yt_dlp/extractor/tenplay.py

   1 import base64
   2 import functools
   3 import itertools
   4 from datetime import datetime
   5
   6 from .common import InfoExtractor
   7 from ..networking import HEADRequest
   8 from ..utils import int_or_none, traverse_obj, urlencode_postdata, urljoin
   9
  10
  11 class TenPlayIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?:[^/]+/)+(?P<id>tpv\d{6}[a-z]{5})'
  13     _NETRC_MACHINE = '10play'
  14     _TESTS = [{
  15         'url': 'https://10play.com.au/neighbours/web-extras/season-39/nathan-borg-is-the-first-aussie-actor-with-a-cochlear-implant-to-join-neighbours/tpv210128qupwd',
  16         'info_dict': {
  17             'id': '6226844312001',
  18             'ext': 'mp4',
  19             'title': 'Nathan Borg Is The First Aussie Actor With A Cochlear Implant To Join Neighbours',
  20             'alt_title': 'Nathan Borg Is The First Aussie Actor With A Cochlear Implant To Join Neighbours',
  21             'description': 'md5:a02d0199c901c2dd4c796f1e7dd0de43',
  22             'duration': 186,
  23             'season': 'Season 39',
  24             'season_number': 39,
  25             'series': 'Neighbours',
  26             'thumbnail': r're:https://.*\.jpg',
  27             'uploader': 'Channel 10',
  28             'age_limit': 15,
  29             'timestamp': 1611810000,
  30             'upload_date': '20210128',
  31             'uploader_id': '2199827728001',
  32         },
  33         'params': {
  34             'skip_download': True,
  35         },
  36         'skip': 'Only available in Australia',
  37     }, {
  38         'url': 'https://10play.com.au/todd-sampsons-body-hack/episodes/season-4/episode-7/tpv200921kvngh',
  39         'info_dict': {
  40             'id': '6192880312001',
  41             'ext': 'mp4',
  42             'title': "Todd Sampson's Body Hack - S4 Ep. 2",
  43             'description': 'md5:fa278820ad90f08ea187f9458316ac74',
  44             'age_limit': 15,
  45             'timestamp': 1600770600,
  46             'upload_date': '20200922',
  47             'uploader': 'Channel 10',
  48             'uploader_id': '2199827728001'
  49         },
  50         'params': {
  51             'skip_download': True,
  52         }
  53     }, {
  54         'url': 'https://10play.com.au/how-to-stay-married/web-extras/season-1/terrys-talks-ep-1-embracing-change/tpv190915ylupc',
  55         'only_matching': True,
  56     }]
  57     _GEO_BYPASS = False
  58
  59     _AUS_AGES = {
  60         'G': 0,
  61         'PG': 15,
  62         'M': 15,
  63         'MA': 15,
  64         'MA15+': 15,
  65         'R': 18,
  66         'X': 18
  67     }
  68
  69     def _get_bearer_token(self, video_id):
  70         username, password = self._get_login_info()
  71         if username is None or password is None:
  72             self.raise_login_required('Your 10play account\'s details must be provided with --username and --password.')
  73         _timestamp = datetime.now().strftime('%Y%m%d000000')
  74         _auth_header = base64.b64encode(_timestamp.encode('ascii')).decode('ascii')
  75         data = self._download_json('https://10play.com.au/api/user/auth', video_id, 'Getting bearer token', headers={
  76             'X-Network-Ten-Auth': _auth_header,
  77         }, data=urlencode_postdata({
  78             'email': username,
  79             'password': password,
  80         }))
  81         return 'Bearer ' + data['jwt']['accessToken']
  82
  83     def _real_extract(self, url):
  84         content_id = self._match_id(url)
  85         data = self._download_json(
  86             'https://10play.com.au/api/v1/videos/' + content_id, content_id)
  87         headers = {}
  88
  89         if data.get('memberGated') is True:
  90             _token = self._get_bearer_token(content_id)
  91             headers = {'Authorization': _token}
  92
  93         _video_url = self._download_json(
  94             data.get('playbackApiEndpoint'), content_id, 'Downloading video JSON',
  95             headers=headers).get('source')
  96         m3u8_url = self._request_webpage(HEADRequest(
  97             _video_url), content_id).url
  98         if '10play-not-in-oz' in m3u8_url:
  99             self.raise_geo_restricted(countries=['AU'])
 100         formats = self._extract_m3u8_formats(m3u8_url, content_id, 'mp4')
 101
 102         return {
 103             'formats': formats,
 104             'subtitles': {'en': [{'url': data.get('captionUrl')}]} if data.get('captionUrl') else None,
 105             'id': data.get('altId') or content_id,
 106             'duration': data.get('duration'),
 107             'title': data.get('subtitle'),
 108             'alt_title': data.get('title'),
 109             'description': data.get('description'),
 110             'age_limit': self._AUS_AGES.get(data.get('classification')),
 111             'series': data.get('tvShow'),
 112             'season_number': int_or_none(data.get('season')),
 113             'episode_number': int_or_none(data.get('episode')),
 114             'timestamp': data.get('published'),
 115             'thumbnail': data.get('imageUrl'),
 116             'uploader': 'Channel 10',
 117             'uploader_id': '2199827728001',
 118         }
 119
 120
 121 class TenPlaySeasonIE(InfoExtractor):
 122     _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?P<show>[^/?#]+)/episodes/(?P<season>[^/?#]+)/?(?:$|[?#])'
 123     _TESTS = [{
 124         'url': 'https://10play.com.au/masterchef/episodes/season-14',
 125         'info_dict': {
 126             'title': 'Season 14',
 127             'id': 'MjMyOTIy',
 128         },
 129         'playlist_mincount': 64,
 130     }, {
 131         'url': 'https://10play.com.au/the-bold-and-the-beautiful-fast-tracked/episodes/season-2022',
 132         'info_dict': {
 133             'title': 'Season 2022',
 134             'id': 'Mjc0OTIw',
 135         },
 136         'playlist_mincount': 256,
 137     }]
 138
 139     def _entries(self, load_more_url, display_id=None):
 140         skip_ids = []
 141         for page in itertools.count(1):
 142             episodes_carousel = self._download_json(
 143                 load_more_url, display_id, query={'skipIds[]': skip_ids},
 144                 note=f'Fetching episodes page {page}')
 145
 146             episodes_chunk = episodes_carousel['items']
 147             skip_ids.extend(ep['id'] for ep in episodes_chunk)
 148
 149             for ep in episodes_chunk:
 150                 yield ep['cardLink']
 151             if not episodes_carousel['hasMore']:
 152                 break
 153
 154     def _real_extract(self, url):
 155         show, season = self._match_valid_url(url).group('show', 'season')
 156         season_info = self._download_json(
 157             f'https://10play.com.au/api/shows/{show}/episodes/{season}', f'{show}/{season}')
 158
 159         episodes_carousel = traverse_obj(season_info, (
 160             'content', 0, 'components', (
 161                 lambda _, v: v['title'].lower() == 'episodes',
 162                 (..., {dict}),
 163             )), get_all=False) or {}
 164
 165         playlist_id = episodes_carousel['tpId']
 166
 167         return self.playlist_from_matches(
 168             self._entries(urljoin(url, episodes_carousel['loadMoreUrl']), playlist_id),
 169             playlist_id, traverse_obj(season_info, ('content', 0, 'title', {str})),
 170             getter=functools.partial(urljoin, url))