Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-13 14:37:43 +01:00
Code Issues Packages Projects Releases Wiki Activity

[ie/youtube] Fix comments extraction (#9775)

Browse Source 
Closes #9358
Authored by: jakeogh, minamotorin, shoxie007, bbilly1

Co-authored-by: minamotorin <76122224+minamotorin@users.noreply.github.com>
Co-authored-by: shoxie007 <74592022+shoxie007@users.noreply.github.com>
Co-authored-by: Simon <35427372+bbilly1@users.noreply.github.com>
This commit is contained in:
Justin Keogh 2024-05-17 07:37:30 -07:00 committed by GitHub
parent dd9ad97b1f
commit 8e15177b41
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 56 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
yt_dlp/extractor/youtube.py
View File

@ -3317,7 +3317,36 @@ def _extract_heatmap(self, data):
'value': ('intensityScoreNormalized', {float_or_none}),
})) or None
def _extract_comment(self, comment_renderer, parent=None):
def _extract_comment(self, entities, parent=None):
comment_entity_payload = get_first(entities, ('payload', 'commentEntityPayload', {dict}))
if not (comment_id := traverse_obj(comment_entity_payload, ('properties', 'commentId', {str}))):
return
toolbar_entity_payload = get_first(entities, ('payload', 'engagementToolbarStateEntityPayload', {dict}))
time_text = traverse_obj(comment_entity_payload, ('properties', 'publishedTime', {str})) or ''
return {
'id': comment_id,
'parent': parent or 'root',
**traverse_obj(comment_entity_payload, {
'text': ('properties', 'content', 'content', {str}),
'like_count': ('toolbar', 'likeCountA11y', {parse_count}),
'author_id': ('author', 'channelId', {self.ucid_or_none}),
'author': ('author', 'displayName', {str}),
'author_thumbnail': ('author', 'avatarThumbnailUrl', {url_or_none}),
'author_is_uploader': ('author', 'isCreator', {bool}),
'author_is_verified': ('author', 'isVerified', {bool}),
'author_url': ('author', 'channelCommand', 'innertubeCommand', (
('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url')
), {lambda x: urljoin('https://www.youtube.com', x)}),
}, get_all=False),
'is_favorited': (None if toolbar_entity_payload is None else
toolbar_entity_payload.get('heartState') == 'TOOLBAR_HEART_STATE_HEARTED'),
'_time_text': time_text, # FIXME: non-standard, but we need a way of showing that it is an estimate.
'timestamp': self._parse_time_text(time_text),
}
def _extract_comment_old(self, comment_renderer, parent=None):
comment_id = comment_renderer.get('commentId')
if not comment_id:
return
@ -3398,21 +3427,39 @@ def extract_header(contents):
break
return _continuation
def extract_thread(contents):
def extract_thread(contents, entity_payloads):
if not parent:
tracker['current_page_thread'] = 0
for content in contents:
if not parent and tracker['total_parent_comments'] >= max_parents:
yield
comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
# old comment format
if not entity_payloads:
comment_renderer = get_first(
(comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
expected_type=dict, default={})
comment = self._extract_comment(comment_renderer, parent)
comment = self._extract_comment_old(comment_renderer, parent)
# new comment format
else:
view_model = (
traverse_obj(comment_thread_renderer, ('commentViewModel', 'commentViewModel', {dict}))
or traverse_obj(content, ('commentViewModel', {dict})))
comment_keys = traverse_obj(view_model, (('commentKey', 'toolbarStateKey'), {str}))
if not comment_keys:
continue
entities = traverse_obj(entity_payloads, lambda _, v: v['entityKey'] in comment_keys)
comment = self._extract_comment(entities, parent)
if comment:
comment['is_pinned'] = traverse_obj(view_model, ('pinnedText', {str})) is not None
if not comment:
continue
comment_id = comment['id']
if comment.get('is_pinned'):
tracker['pinned_comment_ids'].add(comment_id)
# Sometimes YouTube may break and give us infinite looping comments.
@ -3505,7 +3552,7 @@ def extract_thread(contents):
check_get_keys = None
if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0):
check_get_keys = [[*continuation_items_path, ..., (
'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]]
'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentViewModel', 'commentRenderer'))]]
try:
response = self._extract_response(
item_id=None, query=continuation,
@ -3529,6 +3576,7 @@ def extract_thread(contents):
raise
is_forced_continuation = False
continuation = None
mutations = traverse_obj(response, ('frameworkUpdates', 'entityBatchUpdate', 'mutations', ..., {dict}))
for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):
if is_first_continuation:
continuation = extract_header(continuation_items)
@ -3537,7 +3585,7 @@ def extract_thread(contents):
break
continue
for entry in extract_thread(continuation_items):
for entry in extract_thread(continuation_items, mutations):
if not entry:
return
yield entry