_ Git - youtube-dl/blob - youtube_dl/extractor/traileraddict.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class TrailerAddictIE(InfoExtractor):
   7     _VALID_URL = r'(?:http://)?(?:www\.)?traileraddict\.com/(?:trailer|clip)/(?P<movie>.+?)/(?P<trailer_name>.+)'
   8     _TEST = {
   9         u'url': u'http://www.traileraddict.com/trailer/prince-avalanche/trailer',
  10         u'file': u'76184.mp4',
  11         u'md5': u'57e39dbcf4142ceb8e1f242ff423fd71',
  12         u'info_dict': {
  13             u"title": u"Prince Avalanche Trailer",
  14             u"description": u"Trailer for Prince Avalanche.Two highway road workers spend the summer of 1988 away from their city lives. The isolated landscape becomes a place of misadventure as the men find themselves at odds with each other and the women they left behind."
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         mobj = re.match(self._VALID_URL, url)
  20         name = mobj.group('movie') + '/' + mobj.group('trailer_name')
  21         webpage = self._download_webpage(url, name)
  22
  23         title = self._search_regex(r'<title>(.+?)</title>',
  24                 webpage, 'video title').replace(' - Trailer Addict','')
  25         view_count = self._search_regex(r'Views: (.+?)<br />',
  26                 webpage, 'Views Count')
  27         video_id = self._og_search_property('video', webpage, 'Video id').split('=')[1]
  28
  29         # Presence of (no)watchplus function indicates HD quality is available
  30         if re.search(r'function (no)?watchplus()', webpage):
  31             fvar = "fvarhd"
  32         else:
  33             fvar = "fvar"
  34
  35         info_url = "http://www.traileraddict.com/%s.php?tid=%s" % (fvar, str(video_id))
  36         info_webpage = self._download_webpage(info_url, video_id , "Downloading the info webpage")
  37
  38         final_url = self._search_regex(r'&fileurl=(.+)',
  39                 info_webpage, 'Download url').replace('%3F','?')
  40         thumbnail_url = self._search_regex(r'&image=(.+?)&',
  41                 info_webpage, 'thumbnail url')
  42         ext = final_url.split('.')[-1].split('?')[0]
  43
  44         return [{
  45             'id'          : video_id,
  46             'url'         : final_url,
  47             'ext'         : ext,
  48             'title'       : title,
  49             'thumbnail'   : thumbnail_url,
  50             'description' : self._og_search_description(webpage),
  51             'view_count'  : view_count,
  52         }]