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     _WORKING = False
  10     _VALID_URL = r'(?:https?://)?(?:www\.)?traileraddict\.com/(?:trailer|clip)/(?P<movie>.+?)/(?P<trailer_name>.+)'
  11     _TEST = {
  12         'url': 'http://www.traileraddict.com/trailer/prince-avalanche/trailer',
  13         'md5': '41365557f3c8c397d091da510e73ceb4',
  14         'info_dict': {
  15             'id': '76184',
  16             'ext': 'mp4',
  17             'title': 'Prince Avalanche Trailer',
  18             '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.',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         name = mobj.group('movie') + '/' + mobj.group('trailer_name')
  25         webpage = self._download_webpage(url, name)
  26
  27         title = self._search_regex(r'<title>(.+?)</title>',
  28                                    webpage, 'video title').replace(' - Trailer Addict', '')
  29         view_count_str = self._search_regex(
  30             r'<span class="views_n">([0-9,.]+)</span>',
  31             webpage, 'view count', fatal=False)
  32         view_count = (
  33             None if view_count_str is None
  34             else int(view_count_str.replace(',', '')))
  35         video_id = self._search_regex(
  36             r'<param\s+name="movie"\s+value="/emb/([0-9]+)"\s*/>',
  37             webpage, 'video id')
  38
  39         # Presence of (no)watchplus function indicates HD quality is available
  40         if re.search(r'function (no)?watchplus()', webpage):
  41             fvar = 'fvarhd'
  42         else:
  43             fvar = 'fvar'
  44
  45         info_url = 'http://www.traileraddict.com/%s.php?tid=%s' % (fvar, str(video_id))
  46         info_webpage = self._download_webpage(info_url, video_id, 'Downloading the info webpage')
  47
  48         final_url = self._search_regex(r'&fileurl=(.+)',
  49                                        info_webpage, 'Download url').replace('%3F', '?')
  50         thumbnail_url = self._search_regex(r'&image=(.+?)&',
  51                                            info_webpage, 'thumbnail url')
  52
  53         description = self._html_search_regex(
  54             r'(?s)<div class="synopsis">.*?<div class="movie_label_info"[^>]*>(.*?)</div>',
  55             webpage, 'description', fatal=False)
  56
  57         return {
  58             'id': video_id,
  59             'url': final_url,
  60             'title': title,
  61             'thumbnail': thumbnail_url,
  62             'description': description,
  63             'view_count': view_count,
  64         }