yt_dlp/extractor/traileraddict.py

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