ageng/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2025-12-17 22:55:42 +07:00
Code Issues Projects Releases Wiki Activity

[cleanup] Use _html_extract_title

Browse Source
This commit is contained in:
pukkandan
2022-04-04 13:57:35 +05:30
parent 85e801a9db
commit 04f3fd2c89
38 changed files with 51 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
yt_dlp/extractor/nhk.py
View File

@@ -309,7 +309,9 @@ def _real_extract(self, url):
webpage = self._download_webpage(f'https://www.nhk.or.jp/school/{program_id}/', program_id)
title = self._og_search_title(webpage, fatal=False) or self._html_extract_title(webpage, fatal=False) or self._html_search_regex(r'<h3>([^<]+?)とは？\s*</h3>', webpage, 'title', fatal=False)
title = (self._og_search_title(webpage)
or self._html_extract_title(webpage)
or self._html_search_regex(r'<h3>([^<]+?)とは？\s*</h3>', webpage, 'title', fatal=False))
title = re.sub(r'\s*\|\s*NHK\s+for\s+School\s*$', '', title) if title else None
description = self._html_search_regex(
r'(?s)<div\s+class="programDetail\s*">\s*<p>[^<]+</p>',