github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[instagram] Fix extractor

Browse source
This commit is contained in:
The Hatsune Daishi 2020-11-06 15:15:07 +09:00 committed by GitHub
parent adb118da26
commit 987d2e079a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 14 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
youtube_dlc/extractor/instagram.py
View file

@ -126,16 +126,23 @@ def _real_extract(self, url):
uploader_id, like_count, comment_count, comments, height,
width) = [None] * 11
shared_data = self._parse_json(
self._search_regex(
r'window\._sharedData\s*=\s*({.+?});',
webpage, 'shared data', default='{}'),
video_id, fatal=False)
shared_data = try_get(webpage,
(lambda x: self._parse_json(
self._search_regex(
r'window\.__additionalDataLoaded\(\'/(?:p|tv)/(?:[^/?#&]+)/\',({.+?})\);',
x, 'additional data', default='{}'),
video_id, fatal=False),
lambda x: self._parse_json(
self._search_regex(
r'window\._sharedData\s*=\s*({.+?});',
x, 'shared data', default='{}'),
video_id, fatal=False)['entry_data']['PostPage'][0]),
None)
if shared_data:
media = try_get(
shared_data,
(lambda x: x['entry_data']['PostPage'][0]['graphql']['shortcode_media'],
lambda x: x['entry_data']['PostPage'][0]['media']),
(lambda x: x['graphql']['shortcode_media'],
lambda x: x['media']),
dict)
if media:
video_url = media.get('video_url')