projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
a685751
)
[facebook] Fix title extraction (closes #11941)
author
Sergey M․
<dstftw@gmail.com>
Thu, 2 Feb 2017 15:45:18 +0000
(22:45 +0700)
committer
Sergey M․
<dstftw@gmail.com>
Thu, 2 Feb 2017 15:45:18 +0000
(22:45 +0700)
youtube_dl/extractor/facebook.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/facebook.py
b/youtube_dl/extractor/facebook.py
index 47bcc0dbcb6577a0f7ae2491ada336bfa33067b2..b325c82004b8aedc612cf3656c54816dcaf48e94 100644
(file)
--- a/
youtube_dl/extractor/facebook.py
+++ b/
youtube_dl/extractor/facebook.py
@@
-73,7
+73,7
@@
class FacebookIE(InfoExtractor):
'info_dict': {
'id': '274175099429670',
'ext': 'mp4',
'info_dict': {
'id': '274175099429670',
'ext': 'mp4',
- 'title': '
Facebook video #274175099429670
',
+ 'title': '
Asif Nawab Butt posted a video to his Timeline.
',
'uploader': 'Asif Nawab Butt',
'upload_date': '20140506',
'timestamp': 1399398998,
'uploader': 'Asif Nawab Butt',
'upload_date': '20140506',
'timestamp': 1399398998,
@@
-318,10
+318,16
@@
class FacebookIE(InfoExtractor):
video_title = self._html_search_regex(
r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
webpage, 'alternative title', default=None)
video_title = self._html_search_regex(
r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
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(
r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
'timestamp', default=None))
timestamp = int_or_none(self._search_regex(
r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
'timestamp', default=None))