From: Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Date: Thu, 22 Aug 2013 09:57:21 +0000 (+0200)
Subject: Add an extractor for PBS (closes #870 and #873)
X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=9779b63bb6109649a603b2eddd6bbc6a040e1493;p=youtube-dl

Add an extractor for PBS (closes #870 and #873)
---

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index d836a22b5..a3e572923 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -50,6 +50,7 @@ from .myspass import MySpassIE
 from .myvideo import MyVideoIE
 from .nba import NBAIE
 from .ooyala import OoyalaIE
+from .pbs import PBSIE
 from .photobucket import PhotobucketIE
 from .pornotube import PornotubeIE
 from .rbmaradio import RBMARadioIE
diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py
new file mode 100644
index 000000000..65462d867
--- /dev/null
+++ b/youtube_dl/extractor/pbs.py
@@ -0,0 +1,34 @@
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class PBSIE(InfoExtractor):
+    _VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?'
+
+    _TEST = {
+        u'url': u'http://video.pbs.org/video/2365006249/',
+        u'file': u'2365006249.mp4',
+        u'md5': 'ce1888486f0908d555a8093cac9a7362',
+        u'info_dict': {
+            u'title': u'A More Perfect Union',
+            u'description': u'md5:ba0c207295339c8d6eced00b7c363c6a',
+            u'duration': 3190,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
+        info_page = self._download_webpage(info_url, video_id)
+        info =json.loads(info_page)
+        return {'id': video_id,
+                'title': info['title'],
+                'url': info['alternate_encoding']['url'],
+                'ext': 'mp4',
+                'description': info['program'].get('description'),
+                'thumbnail': info.get('image_url'),
+                'duration': info.get('duration'),
+                }