Shortcuts on this page
r m x toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
1"""
2The Article record :meth:`turbohtml.Node.article` returns.
4The content scoring and metadata harvesting all live in the C core (``turbohtml._html``), exposed as the
5:meth:`~turbohtml.Node.article` method. The core builds one :class:`Article` per call; importing this module registers
6the record type with it.
7"""
9from __future__ import annotations
11from typing import NamedTuple
13from turbohtml._html import Element, _register_article # Element stays importable so autodoc resolves it
16class Article(NamedTuple):
17 """
18 The dominant content of a document and the metadata harvested beside it.
20 ``element`` is the scored content body (``None`` when nothing reads as content) and ``text`` its layout-aware plain
21 text (empty then). ``title``, ``byline``, ``date``, ``description``, ``lang``, ``canonical`` (the ``<link
22 rel=canonical>`` URL or ``og:url``), ``site_name`` (``og:site_name`` or ``<meta name=application-name>``) and
23 ``image`` (the ``og:image`` or ``twitter:image`` lead image) are single-valued page metadata, each
24 whitespace-normalized or ``None`` when the source is absent. ``tags`` collects every ``<meta name=keywords>`` value
25 (comma-split) and ``article:tag`` in document order, an empty tuple when none appear. This makes
26 :meth:`~turbohtml.Node.article` a one-call replacement for trafilatura and newspaper3k.
27 """
29 element: Element | None
30 text: str
31 title: str | None
32 byline: str | None
33 date: str | None
34 description: str | None
35 lang: str | None
36 canonical: str | None
37 site_name: str | None
38 tags: tuple[str, ...]
39 image: str | None
42_register_article(Article)