github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[twitter] Improve uploader id extraction (closes #21705)

Browse source
This commit is contained in:
Sergey M․ 2019-07-14 01:19:17 +07:00
parent f9eeeda31c
commit b7ef93f0ab
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 19 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
youtube_dl/extractor/twitter.py
View file

@ -428,11 +428,22 @@ class TwitterIE(InfoExtractor):
'params': { 'params': {
'skip_download': True, # requires ffmpeg 'skip_download': True, # requires ffmpeg
}, },
}, {
'url': 'https://twitter.com/foobar/status/1087791357756956680',
'info_dict': {
'id': '1087791357756956680',
'ext': 'mp4',
'title': 'Twitter - A new is coming. Some of you got an opt-in to try it now. Check out the emoji button, quick keyboard shortcuts, upgraded trends, advanced search, and more. Let us know your thoughts!',
'thumbnail': r're:^https?://.*\.jpg',
'description': 'md5:66d493500c013e3e2d434195746a7f78',
'uploader': 'Twitter',
'uploader_id': 'Twitter',
'duration': 61.567,
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('user_id')
twid = mobj.group('id') twid = mobj.group('id')
webpage, urlh = self._download_webpage_handle( webpage, urlh = self._download_webpage_handle(
@ -441,8 +452,13 @@ def _real_extract(self, url):
if 'twitter.com/account/suspended' in urlh.geturl(): if 'twitter.com/account/suspended' in urlh.geturl():
raise ExtractorError('Account suspended by Twitter.', expected=True) raise ExtractorError('Account suspended by Twitter.', expected=True)
if user_id is None: user_id = None
mobj = re.match(self._VALID_URL, urlh.geturl())
redirect_mobj = re.match(self._VALID_URL, urlh.geturl())
if redirect_mobj:
user_id = redirect_mobj.group('user_id')
if not user_id:
user_id = mobj.group('user_id') user_id = mobj.group('user_id')
username = remove_end(self._og_search_title(webpage), ' on Twitter') username = remove_end(self._og_search_title(webpage), ' on Twitter')