Add documentation

.gitignore

@@ -3,5 +3,6 @@ __pycache__
 *.pyo
 .tox
 dist/
+docs/_build
 build/
 lxml_html_clean.egg-info/

README.md

@@ -7,11 +7,7 @@ This project was initially a part of [lxml](https://github.com/lxml/lxml). Becau
 ## Installation
 
 You can install this project directly via `pip install lxml_html_clean` or soon as an extra of lxml
-itself via `pip install lxml[html_clean]`. Both ways installs this project together with lxml itself.
-
-## Usage
-
-[USAGE.rst](USAGE.rst) contains a part of the lxml documentation related to HTML cleaning.
+via `pip install lxml[html_clean]`. Both ways installs this project together with lxml itself.
 
 ## License
 

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/conf.py

@@ -0,0 +1,37 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+import sys
+
+sys.path.insert(0, "..")
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
+project = 'lxml_html_clean'
+copyright = '2024, Lumír Balhar'
+author = 'Lumír Balhar'
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions = ['sphinx.ext.autodoc']
+
+templates_path = ['_templates']
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+autodoc_default_options = {
+    'ignore-module-all': True,
+    'private-members': True,
+    'inherited-members': True,
+}
+
+autodoc_member_order = 'groupwise'
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_theme = 'sphinx_rtd_theme'
+#html_static_path = ['_static']

docs/index.rst

@@ -0,0 +1,39 @@
+Welcome to lxml_html_clean's documentation!
+===========================================
+
+Motivation
+----------
+
+This project was initially a part of `lxml <https://github.com/lxml/lxml>`_. Because HTML cleaner is designed as blocklist-based,
+many reports about possible security vulnerabilities were filed for lxml and that make the project problematic for
+security-sensitive environments. Therefore we decided to extract the problematic part to a separate project.
+
+Installation
+------------
+
+You can install this project directly via ``pip install lxml_html_clean``` or soon as an extra of lxml
+via ``pip install lxml[html_clean]``. Both ways installs this project together with lxml itself.
+
+Usage
+=====
+
+.. toctree::
+   :maxdepth: 2
+
+   usage
+
+API
+===
+
+.. toctree::
+   :maxdepth: 2
+
+   lxml_html_clean
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

docs/lxml_html_clean.rst

@@ -0,0 +1,10 @@
+lxml\_html\_clean package
+=========================
+
+lxml\_html\_clean.clean module
+------------------------------
+
+.. automodule:: lxml_html_clean.clean
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/modules.rst

@@ -0,0 +1,7 @@
+lxml_html_clean
+===============
+
+.. toctree::
+   :maxdepth: 4
+
+   lxml_html_clean