yt_dlp/extractor/discoveryplusindia.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from ..compat import compat_str
   7 from ..utils import try_get
   8 from .common import InfoExtractor
   9 from .dplay import DPlayIE
  10
  11
  12 class DiscoveryPlusIndiaIE(DPlayIE):
  13     _VALID_URL = r'https?://(?:www\.)?discoveryplus\.in/videos?' + DPlayIE._PATH_REGEX
  14     _TESTS = [{
  15         'url': 'https://www.discoveryplus.in/videos/how-do-they-do-it/fugu-and-more?seasonId=8&type=EPISODE',
  16         'info_dict': {
  17             'id': '27104',
  18             'ext': 'mp4',
  19             'display_id': 'how-do-they-do-it/fugu-and-more',
  20             'title': 'Fugu and More',
  21             'description': 'The Japanese catch, prepare and eat the deadliest fish on the planet.',
  22             'duration': 1319,
  23             'timestamp': 1582309800,
  24             'upload_date': '20200221',
  25             'series': 'How Do They Do It?',
  26             'season_number': 8,
  27             'episode_number': 2,
  28             'creator': 'Discovery Channel',
  29         },
  30         'params': {
  31             'format': 'bestvideo',
  32             'skip_download': True,
  33         },
  34         'skip': 'Cookies (not necessarily logged in) are needed'
  35     }]
  36
  37     def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
  38         headers['x-disco-params'] = 'realm=%s' % realm
  39         headers['x-disco-client'] = 'WEB:UNKNOWN:dplus-india:17.0.0'
  40
  41     def _download_video_playback_info(self, disco_base, video_id, headers):
  42         return self._download_json(
  43             disco_base + 'playback/v3/videoPlaybackInfo',
  44             video_id, headers=headers, data=json.dumps({
  45                 'deviceInfo': {
  46                     'adBlocker': False,
  47                 },
  48                 'videoId': video_id,
  49             }).encode('utf-8'))['data']['attributes']['streaming']
  50
  51     def _real_extract(self, url):
  52         display_id = self._match_id(url)
  53         return self._get_disco_api_info(
  54             url, display_id, 'ap2-prod-direct.discoveryplus.in', 'dplusindia', 'in')
  55
  56
  57 class DiscoveryPlusIndiaShowIE(InfoExtractor):
  58     _VALID_URL = r'https?://(?:www\.)?discoveryplus\.in/show/(?P<show_name>[^/]+)/?(?:[?#]|$)'
  59     _TESTS = [{
  60         'url': 'https://www.discoveryplus.in/show/how-do-they-do-it',
  61         'playlist_mincount': 140,
  62         'info_dict': {
  63             'id': 'how-do-they-do-it',
  64         },
  65     }]
  66
  67     def _entries(self, show_name):
  68         headers = {
  69             'x-disco-client': 'WEB:UNKNOWN:dplus-india:prod',
  70             'x-disco-params': 'realm=dplusindia',
  71             'referer': 'https://www.discoveryplus.in/',
  72         }
  73         show_url = 'https://ap2-prod-direct.discoveryplus.in/cms/routes/show/{}?include=default'.format(show_name)
  74         show_json = self._download_json(show_url,
  75                                         video_id=show_name,
  76                                         headers=headers)['included'][4]['attributes']['component']
  77         show_id = show_json['mandatoryParams'].split('=')[-1]
  78         season_url = 'https://ap2-prod-direct.discoveryplus.in/content/videos?sort=episodeNumber&filter[seasonNumber]={}&filter[show.id]={}&page[size]=100&page[number]={}'
  79         for season in show_json['filters'][0]['options']:
  80             season_id = season['id']
  81             total_pages, page_num = 1, 0
  82             while page_num < total_pages:
  83                 season_json = self._download_json(season_url.format(season_id, show_id, compat_str(page_num + 1)),
  84                                                   video_id=show_id, headers=headers,
  85                                                   note='Downloading JSON metadata%s' % (' page %d' % page_num if page_num else ''))
  86                 if page_num == 0:
  87                     total_pages = try_get(season_json, lambda x: x['meta']['totalPages'], int) or 1
  88                 episodes_json = season_json['data']
  89                 for episode in episodes_json:
  90                     video_id = episode['attributes']['path']
  91                     yield self.url_result(
  92                         'https://discoveryplus.in/videos/%s' % video_id,
  93                         ie=DiscoveryPlusIndiaIE.ie_key(), video_id=video_id)
  94                 page_num += 1
  95
  96     def _real_extract(self, url):
  97         show_name = self._match_valid_url(url).group('show_name')
  98         return self.playlist_result(self._entries(show_name), playlist_id=show_name)