commit: b7ef93f0ab2963047953be1472a5a108d92b621c
parent f9eeeda31c1a643aced8283440983f3a45208840
Author: Sergey M․ <dstftw@gmail.com>
Date: Sun, 14 Jul 2019 01:19:17 +0700
[twitter] Improve uploader id extraction (closes #21705)
Diffstat:
1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py
@@ -428,11 +428,22 @@ class TwitterIE(InfoExtractor):
'params': {
'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):
mobj = re.match(self._VALID_URL, url)
- user_id = mobj.group('user_id')
twid = mobj.group('id')
webpage, urlh = self._download_webpage_handle(
@@ -441,8 +452,13 @@ class TwitterIE(InfoExtractor):
if 'twitter.com/account/suspended' in urlh.geturl():
raise ExtractorError('Account suspended by Twitter.', expected=True)
- if user_id is None:
- mobj = re.match(self._VALID_URL, urlh.geturl())
+ user_id = None
+
+ 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')
username = remove_end(self._og_search_title(webpage), ' on Twitter')