[ie/ard:mediathek] Support cookies to verify age (#9037)

Closes #9035
Authored by: StefanLobbenmeier
This commit is contained in:
Stefan Lobbenmeier 2024-01-21 21:54:11 +01:00 committed by GitHub
parent c0ecceeefe
commit c099ec9392
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -8,6 +8,7 @@ from ..utils import (
determine_ext, determine_ext,
int_or_none, int_or_none,
join_nonempty, join_nonempty,
jwt_decode_hs256,
make_archive_id, make_archive_id,
parse_duration, parse_duration,
parse_iso8601, parse_iso8601,
@ -238,6 +239,7 @@ class ARDBetaMediathekIE(InfoExtractor):
(?P<id>[a-zA-Z0-9]+) (?P<id>[a-zA-Z0-9]+)
/?(?:[?#]|$)''' /?(?:[?#]|$)'''
_GEO_COUNTRIES = ['DE'] _GEO_COUNTRIES = ['DE']
_TOKEN_URL = 'https://sso.ardmediathek.de/sso/token'
_TESTS = [{ _TESTS = [{
'url': 'https://www.ardmediathek.de/video/filme-im-mdr/liebe-auf-vier-pfoten/mdr-fernsehen/Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0', 'url': 'https://www.ardmediathek.de/video/filme-im-mdr/liebe-auf-vier-pfoten/mdr-fernsehen/Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0',
@ -359,12 +361,27 @@ class ARDBetaMediathekIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
query = {'embedded': 'false', 'mcV6': 'true'}
headers = {}
if self._get_cookies(self._TOKEN_URL).get('ams'):
token = self._download_json(
self._TOKEN_URL, display_id, 'Fetching token for age verification',
'Unable to fetch age verification token', fatal=False)
id_token = traverse_obj(token, ('idToken', {str}))
decoded_token = traverse_obj(id_token, ({jwt_decode_hs256}, {dict}))
user_id = traverse_obj(decoded_token, (('user_id', 'sub'), {str}), get_all=False)
if not user_id:
self.report_warning('Unable to extract token, continuing without authentication')
else:
headers['x-authorization'] = f'Bearer {id_token}'
query['userId'] = user_id
if decoded_token.get('age_rating') != 18:
self.report_warning('Account is not verified as 18+; video may be unavailable')
page_data = self._download_json( page_data = self._download_json(
f'https://api.ardmediathek.de/page-gateway/pages/ard/item/{display_id}', display_id, query={ f'https://api.ardmediathek.de/page-gateway/pages/ard/item/{display_id}',
'embedded': 'false', display_id, query=query, headers=headers)
'mcV6': 'true',
})
# For user convenience we use the old contentId instead of the longer crid # For user convenience we use the old contentId instead of the longer crid
# Ref: https://github.com/yt-dlp/yt-dlp/issues/8731#issuecomment-1874398283 # Ref: https://github.com/yt-dlp/yt-dlp/issues/8731#issuecomment-1874398283
@ -383,7 +400,7 @@ class ARDBetaMediathekIE(InfoExtractor):
media_data = traverse_obj(player_data, ('mediaCollection', 'embedded', {dict})) media_data = traverse_obj(player_data, ('mediaCollection', 'embedded', {dict}))
if player_data.get('blockedByFsk'): if player_data.get('blockedByFsk'):
self.raise_no_formats('This video is only available after 22:00', expected=True) self.raise_login_required('This video is only available for age verified users or after 22:00')
formats = [] formats = []
subtitles = {} subtitles = {}