Update upstream source from tag 'upstream/2019.06.08'

[youtubedl] / youtube_dl / extractor / tf1.py

diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py
index 3a68eaa80ea6867e6806a4f242a8afc910b8ba06..903f4738005625f35cebf298ee196dc6128460df 100644 (file)
--- a/youtube_dl/extractor/tf1.py
+++ b/youtube_dl/extractor/tf1.py
@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 class TF1IE(InfoExtractor):
     """TF1 uses the wat.tv player."""
 
 class TF1IE(InfoExtractor):
     """TF1 uses the wat.tv player."""

-    _VALID_URL = r'http://(?:(?:videos|www|lci)\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.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': {
     _TESTS = [{
         'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
         'info_dict': {


@@ -19,10 +19,11 @@ class TF1IE(InfoExtractor):
             # Sometimes wat serves the whole file with the --test option
             'skip_download': True,
         },
             # 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': {
     }, {
         'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
         'info_dict': {

-            'id': '12043945',
+            'id': 'le-grand-mysterioso-chuggington-7085291-739',

             'ext': 'mp4',
             'title': 'Le grand Mystérioso - Chuggington',
             'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.',
             'ext': 'mp4',
             'title': 'Le grand Mystérioso - Chuggington',
             'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.',


@@ -32,22 +33,22 @@ class TF1IE(InfoExtractor):
             # Sometimes wat serves the whole file with the --test option
             'skip_download': True,
         },
             # Sometimes wat serves the whole file with the --test option
             'skip_download': True,
         },

+        'skip': 'HTTP Error 410: Gone',

     }, {
         'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html',
         'only_matching': True,
     }, {
         'url': 'http://lci.tf1.fr/sept-a-huit/videos/sept-a-huit-du-24-mai-2015-8611550.html',
         'only_matching': True,
     }, {
         'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html',
         'only_matching': True,
     }, {
         'url': 'http://lci.tf1.fr/sept-a-huit/videos/sept-a-huit-du-24-mai-2015-8611550.html',
         'only_matching': True,

+    }, {
+        'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
     }]
 
     def _real_extract(self, url):
         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')
-        embed_page = self._download_webpage(embed_url, video_id,
-                                            'Downloading embed player page')
-        wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat 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')
+        wat_id = self._html_search_regex(
+            r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
+            webpage, 'wat id', group='id')
+        return self.url_result('wat:%s' % wat_id, 'Wat')