artem/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-04-02 15:12:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

[ie/youtube] Fix comment subthreads extraction (#15448)

Browse Source 
Fix d22436e5dc7c6808d931e27cbb967b1b2a33c17c

Closes #15444
Authored by: bashonly
This commit is contained in:
bashonly 2025-12-31 03:56:26 -06:00 committed by GitHub
parent ab3ff2d5dd
commit 76c31a7a21
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 40 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
yt_dlp/extractor/youtube/_video.py
View File

@ -1661,7 +1661,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
}, },
'params': {'skip_download': True}, 'params': {'skip_download': True},
}, { }, {
# Threaded comments with 4 levels of depth # Comment subthreads with 4 levels of depth
'url': 'https://www.youtube.com/watch?v=f6HNySwZV4c', 'url': 'https://www.youtube.com/watch?v=f6HNySwZV4c',
'info_dict': { 'info_dict': {
'id': 'f6HNySwZV4c', 'id': 'f6HNySwZV4c',
@ -1675,6 +1675,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'channel': 'cole-dlp-test-acc', 'channel': 'cole-dlp-test-acc',
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
'channel_follower_count': int,
'view_count': int, 'view_count': int,
'like_count': int, 'like_count': int,
'age_limit': 0, 'age_limit': 0,
@ -1689,12 +1690,41 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'playable_in_embed': True, 'playable_in_embed': True,
'availability': 'public', 'availability': 'public',
'live_status': 'not_live', 'live_status': 'not_live',
'comment_count': 15, 'comment_count': 15, # XXX: minimum
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
'getcomments': True, 'getcomments': True,
}, },
}, {
# Comments: `subThreads` containing `commentThreadRenderer`s AND `continuationItemRenderer`
'url': 'https://www.youtube.com/watch?v=3dHQb2Nhma0',
'info_dict': {
'id': '3dHQb2Nhma0',
'ext': 'mp4',
'title': 'Tɪtle',
'description': '',
'media_type': 'video',
'uploader': 'abcdefg',
'uploader_id': '@abcdefg-d5t2c',
'uploader_url': 'https://www.youtube.com/@abcdefg-d5t2c',
'channel': 'abcdefg',
'channel_id': 'UCayEJzV8XSSJkPdA7OAsbew',
'channel_url': 'https://www.youtube.com/channel/UCayEJzV8XSSJkPdA7OAsbew',
'view_count': int,
'like_count': int,
'age_limit': 0,
'duration': 12,
'thumbnail': 'https://i.ytimg.com/vi/3dHQb2Nhma0/maxresdefault.jpg',
'categories': ['People & Blogs'],
'tags': [],
'timestamp': 1767158812,
'upload_date': '20251231',
'playable_in_embed': True,
'availability': 'unlisted',
'live_status': 'not_live',
'comment_count': 9, # XXX: minimum
},
}] }]
_WEBPAGE_TESTS = [{ _WEBPAGE_TESTS = [{
# <object> # <object>
@ -2532,19 +2562,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict) comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
if comment_replies_renderer: if comment_replies_renderer:
subthreads = traverse_obj(comment_replies_renderer, ( subthreads = traverse_obj(comment_replies_renderer, ('subThreads', ..., {dict}))
'subThreads', lambda _, v: v['commentThreadRenderer']))
# Recursively extract from `commentThreadRenderer`s in `subThreads` # Recursively extract from `commentThreadRenderer`s in `subThreads`
if subthreads: if threads := traverse_obj(subthreads, lambda _, v: v['commentThreadRenderer']):
for entry in extract_thread(subthreads, entity_payloads, comment_id, thread_depth + 1): for entry in extract_thread(threads, entity_payloads, comment_id, thread_depth + 1):
if entry: if entry:
yield entry yield entry
# All of the subThreads' `continuationItemRenderer`s were within the nested if not traverse_obj(subthreads, lambda _, v: v['continuationItemRenderer']):
# `commentThreadRenderer`s and are now exhausted, so avoid unnecessary recursion below # All of the subThreads' `continuationItemRenderer`s were within the nested
continue # `commentThreadRenderer`s and are now exhausted, so avoid unnecessary recursion below
continue
tracker['current_page_thread'] += 1 tracker['current_page_thread'] += 1
# Recursively extract from `continuationItemRenderer`s in `subThreads` # Recursively extract from `continuationItemRenderer` in `subThreads`
comment_entries_iter = self._comment_entries( comment_entries_iter = self._comment_entries(
comment_replies_renderer, ytcfg, video_id, comment_replies_renderer, ytcfg, video_id,
parent=comment_id, tracker=tracker, depth=thread_depth + 1) parent=comment_id, tracker=tracker, depth=thread_depth + 1)