youtube_dl/extractor/traileraddict.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class TrailerAddictIE(InfoExtractor):
   9     _VALID_URL = r'(?:http://)?(?:www\.)?traileraddict\.com/(?:trailer|clip)/(?P<movie>.+?)/(?P<trailer_name>.+)'
  10     _TEST = {
  11         'url': 'http://www.traileraddict.com/trailer/prince-avalanche/trailer',
  12         'md5': '41365557f3c8c397d091da510e73ceb4',
  13         'info_dict': {
  14             'id': '76184',
  15             'ext': 'mp4',
  16             'title': 'Prince Avalanche Trailer',
  17             'description': 'Trailer for Prince Avalanche.\n\nTwo 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.',
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23         name = mobj.group('movie') + '/' + mobj.group('trailer_name')
  24         webpage = self._download_webpage(url, name)
  25
  26         title = self._search_regex(r'<title>(.+?)</title>',
  27                 webpage, 'video title').replace(' - Trailer Addict','')
  28         view_count_str = self._search_regex(
  29             r'<span class="views_n">([0-9,.]+)</span>',
  30             webpage, 'view count', fatal=False)
  31         view_count = (
  32             None if view_count_str is None
  33             else int(view_count_str.replace(',', '')))
  34         video_id = self._search_regex(
  35             r'<param\s+name="movie"\s+value="/emb/([0-9]+)"\s*/>',
  36             webpage, 'video id')
  37
  38         # Presence of (no)watchplus function indicates HD quality is available
  39         if re.search(r'function (no)?watchplus()', webpage):
  40             fvar = "fvarhd"
  41         else:
  42             fvar = "fvar"
  43
  44         info_url = "http://www.traileraddict.com/%s.php?tid=%s" % (fvar, str(video_id))
  45         info_webpage = self._download_webpage(info_url, video_id , "Downloading the info webpage")
  46
  47         final_url = self._search_regex(r'&fileurl=(.+)',
  48                 info_webpage, 'Download url').replace('%3F','?')
  49         thumbnail_url = self._search_regex(r'&image=(.+?)&',
  50                 info_webpage, 'thumbnail url')
  51
  52         description = self._html_search_regex(
  53             r'(?s)<div class="synopsis">.*?<div class="movie_label_info"[^>]*>(.*?)</div>',
  54             webpage, 'description', fatal=False)
  55
  56         return {
  57             'id': video_id,
  58             'url': final_url,
  59             'title': title,
  60             'thumbnail': thumbnail_url,
  61             'description': description,
  62             'view_count': view_count,
  63         }