[ie/matchtv] Fix extractor (#10190)

[yt-dlp.git] / yt_dlp / extractor / playsuisse.py

diff --git a/yt_dlp/extractor/playsuisse.py b/yt_dlp/extractor/playsuisse.py
index 76288c7789e28ffc58155eecf17ca9ca16b3f8ca..905f8fc2f6673d13ba13d536deb8ae49eb5c2835 100644 (file)
--- 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<id>[0-9]+)'
     _TESTS = [
         {
@@ -28,7 +36,7 @@ class PlaySuisseIE(InfoExtractor):
                 'episode': 'Knochen',
                 'episode_number': 1,
                 'thumbnail': 're:https://playsuisse-img.akamaized.net/',
-            }
+            },
         }, {
             # film
             'url': 'https://www.playsuisse.ch/watch/808675',
@@ -40,7 +48,7 @@ class PlaySuisseIE(InfoExtractor):
                 'description': 'md5:9f61265c7e6dcc3e046137a792b275fd',
                 'duration': 5280,
                 'thumbnail': 're:https://playsuisse-img.akamaized.net/',
-            }
+            },
         }, {
             # series (treated as a playlist)
             'url': 'https://www.playsuisse.ch/detail/1115687',
@@ -62,7 +70,7 @@ class PlaySuisseIE(InfoExtractor):
                     'series': 'They all came out to Montreux',
                     'thumbnail': 're:https://playsuisse-img.akamaized.net/',
                     'title': 'Folge 1',
-                    'ext': 'mp4'
+                    'ext': 'mp4',
                 },
             }, {
                 'info_dict': {
@@ -76,7 +84,7 @@ class PlaySuisseIE(InfoExtractor):
                     'series': 'They all came out to Montreux',
                     'thumbnail': 're:https://playsuisse-img.akamaized.net/',
                     'title': 'Folge 2',
-                    'ext': 'mp4'
+                    'ext': 'mp4',
                 },
             }, {
                 'info_dict': {
@@ -90,10 +98,10 @@ class PlaySuisseIE(InfoExtractor):
                     'series': 'They all came out to Montreux',
                     'thumbnail': 're:https://playsuisse-img.akamaized.net/',
                     'title': 'Folge 3',
-                    'ext': 'mp4'
-                }
+                    'ext': 'mp4',
+                },
             }],
-        }
+        },
     ]
 
     _GRAPHQL_QUERY = '''
@@ -134,22 +142,60 @@ 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,
-                'variables': {'assetId': media_id}
-            }).encode('utf-8'),
+                'variables': {'assetId': media_id},
+            }).encode(),
             headers={'Content-Type': 'application/json', 'locale': 'de'})
 
         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)