From 52afe996656987ad17999212d8a25e12151147a7 Mon Sep 17 00:00:00 2001
From: Pierre Rudloff <contact@rudloff.pro>
Date: Tue, 3 Sep 2013 01:51:17 +0200
Subject: [PATCH 1/2] Extractor for defense.gouv.fr
---
youtube_dl/extractor/__init__.py | 1 +
youtube_dl/extractor/defense.py | 37 ++++++++++++++++++++++++++++++++
2 files changed, 38 insertions(+)
create mode 100644 youtube_dl/extractor/defense.py
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 9f56e427c3..a96b62d37f 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -21,6 +21,7 @@ from .dailymotion import DailymotionIE, DailymotionPlaylistIE
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
diff --git a/youtube_dl/extractor/defense.py b/youtube_dl/extractor/defense.py
new file mode 100644
index 0000000000..963fb897f4
--- /dev/null
+++ b/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,
+ }
From 025171c47641a47cc2a4e4ed52c7a04b465e0e5d Mon Sep 17 00:00:00 2001
From: Pierre Rudloff <contact@rudloff.pro>
Date: Tue, 3 Sep 2013 12:03:19 +0200
Subject: [PATCH 2/2] Suggested by @phihag
---
youtube_dl/extractor/defense.py | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/youtube_dl/extractor/defense.py b/youtube_dl/extractor/defense.py
index 963fb897f4..424d960da9 100644
--- a/youtube_dl/extractor/defense.py
+++ b/youtube_dl/extractor/defense.py
@@ -1,5 +1,3 @@
-# coding: utf-8
-'''Extractor for defense.gouv.fr'''
import re
import json
@@ -7,14 +5,18 @@ 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/(.*)')
+ r'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')
+ u'url': (u'http://www.defense.gouv.fr/layout/set/ligthboxvideo/'
+ u'base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1'),
+ u'file': u'11213.mp4',
+ u'md5': u'75bba6124da7e63d2d60b5244ec9430c',
+ "info_dict": {
+ "title": "attaque-chimique-syrienne-du-21-aout-2013-1"
+ }
}
def _real_extract(self, url):