Raphaël G. Git Repositories - youtubedl/blob - 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     try_get,
   9     unified_strdate,
  10 )
  11
  12
  13 class AmericasTestKitchenIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)'
  15     _TESTS = [{
  16         'url': 'https://www.americastestkitchen.com/episode/548-summer-dinner-party',
  17         'md5': 'b861c3e365ac38ad319cfd509c30577f',
  18         'info_dict': {
  19             'id': '1_5g5zua6e',
  20             'title': 'Summer Dinner Party',
  21             'ext': 'mp4',
  22             'description': 'md5:858d986e73a4826979b6a5d9f8f6a1ec',
  23             'thumbnail': r're:^https?://.*\.jpg',
  24             'timestamp': 1497285541,
  25             'upload_date': '20170612',
  26             'uploader_id': 'roger.metcalf@americastestkitchen.com',
  27             'release_date': '20170617',
  28             'series': "America's Test Kitchen",
  29             'season_number': 17,
  30             'episode': 'Summer Dinner Party',
  31             'episode_number': 24,
  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         partner_id = self._search_regex(
  47             r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
  48             webpage, 'kaltura partner id')
  49
  50         video_data = self._parse_json(
  51             self._search_regex(
  52                 r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
  53                 webpage, 'initial context'),
  54             video_id)
  55
  56         ep_data = try_get(
  57             video_data,
  58             (lambda x: x['episodeDetail']['content']['data'],
  59              lambda x: x['videoDetail']['content']['data']), dict)
  60         ep_meta = ep_data.get('full_video', {})
  61         external_id = ep_data.get('external_id') or ep_meta['external_id']
  62
  63         title = ep_data.get('title') or ep_meta.get('title')
  64         description = clean_html(ep_meta.get('episode_description') or ep_data.get(
  65             'description') or ep_meta.get('description'))
  66         thumbnail = try_get(ep_meta, lambda x: x['photo']['image_url'])
  67         release_date = unified_strdate(ep_data.get('aired_at'))
  68
  69         season_number = int_or_none(ep_meta.get('season_number'))
  70         episode = ep_meta.get('title')
  71         episode_number = int_or_none(ep_meta.get('episode_number'))
  72
  73         return {
  74             '_type': 'url_transparent',
  75             'url': 'kaltura:%s:%s' % (partner_id, external_id),
  76             'ie_key': 'Kaltura',
  77             'title': title,
  78             'description': description,
  79             'thumbnail': thumbnail,
  80             'release_date': release_date,
  81             'series': "America's Test Kitchen",
  82             'season_number': season_number,
  83             'episode': episode,
  84             'episode_number': episode_number,
  85         }