yt_dlp/extractor/hotstar.py

   1 import hashlib
   2 import hmac
   3 import json
   4 import re
   5 import time
   6 import uuid
   7
   8 from .common import InfoExtractor
   9 from ..networking.exceptions import HTTPError
  10 from ..utils import (
  11     ExtractorError,
  12     determine_ext,
  13     int_or_none,
  14     join_nonempty,
  15     str_or_none,
  16     traverse_obj,
  17     url_or_none,
  18 )
  19
  20
  21 class HotStarBaseIE(InfoExtractor):
  22     _BASE_URL = 'https://www.hotstar.com'
  23     _API_URL = 'https://api.hotstar.com'
  24     _AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
  25
  26     def _call_api_v1(self, path, *args, **kwargs):
  27         return self._download_json(
  28             f'{self._API_URL}/o/v1/{path}', *args, **kwargs,
  29             headers={'x-country-code': 'IN', 'x-platform-code': 'PCTV'})
  30
  31     def _call_api_impl(self, path, video_id, query, st=None, cookies=None):
  32         st = int_or_none(st) or int(time.time())
  33         exp = st + 6000
  34         auth = f'st={st}~exp={exp}~acl=/*'
  35         auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
  36
  37         if cookies and cookies.get('userUP'):
  38             token = cookies.get('userUP').value
  39         else:
  40             token = self._download_json(
  41                 f'{self._API_URL}/um/v3/users',
  42                 video_id, note='Downloading token',
  43                 data=json.dumps({'device_ids': [{'id': str(uuid.uuid4()), 'type': 'device_id'}]}).encode(),
  44                 headers={
  45                     'hotstarauth': auth,
  46                     'x-hs-platform': 'PCTV',  # or 'web'
  47                     'Content-Type': 'application/json',
  48                 })['user_identity']
  49
  50         response = self._download_json(
  51             f'{self._API_URL}/{path}', video_id, query=query,
  52             headers={
  53                 'hotstarauth': auth,
  54                 'x-hs-appversion': '6.72.2',
  55                 'x-hs-platform': 'web',
  56                 'x-hs-usertoken': token,
  57             })
  58
  59         if response['message'] != "Playback URL's fetched successfully":
  60             raise ExtractorError(
  61                 response['message'], expected=True)
  62         return response['data']
  63
  64     def _call_api_v2(self, path, video_id, st=None, cookies=None):
  65         return self._call_api_impl(
  66             f'{path}/content/{video_id}', video_id, st=st, cookies=cookies, query={
  67                 'desired-config': 'audio_channel:stereo|container:fmp4|dynamic_range:hdr|encryption:plain|ladder:tv|package:dash|resolution:fhd|subs-tag:HotstarVIP|video_codec:h265',
  68                 'device-id': cookies.get('device_id').value if cookies.get('device_id') else str(uuid.uuid4()),
  69                 'os-name': 'Windows',
  70                 'os-version': '10',
  71             })
  72
  73     def _playlist_entries(self, path, item_id, root=None, **kwargs):
  74         results = self._call_api_v1(path, item_id, **kwargs)['body']['results']
  75         for video in traverse_obj(results, (('assets', None), 'items', ...)):
  76             if video.get('contentId'):
  77                 yield self.url_result(
  78                     HotStarIE._video_url(video['contentId'], root=root), HotStarIE, video['contentId'])
  79
  80
  81 class HotStarIE(HotStarBaseIE):
  82     IE_NAME = 'hotstar'
  83     _VALID_URL = r'''(?x)
  84         https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/)
  85         (?:
  86             (?P<type>movies|sports|clips|episode|(?P<tv>tv|shows))/
  87             (?(tv)(?:[^/?#]+/){2}|[^?#]*)
  88         )?
  89         [^/?#]+/
  90         (?P<id>\d{10})
  91     '''
  92
  93     _TESTS = [{
  94         'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273',
  95         'info_dict': {
  96             'id': '1000076273',
  97             'ext': 'mp4',
  98             'title': 'Can You Not Spread Rumours?',
  99             'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
 100             'timestamp': 1447248600,
 101             'upload_date': '20151111',
 102             'duration': 381,
 103             'episode': 'Can You Not Spread Rumours?',
 104         },
 105         'params': {'skip_download': 'm3u8'},
 106     }, {
 107         'url': 'https://www.hotstar.com/tv/ek-bhram-sarvagun-sampanna/s-2116/janhvi-targets-suman/1000234847',
 108         'info_dict': {
 109             'id': '1000234847',
 110             'ext': 'mp4',
 111             'title': 'Janhvi Targets Suman',
 112             'description': 'md5:78a85509348910bd1ca31be898c5796b',
 113             'timestamp': 1556670600,
 114             'upload_date': '20190501',
 115             'duration': 1219,
 116             'channel': 'StarPlus',
 117             'channel_id': '3',
 118             'series': 'Ek Bhram - Sarvagun Sampanna',
 119             'season': 'Chapter 1',
 120             'season_number': 1,
 121             'season_id': '6771',
 122             'episode': 'Janhvi Targets Suman',
 123             'episode_number': 8,
 124         },
 125     }, {
 126         'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/anupama-anuj-share-a-moment/1000282843',
 127         'info_dict': {
 128             'id': '1000282843',
 129             'ext': 'mp4',
 130             'title': 'Anupama, Anuj Share a Moment',
 131             'season': 'Chapter 1',
 132             'description': 'md5:8d74ed2248423b8b06d5c8add4d7a0c0',
 133             'timestamp': 1678149000,
 134             'channel': 'StarPlus',
 135             'series': 'Anupama',
 136             'season_number': 1,
 137             'season_id': '7399',
 138             'upload_date': '20230307',
 139             'episode': 'Anupama, Anuj Share a Moment',
 140             'episode_number': 853,
 141             'duration': 1272,
 142             'channel_id': '3',
 143         },
 144         'skip': 'HTTP Error 504: Gateway Time-out',  # XXX: Investigate 504 errors on some episodes
 145     }, {
 146         'url': 'https://www.hotstar.com/in/shows/kana-kaanum-kaalangal/1260097087/back-to-school/1260097320',
 147         'info_dict': {
 148             'id': '1260097320',
 149             'ext': 'mp4',
 150             'title': 'Back To School',
 151             'season': 'Chapter 1',
 152             'description': 'md5:b0d6a4c8a650681491e7405496fc7e13',
 153             'timestamp': 1650564000,
 154             'channel': 'Hotstar Specials',
 155             'series': 'Kana Kaanum Kaalangal',
 156             'season_number': 1,
 157             'season_id': '9441',
 158             'upload_date': '20220421',
 159             'episode': 'Back To School',
 160             'episode_number': 1,
 161             'duration': 1810,
 162             'channel_id': '54',
 163         },
 164     }, {
 165         'url': 'https://www.hotstar.com/in/clips/e3-sairat-kahani-pyaar-ki/1000262286',
 166         'info_dict': {
 167             'id': '1000262286',
 168             'ext': 'mp4',
 169             'title': 'E3 - SaiRat, Kahani Pyaar Ki',
 170             'description': 'md5:e3b4b3203bc0c5396fe7d0e4948a6385',
 171             'episode': 'E3 - SaiRat, Kahani Pyaar Ki',
 172             'upload_date': '20210606',
 173             'timestamp': 1622943900,
 174             'duration': 5395,
 175         },
 176     }, {
 177         'url': 'https://www.hotstar.com/in/movies/premam/1000091195',
 178         'info_dict': {
 179             'id': '1000091195',
 180             'ext': 'mp4',
 181             'title': 'Premam',
 182             'release_year': 2015,
 183             'description': 'md5:d833c654e4187b5e34757eafb5b72d7f',
 184             'timestamp': 1462149000,
 185             'upload_date': '20160502',
 186             'episode': 'Premam',
 187             'duration': 8994,
 188         },
 189     }, {
 190         'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
 191         'only_matching': True,
 192     }, {
 193         'url': 'https://www.hotstar.com/in/sports/cricket/follow-the-blues-2021/recap-eng-fight-back-on-day-2/1260066104',
 194         'only_matching': True,
 195     }, {
 196         'url': 'https://www.hotstar.com/in/sports/football/most-costly-pl-transfers-ft-grealish/1260065956',
 197         'only_matching': True,
 198     }]
 199     _GEO_BYPASS = False
 200
 201     _TYPE = {
 202         'movies': 'movie',
 203         'sports': 'match',
 204         'episode': 'episode',
 205         'tv': 'episode',
 206         'shows': 'episode',
 207         'clips': 'content',
 208         None: 'content',
 209     }
 210
 211     _IGNORE_MAP = {
 212         'res': 'resolution',
 213         'vcodec': 'video_codec',
 214         'dr': 'dynamic_range',
 215     }
 216
 217     _TAG_FIELDS = {
 218         'language': 'language',
 219         'acodec': 'audio_codec',
 220         'vcodec': 'video_codec',
 221     }
 222
 223     @classmethod
 224     def _video_url(cls, video_id, video_type=None, *, slug='ignore_me', root=None):
 225         assert None in (video_type, root)
 226         if not root:
 227             root = join_nonempty(cls._BASE_URL, video_type, delim='/')
 228         return f'{root}/{slug}/{video_id}'
 229
 230     def _real_extract(self, url):
 231         video_id, video_type = self._match_valid_url(url).group('id', 'type')
 232         video_type = self._TYPE.get(video_type, video_type)
 233         cookies = self._get_cookies(url)  # Cookies before any request
 234
 235         video_data = traverse_obj(
 236             self._call_api_v1(
 237                 f'{video_type}/detail', video_id, fatal=False, query={'tas': 10000, 'contentId': video_id}),
 238             ('body', 'results', 'item', {dict})) or {}
 239         if not self.get_param('allow_unplayable_formats') and video_data.get('drmProtected'):
 240             self.report_drm(video_id)
 241
 242         # See https://github.com/yt-dlp/yt-dlp/issues/396
 243         st = self._download_webpage_handle(f'{self._BASE_URL}/in', video_id)[1].headers.get('x-origin-date')
 244
 245         geo_restricted = False
 246         formats, subs = [], {}
 247         headers = {'Referer': f'{self._BASE_URL}/in'}
 248
 249         # change to v2 in the future
 250         playback_sets = self._call_api_v2('play/v1/playback', video_id, st=st, cookies=cookies)['playBackSets']
 251         for playback_set in playback_sets:
 252             if not isinstance(playback_set, dict):
 253                 continue
 254             tags = str_or_none(playback_set.get('tagsCombination')) or ''
 255             if any(f'{prefix}:{ignore}' in tags
 256                    for key, prefix in self._IGNORE_MAP.items()
 257                    for ignore in self._configuration_arg(key)):
 258                 continue
 259
 260             format_url = url_or_none(playback_set.get('playbackUrl'))
 261             if not format_url:
 262                 continue
 263             format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', format_url)
 264             ext = determine_ext(format_url)
 265
 266             current_formats, current_subs = [], {}
 267             try:
 268                 if 'package:hls' in tags or ext == 'm3u8':
 269                     current_formats, current_subs = self._extract_m3u8_formats_and_subtitles(
 270                         format_url, video_id, ext='mp4', headers=headers)
 271                 elif 'package:dash' in tags or ext == 'mpd':
 272                     current_formats, current_subs = self._extract_mpd_formats_and_subtitles(
 273                         format_url, video_id, headers=headers)
 274                 elif ext == 'f4m':
 275                     pass  # XXX: produce broken files
 276                 else:
 277                     current_formats = [{
 278                         'url': format_url,
 279                         'width': int_or_none(playback_set.get('width')),
 280                         'height': int_or_none(playback_set.get('height')),
 281                     }]
 282             except ExtractorError as e:
 283                 if isinstance(e.cause, HTTPError) and e.cause.status == 403:
 284                     geo_restricted = True
 285                 continue
 286
 287             tag_dict = dict((*t.split(':', 1), None)[:2] for t in tags.split(';'))
 288             if tag_dict.get('encryption') not in ('plain', None):
 289                 for f in current_formats:
 290                     f['has_drm'] = True
 291             for f in current_formats:
 292                 for k, v in self._TAG_FIELDS.items():
 293                     if not f.get(k):
 294                         f[k] = tag_dict.get(v)
 295                 if f.get('vcodec') != 'none' and not f.get('dynamic_range'):
 296                     f['dynamic_range'] = tag_dict.get('dynamic_range')
 297                 if f.get('acodec') != 'none' and not f.get('audio_channels'):
 298                     f['audio_channels'] = {
 299                         'stereo': 2,
 300                         'dolby51': 6,
 301                     }.get(tag_dict.get('audio_channel'))
 302                 f['format_note'] = join_nonempty(
 303                     tag_dict.get('ladder'),
 304                     tag_dict.get('audio_channel') if f.get('acodec') != 'none' else None,
 305                     f.get('format_note'),
 306                     delim=', ')
 307
 308             formats.extend(current_formats)
 309             subs = self._merge_subtitles(subs, current_subs)
 310
 311         if not formats and geo_restricted:
 312             self.raise_geo_restricted(countries=['IN'], metadata_available=True)
 313         self._remove_duplicate_formats(formats)
 314         for f in formats:
 315             f.setdefault('http_headers', {}).update(headers)
 316
 317         return {
 318             'id': video_id,
 319             'title': video_data.get('title'),
 320             'description': video_data.get('description'),
 321             'duration': int_or_none(video_data.get('duration')),
 322             'timestamp': int_or_none(traverse_obj(video_data, 'broadcastDate', 'startDate')),
 323             'release_year': int_or_none(video_data.get('year')),
 324             'formats': formats,
 325             'subtitles': subs,
 326             'channel': video_data.get('channelName'),
 327             'channel_id': str_or_none(video_data.get('channelId')),
 328             'series': video_data.get('showName'),
 329             'season': video_data.get('seasonName'),
 330             'season_number': int_or_none(video_data.get('seasonNo')),
 331             'season_id': str_or_none(video_data.get('seasonId')),
 332             'episode': video_data.get('title'),
 333             'episode_number': int_or_none(video_data.get('episodeNo')),
 334         }
 335
 336
 337 class HotStarPrefixIE(InfoExtractor):
 338     """ The "hotstar:" prefix is no longer in use, but this is kept for backward compatibility """
 339     IE_DESC = False
 340     _VALID_URL = r'hotstar:(?:(?P<type>\w+):)?(?P<id>\d+)$'
 341     _TESTS = [{
 342         'url': 'hotstar:1000076273',
 343         'only_matching': True,
 344     }, {
 345         'url': 'hotstar:movies:1260009879',
 346         'info_dict': {
 347             'id': '1260009879',
 348             'ext': 'mp4',
 349             'title': 'Nuvvu Naaku Nachav',
 350             'description': 'md5:d43701b1314e6f8233ce33523c043b7d',
 351             'timestamp': 1567525674,
 352             'upload_date': '20190903',
 353             'duration': 10787,
 354             'episode': 'Nuvvu Naaku Nachav',
 355         },
 356     }, {
 357         'url': 'hotstar:episode:1000234847',
 358         'only_matching': True,
 359     }, {
 360         # contentData
 361         'url': 'hotstar:sports:1260065956',
 362         'only_matching': True,
 363     }, {
 364         # contentData
 365         'url': 'hotstar:sports:1260066104',
 366         'only_matching': True,
 367     }]
 368
 369     def _real_extract(self, url):
 370         video_id, video_type = self._match_valid_url(url).group('id', 'type')
 371         return self.url_result(HotStarIE._video_url(video_id, video_type), HotStarIE, video_id)
 372
 373
 374 class HotStarPlaylistIE(HotStarBaseIE):
 375     IE_NAME = 'hotstar:playlist'
 376     _VALID_URL = r'https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)(?:/[^/]+){2}/list/[^/]+/t-(?P<id>\w+)'
 377     _TESTS = [{
 378         'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
 379         'info_dict': {
 380             'id': '3_2_26',
 381         },
 382         'playlist_mincount': 20,
 383     }, {
 384         'url': 'https://www.hotstar.com/shows/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
 385         'only_matching': True,
 386     }, {
 387         'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
 388         'only_matching': True,
 389     }, {
 390         'url': 'https://www.hotstar.com/in/tv/karthika-deepam/15457/list/popular-clips/t-3_2_1272',
 391         'only_matching': True,
 392     }]
 393
 394     def _real_extract(self, url):
 395         id_ = self._match_id(url)
 396         return self.playlist_result(
 397             self._playlist_entries('tray/find', id_, query={'tas': 10000, 'uqId': id_}), id_)
 398
 399
 400 class HotStarSeasonIE(HotStarBaseIE):
 401     IE_NAME = 'hotstar:season'
 402     _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)/[^/]+/\w+)/seasons/[^/]+/ss-(?P<id>\w+)'
 403     _TESTS = [{
 404         'url': 'https://www.hotstar.com/tv/radhakrishn/1260000646/seasons/season-2/ss-8028',
 405         'info_dict': {
 406             'id': '8028',
 407         },
 408         'playlist_mincount': 35,
 409     }, {
 410         'url': 'https://www.hotstar.com/in/tv/ishqbaaz/9567/seasons/season-2/ss-4357',
 411         'info_dict': {
 412             'id': '4357',
 413         },
 414         'playlist_mincount': 30,
 415     }, {
 416         'url': 'https://www.hotstar.com/in/tv/bigg-boss/14714/seasons/season-4/ss-8208/',
 417         'info_dict': {
 418             'id': '8208',
 419         },
 420         'playlist_mincount': 19,
 421     }, {
 422         'url': 'https://www.hotstar.com/in/shows/bigg-boss/14714/seasons/season-4/ss-8208/',
 423         'only_matching': True,
 424     }]
 425
 426     def _real_extract(self, url):
 427         url, season_id = self._match_valid_url(url).groups()
 428         return self.playlist_result(self._playlist_entries(
 429             'season/asset', season_id, url, query={'tao': 0, 'tas': 0, 'size': 10000, 'id': season_id}), season_id)
 430
 431
 432 class HotStarSeriesIE(HotStarBaseIE):
 433     IE_NAME = 'hotstar:series'
 434     _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)/[^/]+/(?P<id>\d+))/?(?:[#?]|$)'
 435     _TESTS = [{
 436         'url': 'https://www.hotstar.com/in/tv/radhakrishn/1260000646',
 437         'info_dict': {
 438             'id': '1260000646',
 439         },
 440         'playlist_mincount': 690,
 441     }, {
 442         'url': 'https://www.hotstar.com/tv/dancee-/1260050431',
 443         'info_dict': {
 444             'id': '1260050431',
 445         },
 446         'playlist_mincount': 43,
 447     }, {
 448         'url': 'https://www.hotstar.com/in/tv/mahabharat/435/',
 449         'info_dict': {
 450             'id': '435',
 451         },
 452         'playlist_mincount': 267,
 453     }, {
 454         'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/',
 455         'info_dict': {
 456             'id': '1260022017',
 457         },
 458         'playlist_mincount': 940,
 459     }]
 460
 461     def _real_extract(self, url):
 462         url, series_id = self._match_valid_url(url).groups()
 463         id_ = self._call_api_v1(
 464             'show/detail', series_id, query={'contentId': series_id})['body']['results']['item']['id']
 465
 466         return self.playlist_result(self._playlist_entries(
 467             'tray/g/1/items', series_id, url, query={'tao': 0, 'tas': 10000, 'etid': 0, 'eid': id_}), series_id)