Merge pull request #962 from jaimeMF/TF1

Add TF1IE

2 files changed, 35 insertions, 0 deletions

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 65a23d52b..35b619cca 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -47,6 +47,7 @@ from .statigram import StatigramIE
 from .steam import SteamIE
 from .teamcoco import TeamcocoIE
 from .ted import TEDIE
+from .tf1 import TF1IE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
 from .ustream import UstreamIE
diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py
new file mode 100644
index 000000000..2c13db7e6
--- /dev/null
+++ b/youtube_dl/extractor/tf1.py
@@ -0,0 +1,34 @@
+# coding: utf-8
+
+import json
+import re
+
+from .common import 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 or the news.
+    """
+    _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'6bysb.mp4',
+        u'md5': u'66789d3e91278d332f75e1feb7aea327',
+        u'info_dict': {
+            u"title": u"Citroën Grand C4 Picasso 2013 : présentation officielle"
+        }
+    }
+
+    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')