Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/historicfilms.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import parse_duration
   5
   6
   7 class HistoricFilmsIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?historicfilms\.com/(?:tapes/|play)(?P<id>\d+)'
   9     _TEST = {
  10         'url': 'http://www.historicfilms.com/tapes/4728',
  11         'md5': 'd4a437aec45d8d796a38a215db064e9a',
  12         'info_dict': {
  13             'id': '4728',
  14             'ext': 'mov',
  15             'title': 'Historic Films: GP-7',
  16             'description': 'md5:1a86a0f3ac54024e419aba97210d959a',
  17             'thumbnail': r're:^https?://.*\.jpg$',
  18             'duration': 2096,
  19         },
  20     }
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24
  25         webpage = self._download_webpage(url, video_id)
  26
  27         tape_id = self._search_regex(
  28             [r'class="tapeId"[^>]*>([^<]+)<', r'tapeId\s*:\s*"([^"]+)"'],
  29             webpage, 'tape id')
  30
  31         title = self._og_search_title(webpage)
  32         description = self._og_search_description(webpage)
  33         thumbnail = self._html_search_meta(
  34             'thumbnailUrl', webpage, 'thumbnails') or self._og_search_thumbnail(webpage)
  35         duration = parse_duration(self._html_search_meta(
  36             'duration', webpage, 'duration'))
  37
  38         video_url = 'http://www.historicfilms.com/video/%s_%s_web.mov' % (tape_id, video_id)
  39
  40         return {
  41             'id': video_id,
  42             'url': video_url,
  43             'title': title,
  44             'description': description,
  45             'thumbnail': thumbnail,
  46             'duration': duration,
  47         }