mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-30 14:20:46 -05:00
[twitter] Don't check /cards/ URLs
Fixes #9181 In this tweet, there are two cards: 1. https://twitter.com/i/cards/tfw/v1/719944006306701313 This shows #TeamCap vs. #TeamIronMan 2. https://twitter.com/i/videos/tweet/719944021058060289 This is the real video and can be handled by TwitterCardIE In all current test_Twitter* tests, /videos/tweet/ approach works fine.
This commit is contained in:
parent
8c65e4a527
commit
36b7d9dbfa
1 changed files with 11 additions and 11 deletions
|
@ -260,6 +260,17 @@ class TwitterIE(InfoExtractor):
|
||||||
'upload_date': '20140615',
|
'upload_date': '20140615',
|
||||||
},
|
},
|
||||||
'add_ie': ['Vine'],
|
'add_ie': ['Vine'],
|
||||||
|
}, {
|
||||||
|
'url': 'https://twitter.com/captainamerica/status/719944021058060289',
|
||||||
|
# md5 constantly changes
|
||||||
|
'info_dict': {
|
||||||
|
'id': '719944021058060289',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Captain America - @King0fNerd Are you sure you made the right choice? Find out in theaters.',
|
||||||
|
'description': 'Captain America on Twitter: "@King0fNerd Are you sure you made the right choice? Find out in theaters. https://t.co/GpgYi9xMJI"',
|
||||||
|
'uploader_id': 'captainamerica',
|
||||||
|
'uploader': 'Captain America',
|
||||||
|
},
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
|
@ -284,17 +295,6 @@ def _real_extract(self, url):
|
||||||
'title': username + ' - ' + title,
|
'title': username + ' - ' + title,
|
||||||
}
|
}
|
||||||
|
|
||||||
card_id = self._search_regex(
|
|
||||||
r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url', default=None)
|
|
||||||
if card_id:
|
|
||||||
card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
|
|
||||||
info.update({
|
|
||||||
'_type': 'url_transparent',
|
|
||||||
'ie_key': 'TwitterCard',
|
|
||||||
'url': card_url,
|
|
||||||
})
|
|
||||||
return info
|
|
||||||
|
|
||||||
mobj = re.search(r'''(?x)
|
mobj = re.search(r'''(?x)
|
||||||
<video[^>]+class="animated-gif"(?P<more_info>[^>]+)>\s*
|
<video[^>]+class="animated-gif"(?P<more_info>[^>]+)>\s*
|
||||||
<source[^>]+video-src="(?P<url>[^"]+)"
|
<source[^>]+video-src="(?P<url>[^"]+)"
|
||||||
|
|
Loading…
Reference in a new issue