Extractor for defense.gouv.fr

youtube_dl/extractor/__init__.py

@@ -21,6 +21,7 @@
 from .depositfiles import DepositFilesIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
+from .defense import DefenseGouvFrIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .escapist import EscapistIE

youtube_dl/extractor/defense.py

@@ -0,0 +1,37 @@
+# coding: utf-8
+'''Extractor for defense.gouv.fr'''
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class DefenseGouvFrIE(InfoExtractor):
+    '''Extractor for defense.gouv.fr'''
+    _IE_NAME = 'defense.gouv.fr'
+    _VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/'
+        'ligthboxvideo/base-de-medias/webtv/(.*)')
+
+    _TEST = {
+        u'url': (u'http://www.defense.gouv.fr/layout/set/ligthboxvideo/',
+        'base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1')
+    }
+
+    def _real_extract(self, url):
+        title = re.match(self._VALID_URL, url).group(1)
+        webpage = self._download_webpage(url, title)
+        video_id = self._search_regex(
+            r"flashvars.pvg_id=\"(\d+)\";",
+            webpage, 'ID')
+        
+        json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/'
+            + video_id)
+        info = self._download_webpage(json_url, title,
+                                                  'Downloading JSON config')
+        video_url = json.loads(info)['renditions'][0]['url']
+        
+        return {'id': video_id,
+                'ext': 'mp4',
+                'url': video_url,
+                'title': title,
+                }