youtube_dl/extractor/americastestkitchen.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     clean_html,
   7     int_or_none,
   8     js_to_json,
   9     try_get,
  10     unified_strdate,
  11 )
  12
  13
  14 class AmericasTestKitchenIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)'
  16     _TESTS = [{
  17         'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
  18         'md5': 'b861c3e365ac38ad319cfd509c30577f',
  19         'info_dict': {
  20             'id': '5b400b9ee338f922cb06450c',
  21             'title': 'Weeknight Japanese Suppers',
  22             'ext': 'mp4',
  23             'description': 'md5:3d0c1a44bb3b27607ce82652db25b4a8',
  24             'thumbnail': r're:^https?://',
  25             'timestamp': 1523664000,
  26             'upload_date': '20180414',
  27             'release_date': '20180414',
  28             'series': "America's Test Kitchen",
  29             'season_number': 18,
  30             'episode': 'Weeknight Japanese Suppers',
  31             'episode_number': 15,
  32         },
  33         'params': {
  34             'skip_download': True,
  35         },
  36     }, {
  37         'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
  38         'only_matching': True,
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43
  44         webpage = self._download_webpage(url, video_id)
  45
  46         video_data = self._parse_json(
  47             self._search_regex(
  48                 r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
  49                 webpage, 'initial context'),
  50             video_id, js_to_json)
  51
  52         ep_data = try_get(
  53             video_data,
  54             (lambda x: x['episodeDetail']['content']['data'],
  55              lambda x: x['videoDetail']['content']['data']), dict)
  56         ep_meta = ep_data.get('full_video', {})
  57
  58         zype_id = ep_data.get('zype_id') or ep_meta['zype_id']
  59
  60         title = ep_data.get('title') or ep_meta.get('title')
  61         description = clean_html(ep_meta.get('episode_description') or ep_data.get(
  62             'description') or ep_meta.get('description'))
  63         thumbnail = try_get(ep_meta, lambda x: x['photo']['image_url'])
  64         release_date = unified_strdate(ep_data.get('aired_at'))
  65
  66         season_number = int_or_none(ep_meta.get('season_number'))
  67         episode = ep_meta.get('title')
  68         episode_number = int_or_none(ep_meta.get('episode_number'))
  69
  70         return {
  71             '_type': 'url_transparent',
  72             'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id,
  73             'ie_key': 'Zype',
  74             'title': title,
  75             'description': description,
  76             'thumbnail': thumbnail,
  77             'release_date': release_date,
  78             'series': "America's Test Kitchen",
  79             'season_number': season_number,
  80             'episode': episode,
  81             'episode_number': episode_number,
  82         }