youtube-dl

commit ca0a0bbeecf81720c4cc5b403ebc952baf28434b
parent 6119f78cb9c566a6559859bf2b21381803c41727
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Sat, 12 Jan 2013 17:58:39 +0100

RBMA IE (Closes #630)

Diffstat:
M
test/tests.json
 | 
13
+++++++++++++
M
youtube_dl/InfoExtractors.py
 | 
35
+++++++++++++++++++++++++++++++++++

2 files changed, 48 insertions(+), 0 deletions(-)
diff --git a/test/tests.json b/test/tests.json
@@ -212,5 +212,18 @@
         }
       }
     ]
+  },
+  {
+    "name": "RBMARadio",
+    "url": "http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011",
+    "file": "ford-lopatin-live-at-primavera-sound-2011.mp3",
+    "md5": "6bc6f9bcb18994b4c983bc3bf4384d95",
+    "info_dict": {
+        "title": "Live at Primavera Sound 2011",
+        "description": "Joel Ford and Daniel \u2019Oneohtrix Point Never\u2019 Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.",
+        "uploader": "Ford & Lopatin",
+        "uploader_id": "ford-lopatin",
+        "location": "Spain"
+    }
   }
 ]
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
@@ -3728,6 +3728,40 @@ class UstreamIE(InfoExtractor):
                   }
         return [info]
 
+class RBMARadioIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('videoID')
+
+        webpage = self._download_webpage(url, video_id)
+        m = re.search(r'<script>window.gon = {.*?};gon\.show=(.+?);</script>', webpage)
+        if not m:
+            raise ExtractorError(u'Cannot find metadata')
+        json_data = m.group(1)
+
+        try:
+            data = json.loads(json_data)
+        except ValueError as e:
+            raise ExtractorError(u'Invalid JSON: ' + str(e))
+
+        video_url = data['akamai_url'] + '&cbr=256'
+        url_parts = compat_urllib_parse_urlparse(video_url)
+        video_ext = url_parts.path.rpartition('.')[2]
+        info = {
+                'id': video_id,
+                'url': video_url,
+                'ext': video_ext,
+                'title': data['title'],
+                'description': data.get('teaser_text'),
+                'location': data.get('country_of_origin'),
+                'uploader': data.get('host', {}).get('name'),
+                'uploader_id': data.get('host', {}).get('slug'),
+                'thumbnail': data.get('image').get('large_url_2x'),
+                'duration': data.get('duration'),
+        }
+        return [info]
 
 
 class YouPornIE(InfoExtractor):
@@ -3984,6 +4018,7 @@ def gen_extractors():
         TweetReelIE(),
         SteamIE(),
         UstreamIE(),
+        RBMARadioIE(),
         GenericIE()
     ]