[ie/DiscoveryNetworksDe] Restore original display_id (#14958)

Fix 10dea209d2

Authored by: bashonly

.github/workflows/build.yml

@@ -153,10 +153,12 @@ jobs:
                   'os': 'musllinux',
                   'arch': 'x86_64',
                   'runner': 'ubuntu-24.04',
+                  'python_version': '3.14',
               }, {
                   'os': 'musllinux',
                   'arch': 'aarch64',
                   'runner': 'ubuntu-24.04-arm',
+                  'python_version': '3.14',
               }],
           }
           INPUTS = json.loads(os.environ['INPUTS'])

yt_dlp/extractor/_extractors.py

@@ -1197,6 +1197,7 @@
     MusicdexPlaylistIE,
     MusicdexSongIE,
 )
+from .mux import MuxIE
 from .mx3 import (
     Mx3IE,
     Mx3NeoIE,

yt_dlp/extractor/bunnycdn.py

@@ -39,7 +39,7 @@ class BunnyCdnIE(InfoExtractor):
             'timestamp': 1691145748,
             'thumbnail': r're:^https?://.*\.b-cdn\.net/32e34c4b-0d72-437c-9abb-05e67657da34/thumbnail_9172dc16\.jpg',
             'duration': 106.0,
-            'description': 'md5:981a3e899a5c78352b21ed8b2f1efd81',
+            'description': 'md5:11452bcb31f379ee3eaf1234d3264e44',
             'upload_date': '20230804',
             'title': 'Sanela ist Teil der #arbeitsmarktkraft',
         },
@@ -58,6 +58,20 @@ class BunnyCdnIE(InfoExtractor):
             'thumbnail': r're:^https?://.*\.b-cdn\.net/2e8545ec-509d-4571-b855-4cf0235ccd75/thumbnail\.jpg',
         },
         'params': {'skip_download': True},
+    }, {
+        # Requires any Referer
+        'url': 'https://iframe.mediadelivery.net/embed/289162/6372f5a3-68df-4ef7-a115-e1110186c477',
+        'info_dict': {
+            'id': '6372f5a3-68df-4ef7-a115-e1110186c477',
+            'ext': 'mp4',
+            'title': '12-Creating Small Asset Blockouts -Timelapse.mp4',
+            'description': '',
+            'duration': 263.0,
+            'timestamp': 1724485440,
+            'upload_date': '20240824',
+            'thumbnail': r're:^https?://.*\.b-cdn\.net/6372f5a3-68df-4ef7-a115-e1110186c477/thumbnail\.jpg',
+        },
+        'params': {'skip_download': True},
     }]
     _WEBPAGE_TESTS = [{
         # Stream requires Referer
@@ -100,7 +114,7 @@ def _real_extract(self, url):
         video_id, library_id = self._match_valid_url(url).group('id', 'library_id')
         webpage = self._download_webpage(
             f'https://iframe.mediadelivery.net/embed/{library_id}/{video_id}', video_id,
-            headers=traverse_obj(smuggled_data, {'Referer': 'Referer'}),
+            headers={'Referer': smuggled_data.get('Referer') or 'https://iframe.mediadelivery.net/'},
             query=traverse_obj(parse_qs(url), {'token': 'token', 'expires': 'expires'}))
 
         if html_title := self._html_extract_title(webpage, default=None) == '403':

yt_dlp/extractor/dplay.py

@@ -1063,7 +1063,7 @@ class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
             'ext': 'mp4',
             'title': 'German Gold',
             'description': 'md5:f3073306553a8d9b40e6ac4cdbf09fc6',
-            'display_id': 'german-gold',
+            'display_id': 'goldrausch-in-australien/german-gold',
             'episode': 'Episode 1',
             'episode_number': 1,
             'season': 'Season 5',
@@ -1112,7 +1112,7 @@ class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
             'ext': 'mp4',
             'title': '24 Stunden auf der Feuerwache 3',
             'description': 'md5:f3084ef6170bfb79f9a6e0c030e09330',
-            'display_id': '24-stunden-auf-der-feuerwache-3',
+            'display_id': 'feuerwache-3-alarm-in-muenchen/24-stunden-auf-der-feuerwache-3',
             'episode': 'Episode 1',
             'episode_number': 1,
             'season': 'Season 1',
@@ -1134,7 +1134,7 @@ class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
             'ext': 'mp4',
             'title': 'Der Poltergeist im Kostümladen',
             'description': 'md5:20b52b9736a0a3a7873d19a238fad7fc',
-            'display_id': 'der-poltergeist-im-kostumladen',
+            'display_id': 'ghost-adventures/der-poltergeist-im-kostumladen',
             'episode': 'Episode 1',
             'episode_number': 1,
             'season': 'Season 25',
@@ -1156,7 +1156,7 @@ class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
             'ext': 'mp4',
             'title': 'Das Geheimnis meines Bruders',
             'description': 'md5:3167550bb582eb9c92875c86a0a20882',
-            'display_id': 'das-geheimnis-meines-bruders',
+            'display_id': 'evil-gesichter-des-boesen/das-geheimnis-meines-bruders',
             'episode': 'Episode 1',
             'episode_number': 1,
             'season': 'Season 1',
@@ -1175,18 +1175,19 @@ class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
 
     def _real_extract(self, url):
         domain, programme, alternate_id = self._match_valid_url(url).groups()
+        display_id = f'{programme}/{alternate_id}'
         meta = self._download_json(
             f'https://de-api.loma-cms.com/feloma/videos/{alternate_id}/',
-            alternate_id, query={
+            display_id, query={
                 'environment': domain.split('.')[0],
                 'v': '2',
                 'filter[show.slug]': programme,
             }, fatal=False)
-        video_id = traverse_obj(meta, ('uid', {str}, {lambda s: s[-7:]})) or alternate_id
+        video_id = traverse_obj(meta, ('uid', {str}, {lambda s: s[-7:]})) or display_id
 
         disco_api_info = self._get_disco_api_info(
             url, video_id, 'eu1-prod.disco-api.com', domain.replace('.', ''), 'DE')
-        disco_api_info['display_id'] = alternate_id
+        disco_api_info['display_id'] = display_id
         disco_api_info['categories'] = traverse_obj(meta, (
             'taxonomies', lambda _, v: v['category'] == 'genre', 'title', {str.strip}, filter, all, filter))
 

yt_dlp/extractor/mux.py

@@ -0,0 +1,92 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    extract_attributes,
+    filter_dict,
+    parse_qs,
+    smuggle_url,
+    unsmuggle_url,
+    update_url_query,
+)
+from ..utils.traversal import traverse_obj
+
+
+class MuxIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:stream\.new/v|player\.mux\.com)/(?P<id>[A-Za-z0-9-]+)'
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:stream\.new/v|player\.mux\.com)/(?P<id>[A-Za-z0-9-]+)[^"\']+)']
+    _TESTS = [{
+        'url': 'https://stream.new/v/OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j/embed',
+        'info_dict': {
+            'ext': 'mp4',
+            'id': 'OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
+            'title': 'OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
+        },
+    }, {
+        'url': 'https://player.mux.com/OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
+        'info_dict': {
+            'ext': 'mp4',
+            'id': 'OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
+            'title': 'OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
+        },
+    }]
+    _WEBPAGE_TESTS = [{
+        # iframe embed
+        'url': 'https://www.redbrickai.com/blog/2025-07-14-FAST-brush',
+        'info_dict': {
+            'ext': 'mp4',
+            'id': 'cXhzAiW1AmsHY01eRbEYFcTEAn0102aGN8sbt8JprP6Dfw',
+            'title': 'cXhzAiW1AmsHY01eRbEYFcTEAn0102aGN8sbt8JprP6Dfw',
+        },
+    }, {
+        # mux-player embed
+        'url': 'https://muxvideo.2coders.com/download/',
+        'info_dict': {
+            'ext': 'mp4',
+            'id': 'JBuasdg35Hw7tYmTe9k68QLPQKixL300YsWHDz5Flit8',
+            'title': 'JBuasdg35Hw7tYmTe9k68QLPQKixL300YsWHDz5Flit8',
+        },
+    }, {
+        # mux-player with title metadata
+        'url': 'https://datastar-todomvc.cross.stream/',
+        'info_dict': {
+            'ext': 'mp4',
+            'id': 'KX01ZSZ8CXv5SVfVwMZKJTcuBcUQmo1ReS9U5JjoHm4k',
+            'title': 'TodoMVC with Datastar Tutorial',
+        },
+    }]
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        yield from super()._extract_embed_urls(url, webpage)
+        for mux_player in re.findall(r'<mux-(?:player|video)\b[^>]*\bplayback-id=[^>]+>', webpage):
+            attrs = extract_attributes(mux_player)
+            playback_id = attrs.get('playback-id')
+            if not playback_id:
+                continue
+            token = attrs.get('playback-token') or traverse_obj(playback_id, ({parse_qs}, 'token', -1))
+            playback_id = playback_id.partition('?')[0]
+
+            embed_url = update_url_query(
+                f'https://player.mux.com/{playback_id}',
+                filter_dict({'playback-token': token}))
+            if title := attrs.get('metadata-video-title'):
+                embed_url = smuggle_url(embed_url, {'title': title})
+            yield embed_url
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        video_id = self._match_id(url)
+
+        token = traverse_obj(parse_qs(url), ('playback-token', -1))
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            f'https://stream.mux.com/{video_id}.m3u8', video_id, 'mp4',
+            query=filter_dict({'token': token}))
+
+        return {
+            'id': video_id,
+            'title': smuggled_data.get('title') or video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+        }