mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 18:41:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

[extractor/iprima] Fix extractor (#6291)

Browse source 
Authored by: std-move
Closes #6187
This commit is contained in:
std-move 2023-03-02 19:33:33 +01:00 committed by GitHub
parent b38cae49e6
commit 9fddc12ab0
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 29 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

41
yt_dlp/extractor/iprima.py
View file

@ -7,7 +7,8 @@
js_to_json, js_to_json,
urlencode_postdata, urlencode_postdata,
ExtractorError, ExtractorError,
parse_qs parse_qs,
traverse_obj
) )
@ -15,8 +16,7 @@ class IPrimaIE(InfoExtractor):
_VALID_URL = r'https?://(?!cnn)(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?!cnn)(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_GEO_BYPASS = False _GEO_BYPASS = False
_NETRC_MACHINE = 'iprima' _NETRC_MACHINE = 'iprima'
_LOGIN_URL = 'https://auth.iprima.cz/oauth2/login' _AUTH_ROOT = 'https://auth.iprima.cz'
_TOKEN_URL = 'https://auth.iprima.cz/oauth2/token'
access_token = None access_token = None
_TESTS = [{ _TESTS = [{
@ -67,7 +67,7 @@ def _perform_login(self, username, password):
return return
login_page = self._download_webpage( login_page = self._download_webpage(
self._LOGIN_URL, None, note='Downloading login page', f'{self._AUTH_ROOT}/oauth2/login', None, note='Downloading login page',
errnote='Downloading login page failed') errnote='Downloading login page failed')
login_form = self._hidden_inputs(login_page) login_form = self._hidden_inputs(login_page)
@ -76,11 +76,20 @@ def _perform_login(self, username, password):
'_email': username, '_email': username,
'_password': password}) '_password': password})
_, login_handle = self._download_webpage_handle( profile_select_html, login_handle = self._download_webpage_handle(
self._LOGIN_URL, None, data=urlencode_postdata(login_form), f'{self._AUTH_ROOT}/oauth2/login', None, data=urlencode_postdata(login_form),
note='Logging in') note='Logging in')
code = parse_qs(login_handle.geturl()).get('code')[0] # a profile may need to be selected first, even when there is only a single one
if '/profile-select' in login_handle.geturl():
profile_id = self._search_regex(
r'data-identifier\s*=\s*["\']?(\w+)', profile_select_html, 'profile id')
login_handle = self._request_webpage(
f'{self._AUTH_ROOT}/user/profile-select-perform/{profile_id}', None,
query={'continueUrl': '/user/login?redirect_uri=/user/'}, note='Selecting profile')
code = traverse_obj(login_handle.geturl(), ({parse_qs}, 'code', 0))
if not code: if not code:
raise ExtractorError('Login failed', expected=True) raise ExtractorError('Login failed', expected=True)
@ -89,10 +98,10 @@ def _perform_login(self, username, password):
'client_id': 'prima_sso', 'client_id': 'prima_sso',
'grant_type': 'authorization_code', 'grant_type': 'authorization_code',
'code': code, 'code': code,
'redirect_uri': 'https://auth.iprima.cz/sso/auth-check'} 'redirect_uri': f'{self._AUTH_ROOT}/sso/auth-check'}
token_data = self._download_json( token_data = self._download_json(
self._TOKEN_URL, None, f'{self._AUTH_ROOT}/oauth2/token', None,
note='Downloading token', errnote='Downloading token failed', note='Downloading token', errnote='Downloading token failed',
data=urlencode_postdata(token_request_data)) data=urlencode_postdata(token_request_data))
@ -115,14 +124,22 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_meta( title = self._html_extract_title(webpage) or self._html_search_meta(
['og:title', 'twitter:title'], ['og:title', 'twitter:title'],
webpage, 'title', default=None) webpage, 'title', default=None)
video_id = self._search_regex(( video_id = self._search_regex((
r'productId\s*=\s*([\'"])(?P<id>p\d+)\1', r'productId\s*=\s*([\'"])(?P<id>p\d+)\1',
r'pproduct_id\s*=\s*([\'"])(?P<id>p\d+)\1'), r'pproduct_id\s*=\s*([\'"])(?P<id>p\d+)\1',
webpage, 'real id', group='id') ), webpage, 'real id', group='id', default=None)
if not video_id:
nuxt_data = self._search_nuxt_data(webpage, video_id, traverse='data')
video_id = traverse_obj(
nuxt_data, (..., 'content', 'additionals', 'videoPlayId', {str}), get_all=False)
if not video_id:
self.raise_no_formats('Unable to extract video ID from webpage')
metadata = self._download_json( metadata = self._download_json(
f'https://api.play-backend.iprima.cz/api/v1//products/id-{video_id}/play', f'https://api.play-backend.iprima.cz/api/v1//products/id-{video_id}/play',