youtube-dl

commit b8f7b1579a61e52fd9dcb4920d919ed732083924
parent e88f5e0b4e1e77c13f6ec3fc6188166be95940c5
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Thu, 27 Jun 2013 17:52:41 +0200

Merge remote-tracking branch 'JohnyMoSwag/master'

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
2
++
A
youtube_dl/extractor/hotnewhiphop.py
 | 
43
+++++++++++++++++++++++++++++++++++++++++++

2 files changed, 45 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -18,6 +18,7 @@ from .gametrailers import GametrailersIE
 from .generic import GenericIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
+from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .hypem import HypemIE
 from .ina import InaIE
@@ -136,6 +137,7 @@ def gen_extractors():
         TudouIE(),
         CSpanIE(),
         WimpIE(),
+        HotNewHipHopIE(),
         GenericIE()
     ]
 
diff --git a/youtube_dl/extractor/hotnewhiphop.py b/youtube_dl/extractor/hotnewhiphop.py
@@ -0,0 +1,42 @@
+import re
+import base64
+
+from .common import InfoExtractor
+
+
+class HotNewHipHopIE(InfoExtractor):
+    _VALID_URL = r'(http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html)'
+    IE_NAME = u'HotNewHipHop'
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+
+        webpage_src = self._download_webpage(url, video_id)
+
+        video_url_base64 = self._search_regex(r'data-path="(.*?)"',
+            webpage_src, u'video URL', fatal=False)
+
+        if video_url_base64 == None:
+            video_url = self._search_regex(r'"contentUrl" content="(.*?)"', webpage_src,
+                u'video URL')
+            return self.url_result(video_url, ie='Youtube')
+
+        video_url = base64.b64decode(video_url_base64)
+
+        video_title = self._html_search_regex(r"<title>(.*)</title>",
+            webpage_src, u'title')
+        
+        #"og:image" content=
+        # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
+        thumbnail = self._html_search_regex(r'"og:image" content="(.*)"',
+            webpage_src, u'thumbnail', fatal=False)
+
+        results = [{
+                    'id': video_id,
+                    'url' : video_url,
+                    'title' : video_title,
+                    'thumbnail' : thumbnail,
+                    'ext' : 'mp3',
+                    }]
+        return results+
\ No newline at end of file