Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-07-01 09:50:05 +02:00
Code Issues Releases Activity

Merge c1589ea3fe into f3411af12e

Browse Source
This commit is contained in:
Sebastian Kondraciuk 2024-06-25 21:45:48 +09:00 committed by GitHub
commit e154e4c2a9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 26 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
yt_dlp/extractor/facebook.py
View File

@ -476,6 +476,29 @@ def _extract_from_url(self, url, video_id):
webpage = self._download_webpage(
url.replace('://m.facebook.com/', '://www.facebook.com/'), video_id)
def extract_follower_count(webpage):
post_data = [self._parse_json(j, video_id, fatal=False) for j in re.findall(
r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage)]
post = traverse_obj(post_data, (
..., 'require', ..., ..., ..., '__bbox', 'require', ..., ..., ..., '__bbox', 'result', 'data'), expected_type=dict) or []
followers = get_first(post, ('user', 'profile_header_renderer', 'user', 'profile_social_context', 'content', ..., 'text',
lambda k, v: k == 'text' and isinstance(v, str) and v.endswith('followers'))) or None
if not isinstance(followers, str):
return None
matches = re.search(r"(\d+)([K|M])?", followers)
if matches is None:
return None
count = int(matches[1])
unit = matches[2]
if unit == "K":
count *= 1_000
elif unit == "M":
count *= 1_000_000
return count
def extract_metadata(webpage):
post_data = [self._parse_json(j, video_id, fatal=False) for j in re.findall(
r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage)]
@ -513,6 +536,8 @@ def extract_metadata(webpage):
# in https://www.facebook.com/yaroslav.korpan/videos/1417995061575415/
if thumbnail and not re.search(r'\.(?:jpg|png)', thumbnail):
thumbnail = None
profile_url = get_first(post, ('attachments', ..., 'media', 'creation_story', 'comet_sections', 'actor_photo', 'story', 'actors', ..., 'profile_url'))
follower_count = extract_follower_count(self._download_webpage(profile_url, None))
info_dict = {
'description': description,
'uploader': uploader,
@ -524,6 +549,7 @@ def extract_metadata(webpage):
webpage, 'view count', default=None)),
'concurrent_view_count': get_first(post, (
('video', (..., ..., 'attachments', ..., 'media')), 'liveViewerCount', {int_or_none})),
'channel_follower_count': follower_count,
}
info_json_ld = self._search_json_ld(webpage, video_id, default={})