordPress 5.4.2"></head></html>', {})
123 |     
124 |     categories = {
125 |         "1": {
126 |             "name": "CMS",
127 |             "priority": 1
128 |         },
129 |         "11": {
130 |             "name": "Blog",
131 |             "priority": 1
132 |         }
133 |     }
134 | 
135 |     technologies = {
136 |         "WordPress": {
137 |             "cats": [
138 |                 1,
139 |                 11
140 |             ],
141 |             "html": [],
142 |             "icon": "WordPress.svg",
143 |             "implies": [
144 |                 "PHP",
145 |                 "MySQL"
146 |             ],
147 |             "meta": {
148 |                 "generator": "^WordPress ?([\\d.]+)?\\;version:\\1"
149 |             },
150 |             "website": "https://wordpress.org"
151 |             },
152 |         'b': {
153 |             'html': 'bbb',
154 |             'cats': [1, 2],
155 |         },
156 |         "PHP": {
157 |             "website": "http://php.net"
158 |         },
159 |         "MySQL": {
160 |             "website": "http://mysql.com"
161 |         },
162 |     }
163 | 
164 |     analyzer = Wappalyzer(categories=categories, technologies=technologies)
165 |     result = analyzer.analyze_with_versions(webpage)
166 | 
167 |     assert ("WordPress", {"versions": ["5.4.2"]}) in result.items()
168 | 
169 | def test_analyze_with_versions_and_categories():
170 |     
171 |     webpage = WebPage('http://wordpress-example.com', '<html><head><meta name="generator" content="WordPress 5.4.2"></head></html>', {})
172 |     
173 |     categories = {
174 |         "1": {
175 |             "name": "CMS",
176 |             "priority": 1
177 |         },
178 |         "11": {
179 |             "name": "Blog",
180 |             "priority": 1
181 |         }
182 |     }
183 | 
184 |     technologies = {
185 |         "WordPress": {
186 |             "cats": [
187 |                 1,
188 |                 11
189 |             ],
190 |             "html": [],
191 |             "icon": "WordPress.svg",
192 |             "implies": [
193 |                 "PHP",
194 |                 "MySQL"
195 |             ],
196 |             "meta": {
197 |                 "generator": "^WordPress ?([\\d.]+)?\\;version:\\1"
198 |             },
199 |             "website": "https://wordpress.org"
200 |             },
201 |         'b': {
202 |             'html': 'bbb',
203 |             'cats': [1, 2],
204 |         },
205 |         "PHP": {
206 |             "website": "http://php.net"
207 |         },
208 |         "MySQL": {
209 |             "website": "http://mysql.com"
210 |         },
211 |     }
212 | 
213 |     analyzer = Wappalyzer(categories=categories, technologies=technologies)
214 |     result = analyzer.analyze_with_versions_and_categories(webpage)
215 |     assert analyzer.get_versions(webpage.url, 'WordPress') == ["5.4.2"], analyzer._detected_technologies[webpage.url]
216 |     assert ("WordPress", {"categories": ["CMS", "Blog"], "versions": ["5.4.2"]}) in result.items()
217 | 
218 | def test_analyze_with_versions_and_categories_pattern_lists():
219 |     
220 |     webpage = WebPage('http://wordpress-example.com', '<html><head><meta name="generator" content="WordPress 5.4.2"></head></html>', {})
221 |     
222 |     categories = {
223 |         "1": {
224 |             "name": "CMS",
225 |             "priority": 1
226 |         },
227 |         "11": {
228 |             "name": "Blog",
229 |             "priority": 1
230 |         }
231 |     }
232 | 
233 |     technologies = {
234 |         "WordPress": {
235 |             "cats": [
236 |                 1,
237 |                 11
238 |             ],
239 |             "html": [],
240 |             "icon": "WordPress.svg",
241 |             "implies": [
242 |                 "PHP",
243 |                 "MySQL"
244 |             ],
245 |             "meta": {
246 |                 "generator": ["Whatever123", "Whatever456", "^WordPress ?([\\d.]+)?\\;version:\\1", "Whatever"]
247 |             },
248 |             "website": "https://wordpress.org"
249 |             },
250 |         'b': {
251 |             'html': 'bbb',
252 |             'cats': [1, 2],
253 |         },
254 |         "PHP": {
255 |             "website": "http://php.net"
256 |         },
257 |         "MySQL": {
258 |             "website": "http://mysql.com"
259 |         },
260 |     }
261 | 
262 |     analyzer = Wappalyzer(categories=categories, technologies=technologies)
263 |     result = analyzer.analyze_with_versions_and_categories(webpage)
264 | 
265 |     assert ("WordPress", {"categories": ["CMS", "Blog"], "versions": ["5.4.2"]}) in result.items()
266 | 
267 | def test_analyze_dom_string():
268 | 
269 |     webpageA = WebPage('http://example.com', '<html><p class="aaa">webpage a</p></html>', {})
270 |     webpageB = WebPage('http://example.com', '<html><p id="bbb">webpage b</p></html>', {})
271 |     categories = {}
272 |     technologies = {
273 |         'a': { 'dom': '.aaa', },
274 |         'b': {'dom': '#bbb', }
275 |     }
276 |     analyzer = Wappalyzer(categories=categories, technologies=technologies)
277 | 
278 |     assert analyzer.analyze(webpageA) == {"a"}
279 |     assert analyzer.analyze(webpageB) == {"b"}
280 | 
281 | def test_analyze_dom_list():
282 |     webpageA = WebPage('http://example.com', '<html><p class="aaa">webpage a</p></html>', {})
283 |     webpageB = WebPage('http://example.com', '<html><p id="bbb">webpage b</p></html>', {})
284 |     categories = {}
285 |     technologies = {
286 |         'a': { 'dom': ['.aaa', '[some-other-css-selector]'], },
287 |         'b': { 'dom': ['[some-other-css-selector]', '#bbb'], }
288 |     }
289 |     analyzer = Wappalyzer(categories=categories, technologies=technologies)
290 |     assert analyzer.analyze(webpageA) == {"a"}
291 |     assert analyzer.analyze(webpageB) == {"b"}
292 | 
293 | def test_analyze_dom_dict_text():
294 |     webpageA = WebPage('http://example.com', '<html><p class="aaa">webpage a</p></html>', {})
295 |     webpageB = WebPage('http://example.com', '<html><p id="bbb">webpage b</p></html>', {})
296 |     categories = {}
297 |     get_dom_val = lambda cat: {
298 |                 '#bbb': { 'text': f"webpage\\ {cat}", },
299 |                 '.aaa': { 'text': f"webpage\\ {cat}", }
300 |             }
301 |     technologies = {
302 |         'a': { 'dom': get_dom_val('a') },
303 |         'b': { 'dom': get_dom_val('b'), }
304 |     }
305 |     analyzer = Wappalyzer(categories=categories, technologies=technologies)
306 | 
307 |     assert analyzer.analyze(webpageA) == {"a"}
308 |     assert analyzer.analyze(webpageB) == {"b"}
309 | 
310 | def test_analyze_dom_dict_exists():
311 |     webpageA = WebPage('http://example.com', '<html><p class="aaa">webpage a</p></html>', {})
312 |     webpageB = WebPage('http://example.com', '<html><p id="bbb">webpage b</p></html>', {})
313 |     categories = {}
314 |     get_dom_val = lambda cat: {
315 |                 f'#{cat*3}': { 'exists': "", },
316 |                 f'.{cat*3}': { 'exists': "", }
317 |             }
318 |     technologies = {
319 |         'a': { 'dom': get_dom_val('a') },
320 |         'b': { 'dom': get_dom_val('b'), }
321 |     }
322 |     analyzer = Wappalyzer(categories=categories, technologies=technologies)
323 | 
324 |     assert analyzer.analyze(webpageA) == {"a"}
325 |     assert analyzer.analyze(webpageB) == {"b"}
326 | 
327 | def test_analyze_dom_dict_attributes():
328 |     webpageA = WebPage('http://example.com', '<html><p class="aaa" onclick="webpageAScript()">webpage a</p></html>', {})
329 |     webpageB = WebPage('http://example.com', '<html><p id="bbb" onclick="webpageBScript()">webpage b</p></html>', {})
330 |     categories = {}
331 |     get_dom_val = lambda cat: {
332 |                 f'#{cat*3}': { 'attributes': {'onclick': f'webpage{cat.upper()}Script.*'}, },
333 |                 f'.{cat*3}': { 'attributes': {'onclick': f'webpage{cat.upper()}Script.*'}, }
334 |             }
335 |     technologies = {
336 |         'a': { 'dom': get_dom_val('a') },
337 |         'b': { 'dom': get_dom_val('b'), }
338 |     }
339 |     analyzer = Wappalyzer(categories=categories, technologies=technologies)
340 |     assert analyzer.analyze(webpageA) == {"a"}
341 |     assert analyzer.analyze(webpageB) == {"b"}
342 | 
343 | def test_analyze_scriptSrc():
344 |     ...
345 |     #TODO
346 | 
347 | def test_analyze_text():
348 |     ...
349 |     #TODO
350 | 
351 | def test_fingerprint():
352 |     tech_fingerprint = Fingerprint(name='WordPress', **{
353 |             "cats": [
354 |                 1,
355 |                 11
356 |             ],
357 |             "html": [],
358 |             "icon": "WordPress.svg",
359 |             "implies": [
360 |                 "PHP",
361 |                 "MySQL"
362 |             ],
363 |             "meta": {
364 |                 "generator": ["Whatever123", "Whatever456", "^WordPress ?([\\d.]+)?\\;version:\\1", "Whatever"]
365 |             },
366 |             "website": "https://wordpress.org"
367 |             })
368 |     assert tech_fingerprint.meta['generator'][-2].version == '\\1'
369 |     assert tech_fingerprint.meta['generator'][-2].regex.pattern == '^WordPress ?([\d.]+)?'
370 | 
371 | def cli(*args):
372 |     """Wrap python-Wappalyzer CLI exec"""
373 | 
374 |     with StringIO() as stream:
375 |         with redirect_stdout(stream):
376 |             main(get_parser().parse_args(args))
377 |         result = json.loads(stream.getvalue())
378 |     return result
379 | 
380 | @pytest.mark.skipif(os.getenv('GITHUB_ACTIONS') is not None, reason="This test fails on the github CI, python3.9 for some reason.")
381 | def test_cli():
382 |     r = cli('http://exemple.com', '--update', '--user-agent', 'Mozilla/5.0', '--timeout', '30')
383 |     assert len(r) > 2
384 |     assert "Bootstrap" in r
385 | 
386 | 
387 | 


--------------------------------------------------------------------------------
/Wappalyzer/Wappalyzer.py:
--------------------------------------------------------------------------------
  1 | 
  2 | from typing import Callable, Dict, Iterable, List, Any, Mapping, Set
  3 | import json
  4 | import logging
  5 | import pkg_resources
  6 | import re
  7 | import os
  8 | import pathlib
  9 | import requests
 10 | 
 11 | from datetime import datetime, timedelta
 12 | from typing import Optional
 13 | 
 14 | from Wappalyzer.fingerprint import Fingerprint, Pattern, Technology, Category
 15 | from Wappalyzer.webpage import WebPage, IWebPage
 16 | 
 17 | logger = logging.getLogger(name="python-Wappalyzer")
 18 | 
 19 | class WappalyzerError(Exception):
 20 |     # unused for now
 21 |     """
 22 |     Raised for fatal Wappalyzer errors.
 23 |     """
 24 |     pass
 25 | 
 26 | class Wappalyzer:
 27 |     """
 28 |     Python Wappalyzer driver.
 29 | 
 30 |     Consider the following exemples.
 31 |     
 32 |     Here is how you can use the latest technologies file from AliasIO/wappalyzer repository. 
 33 |     
 34 |     .. python::
 35 | 
 36 |         from Wappalyzer import Wappalyzer
 37 |         wappalyzer=Wappalyzer.latest(update=True)
 38 |         # Create webpage
 39 |         webpage=WebPage.new_from_url('http://example.com')
 40 |         # analyze
 41 |         results = wappalyzer.analyze_with_categories(webpage)
 42 | 
 43 | 
 44 |     Here is how you can custom request and headers arguments:
 45 |     
 46 |     .. python::
 47 | 
 48 |         import requests
 49 |         from Wappalyzer import Wappalyzer, WebPage
 50 |         wappalyzer = Wappalyzer.latest()
 51 |         webpage = WebPage.new_from_url('http://exemple.com', headers={'User-Agent': 'Custom user agent'})
 52 |         wappalyzer.analyze_with_categories(webpage)
 53 | 
 54 |     """
 55 | 
 56 |     def __init__(self, categories:Dict[str, Any], technologies:Dict[str, Any]):
 57 |         """
 58 |         Manually initialize a new Wappalyzer instance. 
 59 |         
 60 |         You might want to use the factory method: `latest`
 61 | 
 62 |         :param categories: Map of category ids to names, as in ``technologies.json``.
 63 |         :param technologies: Map of technology names to technology dicts, as in ``technologies.json``.
 64 |         """
 65 |         self.categories: Mapping[str, Category] = {k:Category(**v) for k,v in categories.items()}
 66 |         self.technologies: Mapping[str, Fingerprint] = {k:Fingerprint(name=k, **v) for k,v in technologies.items()}
 67 |         self.detected_technologies: Dict[str, Dict[str, Technology]] = {}
 68 | 
 69 |         self._confidence_regexp = re.compile(r"(.+)\\;confidence:(\d+)")
 70 | 
 71 |     @classmethod
 72 |     def latest(cls, technologies_file:str=None, update:bool=False) -> 'Wappalyzer':
 73 |         """
 74 |         Construct a Wappalyzer instance.
 75 |         
 76 |         Use ``update=True`` to download the very latest file from internet. 
 77 |         Do not update if the file has already been updated in the last 24 hours. 
 78 |         *New in version 0.4.0*
 79 | 
 80 |         Use ``technologies_file=/some/path/technologies.json`` to load a 
 81 |         custom technologies file. 
 82 |         
 83 |         If no arguments is passed, load the default ``data/technologies.json`` file
 84 |         inside the package ressource.
 85 | 
 86 |         :param technologies_file: File path
 87 |         :param update: Download and use the latest ``technologies.json`` file 
 88 |             from `AliasIO/wappalyzer <https://github.com/AliasIO/wappalyzer>`_ repository.  
 89 |         
 90 |         """
 91 |         default=pkg_resources.resource_string(__name__, "data/technologies.json")
 92 |         defaultobj = json.loads(default)
 93 | 
 94 |         if technologies_file:
 95 |             with open(technologies_file, 'r', encoding='utf-8') as fd:
 96 |                 obj = json.load(fd)
 97 |         elif update:
 98 |             should_update = True
 99 |             _technologies_file: pathlib.Path
100 |             _files = cls._find_files(['HOME', 'APPDATA',], ['.python-Wappalyzer/technologies.json'])
101 |             if _files:
102 |                 _technologies_file = pathlib.Path(_files[0])
103 |                 last_modification_time = datetime.fromtimestamp(_technologies_file.stat().st_mtime)
104 |                 if datetime.now() - last_modification_time < timedelta(hours=24):
105 |                     should_update = False
106 | 
107 |             # Get the lastest file
108 |             if should_update:
109 |                 try:
110 |                     lastest_technologies_file=requests.get('https://raw.githubusercontent.com/AliasIO/wappalyzer/master/src/technologies.json')
111 |                     obj = lastest_technologies_file.json()
112 |                     _technologies_file = pathlib.Path(cls._find_files(
113 |                         ['HOME', 'APPDATA',],
114 |                         ['.python-Wappalyzer/technologies.json'],
115 |                         create = True
116 |                         ).pop())
117 |                     
118 |                     if obj != defaultobj:
119 |                         with _technologies_file.open('w', encoding='utf-8') as tfile:
120 |                             tfile.write(lastest_technologies_file.text)
121 |                         logger.info("python-Wappalyzer technologies.json file updated")
122 | 
123 |                 except Exception as err: # Or loads default
124 |                     logger.error("Could not download latest Wappalyzer technologies.json file because of error : '{}'. Using default. ".format(err))
125 |                     obj = defaultobj
126 |             else:
127 |                 logger.debug("python-Wappalyzer technologies.json file not updated because already updated in the last 24h")
128 |                 with _technologies_file.open('r', encoding='utf-8') as tfile:
129 |                     obj = json.load(tfile)
130 | 
131 |             logger.info("Using technologies.json file at {}".format(_technologies_file.as_posix()))
132 |         else:
133 |             obj = defaultobj
134 | 
135 |         
136 |         return cls(categories=obj['categories'], technologies=obj['technologies'])
137 | 
138 |     @staticmethod
139 |     def _find_files(
140 |         env_location: List[str],
141 |         potential_files: List[str],
142 |         default_content: str = "",
143 |         create: bool = False,
144 |     ) -> List[str]:
145 |         """Find existent files based on folders name and file names.
146 |         Arguments:
147 |         - `env_location`: list of environment variable to use as a base path. Exemple: ['HOME', 'XDG_CONFIG_HOME', 'APPDATA', 'PWD']
148 |         - `potential_files`: list of filenames. Exemple: ['.myapp/conf.ini',]
149 |         - `default_content`: Write default content if the file does not exist
150 |         - `create`: Create the file in the first existing env_location with default content if the file does not exist
151 |         """
152 |         potential_paths = []
153 |         existent_files = []
154 | 
155 |         env_loc_exists = False
156 |         # build potential_paths of config file
157 |         for env_var in env_location:
158 |             if env_var in os.environ:
159 |                 env_loc_exists = True
160 |                 for file_path in potential_files:
161 |                     potential_paths.append(os.path.join(os.environ[env_var], file_path))
162 |         if not env_loc_exists and create:
163 |             raise RuntimeError(f"Cannot find any of the env locations {env_location}. ")
164 |         # If file exist, add to list
165 |         for p in potential_paths:
166 |             if os.path.isfile(p):
167 |                 existent_files.append(p)
168 |         # If no file foud and create=True, init new file
169 |         if len(existent_files) == 0 and create:
170 |             os.makedirs(os.path.dirname(potential_paths[0]), exist_ok=True)
171 |             with open(potential_paths[0], "w", encoding='utf-8') as config_file:
172 |                 config_file.write(default_content)
173 |             existent_files.append(potential_paths[0])
174 |         return existent_files
175 | 
176 |     def _has_technology(self, tech_fingerprint: Fingerprint, webpage: IWebPage) -> bool:
177 |         """
178 |         Determine whether the web page matches the technology signature.
179 |         """
180 | 
181 |         has_tech = False
182 |         # Search the easiest things first and save the full-text search of the
183 |         # HTML for last
184 | 
185 |         # analyze url patterns
186 |         for pattern in tech_fingerprint.url:
187 |             if pattern.regex.search(webpage.url):
188 |                 self._set_detected_app(webpage.url, tech_fingerprint, 'url', pattern, value=webpage.url)
189 |         # analyze headers patterns
190 |         for name, patterns in list(tech_fingerprint.headers.items()):
191 |             if name in webpage.headers:
192 |                 content = webpage.headers[name]
193 |                 for pattern in patterns:
194 |                     if pattern.regex.search(content):
195 |                         self._set_detected_app(webpage.url, tech_fingerprint, 'headers', pattern, value=content, key=name)
196 |                         has_tech = True
197 |         # analyze scripts patterns
198 |         for pattern in tech_fingerprint.scripts:
199 |             for script in webpage.scripts:
200 |                 if pattern.regex.search(script):
201 |                     self._set_detected_app(webpage.url, tech_fingerprint, 'scripts', pattern, value=script)
202 |                     has_tech = True
203 |         # analyze meta patterns
204 |         for name, patterns in list(tech_fingerprint.meta.items()):
205 |             if name in webpage.meta:
206 |                 content = webpage.meta[name]
207 |                 for pattern in patterns:
208 |                     if pattern.regex.search(content):
209 |                         self._set_detected_app(webpage.url, tech_fingerprint, 'meta', pattern, value=content, key=name)
210 |                         has_tech = True
211 |         # analyze html patterns
212 |         for pattern in tech_fingerprint.html:
213 |             if pattern.regex.search(webpage.html):
214 |                 self._set_detected_app(webpage.url, tech_fingerprint, 'html', pattern, value=webpage.html)
215 |                 has_tech = True
216 |         # analyze dom patterns
217 |         # css selector, list of css selectors, or dict from css selector to dict with some of keys:
218 |         #           - "exists": "": only check if the selector matches somthing, equivalent to the list form. 
219 |         #           - "text": "regex": check if the .innerText property of the element that matches the css selector matches the regex (with version extraction).
220 |         #           - "attributes": {dict from attr name to regex}: check if the attribute value of the element that matches the css selector matches the regex (with version extraction).
221 |         for selector in tech_fingerprint.dom:
222 |             for item in webpage.select(selector.selector):
223 |                 if selector.exists:
224 |                     self._set_detected_app(webpage.url, tech_fingerprint, 'dom', Pattern(string=selector.selector), value='')
225 |                     has_tech = True
226 |                 if selector.text:
227 |                     for pattern in selector.text:
228 |                         if pattern.regex.search(item.inner_html):
229 |                             self._set_detected_app(webpage.url, tech_fingerprint, 'dom', pattern, value=item.inner_html)
230 |                             has_tech = True
231 |                 if selector.attributes:
232 |                     for attrname, patterns in list(selector.attributes.items()):
233 |                         _content = item.attributes.get(attrname)
234 |                         if _content:
235 |                             for pattern in patterns:
236 |                                 if pattern.regex.search(_content):
237 |                                     self._set_detected_app(webpage.url, tech_fingerprint, 'dom', pattern, value=_content)
238 |                                     has_tech = True
239 |         return has_tech
240 | 
241 |     def _set_detected_app(self, url:str,
242 |                                 tech_fingerprint: Fingerprint, 
243 |                                 app_type:str, 
244 |                                 pattern: Pattern, 
245 |                                 value:str, 
246 |                                 key='') -> None:
247 |         """
248 |         Store detected technology to the detected_technologies dict.
249 |         """
250 |         # Lookup Technology object in the cache
251 |         if url not in self.detected_technologies:
252 |             self.detected_technologies[url] = {}
253 |         if tech_fingerprint.name not in self.detected_technologies[url]:
254 |             self.detected_technologies[url][tech_fingerprint.name] = Technology(tech_fingerprint.name)
255 |         detected_tech = self.detected_technologies[url][tech_fingerprint.name]
256 | 
257 |         # Set confidence level
258 |         if key != '': key += ' '
259 |         match_name = app_type + ' ' + key + pattern.string
260 |         
261 |         detected_tech.confidence[match_name] = pattern.confidence
262 | 
263 |         # Dectect version number
264 |         if pattern.version:
265 |             allmatches = re.findall(pattern.regex, value)
266 |             for i, matches in enumerate(allmatches):
267 |                 version = pattern.version
268 |                 # Check for a string to avoid enumerating the string
269 |                 if isinstance(matches, str):
270 |                     matches = [(matches)]
271 |                 for index, match in enumerate(matches):
272 |                     # Parse ternary operator
273 |                     ternary = re.search(re.compile('\\\\' + str(index + 1) + '\\?([^:]+):(.*)$', re.I), version)
274 |                     if ternary and len(ternary.groups()) == 2 and ternary.group(1) is not None and ternary.group(2) is not None:
275 |                         version = version.replace(ternary.group(0), ternary.group(1) if match != ''
276 |                                                   else ternary.group(2))
277 |                     # Replace back references
278 |                     version = version.replace('\\' + str(index + 1), match)
279 |                 if version != '' and version not in detected_tech.versions:
280 |                     detected_tech.versions.append(version)
281 |             self._sort_app_version(detected_tech)
282 | 
283 |     def _sort_app_version(self, detected_tech: Technology) -> None:
284 |         """
285 |         Sort version number (find the longest version number that *is supposed to* contains all shorter detected version numbers).
286 |         """
287 |         if len(detected_tech.versions) >= 1:
288 |             return
289 |         detected_tech.versions = sorted(detected_tech.versions, key=self._cmp_to_key(self._sort_app_versions))
290 | 
291 |     def _get_implied_technologies(self, detected_technologies:Iterable[str]) -> Iterable[str]:
292 |         """
293 |         Get the set of technologies implied by `detected_technologies`.
294 |         """
295 |         def __get_implied_technologies(technologies:Iterable[str]) -> Iterable[str] :
296 |             _implied_technologies = set()
297 |             for tech in technologies:
298 |                 try:
299 |                     for implie in self.technologies[tech].implies:
300 |                         # If we have no doubts just add technology
301 |                         if 'confidence' not in implie:
302 |                             _implied_technologies.add(implie)
303 | 
304 |                         # Case when we have "confidence" (some doubts)
305 |                         else:
306 |                             try:
307 |                                 # Use more strict regexp (cause we have already checked the entry of "confidence")
308 |                                 # Also, better way to compile regexp one time, instead of every time
309 |                                 app_name, confidence = self._confidence_regexp.search(implie).groups() # type: ignore
310 |                                 if int(confidence) >= 50:
311 |                                     _implied_technologies.add(app_name)
312 |                             except (ValueError, AttributeError):
313 |                                 pass
314 |                 except KeyError:
315 |                     pass
316 |             return _implied_technologies
317 | 
318 |         implied_technologies = __get_implied_technologies(detected_technologies)
319 |         all_implied_technologies : Set[str] = set()
320 | 
321 |         # Descend recursively until we've found all implied technologies
322 |         while not all_implied_technologies.issuperset(implied_technologies):
323 |             all_implied_technologies.update(implied_technologies)
324 |             implied_technologies = __get_implied_technologies(all_implied_technologies)
325 | 
326 |         return all_implied_technologies
327 | 
328 |     def get_categories(self, tech_name:str) -> List[str]:
329 |         """
330 |         Returns a list of the categories for an technology name.
331 | 
332 |         :param tech_name: Tech name
333 |         """
334 |         cat_nums = self.technologies[tech_name].cats if tech_name in self.technologies else []
335 |         cat_names = [self.categories[str(cat_num)].name
336 |                      for cat_num in cat_nums if str(cat_num) in self.categories]
337 |         return cat_names
338 | 
339 |     def get_versions(self, url:str, app_name:str) -> List[str]:
340 |         """
341 |         Retuns a list of the discovered versions for an app name.
342 | 
343 |         :param url: URL of the webpage
344 |         :param app_name: App name
345 |         """
346 |         try:
347 |             return self.detected_technologies[url][app_name].versions
348 |         except KeyError:
349 |             return []
350 | 
351 |     def get_confidence(self, url:str, app_name:str) -> Optional[int]:
352 |         """
353 |         Returns the total confidence for an app name.
354 | 
355 |         :param url: URL of the webpage
356 |         :param app_name: App name
357 |         """
358 |         try:
359 |             return self.detected_technologies[url][app_name].confidenceTotal
360 |         except KeyError:
361 |             return None
362 | 
363 |     def analyze(self, webpage:IWebPage) -> Set[str]:
364 |         """
365 |         Return a set of technology that can be detected on the web page.
366 | 
367 |         :param webpage: The Webpage to analyze
368 |         """
369 |         detected_technologies = set()
370 | 
371 |         for tech_name, technology in list(self.technologies.items()):
372 |             if self._has_technology(technology, webpage):
373 |                 detected_technologies.add(tech_name)
374 | 
375 |         detected_technologies.update(self._get_implied_technologies(detected_technologies))
376 | 
377 |         return detected_technologies
378 | 
379 |     def analyze_with_versions(self, webpage:IWebPage) -> Dict[str, Dict[str, Any]]:
380 |         """
381 |         Return a dict of applications and versions that can be detected on the web page.
382 | 
383 |         :param webpage: The Webpage to analyze
384 |         """
385 |         detected_apps = self.analyze(webpage)
386 |         versioned_apps = {}
387 | 
388 |         for app_name in detected_apps:
389 |             versions = self.get_versions(webpage.url, app_name)
390 |             versioned_apps[app_name] = {"versions": versions}
391 | 
392 |         return versioned_apps
393 | 
394 |     def analyze_with_categories(self, webpage:IWebPage) -> Dict[str, Dict[str, Any]]:
395 |         """
396 |         Return a dict of technologies and categories that can be detected on the web page.
397 | 
398 |         :param webpage: The Webpage to analyze
399 | 
400 |         >>> wappalyzer.analyze_with_categories(webpage)
401 |         {'Amazon ECS': {'categories': ['IaaS']},
402 |         'Amazon Web Services': {'categories': ['PaaS']},
403 |         'Azure CDN': {'categories': ['CDN']},
404 |         'Docker': {'categories': ['Containers']}}
405 | 
406 |         """
407 |         detected_technologies = self.analyze(webpage)
408 |         categorised_technologies = {}
409 | 
410 |         for tech_name in detected_technologies:
411 |             cat_names = self.get_categories(tech_name)
412 |             categorised_technologies[tech_name] = {"categories": cat_names}
413 | 
414 |         return categorised_technologies
415 | 
416 |     def analyze_with_versions_and_categories(self, webpage:IWebPage) -> Dict[str, Dict[str, Any]]:
417 |         """
418 |         Return a dict of applications and versions and categories that can be detected on the web page.
419 | 
420 |         :param webpage: The Webpage to analyze
421 | 
422 |         >>> wappalyzer.analyze_with_versions_and_categories(webpage)
423 |         {'Font Awesome': {'categories': ['Font scripts'], 'versions': ['5.4.2']},
424 |         'Google Font API': {'categories': ['Font scripts'], 'versions': []},
425 |         'MySQL': {'categories': ['Databases'], 'versions': []},
426 |         'Nginx': {'categories': ['Web servers', 'Reverse proxies'], 'versions': []},
427 |         'PHP': {'categories': ['Programming languages'], 'versions': ['5.6.40']},
428 |         'WordPress': {'categories': ['CMS', 'Blogs'], 'versions': ['5.4.2']},
429 |         'Yoast SEO': {'categories': ['SEO'], 'versions': ['14.6.1']}}
430 | 
431 |         """
432 |         versioned_apps = self.analyze_with_versions(webpage)
433 |         versioned_and_categorised_apps = versioned_apps
434 | 
435 |         for app_name in versioned_apps:
436 |             cat_names = self.get_categories(app_name)
437 |             versioned_and_categorised_apps[app_name]["categories"] = cat_names
438 | 
439 |         return versioned_and_categorised_apps
440 | 
441 |     def _sort_app_versions(self, version_a: str, version_b: str) -> int:
442 |         return len(version_a) - len(version_b)
443 | 
444 |     def _cmp_to_key(self, mycmp: Callable[..., Any]):
445 |         """
446 |         Convert a cmp= function into a key= function
447 |         """
448 | 
449 |         # https://docs.python.org/3/howto/sorting.html
450 |         class CmpToKey:
451 |             def __init__(self, obj, *args):
452 |                 self.obj = obj
453 | 
454 |             def __lt__(self, other):
455 |                 return mycmp(self.obj, other.obj) < 0
456 | 
457 |             def __gt__(self, other):
458 |                 return mycmp(self.obj, other.obj) > 0
459 | 
460 |             def __eq__(self, other):
461 |                 return mycmp(self.obj, other.obj) == 0
462 | 
463 |             def __le__(self, other):
464 |                 return mycmp(self.obj, other.obj) <= 0
465 | 
466 |             def __ge__(self, other):
467 |                 return mycmp(self.obj, other.obj) >= 0
468 | 
469 |             def __ne__(self, other):
470 |                 return mycmp(self.obj, other.obj) != 0
471 | 
472 |         return CmpToKey
473 | 
474 | def analyze(url:str, 
475 |             update:bool=False, 
476 |             useragent:str=None,
477 |             timeout:int=10,
478 |             verify:bool=True) -> Dict[str, Dict[str, Any]]:
479 |     """
480 |     Quick utility method to analyze a website with minimal configurable options. 
481 | 
482 |     :See: `WebPage` and `Wappalyzer`. 
483 | 
484 |     :Parameters:
485 |         - `url`: URL
486 |         - `update`: Update the technologies file from the internet
487 |         - `useragent`: Request user agent
488 |         - `timeout`: Request timeout
489 |         - `verify`: SSL cert verify
490 |     
491 |     :Return: 
492 |         `dict`. Just as `Wappalyzer.analyze_with_versions_and_categories`. 
493 |     :Note: More information might be added to the returned values in the future
494 |     """
495 |     # Create Wappalyzer
496 |     wappalyzer=Wappalyzer.latest(update=update)
497 |     # Create WebPage
498 |     headers={}
499 |     if useragent:
500 |         headers['User-Agent'] = useragent
501 |     webpage=WebPage.new_from_url(url, 
502 |         headers=headers, 
503 |         timeout=timeout, 
504 |         verify=verify)
505 |     # Analyze
506 |     results = wappalyzer.analyze_with_versions_and_categories(webpage)
507 |     return results
508 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
  1 |                     GNU GENERAL PUBLIC LICENSE
  2 |                        Version 3, 29 June 2007
  3 | 
  4 |  Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
  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 <http://www.gnu.org/licenses/>.
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 |     <program>  Copyright (C) <year>  <name of author>
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 | <http://www.gnu.org/licenses/>.
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 | <http://www.gnu.org/philosophy/why-not-lgpl.html>.
675 | 


--------------------------------------------------------------------------------