mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 12:01:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

[ie/instagram] Fix stories extraction (#8843)

Browse source 
Closes #8290
Authored by: bashonly
This commit is contained in:
bashonly 2023-12-24 10:40:03 -06:00 committed by GitHub
parent f45c4efcd9
commit 50eaea9fd7
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
yt_dlp/extractor/instagram.py
View file

@ -10,6 +10,7 @@
ExtractorError,
decode_base_n,
encode_base_n,
filter_dict,
float_or_none,
format_field,
get_element_by_attribute,
@ -703,28 +704,31 @@ def _real_extract(self, url):
user_info = self._search_json(r'"user":', story_info, 'user info', story_id, fatal=False)
if not user_info:
self.raise_login_required('This content is unreachable')
user_id = user_info.get('id')
user_id = traverse_obj(user_info, 'pk', 'id', expected_type=str)
story_info_url = user_id if username != 'highlights' else f'highlight:{story_id}'
if not story_info_url: # user id is only mandatory for non-highlights
raise ExtractorError('Unable to extract user id')
videos = traverse_obj(self._download_json(
f'{self._API_BASE_URL}/feed/reels_media/?reel_ids={story_info_url}',
story_id, errnote=False, fatal=False, headers=self._API_HEADERS), 'reels')
if not videos:
self.raise_login_required('You need to log in to access this content')
full_name = traverse_obj(videos, (f'highlight:{story_id}', 'user', 'full_name'), (str(user_id), 'user', 'full_name'))
full_name = traverse_obj(videos, (f'highlight:{story_id}', 'user', 'full_name'), (user_id, 'user', 'full_name'))
story_title = traverse_obj(videos, (f'highlight:{story_id}', 'title'))
if not story_title:
story_title = f'Story by {username}'
highlights = traverse_obj(videos, (f'highlight:{story_id}', 'items'), (str(user_id), 'items'))
highlights = traverse_obj(videos, (f'highlight:{story_id}', 'items'), (user_id, 'items'))
info_data = []
for highlight in highlights:
highlight_data = self._extract_product(highlight)
if highlight_data.get('formats'):
info_data.append({
**highlight_data,
'uploader': full_name,
'uploader_id': user_id,
**filter_dict(highlight_data),
})
return self.playlist_result(info_data, playlist_id=story_id, playlist_title=story_title)