Add VevoIE

test/tests.json

@@ -649,5 +649,16 @@
     "info_dict": {
         "title": "When Girls Act Like D-Bags"
     }
+  },
+  {
+    "name": "Vevo",
+    "url": "http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280",
+    "file": "GB1101300280.mp4",
+    "md5": "06bea460acb744eab74a9d7dcb4bfd61",
+    "info_dict": {
+        "title": "Somebody To Die For",
+        "upload_date": "20130624",
+        "uploader": "Hurts"
+    }
   }
 ]

youtube_dl/extractor/__init__.py

@@ -44,6 +44,7 @@ from .ted import TEDIE
 from .tumblr import TumblrIE
 from .ustream import UstreamIE
 from .vbox7 import Vbox7IE
+from .vevo import VevoIE
 from .vimeo import VimeoIE
 from .vine import VineIE
 from .worldstarhiphop import WorldStarHipHopIE
@@ -125,6 +126,7 @@ def gen_extractors():
         GametrailersIE(),
         StatigramIE(),
         BreakIE(),
+        VevoIE(),
         GenericIE()
     ]
 

youtube_dl/extractor/vevo.py

@@ -0,0 +1,40 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    unified_strdate,
+    ExtractorError,
+)
+
+class VevoIE(InfoExtractor):
+    _VALID_URL = r'http://www.vevo.com/watch/.*?/.*?/(?P<id>.*)$'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        json_url = 'http://www.vevo.com/data/video/%s' % video_id
+        base_url = 'http://smil.lvl3.vevo.com'
+        videos_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (base_url, video_id, video_id.lower())
+        info_json = self._download_webpage(json_url, video_id, u'Downloading json info')
+        links_webpage = self._download_webpage(videos_url, video_id, u'Downloading videos urls')
+
+        self.report_extraction(video_id)
+        video_info = json.loads(info_json)
+        m_urls = list(re.finditer(r'<video src="(?P<ext>.*?):(?P<url>.*?)"', links_webpage))
+        if m_urls is None or len(m_urls) == 0:
+            raise ExtractorError(u'Unable to extract video url')
+        # They are sorted from worst to best quality
+        m_url = m_urls[-1]
+        video_url = base_url + m_url.group('url')
+        ext = m_url.group('ext')
+
+        return {'url': video_url,
+                'ext': ext,
+                'id': video_id,
+                'title': video_info['title'],
+                'thumbnail': video_info['img'],
+                'upload_date': video_info['launchDate'].replace('/',''),
+                'uploader': video_info['Artists'][0]['title'],
+                }