Merge 5579d7902d into 404bd889d0

yt_dlp/extractor/_extractors.py

@@ -2323,6 +2323,7 @@ from .vgtv import (
     BTVestlendingenIE,
 )
 from .vh1 import VH1IE
+from .viacomcbs import ViacomcbsIE
 from .vice import (
     ViceArticleIE,
     ViceIE,

yt_dlp/extractor/southpark.py

@@ -1,4 +1,5 @@
 from .mtv import MTVServicesInfoExtractor
+from .viacomcbs import ViacomcbsIE
 
 
 class SouthParkIE(MTVServicesInfoExtractor):
@@ -50,7 +51,7 @@ class SouthParkEsIE(SouthParkIE):  # XXX: Do not subclass from concrete IE
     }]
 
 
-class SouthParkDeIE(SouthParkIE):  # XXX: Do not subclass from concrete IE
+class SouthParkDeIE(ViacomcbsIE):
     IE_NAME = 'southpark.de'
     _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.de/(?:(en/(videoclip|collections|episodes|video-clips))|(videoclip|collections|folgen))/(?P<id>(?P<unique_id>.+?)/.+?)(?:\?|#|$))'
     _TESTS = [{

yt_dlp/extractor/viacomcbs.py

@@ -0,0 +1,28 @@
+from yt_dlp.utils.traversal import traverse_obj
+
+from .common import InfoExtractor
+
+
+class ViacomcbsIE(InfoExtractor):
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        mgid = self._html_search_regex(r'\"videoServiceUrl\":.*(mgid[\w:\.\-]+).*mica.*json', webpage, 'mgid')
+        title = self._html_search_regex(r'\"shortTitle\":\"([\w\s]+)\"', webpage, 'title')
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(self._get_video_url(mgid, video_id), video_id)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+    def _get_video_url(self, mgid, video_id):
+        config = self._download_json(
+            f'https://topaz.viacomcbs.digital/topaz/api/{mgid}/mica.json?clientPlatform=desktop', video_id)
+        return traverse_obj(config, ('stitchedstream', 'source'))