github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

[facebook] Fix title extraction (closes #11941)

Browse source
This commit is contained in:
Sergey M․ 2017-02-02 22:45:18 +07:00
parent a685751051
commit 5a116e1302
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 9 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
youtube_dl/extractor/facebook.py
View file

@ -73,7 +73,7 @@ class FacebookIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '274175099429670', 'id': '274175099429670',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Facebook video #274175099429670', 'title': 'Asif Nawab Butt posted a video to his Timeline.',
'uploader': 'Asif Nawab Butt', 'uploader': 'Asif Nawab Butt',
'upload_date': '20140506', 'upload_date': '20140506',
'timestamp': 1399398998, 'timestamp': 1399398998,
@ -318,10 +318,16 @@ class FacebookIE(InfoExtractor):
video_title = self._html_search_regex( video_title = self._html_search_regex(
r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>', r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
webpage, 'alternative title', default=None) webpage, 'alternative title', default=None)
video_title = limit_length(video_title, 80)
if not video_title: if not video_title:
video_title = self._html_search_meta(
'description', webpage, 'title')
if video_title:
video_title = limit_length(video_title, 80)
else:
video_title = 'Facebook video #%s' % video_id video_title = 'Facebook video #%s' % video_id
uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage)) uploader = clean_html(get_element_by_id(
'fbPhotoPageAuthorName', webpage)) or self._search_regex(
r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader', fatal=False)
timestamp = int_or_none(self._search_regex( timestamp = int_or_none(self._search_regex(
r'<abbr[^>]+data-utime=["\'](\d+)', webpage, r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
'timestamp', default=None)) 'timestamp', default=None))