wp-details detector

.github/workflows/pipy-publish.yml

@@ -0,0 +1,34 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+
+name: Upload Python Package
+
+on:
+  #push:
+  #  branches: [main]
+
+  release:
+    types: [published]
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install setuptools wheel twine
+    - name: Build and publish
+      env:
+        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+      run: |
+        python setup.py sdist bdist_wheel
+        twine upload dist/*

.gitignore

@@ -0,0 +1,129 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

README.md

@@ -0,0 +1,19 @@
+# cms-detector
+
+## Whats in cms-detector?
+
+A Python Package to detect the Content Management System of a Website.
+
+We believe in monolithic software development and created this tiny package that does its job without any bloat. 
+
+## How to Use cms-detector?
+
+You can find detailed tutorial on [cms-detector tutorial website](https://serpwings.com/software/python-cms-detector/).
+
+## Contribute
+
+Pull Requests, Feature Suggestions, and collaborations are welcome.
+
+## About Us
+
+This work is a collaborative effort of [seowings](https://seowings.org/), and [serpwings](https://serpwings.com/).

cms_detector/__init__.py

@@ -0,0 +1,141 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*- #
+
+"""
+cms-detector: A Python Package to detect the Content Management System of a Website.
+
+MIT License
+Copyright (c) 2023 SERP Wings www.serpwings.com
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+"""
+
+
+# +++++++++++++++++++++++++++++++++++++++++++++++++++++
+# IMPORTS Standard Library
+# +++++++++++++++++++++++++++++++++++++++++++++++++++++
+
+import re
+from unittest.mock import Mock
+
+# +++++++++++++++++++++++++++++++++++++++++++++++++++++
+# IMPORTS 3rd Party Libraries
+# +++++++++++++++++++++++++++++++++++++++++++++++++++++
+
+import requests
+from requests.adapters import HTTPAdapter
+from requests.models import Response
+from bs4 import BeautifulSoup
+
+# +++++++++++++++++++++++++++++++++++++++++++++++++++++
+# DATABASE/CONSTANTS LIST
+# +++++++++++++++++++++++++++++++++++++++++++++++++++++
+
+HEADER = {
+    "User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0",
+}
+
+# +++++++++++++++++++++++++++++++++++++++++++++++++++++
+# Utility Functions
+# +++++++++++++++++++++++++++++++++++++++++++++++++++++
+
+
+def mock_requests_object(url):
+    """Generates a mock request object"""
+    response = Mock(spec=Response)
+    response.text = ""
+    response.status_code = 9999
+    response.url = url
+    return response
+
+
+def get_remote_content(url, max_retires=2):
+    """Get remote content avialble on a given url"""
+    try:
+        s = requests.Session()
+        s.mount(url, HTTPAdapter(max_retries=max_retires))
+        return s.get(url, headers=HEADER)
+    except:
+        return mock_requests_object(url)
+
+
+def get_corrected_url(url, fix_slash="/"):
+    """correct scheme and end slash of a url"""
+    if not url.startswith("http://") and not url.startswith("https://"):
+        url = f"http://{url}"
+
+    if not url.endswith(fix_slash):
+        url = f"{url}{fix_slash}"
+
+    return url
+
+
+def wp_details(target_url):
+    """Check if WordPress is installed on a given webiste.
+
+    It will also return name of plugins and themes, if installed on the website.
+
+    """
+
+    target_url = get_corrected_url(target_url, fix_slash="/")
+    response = get_remote_content(target_url)
+
+    if response.status_code < 400:
+        link_regex = re.compile(
+            "((https?):((/)|(\\\\))+([\w\d:#@%/;$()~_?\+-=\\\.&](#!)?)*)",
+            re.DOTALL,
+        )
+        all_link = set([link[0] for link in re.findall(link_regex, response.text)])
+        wp_content = [meta for meta in all_link if "wp-content" in meta]
+        wp_includes = [meta for meta in all_link if "wp-includes" in meta]
+        wp_json = [meta for meta in all_link if "wp-json" in meta]
+
+        themes = [
+            re.search("/themes/(.*)/", link) for link in all_link if "/themes/" in link
+        ]
+
+        if themes:
+            themes = list(
+                set([theme.group(1).split("/")[0] for theme in themes if theme])
+            )
+
+        plugins = [
+            re.search("/plugins/(.*)/", link)
+            for link in all_link
+            if "/plugins/" in link
+        ]
+
+        if plugins:
+            plugins = list(
+                set([plugin.group(1).split("/")[0] for plugin in plugins if plugin])
+            )
+
+        wp_found = False
+        wp_version = ""
+
+        if any([wp_content, wp_includes, wp_json]):
+            wp_found = True
+            soup_xml = BeautifulSoup(response.content, "lxml")
+            wp_version_tag = soup_xml.find("meta", attrs={"name": "generator"})
+            if wp_version_tag:
+                wp_version = wp_version_tag.get("content")
+
+        return {
+            "is_wp_installed": wp_found,
+            "wp_version": wp_version,
+            "themes": themes,
+            "plugins": plugins,
+        }

examples/tutorial.py

@@ -0,0 +1,5 @@
+from cms_detector import wp_details
+
+result = wp_details(target_url="https://wordpress.org")
+
+print(result)