administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-10 03:10:38 +00:00
Code Issues Projects Releases Wiki Activity

[extractor/youtube] Improve chapter parsing from description

Browse Source 
Closes #5448
This commit is contained in:
pukkandan 2022-11-05 15:34:53 +05:30
parent 68a9a450d4
commit 2e30b46fe4
No known key found for this signature in database
GPG Key ID: 7EEE9E1E817D0A39
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
yt_dlp/extractor/youtube.py
View File

@ -3027,9 +3027,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
for contents in content_list)), [])
def _extract_chapters_from_description(self, description, duration):
duration_re = r'(?:\d+:)?\d{1,2}:\d{2}'
sep_re = r'(?m)^\s*(%s)\b\W*\s(%s)\s*$'
return self._extract_chapters(
re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
re.findall(sep_re % (duration_re, r'.+?'), description or ''),
chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
duration=duration, strict=False) or self._extract_chapters(
re.findall(sep_re % (r'.+?', duration_re), description or ''),
chapter_time=lambda x: parse_duration(x[1]), chapter_title=lambda x: x[0],
duration=duration, strict=False)
def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):