From cae6e461073fb7c32fd32052a3e6721447c469bc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=BCndig?= Date: Sun, 28 Jan 2024 03:19:54 +0100 Subject: [PATCH] [ie/PlaySuisse] Add login support (#9077) Closes #7974 Authored by: chkuendig --- yt_dlp/extractor/playsuisse.py | 53 ++++++++++++++++++++++++++++++++-- 1 file changed, 50 insertions(+), 3 deletions(-) diff --git a/yt_dlp/extractor/playsuisse.py b/yt_dlp/extractor/playsuisse.py index 76288c778..7c5cad1be 100644 --- a/yt_dlp/extractor/playsuisse.py +++ b/yt_dlp/extractor/playsuisse.py @@ -1,10 +1,18 @@ import json from .common import InfoExtractor -from ..utils import int_or_none, traverse_obj +from ..utils import ( + ExtractorError, + int_or_none, + parse_qs, + traverse_obj, + update_url_query, + urlencode_postdata, +) class PlaySuisseIE(InfoExtractor): + _NETRC_MACHINE = 'playsuisse' _VALID_URL = r'https?://(?:www\.)?playsuisse\.ch/(?:watch|detail)/(?:[^#]*[?&]episodeId=)?(?P[0-9]+)' _TESTS = [ { @@ -134,12 +142,47 @@ class PlaySuisseIE(InfoExtractor): id url }''' + _LOGIN_BASE_URL = 'https://login.srgssr.ch/srgssrlogin.onmicrosoft.com' + _LOGIN_PATH = 'B2C_1A__SignInV2' + _ID_TOKEN = None + + def _perform_login(self, username, password): + login_page = self._download_webpage( + 'https://www.playsuisse.ch/api/sso/login', None, note='Downloading login page', + query={'x': 'x', 'locale': 'de', 'redirectUrl': 'https://www.playsuisse.ch/'}) + settings = self._search_json(r'var\s+SETTINGS\s*=', login_page, 'settings', None) + + csrf_token = settings['csrf'] + query = {'tx': settings['transId'], 'p': self._LOGIN_PATH} + + status = traverse_obj(self._download_json( + f'{self._LOGIN_BASE_URL}/{self._LOGIN_PATH}/SelfAsserted', None, 'Logging in', + query=query, headers={'X-CSRF-TOKEN': csrf_token}, data=urlencode_postdata({ + 'request_type': 'RESPONSE', + 'signInName': username, + 'password': password + }), expected_status=400), ('status', {int_or_none})) + if status == 400: + raise ExtractorError('Invalid username or password', expected=True) + + urlh = self._request_webpage( + f'{self._LOGIN_BASE_URL}/{self._LOGIN_PATH}/api/CombinedSigninAndSignup/confirmed', + None, 'Downloading ID token', query={ + 'rememberMe': 'false', + 'csrf_token': csrf_token, + **query, + 'diags': '', + }) + + self._ID_TOKEN = traverse_obj(parse_qs(urlh.url), ('id_token', 0)) + if not self._ID_TOKEN: + raise ExtractorError('Login failed') def _get_media_data(self, media_id): # NOTE In the web app, the "locale" header is used to switch between languages, # However this doesn't seem to take effect when passing the header here. response = self._download_json( - 'https://4bbepzm4ef.execute-api.eu-central-1.amazonaws.com/prod/graphql', + 'https://www.playsuisse.ch/api/graphql', media_id, data=json.dumps({ 'operationName': 'AssetWatch', 'query': self._GRAPHQL_QUERY, @@ -150,6 +193,9 @@ def _get_media_data(self, media_id): return response['data']['assetV2'] def _real_extract(self, url): + if not self._ID_TOKEN: + self.raise_login_required(method='password') + media_id = self._match_id(url) media_data = self._get_media_data(media_id) info = self._extract_single(media_data) @@ -168,7 +214,8 @@ def _extract_single(self, media_data): if not media.get('url') or media.get('type') != 'HLS': continue f, subs = self._extract_m3u8_formats_and_subtitles( - media['url'], media_data['id'], 'mp4', m3u8_id='HLS', fatal=False) + update_url_query(media['url'], {'id_token': self._ID_TOKEN}), + media_data['id'], 'mp4', m3u8_id='HLS', fatal=False) formats.extend(f) self._merge_subtitles(subs, target=subtitles)