[tf1] add support for TFOU
authort0mm0 <dev@onairsoftware.co.uk>
Sun, 4 Jan 2015 00:05:31 +0000 (00:05 +0000)
committert0mm0 <dev@onairsoftware.co.uk>
Sun, 4 Jan 2015 00:05:31 +0000 (00:05 +0000)
youtube_dl/extractor/tf1.py

index 6e61cc9e2ecf621b19fe13924456970b091bce1c..384b4c3f874d5f5464f1cf95eed636976e5cfe59 100644 (file)
@@ -8,8 +8,8 @@ from .common import InfoExtractor
 
 class TF1IE(InfoExtractor):
     """TF1 uses the wat.tv player."""
-    _VALID_URL = r'http://videos\.tf1\.fr/.*-(?P<id>.*?)\.html'
-    _TEST = {
+    _VALID_URL = r'http://(?:videos\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html'
+    _TESTS = {
         'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
         'info_dict': {
             'id': '10635995',
@@ -21,14 +21,25 @@ class TF1IE(InfoExtractor):
             # Sometimes wat serves the whole file with the --test option
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
+        'info_dict': {
+            'id': '7085291',
+            'ext': 'mp4',
+            'title': 'Le grand Mystérioso - Chuggington',
+            'description': 'Emery rêve qu\'un article lui soit consacré dans le journal.',
+        },
+        'params': {
+            # Sometimes wat serves the whole file with the --test option
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         embed_url = self._html_search_regex(
-            r'"(https://www.wat.tv/embedframe/.*?)"', webpage, 'embed url')
+            r'["\'](http(?:s)?://www.wat.tv/embedframe/.*?)["\']', webpage, 'embed url')
         embed_page = self._download_webpage(embed_url, video_id,
                                             'Downloading embed player page')
         wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')