admin-valentin/wewrite
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat: learn_theme — add HTML fetch/extract layer (fetch_article, extract_styles, parse_inline_style)

Browse source 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
wangzhuc 2026-04-01 01:55:48 +08:00
parent 1168768618
commit e457b4463b
1 changed files with 7 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
scripts/learn_theme.py
View file

@ -158,13 +158,18 @@ _BROWSER_UA = (
) )
def fetch_article(url: str) -> "BeautifulSoup tag": def fetch_article(url: str, timeout: int = 20) -> "BeautifulSoup tag":
"""Fetch a WeChat article, return the ``#js_content`` element. """Fetch a WeChat article, return the ``#js_content`` element.
The article title is attached as ``content._wewrite_title`` (empty string The article title is attached as ``content._wewrite_title`` (empty string
if not found). Exits with code 1 if ``#js_content`` is absent. if not found). Exits with code 1 if ``#js_content`` is absent.
Parameters
----------
url: WeChat article URL (mp.weixin.qq.com/…)
timeout: HTTP request timeout in seconds (default 20).
""" """
resp = requests.get(url, headers={"User-Agent": _BROWSER_UA}, timeout=20) resp = requests.get(url, headers={"User-Agent": _BROWSER_UA}, timeout=timeout)
resp.encoding = "utf-8" resp.encoding = "utf-8"
soup = BeautifulSoup(resp.text, "html.parser") soup = BeautifulSoup(resp.text, "html.parser")