youtube-dl

commit 7f5bd09baf2118510c52115829180888ca7111ee
parent 02d5eb935f020241ff33b4b91ba88b92eee66b97
Author: julien <julien@julien-ThinkPad-X220.(none)>
Date:   Sun,  5 May 2013 16:07:19 +0200

Add support to www.ina.fr

Diffstat:
M
test/tests.json
 | 
9
+++++++++
M
youtube_dl/InfoExtractors.py
 | 
37
+++++++++++++++++++++++++++++++++++++

2 files changed, 46 insertions(+), 0 deletions(-)
diff --git a/test/tests.json b/test/tests.json
@@ -420,5 +420,14 @@
     "info_dict":{
       "title":"Tired of Link Building? Try BacklinkMyDomain.com!"
     }
+  },
+  {
+    "name": "Ina",
+    "url": "www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html",
+    "file": "I12055569.mp4",
+    "md5": "a667021bf2b41f8dc6049479d9bb38a3",
+    "info_dict":{
+      "title":"François Hollande \"Je crois que c'est clair\""
+    }
   }
 ]
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
@@ -4124,7 +4124,43 @@ class RedTubeIE(InfoExtractor):
             'ext':      video_extension,
             'title':    video_title,
         }]
+        
+class InaIE(InfoExtractor):
+    """Information Extractor for Ina.fr"""
+    _VALID_URL = r'(?:http://)?(?:www.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
+    IE_NAME = u'Ina'
+    def _real_extract(self,url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+        video_id = mobj.group('id')
+        self.to_screen(u'video id : %s' % video_id)
+        mrss_url='http://player.ina.fr/notices/%s.mrss'%video_id
+        self.to_screen(u'mrss url : %s' % mrss_url)
+        video_extension = 'mp4'        
+        webpage = self._download_webpage(mrss_url,video_id)
+        self.report_extraction(video_id)
+        reg1=r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)'
+        mobj = re.search(reg1,webpage)
+
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract media URL')
 
+        video_url = mobj.group(1)
+        reg2=r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>'
+        mobj = re.search(reg2,webpage)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract title')
+        video_title = mobj.group(1)
+        
+        self.to_screen(u'Titre de la video : %s' % video_title)
+
+        return [{
+            'id':       video_id,
+            'url':      video_url,
+            'ext':      video_extension,
+            'title':    video_title,
+        }]
 
 def gen_extractors():
     """ Return a list of an instance of every supported extractor.
@@ -4182,6 +4218,7 @@ def gen_extractors():
         TumblrIE(),
         BandcampIE(),
         RedTubeIE(),
+        InaIE,
         GenericIE()
     ]