mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-11-01 07:05:14 +00:00
Code Issues Projects Releases Wiki Activity

[extractor/rutube] Extract chapters from description (#6345)

Browse Source 
Authored by: mushbite
This commit is contained in:
mushbite
2023-03-04 15:33:17 +02:00
committed by GitHub
parent 08ff6d59f9
commit 22ccd5420b
3 changed files with 66 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
yt_dlp/extractor/youtube.py
View File

@@ -3205,11 +3205,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
), expected_type=list)
return self._extract_chapters(
return self._extract_chapters_helper(
chapter_list,
chapter_time=lambda chapter: float_or_none(
start_function=lambda chapter: float_or_none(
traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
chapter_title=lambda chapter: traverse_obj(
title_function=lambda chapter: traverse_obj(
chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
duration=duration)
@@ -3222,42 +3222,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
chapter_title = lambda chapter: self._get_text(chapter, 'title')
return next(filter(None, (
self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
chapter_time, chapter_title, duration)
self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
chapter_time, chapter_title, duration)
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(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):
if not duration:
return
chapter_list = [{
'start_time': chapter_time(chapter),
'title': chapter_title(chapter),
} for chapter in chapter_list or []]
if not strict:
chapter_list.sort(key=lambda c: c['start_time'] or 0)
chapters = [{'start_time': 0}]
for idx, chapter in enumerate(chapter_list):
if chapter['start_time'] is None:
self.report_warning(f'Incomplete chapter {idx}')
elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
chapters.append(chapter)
elif chapter not in chapters:
self.report_warning(
f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"')
return chapters[1:]
def _extract_comment(self, comment_renderer, parent=None):
comment_id = comment_renderer.get('commentId')
if not comment_id: