# Configuration file for the Sphinx documentation builder. # # This file only contains a selection of the most common options. For a full # list see the documentation: # https://www.sphinx-doc.org/en/master/usage/configuration.html # -- Path setup -------------------------------------------------------------- # 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 trafilatura # -- Project information ----------------------------------------------------- project = 'Trafilatura' copyright = '2025, Adrien Barbaresi' html_show_sphinx = False author = 'Adrien Barbaresi' version = trafilatura.__version__ # -- General configuration --------------------------------------------------- # The master toctree document. master_doc = 'index' # 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 = trafilatura.__version__ # The full version, including alpha/beta/rc tags. release = trafilatura.__version__ # The language for content autogenerated by Sphinx. Refer to documentation # for a list of supported languages. language = 'en' # 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.intersphinx', 'sphinx.ext.napoleon', 'sphinx.ext.viewcode', 'sphinx_sitemap' ] # Add any paths that contain templates here, relative to this directory. templates_path = ['_templates'] # List of patterns, relative to source directory, that match files and # directories to ignore when looking for source files. # This pattern also affects html_static_path and html_extra_path. exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store'] # If true, the current module name will be prepended to all description # unit titles (such as .. function::). add_module_names = True # -- 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 = 'pydata_sphinx_theme' # 'furo' # 'alabaster' # 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'] # 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. ## pydata options html_theme_options = { "github_url": "https://github.com/adbar/trafilatura", "external_links": [ {"name": "Blog", "url": "https://adrien.barbaresi.eu/blog/tag/trafilatura.html"}, ], "navigation_with_keys": False, # "use_edit_page_button": True, # "navigation_depth": 3, # "show_toc_level": 3, } html_theme_options["analytics"] = { "google_analytics_id": "G-K3R5QCVDF1", "analytics_anonymize_ip": True, } html_logo = "trafilatura-logo.png" html_context = { # "github_url": "https://github.com", # or your GitHub Enterprise interprise "github_user": "adbar", "github_repo": "trafilatura", "github_version": "master", "doc_path": "docs", } ## furo options #html_theme_options = { # "announcement": "Important announcement!", #} ## alabaster theme #html_theme_options = { # "description": "Web scraping tool for text discovery and retrieval", # "show_powered_by": False, # "github_button": False, # "github_user": "adbar", # "github_repo": "trafilatura", # "github_count": True, # "github_banner": False, # "show_related": False, # "sidebar_collapse": True, # "extra_nav_links": {'test': 'https://example.org'}, # "note_bg": "#FFF59C", #} intersphinx_mapping = { "python": ("https://docs.python.org/3/", None), } html_baseurl = 'https://trafilatura.readthedocs.io/' sitemap_url_scheme = "{lang}latest/{link}" html_extra_path = ['robots.txt']