youtube_dl/extractor/dotsub.py

   1 import re
   2 import json
   3 import time
   4
   5 from .common import InfoExtractor
   6
   7
   8 class DotsubIE(InfoExtractor):
   9     _VALID_URL = r'(?:http://)?(?:www\.)?dotsub\.com/view/([^/]+)'
  10     _TEST = {
  11         u'url': u'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
  12         u'file': u'aed3b8b2-1889-4df5-ae63-ad85f5572f27.flv',
  13         u'md5': u'0914d4d69605090f623b7ac329fea66e',
  14         u'info_dict': {
  15             u"title": u"Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary",
  16             u"uploader": u"4v4l0n42",
  17             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',
  18             u'thumbnail': u'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
  19             u'upload_date': u'20101213',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group(1)
  26         info_url = "https://dotsub.com/api/media/%s/metadata" %(video_id)
  27         webpage = self._download_webpage(info_url, video_id)
  28         info = json.loads(webpage)
  29         date = time.gmtime(info['dateCreated']/1000) # The timestamp is in miliseconds
  30
  31         return [{
  32             'id':          video_id,
  33             'url':         info['mediaURI'],
  34             'ext':         'flv',
  35             'title':       info['title'],
  36             'thumbnail':   info['screenshotURI'],
  37             'description': info['description'],
  38             'uploader':    info['user'],
  39             'view_count':  info['numberOfViews'],
  40             'upload_date': u'%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday),
  41         }]