yt_dlp/extractor/adultswim.py

   1 import json
   2
   3 from .turner import TurnerBaseIE
   4 from ..utils import (
   5     determine_ext,
   6     float_or_none,
   7     int_or_none,
   8     mimetype2ext,
   9     parse_age_limit,
  10     parse_iso8601,
  11     strip_or_none,
  12     try_get,
  13 )
  14
  15
  16 class AdultSwimIE(TurnerBaseIE):
  17     _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<show_path>[^/?#]+)(?:/(?P<episode_path>[^/?#]+))?'
  18
  19     _TESTS = [{
  20         'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
  21         'info_dict': {
  22             'id': 'rQxZvXQ4ROaSOqq-or2Mow',
  23             'ext': 'mp4',
  24             'title': 'Rick and Morty - Pilot',
  25             'description': 'Rick moves in with his daughter\'s family and establishes himself as a bad influence on his grandson, Morty.',
  26             'timestamp': 1543294800,
  27             'upload_date': '20181127',
  28         },
  29         'params': {
  30             # m3u8 download
  31             'skip_download': True,
  32         },
  33         'expected_warnings': ['Unable to download f4m manifest'],
  34     }, {
  35         'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
  36         'info_dict': {
  37             'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
  38             'ext': 'mp4',
  39             'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
  40             'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.',
  41             'upload_date': '20080124',
  42             'timestamp': 1201150800,
  43         },
  44         'params': {
  45             # m3u8 download
  46             'skip_download': True,
  47         },
  48         'skip': '404 Not Found',
  49     }, {
  50         'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
  51         'info_dict': {
  52             'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
  53             'ext': 'mp4',
  54             'title': 'Decker - Inside Decker: A New Hero',
  55             'description': 'The guys recap the conclusion of the season. They announce a new hero, take a peek into the Victorville Film Archive and welcome back the talented James Dean.',
  56             'timestamp': 1469480460,
  57             'upload_date': '20160725',
  58         },
  59         'params': {
  60             # m3u8 download
  61             'skip_download': True,
  62         },
  63         'expected_warnings': ['Unable to download f4m manifest'],
  64     }, {
  65         'url': 'http://www.adultswim.com/videos/attack-on-titan',
  66         'info_dict': {
  67             'id': 'attack-on-titan',
  68             'title': 'Attack on Titan',
  69             'description': 'md5:41caa9416906d90711e31dc00cb7db7e',
  70         },
  71         'playlist_mincount': 12,
  72     }, {
  73         'url': 'http://www.adultswim.com/videos/streams/williams-stream',
  74         'info_dict': {
  75             'id': 'd8DEBj7QRfetLsRgFnGEyg',
  76             'ext': 'mp4',
  77             'title': r're:^Williams Stream \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
  78             'description': 'original programming',
  79         },
  80         'params': {
  81             # m3u8 download
  82             'skip_download': True,
  83         },
  84         'skip': '404 Not Found',
  85     }]
  86
  87     def _real_extract(self, url):
  88         show_path, episode_path = self._match_valid_url(url).groups()
  89         display_id = episode_path or show_path
  90         query = '''query {
  91   getShowBySlug(slug:"%s") {
  92     %%s
  93   }
  94 }''' % show_path  # noqa: UP031
  95         if episode_path:
  96             query = query % '''title
  97     getVideoBySlug(slug:"%s") {
  98       _id
  99       auth
 100       description
 101       duration
 102       episodeNumber
 103       launchDate
 104       mediaID
 105       seasonNumber
 106       poster
 107       title
 108       tvRating
 109     }''' % episode_path
 110         else:
 111             query = query % '''metaDescription
 112     title
 113     videos(first:1000,sort:["episode_number"]) {
 114       edges {
 115         node {
 116            _id
 117            slug
 118         }
 119       }
 120     }'''
 121         show_data = self._download_json(
 122             'https://www.adultswim.com/api/search', display_id,
 123             data=json.dumps({'query': query}).encode(),
 124             headers={'Content-Type': 'application/json'})['data']['getShowBySlug']
 125         if episode_path:
 126             video_data = show_data['getVideoBySlug']
 127             video_id = video_data['_id']
 128             episode_title = title = video_data['title']
 129             series = show_data.get('title')
 130             if series:
 131                 title = f'{series} - {title}'
 132             info = {
 133                 'id': video_id,
 134                 'title': title,
 135                 'description': strip_or_none(video_data.get('description')),
 136                 'duration': float_or_none(video_data.get('duration')),
 137                 'formats': [],
 138                 'subtitles': {},
 139                 'age_limit': parse_age_limit(video_data.get('tvRating')),
 140                 'thumbnail': video_data.get('poster'),
 141                 'timestamp': parse_iso8601(video_data.get('launchDate')),
 142                 'series': series,
 143                 'season_number': int_or_none(video_data.get('seasonNumber')),
 144                 'episode': episode_title,
 145                 'episode_number': int_or_none(video_data.get('episodeNumber')),
 146             }
 147
 148             auth = video_data.get('auth')
 149             media_id = video_data.get('mediaID')
 150             if media_id:
 151                 info.update(self._extract_ngtv_info(media_id, {
 152                     # CDN_TOKEN_APP_ID from:
 153                     # https://d2gg02c3xr550i.cloudfront.net/assets/asvp.e9c8bef24322d060ef87.bundle.js
 154                     'appId': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhcHBJZCI6ImFzLXR2ZS1kZXNrdG9wLXB0enQ2bSIsInByb2R1Y3QiOiJ0dmUiLCJuZXR3b3JrIjoiYXMiLCJwbGF0Zm9ybSI6ImRlc2t0b3AiLCJpYXQiOjE1MzI3MDIyNzl9.BzSCk-WYOZ2GMCIaeVb8zWnzhlgnXuJTCu0jGp_VaZE',
 155                 }, {
 156                     'url': url,
 157                     'site_name': 'AdultSwim',
 158                     'auth_required': auth,
 159                 }))
 160
 161             if not auth:
 162                 extract_data = self._download_json(
 163                     'https://www.adultswim.com/api/shows/v1/videos/' + video_id,
 164                     video_id, query={'fields': 'stream'}, fatal=False) or {}
 165                 assets = try_get(extract_data, lambda x: x['data']['video']['stream']['assets'], list) or []
 166                 for asset in assets:
 167                     asset_url = asset.get('url')
 168                     if not asset_url:
 169                         continue
 170                     ext = determine_ext(asset_url, mimetype2ext(asset.get('mime_type')))
 171                     if ext == 'm3u8':
 172                         fmts, subs = self._extract_m3u8_formats_and_subtitles(
 173                             asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
 174                         info['formats'].extend(fmts)
 175                         self._merge_subtitles(subs, target=info['subtitles'])
 176                     elif ext == 'f4m':
 177                         continue
 178                         # info['formats'].extend(self._extract_f4m_formats(
 179                         #     asset_url, video_id, f4m_id='hds', fatal=False))
 180                     elif ext in ('scc', 'ttml', 'vtt'):
 181                         info['subtitles'].setdefault('en', []).append({
 182                             'url': asset_url,
 183                         })
 184
 185             return info
 186         else:
 187             entries = []
 188             for edge in show_data.get('videos', {}).get('edges', []):
 189                 video = edge.get('node') or {}
 190                 slug = video.get('slug')
 191                 if not slug:
 192                     continue
 193                 entries.append(self.url_result(
 194                     f'http://adultswim.com/videos/{show_path}/{slug}',
 195                     'AdultSwim', video.get('_id')))
 196             return self.playlist_result(
 197                 entries, show_path, show_data.get('title'),
 198                 strip_or_none(show_data.get('metaDescription')))