Merge remote-tracking branch 'rzhxeo/crunchyroll'

[youtube-dl] / youtube_dl / extractor / hotnewhiphop.py

diff --git a/youtube_dl/extractor/hotnewhiphop.py b/youtube_dl/extractor/hotnewhiphop.py
index fb403b14e692d5a17057ae942d5370f3e3ffe662..0ee74fb38410a4acce1e15c7a9ce98d80409012e 100644 (file)
--- a/youtube_dl/extractor/hotnewhiphop.py
+++ b/youtube_dl/extractor/hotnewhiphop.py
@@ -5,8 +5,15 @@ from .common import InfoExtractor
 
 
 class HotNewHipHopIE(InfoExtractor):
-    _VALID_URL = r'(http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html)'
-    IE_NAME = u'HotNewHipHop'
+    _VALID_URL = r'http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html'
+    _TEST = {
+        u'url': u"http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html",
+        u'file': u'1435540.mp3',
+        u'md5': u'2c2cd2f76ef11a9b3b581e8b232f3d96',
+        u'info_dict': {
+            u"title": u'Freddie Gibbs "Lay It Down"'
+        }
+    }
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
@@ -14,26 +21,24 @@ class HotNewHipHopIE(InfoExtractor):
 
         webpage_src = self._download_webpage(url, video_id)
 
-        print video_id
-
         video_url_base64 = self._search_regex(r'data-path="(.*?)"',
-            webpage_src, u'video URL')
+            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_url = base64.b64decode(video_url_base64).decode('utf-8')
 
         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,
+                    'thumbnail' : self._og_search_thumbnail(webpage_src),
                     'ext' : 'mp3',
                     }]
-        return results
\ No newline at end of file
+        return results