[facebook] Support thumbnails (closes #14416)

This commit is contained in:
Yen Chi Hsuan 2017-10-10 23:20:38 +08:00
parent 9e71f88105
commit 01c742ecd0
2 changed files with 20 additions and 4 deletions

View file

@ -1,3 +1,9 @@
version <unreleased>
Extractors
+ [facebook] Support thumbnails (#14416)
version 2017.10.07 version 2017.10.07
Core Core

View file

@ -67,9 +67,9 @@ class FacebookIE(InfoExtractor):
'uploader': 'Tennis on Facebook', 'uploader': 'Tennis on Facebook',
'upload_date': '20140908', 'upload_date': '20140908',
'timestamp': 1410199200, 'timestamp': 1410199200,
} },
'skip': 'Requires logging in',
}, { }, {
'note': 'Video without discernible title',
'url': 'https://www.facebook.com/video.php?v=274175099429670', 'url': 'https://www.facebook.com/video.php?v=274175099429670',
'info_dict': { 'info_dict': {
'id': '274175099429670', 'id': '274175099429670',
@ -78,6 +78,7 @@ class FacebookIE(InfoExtractor):
'uploader': 'Asif Nawab Butt', 'uploader': 'Asif Nawab Butt',
'upload_date': '20140506', 'upload_date': '20140506',
'timestamp': 1399398998, 'timestamp': 1399398998,
'thumbnail': r're:^https?://.*',
}, },
'expected_warnings': [ 'expected_warnings': [
'title' 'title'
@ -94,6 +95,7 @@ class FacebookIE(InfoExtractor):
'upload_date': '20160110', 'upload_date': '20160110',
'timestamp': 1452431627, 'timestamp': 1452431627,
}, },
'skip': 'Requires logging in',
}, { }, {
'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570', 'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6', 'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6',
@ -121,7 +123,11 @@ class FacebookIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '10153664894881749', 'id': '10153664894881749',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Facebook video #10153664894881749', 'title': 'Average time to confirm recent Supreme Court nominees: 67 days Longest it\'s t...',
'thumbnail': r're:^https?://.*',
'timestamp': 1456259628,
'upload_date': '20160223',
'uploader': 'Barack Obama',
}, },
}, { }, {
# have 1080P, but only up to 720p in swf params # have 1080P, but only up to 720p in swf params
@ -130,10 +136,11 @@ class FacebookIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '10155529876156509', 'id': '10155529876156509',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Holocaust survivor becomes US citizen', 'title': 'She survived the holocaust — and years later, shes getting her citizenship s...',
'timestamp': 1477818095, 'timestamp': 1477818095,
'upload_date': '20161030', 'upload_date': '20161030',
'uploader': 'CNN', 'uploader': 'CNN',
'thumbnail': r're:^https?://.*',
}, },
}, { }, {
# bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall
@ -158,6 +165,7 @@ class FacebookIE(InfoExtractor):
'timestamp': 1477305000, 'timestamp': 1477305000,
'upload_date': '20161024', 'upload_date': '20161024',
'uploader': 'La Guía Del Varón', 'uploader': 'La Guía Del Varón',
'thumbnail': r're:^https?://.*',
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
@ -376,6 +384,7 @@ class FacebookIE(InfoExtractor):
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))
thumbnail = self._og_search_thumbnail(webpage)
info_dict = { info_dict = {
'id': video_id, 'id': video_id,
@ -383,6 +392,7 @@ class FacebookIE(InfoExtractor):
'formats': formats, 'formats': formats,
'uploader': uploader, 'uploader': uploader,
'timestamp': timestamp, 'timestamp': timestamp,
'thumbnail': thumbnail,
} }
return webpage, info_dict return webpage, info_dict