mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-17 21:59:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

apply patch from issues/9358#issuecomment-2072600506

Browse source
This commit is contained in:
jakeogh 2024-04-23 12:16:30 -07:00
parent 89f535e265
commit ee81ca4a95
1 changed files with 31 additions and 30 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

61
yt_dlp/extractor/youtube.py
View file

@ -3307,23 +3307,22 @@ def _extract_heatmap(self, data):
'value': ('intensityScoreNormalized', {float_or_none}), 'value': ('intensityScoreNormalized', {float_or_none}),
})) or None })) or None
def _extract_comment(self, comment_renderer, parent=None): def _extract_comment(self, view_model, entity, parent=None):
comment_id = comment_renderer.get('commentId') entity_payload = entity['payload']['commentEntityPayload']
if not comment_id: comment_id = entity_payload.get('properties').get('commentId')
return
info = { info = {
'id': comment_id, 'id': comment_id,
'text': self._get_text(comment_renderer, 'contentText'), 'text': self._get_text(entity_payload, ('properties', 'content', 'contetn')),
'like_count': self._get_count(comment_renderer, 'voteCount'), 'like_count': self._get_count(entity_payload, ('toolbar', 'likeCountNotliked')),
'author_id': traverse_obj(comment_renderer, ('authorEndpoint', 'browseEndpoint', 'browseId', {self.ucid_or_none})), 'author_id': traverse_obj(entity_payload, ('author', 'channelId', {self.ucid_or_none})),
'author': self._get_text(comment_renderer, 'authorText'), 'author': self._get_text(entity_payload, ('author', 'displayName')),
'author_thumbnail': traverse_obj(comment_renderer, ('authorThumbnail', 'thumbnails', -1, 'url', {url_or_none})), 'author_thumbnail': traverse_obj(entity_payload, ('author', 'avatarThumbnailUrl', {url_or_none})),
'parent': parent or 'root', 'parent': parent or 'root',
} }
# Timestamp is an estimate calculated from the current time and time_text # Timestamp is an estimate calculated from the current time and time_text
time_text = self._get_text(comment_renderer, 'publishedTimeText') or '' time_text = self._get_text(entity_payload, ('properties', 'publishedTime')) or ''
timestamp = self._parse_time_text(time_text) timestamp = self._parse_time_text(time_text)
info.update({ info.update({
@ -3333,25 +3332,23 @@ def _extract_comment(self, comment_renderer, parent=None):
}) })
info['author_url'] = urljoin( info['author_url'] = urljoin(
'https://www.youtube.com', traverse_obj(comment_renderer, ('authorEndpoint', ( 'https://www.youtube.com', traverse_obj(entity_payload,
('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url'))), ('author', 'channelCommand', 'innertubeCommand', 'browseEndpoint', 'canonicalBaseUrl'),
expected_type=str, get_all=False)) expected_type=str, get_all=False))
author_is_uploader = traverse_obj(comment_renderer, 'authorIsChannelOwner') author_is_uploader = traverse_obj(entity_payload, ('author', 'isCreator'))
if author_is_uploader is not None: if author_is_uploader is not None:
info['author_is_uploader'] = author_is_uploader info['author_is_uploader'] = author_is_uploader
comment_abr = traverse_obj( comment_abr = traverse_obj(
comment_renderer, ('actionButtons', 'commentActionButtonsRenderer'), expected_type=dict) entity, ('payload', 'engagementToolbarStateEntityPayload', 'heartState'), expected_type=str)
if comment_abr is not None: if comment_abr is not None:
info['is_favorited'] = 'creatorHeart' in comment_abr info['is_favorited'] = comment_abr == 'TOOLBAR_HEART_STATE_HEARTED'
badges = self._extract_badges([traverse_obj(comment_renderer, 'authorCommentBadge')]) info['author_is_verified'] = traverse_obj(entity_payload, ('author', 'isVerified')) == 'true'
if self._has_badge(badges, BadgeType.VERIFIED):
info['author_is_verified'] = True
is_pinned = traverse_obj(comment_renderer, 'pinnedCommentBadge') pinned_text = traverse_obj(view_model, 'pinnedText')
if is_pinned: if pinned_text:
info['is_pinned'] = True info['is_pinned'] = True
return info return info
@ -3388,21 +3385,25 @@ def extract_header(contents):
break break
return _continuation return _continuation
def extract_thread(contents): def extract_thread(contents, entity_payloads):
if not parent: if not parent:
tracker['current_page_thread'] = 0 tracker['current_page_thread'] = 0
for content in contents: for content in contents:
if not parent and tracker['total_parent_comments'] >= max_parents: if not parent and tracker['total_parent_comments'] >= max_parents:
yield yield
comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer']) comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
comment_renderer = get_first( view_model = traverse_obj(comment_thread_renderer, ('commentViewModel', 'commentViewModel'))
(comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]], if not view_model:
expected_type=dict, default={}) view_model = content.get('commentViewModel')
if not view_model:
comment = self._extract_comment(comment_renderer, parent)
if not comment:
continue continue
comment_id = comment['id'] comment_id = view_model['commentId']
for entity in entity_payloads:
if traverse_obj(entity, ('payload', 'commentEntityPayload', 'properties', 'commentId')) == comment_id:
entity = entity
break
comment = self._extract_comment(view_model, entity, parent)
if comment.get('is_pinned'): if comment.get('is_pinned'):
tracker['pinned_comment_ids'].add(comment_id) tracker['pinned_comment_ids'].add(comment_id)
# Sometimes YouTube may break and give us infinite looping comments. # Sometimes YouTube may break and give us infinite looping comments.
@ -3495,7 +3496,7 @@ def extract_thread(contents):
check_get_keys = None check_get_keys = None
if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0): if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0):
check_get_keys = [[*continuation_items_path, ..., ( check_get_keys = [[*continuation_items_path, ..., (
'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]] 'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentViewModel'))]]
try: try:
response = self._extract_response( response = self._extract_response(
item_id=None, query=continuation, item_id=None, query=continuation,
@ -3527,7 +3528,7 @@ def extract_thread(contents):
break break
continue continue
for entry in extract_thread(continuation_items): for entry in extract_thread(continuation_items, response['frameworkUpdates']['entityBatchUpdate']['mutations']):
if not entry: if not entry:
return return
yield entry yield entry