Merge tag 'upstream/2017.02.24.1'

[youtubedl] / youtube_dl / extractor / tf1.py

diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py
index e0ffeced50eabae1a9f7d0a9920e1df18c5fa4c6..e595c4a69b3f03361abc05f6bca61adecb61cf36 100644 (file)
--- a/youtube_dl/extractor/tf1.py
+++ b/youtube_dl/extractor/tf1.py
@@ -1,35 +1,53 @@
 # coding: utf-8
 # coding: utf-8

-
-import json
-import re
+from __future__ import unicode_literals

 
 from .common import InfoExtractor
 
 
 from .common import InfoExtractor
 

+

 class TF1IE(InfoExtractor):
 class TF1IE(InfoExtractor):

-    """
-    TF1 uses the wat.tv player, currently it can only download videos with the
-    html5 player enabled, it cannot download HD videos.
-    """
-    _VALID_URL = r'http://videos.tf1.fr/.*-(.*?).html'
-    _TEST = {
-        u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
-        u'file': u'10635995.mp4',
-        u'md5': u'66789d3e91278d332f75e1feb7aea327',
-        u'info_dict': {
-            u'title': u'Citroën Grand C4 Picasso 2013 : présentation officielle',
-            u'description': u'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
-        }
-    }
+    """TF1 uses the wat.tv player."""
+    _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': {
+            'id': '10635995',
+            'ext': 'mp4',
+            'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle',
+            'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
+        },
+        'params': {
+            # 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': '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.',
+            'upload_date': '20150103',
+        },
+        'params': {
+            # 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/hd1/documentaire/videos/mylene-farmer-d-une-icone.html',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        id = mobj.group(1)
-        webpage = self._download_webpage(url, id)
-        embed_url = self._html_search_regex(r'"(https://www.wat.tv/embedframe/.*?)"',
-                                webpage, 'embed url')
-        embed_page = self._download_webpage(embed_url, id, u'Downloading embed player page')
-        wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')
-        wat_info = self._download_webpage('http://www.wat.tv/interface/contentv3/%s' % wat_id, id, u'Downloading Wat info')
-        wat_info = json.loads(wat_info)['media']
-        wat_url = wat_info['url']
-        return self.url_result(wat_url, 'Wat')
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        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')