mirror/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-03-09 12:50:23 -05:00
Code Activity

Only download specific video if --no-playlist, and add support user story URL without story_id

Browse source
This commit is contained in:
fireattack 2025-02-19 16:55:44 +08:00
parent 4492b66add
commit 373147bf9c
1 changed files with 22 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
yt_dlp/extractor/instagram.py
View file

@ -689,7 +689,7 @@ def _query_vars_for(data):
class InstagramStoryIE(InstagramBaseIE): class InstagramStoryIE(InstagramBaseIE):
_VALID_URL = r'https?://(?:www\.)?instagram\.com/stories/(?P<user>[^/]+)/(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?instagram\.com/stories/(?P<user>[^/]+)(?:/(?P<id>\d+))?'
IE_NAME = 'instagram:story' IE_NAME = 'instagram:story'
_TESTS = [{ _TESTS = [{
@ -699,23 +699,34 @@ class InstagramStoryIE(InstagramBaseIE):
'title': 'Rare', 'title': 'Rare',
}, },
'playlist_mincount': 50, 'playlist_mincount': 50,
}, {
'url': 'https://www.instagram.com/stories/fruits_zipper/3570766765028588805/',
'only_matching': True,
}, {
'url': 'https://www.instagram.com/stories/fruits_zipper',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
username, story_id = self._match_valid_url(url).groups() username, story_id = self._match_valid_url(url).groups()
story_info = self._download_webpage(url, story_id) story_info = self._download_webpage(url, story_id or username)
user_info = self._search_json(r'"user":', story_info, 'user info', story_id, fatal=False) user_info = self._search_json(r'"user":', story_info, 'user info', story_id or username, fatal=False)
if not user_info: if not user_info:
self.raise_login_required('This content is unreachable') self.raise_login_required('This content is unreachable')
user_id = traverse_obj(user_info, 'pk', 'id', expected_type=str) 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 username == 'highlights':
if not story_info_url: # user id is only mandatory for non-highlights story_info_url = f'highlight:{story_id}'
raise ExtractorError('Unable to extract user id') if not story_id: # story id is only mandatory for highlights
raise ExtractorError('Missing highlight id')
else:
if not user_id: # user id is only mandatory for non-highlights
raise ExtractorError('Unable to extract user id')
story_info_url = user_id
videos = traverse_obj(self._download_json( videos = traverse_obj(self._download_json(
f'{self._API_BASE_URL}/feed/reels_media/?reel_ids={story_info_url}', f'{self._API_BASE_URL}/feed/reels_media/?reel_ids={story_info_url}',
story_id, errnote=False, fatal=False, headers=self._API_HEADERS), 'reels') story_id or username, errnote=False, fatal=False, headers=self._API_HEADERS), 'reels')
if not videos: if not videos:
self.raise_login_required('You need to log in to access this content') self.raise_login_required('You need to log in to access this content')
@ -724,7 +735,7 @@ def _real_extract(self, url):
if not story_title: if not story_title:
story_title = f'Story by {username}' story_title = f'Story by {username}'
highlights = traverse_obj(videos, (f'highlight:{story_id}', 'items'), (user_id, 'items', lambda _, v: v['pk'] == story_id)) highlights = traverse_obj(videos, (f'highlight:{story_id}', 'items'), (user_id, 'items'))
info_data = [] info_data = []
for highlight in highlights: for highlight in highlights:
highlight_data = self._extract_product(highlight) highlight_data = self._extract_product(highlight)
@ -734,4 +745,7 @@ def _real_extract(self, url):
'uploader_id': user_id, 'uploader_id': user_id,
**filter_dict(highlight_data), **filter_dict(highlight_data),
}) })
if username != 'highlights' and story_id and not self._yes_playlist(story_title, story_id):
return traverse_obj(info_data, (lambda _, v: v['id'] == _pk_to_id(story_id), any))
return self.playlist_result(info_data, playlist_id=story_id, playlist_title=story_title) return self.playlist_result(info_data, playlist_id=story_id, playlist_title=story_title)