[twitter] try to use a Generic fallback for unknown twitter cards(closes #25982)

This commit is contained in:
Remita Amine 2021-01-03 13:29:00 +01:00
parent 8522bcd97c
commit 491ee7efe4
1 changed files with 30 additions and 22 deletions

View File

@ -251,10 +251,10 @@ class TwitterIE(TwitterBaseIE):
'info_dict': { 'info_dict': {
'id': '700207533655363584', 'id': '700207533655363584',
'ext': 'mp4', 'ext': 'mp4',
'title': 'simon vetugo - BEAT PROD: @suhmeduh #Damndaniel', 'title': 'simon vertugo - BEAT PROD: @suhmeduh #Damndaniel',
'description': 'BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ', 'description': 'BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ',
'thumbnail': r're:^https?://.*\.jpg', 'thumbnail': r're:^https?://.*\.jpg',
'uploader': 'simon vetugo', 'uploader': 'simon vertugo',
'uploader_id': 'simonvertugo', 'uploader_id': 'simonvertugo',
'duration': 30.0, 'duration': 30.0,
'timestamp': 1455777459, 'timestamp': 1455777459,
@ -312,6 +312,7 @@ class TwitterIE(TwitterBaseIE):
'timestamp': 1492000653, 'timestamp': 1492000653,
'upload_date': '20170412', 'upload_date': '20170412',
}, },
'skip': 'Account suspended',
}, { }, {
'url': 'https://twitter.com/i/web/status/910031516746514432', 'url': 'https://twitter.com/i/web/status/910031516746514432',
'info_dict': { 'info_dict': {
@ -380,6 +381,14 @@ class TwitterIE(TwitterBaseIE):
# promo_video_website card # promo_video_website card
'url': 'https://twitter.com/GunB1g/status/1163218564784017422', 'url': 'https://twitter.com/GunB1g/status/1163218564784017422',
'only_matching': True, 'only_matching': True,
}, {
# promo_video_convo card
'url': 'https://twitter.com/poco_dandy/status/1047395834013384704',
'only_matching': True,
}, {
# appplayer card
'url': 'https://twitter.com/poco_dandy/status/1150646424461176832',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -462,7 +471,25 @@ class TwitterIE(TwitterBaseIE):
return try_get(o, lambda x: x[x['type'].lower() + '_value']) return try_get(o, lambda x: x[x['type'].lower() + '_value'])
card_name = card['name'].split(':')[-1] card_name = card['name'].split(':')[-1]
if card_name in ('amplify', 'promo_video_website'): if card_name == 'player':
info.update({
'_type': 'url',
'url': get_binding_value('player_url'),
})
elif card_name == 'periscope_broadcast':
info.update({
'_type': 'url',
'url': get_binding_value('url') or get_binding_value('player_url'),
'ie_key': PeriscopeIE.ie_key(),
})
elif card_name == 'broadcast':
info.update({
'_type': 'url',
'url': get_binding_value('broadcast_url'),
'ie_key': TwitterBroadcastIE.ie_key(),
})
# amplify, promo_video_website, promo_video_convo, appplayer, ...
else:
is_amplify = card_name == 'amplify' is_amplify = card_name == 'amplify'
vmap_url = get_binding_value('amplify_url_vmap') if is_amplify else get_binding_value('player_stream_url') vmap_url = get_binding_value('amplify_url_vmap') if is_amplify else get_binding_value('player_stream_url')
content_id = get_binding_value('%s_content_id' % (card_name if is_amplify else 'player')) content_id = get_binding_value('%s_content_id' % (card_name if is_amplify else 'player'))
@ -488,25 +515,6 @@ class TwitterIE(TwitterBaseIE):
'duration': int_or_none(get_binding_value( 'duration': int_or_none(get_binding_value(
'content_duration_seconds')), 'content_duration_seconds')),
}) })
elif card_name == 'player':
info.update({
'_type': 'url',
'url': get_binding_value('player_url'),
})
elif card_name == 'periscope_broadcast':
info.update({
'_type': 'url',
'url': get_binding_value('url') or get_binding_value('player_url'),
'ie_key': PeriscopeIE.ie_key(),
})
elif card_name == 'broadcast':
info.update({
'_type': 'url',
'url': get_binding_value('broadcast_url'),
'ie_key': TwitterBroadcastIE.ie_key(),
})
else:
raise ExtractorError('Unsupported Twitter Card.')
else: else:
expanded_url = try_get(status, lambda x: x['entities']['urls'][0]['expanded_url']) expanded_url = try_get(status, lambda x: x['entities']['urls'][0]['expanded_url'])
if not expanded_url: if not expanded_url: