[youtube] Fix extraction (closes #20758, closes #20759, closes #20761, closes #20762...
[youtube-dl] / youtube_dl / extractor / tf1.py
index 6890021cf199e8b53a19cfa291bf7800477dab3b..903f4738005625f35cebf298ee196dc6128460df 100644 (file)
@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 class TF1IE(InfoExtractor):
     """TF1 uses the wat.tv player."""
-    _VALID_URL = r'http://(?:(?:videos|www|lci)\.tf1|www\.tfou)\.fr/(?:[^/]+/)*(?P<id>.+?)\.html'
+    _VALID_URL = r'https?://(?:(?:videos|www|lci)\.tf1|(?:www\.)?(?:tfou|ushuaiatv|histoire|tvbreizh))\.fr/(?:[^/]+/)*(?P<id>[^/?#.]+)'
     _TESTS = [{
         'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
         'info_dict': {
@@ -19,6 +19,7 @@ class TF1IE(InfoExtractor):
             # Sometimes wat serves the whole file with the --test option
             'skip_download': True,
         },
+        'expected_warnings': ['HTTP Error 404'],
     }, {
         'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
         'info_dict': {
@@ -50,6 +51,4 @@ class TF1IE(InfoExtractor):
         wat_id = self._html_search_regex(
             r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
             webpage, 'wat id', group='id')
-        wat_info = self._download_json(
-            'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id)
-        return self.url_result(wat_info['media']['url'], 'Wat')
+        return self.url_result('wat:%s' % wat_id, 'Wat')