Merge pull request #730 by @JohnyMoSwag

Support for Worldstarhiphop.com

diff --git a/.gitignore b/.gitignore
index 77469b8a7993a9b529769452f109e8805e8b1e50..ca4e8f35321bea65b42197d82b63769a35944168 100644 (file)
--- a/.gitignore
+++ b/.gitignore
@@ -17,4 +17,4 @@ youtube-dl.tar.gz
 .coverage
 cover/
 updates_key.pem
-*.egg-info
+*.egg-info
\ No newline at end of file

diff --git a/test/tests.json b/test/tests.json
index 929d454ffa115582d85053a04034a27d03096246..0c94c65bdee2d77cd3a2ffadb0b403444ba1d8e2 100644 (file)
--- a/test/tests.json
+++ b/test/tests.json
@@ -319,5 +319,14 @@
         "description": "extremely bad day for this guy..!",
         "uploader": "ljfriel2"
     }
+  },
+  {
+    "name": "WorldStarHipHop",
+    "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
+    "file": "wshh6a7q1ny0G34ZwuIO.mp4",
+    "md5": "9d04de741161603bf7071bbf4e883186",
+    "info_dict": {
+        "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick! "
+    }
   }
 ]

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index b3c3dbb4385bfd6f612c30f5aab8c183edf13738..b4c86cfa311b8391c40bf6e5f0f179724fae7057 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -3687,6 +3687,62 @@ class UstreamIE(InfoExtractor):
                   }
         return [info]
 
+class WorldStarHipHopIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
+    IE_NAME = u'WorldStarHipHop'
+
+    def _real_extract(self, url):
+        _src_url = r"""(http://hw-videos.*(?:mp4|flv))"""
+
+        webpage_src = compat_urllib_request.urlopen(url).read()
+        webpage_src = webpage_src.decode('utf-8')
+
+        mobj = re.search(_src_url, webpage_src)
+
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+
+        if mobj is not None:
+            video_url = mobj.group()
+            if 'mp4' in video_url:
+                ext = 'mp4'
+            else:
+                ext = 'flv'
+        else:
+            self._downloader.trouble(u'ERROR: Cannot find video url for %s' % video_id)
+            return
+
+        _title = r"""<title>(.*)</title>"""
+
+        mobj = re.search(_title, webpage_src)
+        
+        if mobj is not None:
+            title = mobj.group(1)
+        else:
+            title = 'World Start Hip Hop - %s' % time.ctime()
+
+        _thumbnail = r"""rel="image_src" href="(.*)" />"""
+        mobj = re.search(_thumbnail, webpage_src)
+
+        # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
+        if mobj is not None:
+            thumbnail = mobj.group(1)
+        else:
+            _title = r"""candytitles.*>(.*)</span>"""
+            mobj = re.search(_title, webpage_src)
+            if mobj is not None:
+                title = mobj.group(1)
+            thumbnail = None
+        
+        results = [{
+                    'id': video_id,
+                    'url' : video_url,
+                    'title' : title,
+                    'thumbnail' : thumbnail,
+                    'ext' : ext,
+                    }]
+        return results
+
 class RBMARadioIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
 
@@ -4249,6 +4305,7 @@ def gen_extractors():
         GooglePlusIE(),
         ArteTvIE(),
         NBAIE(),
+        WorldStarHipHopIE(),
         JustinTVIE(),
         FunnyOrDieIE(),
         SteamIE(),