Support Tele5 pages with Discovery Networks format instead of JWPlatform

youtube_dl/extractor/tele5.py

@@ -1,19 +1,16 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
-from .common import InfoExtractor
-from .jwplatform import JWPlatformIE
-from .nexx import NexxIE
 from ..compat import compat_urlparse
 from ..utils import (
-    NO_DEFAULT,
+    ExtractorError,
-    smuggle_url,
+    extract_attributes,
 )
 
+from .dplay import DPlayIE
 
-class Tele5IE(InfoExtractor):
+
+class Tele5IE(DPlayIE):
     _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _GEO_COUNTRIES = ['DE']
     _TESTS = [{
@@ -28,6 +25,7 @@ class Tele5IE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+        'skip': 'No longer available: "404 Seite nicht gefunden"',
     }, {
         # jwplatform, nexx unavailable
         'url': 'https://www.tele5.de/filme/ghoul-das-geheimnis-des-friedhofmonsters/',
@@ -42,7 +40,20 @@ class Tele5IE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
-        'add_ie': [JWPlatformIE.ie_key()],
+        'skip': 'No longer available, redirects to Filme page',
+    }, {
+        'url': 'https://tele5.de/mediathek/angel-of-mine/',
+        'info_dict': {
+            'id': '1252360',
+            'ext': 'mp4',
+            'upload_date': '20220109',
+            'timestamp': 1641762000,
+            'title': 'Angel of Mine',
+            'description': 'md5:a72546a175e1286eb3251843a52d1ad7',
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
     }, {
         'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
         'only_matching': True,
@@ -64,45 +75,18 @@ class Tele5IE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+        video_id = self._match_id(url)
-        video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0]
+        webpage = self._download_webpage(url, video_id)
-
+        player_element = self._search_regex(r'(<hyoga-player\b[^>]+?>)', webpage, 'video player')
-        NEXX_ID_RE = r'\d{6,}'
+        player_info = extract_attributes(player_element)
-        JWPLATFORM_ID_RE = r'[a-zA-Z0-9]{8}'
+        asset_id, country, realm = (player_info[x] for x in ('assetid', 'locale', 'realm', ))
-
+        endpoint = compat_urlparse.urlparse(player_info['endpoint']).hostname
-        def nexx_result(nexx_id):
+        source_type = player_info.get('sourcetype')
-            return self.url_result(
+        if source_type:
-                'https://api.nexx.cloud/v3/759/videos/byid/%s' % nexx_id,
+            endpoint = '%s-%s' % (source_type, endpoint)
-                ie=NexxIE.ie_key(), video_id=nexx_id)
+        try:
-
+            return self._get_disco_api_info(url, asset_id, endpoint, realm, country)
-        nexx_id = jwplatform_id = None
+        except ExtractorError as e:
-
+            if getattr(e, 'message', '') == 'Missing deviceId in context':
-        if video_id:
+                raise ExtractorError('DRM protected', cause=e, expected=True)
-            if re.match(NEXX_ID_RE, video_id):
+            raise
-                return nexx_result(video_id)
-            elif re.match(JWPLATFORM_ID_RE, video_id):
-                jwplatform_id = video_id
-
-        if not nexx_id:
-            display_id = self._match_id(url)
-            webpage = self._download_webpage(url, display_id)
-
-            def extract_id(pattern, name, default=NO_DEFAULT):
-                return self._html_search_regex(
-                    (r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](%s)' % pattern,
-                     r'\s+id\s*=\s*["\']player_(%s)' % pattern,
-                     r'\bdata-id\s*=\s*["\'](%s)' % pattern), webpage, name,
-                    default=default)
-
-            nexx_id = extract_id(NEXX_ID_RE, 'nexx id', default=None)
-            if nexx_id:
-                return nexx_result(nexx_id)
-
-            if not jwplatform_id:
-                jwplatform_id = extract_id(JWPLATFORM_ID_RE, 'jwplatform id')
-
-        return self.url_result(
-            smuggle_url(
-                'jwplatform:%s' % jwplatform_id,
-                {'geo_countries': self._GEO_COUNTRIES}),
-            ie=JWPlatformIE.ie_key(), video_id=jwplatform_id)