[ard:beta] Relax _VALID_URL (closes #18441)

[youtube-dl] / youtube_dl / extractor / ard.py

diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py
index 194a369c06343bf4beefc2e3cb17840005b7bff5..a5df7f0f9dbd05bf338fc4f4ff5e83b378e1db9d 100644 (file)
--- a/youtube_dl/extractor/ard.py
+++ b/youtube_dl/extractor/ard.py
@@ -21,7 +21,7 @@ from ..compat import compat_etree_fromstring
 
 class ARDMediathekIE(InfoExtractor):
     IE_NAME = 'ARD:mediathek'
-    _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
+    _VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
     _TESTS = [{
         # available till 26.07.2022
@@ -37,6 +37,9 @@ class ARDMediathekIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         }
+    }, {
+        'url': 'https://one.ard.de/tv/Mord-mit-Aussicht/Mord-mit-Aussicht-6-39-T%C3%B6dliche-Nach/ONE/Video?bcastId=46384294&documentId=55586872',
+        'only_matching': True,
     }, {
         # audio
         'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
@@ -48,8 +51,15 @@ class ARDMediathekIE(InfoExtractor):
         # audio
         'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158',
         'only_matching': True,
+    }, {
+        'url': 'https://classic.ardmediathek.de/tv/Panda-Gorilla-Co/Panda-Gorilla-Co-Folge-274/Das-Erste/Video?bcastId=16355486&documentId=58234698',
+        'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return False if ARDBetaMediathekIE.suitable(url) else super(ARDMediathekIE, cls).suitable(url)
+
     def _extract_media_info(self, media_info_url, webpage, video_id):
         media_info = self._download_json(
             media_info_url, video_id, 'Downloading media JSON')
@@ -170,13 +180,18 @@ class ARDMediathekIE(InfoExtractor):
         title = self._html_search_regex(
             [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
              r'<meta name="dcterms\.title" content="(.*?)"/>',
-             r'<h4 class="headline">(.*?)</h4>'],
+             r'<h4 class="headline">(.*?)</h4>',
+             r'<title[^>]*>(.*?)</title>'],
             webpage, 'title')
         description = self._html_search_meta(
             'dcterms.abstract', webpage, 'description', default=None)
         if description is None:
             description = self._html_search_meta(
-                'description', webpage, 'meta description')
+                'description', webpage, 'meta description', default=None)
+        if description is None:
+            description = self._html_search_regex(
+                r'<p\s+class="teasertext">(.+?)</p>',
+                webpage, 'teaser text', default=None)
 
         # Thumbnail is sometimes not present.
         # It is in the mobile version, but that seems to use a different URL
@@ -285,7 +300,7 @@ class ARDIE(InfoExtractor):
 
 
 class ARDBetaMediathekIE(InfoExtractor):
-    _VALID_URL = r'https://beta\.ardmediathek\.de/[a-z]+/player/(?P<video_id>[a-zA-Z0-9]+)/(?P<display_id>[^/?#]+)'
+    _VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/[^/]+/(?:player|live)/(?P<video_id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^/?#]+))?'
     _TESTS = [{
         'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita',
         'md5': '2d02d996156ea3c397cfc5036b5d7f8f',
@@ -299,12 +314,18 @@ class ARDBetaMediathekIE(InfoExtractor):
             'upload_date': '20180826',
             'ext': 'mp4',
         },
+    }, {
+        'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3N3ci5kZS9hZXgvbzEwNzE5MTU/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.ardmediathek.de/swr/live/Y3JpZDovL3N3ci5kZS8xMzQ4MTA0Mg',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('video_id')
-        display_id = mobj.group('display_id')
+        display_id = mobj.group('display_id') or video_id
 
         webpage = self._download_webpage(url, display_id)
         data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);\n', webpage, 'json')