diff options
| author | chris <6024426+iw0nderhow@users.noreply.github.com> | 2022-01-01 22:07:00 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2022-01-02 02:37:00 +0530 |
| commit | f5225737877a78f63b9a6f1de675c95c650f65d6 (patch) | |
| tree | 6481494f9e2fc6063646be74df7cec4199f327d4 /yt_dlp | |
| parent | 7592749cbe377675688dfcad5b7c1d46bbb684e1 (diff) | |
| download | hypervideo-pre-f5225737877a78f63b9a6f1de675c95c650f65d6.tar.lz hypervideo-pre-f5225737877a78f63b9a6f1de675c95c650f65d6.tar.xz hypervideo-pre-f5225737877a78f63b9a6f1de675c95c650f65d6.zip | |
[extractor] Extract chapters from JSON-LD (#2031)
Authored by: iw0nderhow, pukkandan
Diffstat (limited to 'yt_dlp')
| -rw-r--r-- | yt_dlp/extractor/common.py | 18 |
1 files changed, 18 insertions, 0 deletions
diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index 1d694293e..79f53c9c2 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -1429,6 +1429,23 @@ class InfoExtractor(object): continue info[count_key] = interaction_count + def extract_chapter_information(e): + chapters = [{ + 'title': part.get('name'), + 'start_time': part.get('startOffset'), + 'end_time': part.get('endOffset'), + } for part in e.get('hasPart', []) if part.get('@type') == 'Clip'] + for idx, (last_c, current_c, next_c) in enumerate(zip( + [{'end_time': 0}] + chapters, chapters, chapters[1:])): + current_c['end_time'] = current_c['end_time'] or next_c['start_time'] + current_c['start_time'] = current_c['start_time'] or last_c['end_time'] + if None in current_c.values(): + self.report_warning(f'Chapter {idx} contains broken data. Not extracting chapters') + return + if chapters: + chapters[-1]['end_time'] = chapters[-1]['end_time'] or info['duration'] + info['chapters'] = chapters + def extract_video_object(e): assert e['@type'] == 'VideoObject' author = e.get('author') @@ -1452,6 +1469,7 @@ class InfoExtractor(object): 'view_count': int_or_none(e.get('interactionCount')), }) extract_interaction_statistic(e) + extract_chapter_information(e) def traverse_json_ld(json_ld, at_top_level=True): for e in json_ld: |