[ie/crunchyroll] Fix stream extraction (#10005)

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

diff --git a/yt_dlp/extractor/lci.py b/yt_dlp/extractor/lci.py
index 81cf88b6c7a3b202b8da7e3477e51ef67a197a1a..e7d2f8a24c2e549c0d8cda39f0862f3142b4b7fd 100644 (file)
--- a/yt_dlp/extractor/lci.py
+++ b/yt_dlp/extractor/lci.py
@@ -2,22 +2,27 @@
 
 
 class LCIIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?lci\.fr/[^/]+/[\w-]+-(?P<id>\d+)\.html'
-    _TEST = {
-        'url': 'http://www.lci.fr/international/etats-unis-a-j-62-hillary-clinton-reste-sans-voix-2001679.html',
-        'md5': '2fdb2538b884d4d695f9bd2bde137e6c',
+    _VALID_URL = r'https?://(?:www\.)?(?:lci|tf1info)\.fr/[^/]+/[\w-]+-(?P<id>\d+)\.html'
+    _TESTS = [{
+        'url': 'https://www.tf1info.fr/politique/election-presidentielle-2022-second-tour-j-2-marine-le-pen-et-emmanuel-macron-en-interview-de-lci-vendredi-soir-2217486.html',
         'info_dict': {
-            'id': '13244802',
+            'id': '13875948',
             'ext': 'mp4',
-            'title': 'Hillary Clinton et sa quinte de toux, en plein meeting',
-            'description': 'md5:a4363e3a960860132f8124b62f4a01c9',
-        }
-    }
+            'title': 'md5:660df5481fd418bc3bbb0d070e6fdb5a',
+            'thumbnail': 'https://photos.tf1.fr/1280/720/presidentielle-2022-marine-le-pen-et-emmanuel-macron-invites-de-lci-ce-vendredi-9c0e73-e1a036-0@1x.jpg',
+            'upload_date': '20220422',
+            'duration': 33,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.lci.fr/politique/election-presidentielle-2022-second-tour-j-2-marine-le-pen-et-emmanuel-macron-en-interview-de-lci-vendredi-soir-2217486.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        wat_id = self._search_regex(
-            (r'data-watid=[\'"](\d+)', r'idwat["\']?\s*:\s*["\']?(\d+)'),
-            webpage, 'wat id')
+        wat_id = self._search_regex(r'watId["\']?\s*:\s*["\']?(\d+)', webpage, 'wat id')
         return self.url_result('wat:' + wat_id, 'Wat', wat_id)