Documentation draft

README.rst

@@ -50,7 +50,7 @@ Change Log
 -  0.3 Added Document.encoding, positive\_keywords and negative\_keywords
 
 Licensing
-=========
+--------
 
 This code is under `the Apache License
 2.0 <http://www.apache.org/licenses/LICENSE-2.0>`__ license.

doc/source/api.rst

@@ -0,0 +1,30 @@
+Reference
+=========
+
+.. automodule:: readability
+    :members:
+    :show-inheritance:
+
+.. automodule:: readability.browser
+    :members:
+    :show-inheritance:
+
+.. automodule:: readability.cleaners
+    :members:
+    :show-inheritance:
+
+.. automodule:: readability.debug
+    :members:
+    :show-inheritance:
+
+.. automodule:: readability.encoding
+    :members:
+    :show-inheritance:
+
+.. automodule:: readability.htmls
+    :members:
+    :show-inheritance:
+
+.. automodule:: readability.readability
+    :members:
+    :show-inheritance:

doc/source/conf.py

@@ -0,0 +1,164 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# readability documentation build configuration file, created by
+# sphinx-quickstart on Thu Mar 23 16:29:38 2017.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+import os
+import sys
+
+sys.path.insert(0, os.path.abspath("../.."))
+
+import readability
+
+# -- General configuration ------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    "sphinx.ext.autodoc",
+    "sphinx.ext.doctest",
+    "sphinx.ext.intersphinx",
+    "sphinx.ext.todo",
+    "recommonmark",
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ["_templates"]
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+source_suffix = [".rst", ".md"]
+
+# The master toctree document.
+master_doc = "index"
+
+# General information about the project.
+project = "readability"
+copyright = "2020, Yuri Baburov"
+author = "Yuri Baburov"
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+
+# The short X.Y version.
+version = readability.__version__
+
+# The full version, including alpha/beta/rc tags.
+release = readability.__version__
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This patterns also effect to html_static_path and html_extra_path
+exclude_patterns = []
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = "sphinx"
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = False
+
+
+# -- Options for HTML output ----------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = "sphinx_rtd_theme"
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#
+# html_theme_options = {}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = []  #'_static']
+
+
+# -- Options for HTMLHelp output ------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = "readabilitydoc"
+
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [(master_doc, "readability.tex", "Readability Documentation", "Yuri Baburov", "manual")]
+
+
+# -- Options for manual page output ---------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [(master_doc, "readability", "readability Documentation", [author], 1)]
+
+
+# -- Options for Texinfo output -------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (
+        master_doc,
+        "readability",
+        "Readability Documentation",
+        author,
+        "readability",
+        "One line description of project.",
+        "Miscellaneous",
+    )
+]
+
+
+intersphinx_mapping = {
+    "python": ("https://docs.python.org/3", None),
+}

doc/source/index.rst

@@ -0,0 +1,13 @@
+.. include:: ../../README.rst
+
+.. toctree::
+    :maxdepth: 2
+
+    api
+
+Indices and tables
+------------------
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

readability/readability.py

@@ -178,7 +178,7 @@ class Document:
         Given a HTML file, extracts the text of the article.
 
         :param html_partial: return only the div of the document, don't wrap
-        in html and body tags.
+                             in html and body tags.
 
         Warning: It mutates internal DOM representation of the HTML document,
         so it is better to call other API methods before this one.

tox.ini

@@ -4,10 +4,15 @@
 # and then run "tox" from this directory.
 
 [tox]
-envlist = py27, py35, py36, py37
+envlist = py27, py35, py36, py37, doc
 
 [testenv]
-deps=pytest
+deps =
+    pytest
+    doc: sphinx
+    doc: sphinx_rtd_theme
+    doc: recommonmark
+
 # This creates the virtual envs with --site-packages so already packages
 # that are already installed will be reused. This is especially useful on
 # Windows. Since we use lxml instead of compiling it locally (which in turn
@@ -18,3 +23,7 @@ sitepackages=True
 commands =
     pip install -r requirements.txt -e ".[test]"
     py.test
+
+[testenv:doc]
+commands =
+    python setup.py build_sphinx