mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-10 10:23:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

[extractor/instagram] Fix bugs in 7d3b98be4c (#4701)

Browse source 
Authored by: bashonly
This commit is contained in:
bashonly 2022-08-18 22:15:49 +00:00 committed by GitHub
parent 4d37d4a77c
commit 8a3da4c68c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
yt_dlp/extractor/instagram.py
View file

@ -378,12 +378,12 @@ def _real_extract(self, url):
self.report_warning('Instagram API is not granting access', video_id) self.report_warning('Instagram API is not granting access', video_id)
else: else:
if self._get_cookies(url).get('sessionid'): if self._get_cookies(url).get('sessionid'):
media = traverse_obj(self._download_json( media.update(traverse_obj(self._download_json(
f'{self._API_BASE_URL}/media/{_id_to_pk(video_id)}/info/', video_id, f'{self._API_BASE_URL}/media/{_id_to_pk(video_id)}/info/', video_id,
fatal=False, note='Downloading video info', headers={ fatal=False, note='Downloading video info', headers={
**self._API_HEADERS, **self._API_HEADERS,
'X-CSRFToken': csrf_token.value, 'X-CSRFToken': csrf_token.value,
}), ('items', 0)) }), ('items', 0)) or {})
if media: if media:
return self._extract_product(media) return self._extract_product(media)
@ -405,15 +405,15 @@ def _real_extract(self, url):
'query_hash': '9f8827793ef34641b2fb195d4d41151c', 'query_hash': '9f8827793ef34641b2fb195d4d41151c',
'variables': json.dumps(variables, separators=(',', ':')), 'variables': json.dumps(variables, separators=(',', ':')),
}) })
media = traverse_obj(general_info, ('data', 'shortcode_media')) media.update(traverse_obj(general_info, ('data', 'shortcode_media')) or {})
if not media: if not media:
self.report_warning('General metadata extraction failed (some metadata might be missing).', video_id) self.report_warning('General metadata extraction failed (some metadata might be missing).', video_id)
webpage, urlh = self._download_webpage_handle(url, video_id) webpage, urlh = self._download_webpage_handle(url, video_id)
shared_data = self._search_json( shared_data = self._search_json(
r'window\._sharedData\s*=', webpage, 'shared data', video_id, fatal=False) r'window\._sharedData\s*=', webpage, 'shared data', video_id, fatal=False) or {}
if self._LOGIN_URL not in urlh.geturl(): if shared_data and self._LOGIN_URL not in urlh.geturl():
media.update(traverse_obj( media.update(traverse_obj(
shared_data, ('entry_data', 'PostPage', 0, 'graphql', 'shortcode_media'), shared_data, ('entry_data', 'PostPage', 0, 'graphql', 'shortcode_media'),
('entry_data', 'PostPage', 0, 'media'), expected_type=dict) or {}) ('entry_data', 'PostPage', 0, 'media'), expected_type=dict) or {})
@ -424,7 +424,7 @@ def _real_extract(self, url):
additional_data = self._search_json( additional_data = self._search_json(
r'window\.__additionalDataLoaded\s*\(\s*[^,]+,\s*', webpage, 'additional data', video_id, fatal=False) r'window\.__additionalDataLoaded\s*\(\s*[^,]+,\s*', webpage, 'additional data', video_id, fatal=False)
if not additional_data: if not additional_data:
self.raise_login_required('Requested content was not found, the content might be private') self.raise_login_required('Requested content is not available, rate-limit reached or login required')
product_item = traverse_obj(additional_data, ('items', 0), expected_type=dict) product_item = traverse_obj(additional_data, ('items', 0), expected_type=dict)
if product_item: if product_item: