[dotsub] Modernize

youtube_dl/extractor/dotsub.py

@@ -1,41 +1,42 @@
+from __future__ import unicode_literals
+
 import re
-import json
 import time
 
 from .common import InfoExtractor
 
 
 class DotsubIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?dotsub\.com/view/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
     _TEST = {
-        u'url': u'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
+        'url': 'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
-        u'file': u'aed3b8b2-1889-4df5-ae63-ad85f5572f27.flv',
+        'md5': '0914d4d69605090f623b7ac329fea66e',
-        u'md5': u'0914d4d69605090f623b7ac329fea66e',
+        'info_dict': {
-        u'info_dict': {
+            'id': 'aed3b8b2-1889-4df5-ae63-ad85f5572f27',
-            u"title": u"Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary",
+            'ext': 'flv',
-            u"uploader": u"4v4l0n42",
+            'title': 'Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary',
-            u'description': u'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism  and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com',
+            'uploader': '4v4l0n42',
-            u'thumbnail': u'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
+            'description': 'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism  and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com',
-            u'upload_date': u'20101213',
+            'thumbnail': 'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
+            'upload_date': '20101213',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')
-        info_url = "https://dotsub.com/api/media/%s/metadata" %(video_id)
+        info_url = "https://dotsub.com/api/media/%s/metadata" % video_id
-        webpage = self._download_webpage(info_url, video_id)
+        info = self._download_json(info_url, video_id)
-        info = json.loads(webpage)
         date = time.gmtime(info['dateCreated']/1000) # The timestamp is in miliseconds
 
-        return [{
+        return {
-            'id':          video_id,
+            'id': video_id,
-            'url':         info['mediaURI'],
+            'url': info['mediaURI'],
-            'ext':         'flv',
+            'ext': 'flv',
-            'title':       info['title'],
+            'title': info['title'],
-            'thumbnail':   info['screenshotURI'],
+            'thumbnail': info['screenshotURI'],
             'description': info['description'],
-            'uploader':    info['user'],
+            'uploader': info['user'],
-            'view_count':  info['numberOfViews'],
+            'view_count': info['numberOfViews'],
-            'upload_date': u'%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday),
+            'upload_date': '%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday),
-        }]
+        }