_ 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/([^/]+)/(?:trailer|feature-trailer)'
   8     _TEST = {
   9         u'url': u'http://www.traileraddict.com/trailer/prince-avalanche/trailer',
  10         u'file': u'76184.mp4',
  11         u'md5': u'41365557f3c8c397d091da510e73ceb4',
  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         video_id = mobj.group(1)
  21         webpage = self._download_webpage(url, video_id)
  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         description = self._search_regex(r'<meta property="og:description" content="(.+?)" />',
  28                 webpage, 'video description')
  29         video_id = self._search_regex(r'<meta property="og:video" content="(.+?)" />',
  30                 webpage, 'Video id').split('=')[1]
  31
  32         info_url = "http://www.traileraddict.com/fvar.php?tid=%s" %(str(video_id))
  33         info_webpage = self._download_webpage(info_url, video_id , "Downloading the info webpage")
  34
  35         final_url = self._search_regex(r'&fileurl=(.+)',
  36                 info_webpage, 'Download url').replace('%3F','?')
  37         thumbnail_url = self._search_regex(r'&image=(.+?)&',
  38                 info_webpage, 'thumbnail url')
  39         ext = final_url.split('.')[-1].split('?')[0]
  40
  41         return [{
  42             'id'          : video_id,
  43             'url'         : final_url,
  44             'ext'         : ext,
  45             'title'       : title,
  46             'thumbnail'   : thumbnail_url,
  47             'description' : description,
  48             'view_count'  : view_count,
  49         }]