[yt-dlp.git] / yt_dlp / extractor / hotstar.py

import hashlib
import hmac
import json
import re
import time
import uuid

from .common import InfoExtractor
from ..compat import compat_str
from ..networking.exceptions import HTTPError
from ..utils import (
    ExtractorError,
    determine_ext,
    int_or_none,
    join_nonempty,
    str_or_none,
    traverse_obj,
    url_or_none,
)


class HotStarBaseIE(InfoExtractor):
    _BASE_URL = 'https://www.hotstar.com'
    _API_URL = 'https://api.hotstar.com'
    _AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'

    def _call_api_v1(self, path, *args, **kwargs):
        return self._download_json(
            f'{self._API_URL}/o/v1/{path}', *args, **kwargs,
            headers={'x-country-code': 'IN', 'x-platform-code': 'PCTV'})

    def _call_api_impl(self, path, video_id, query, st=None, cookies=None):
        st = int_or_none(st) or int(time.time())
        exp = st + 6000
        auth = 'st=%d~exp=%d~acl=/*' % (st, exp)
        auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()

        if cookies and cookies.get('userUP'):
            token = cookies.get('userUP').value
        else:
            token = self._download_json(
                f'{self._API_URL}/um/v3/users',
                video_id, note='Downloading token',
                data=json.dumps({"device_ids": [{"id": compat_str(uuid.uuid4()), "type": "device_id"}]}).encode('utf-8'),
                headers={
                    'hotstarauth': auth,
                    'x-hs-platform': 'PCTV',  # or 'web'
                    'Content-Type': 'application/json',
                })['user_identity']

        response = self._download_json(
            f'{self._API_URL}/{path}', video_id, query=query,
            headers={
                'hotstarauth': auth,
                'x-hs-appversion': '6.72.2',
                'x-hs-platform': 'web',
                'x-hs-usertoken': token,
            })

        if response['message'] != "Playback URL's fetched successfully":
            raise ExtractorError(
                response['message'], expected=True)
        return response['data']

    def _call_api_v2(self, path, video_id, st=None, cookies=None):
        return self._call_api_impl(
            f'{path}/content/{video_id}', video_id, st=st, cookies=cookies, query={
                'desired-config': 'audio_channel:stereo|container:fmp4|dynamic_range:hdr|encryption:plain|ladder:tv|package:dash|resolution:fhd|subs-tag:HotstarVIP|video_codec:h265',
                'device-id': cookies.get('device_id').value if cookies.get('device_id') else compat_str(uuid.uuid4()),
                'os-name': 'Windows',
                'os-version': '10',
            })

    def _playlist_entries(self, path, item_id, root=None, **kwargs):
        results = self._call_api_v1(path, item_id, **kwargs)['body']['results']
        for video in traverse_obj(results, (('assets', None), 'items', ...)):
            if video.get('contentId'):
                yield self.url_result(
                    HotStarIE._video_url(video['contentId'], root=root), HotStarIE, video['contentId'])


class HotStarIE(HotStarBaseIE):
    IE_NAME = 'hotstar'
    _VALID_URL = r'''(?x)
        https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/)
        (?:
            (?P<type>movies|sports|clips|episode|(?P<tv>tv|shows))/
            (?(tv)(?:[^/?#]+/){2}|[^?#]*)
        )?
        [^/?#]+/
        (?P<id>\d{10})
    '''

    _TESTS = [{
        'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273',
        'info_dict': {
            'id': '1000076273',
            'ext': 'mp4',
            'title': 'Can You Not Spread Rumours?',
            'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
            'timestamp': 1447248600,
            'upload_date': '20151111',
            'duration': 381,
            'episode': 'Can You Not Spread Rumours?',
        },
        'params': {'skip_download': 'm3u8'},
    }, {
        'url': 'https://www.hotstar.com/tv/ek-bhram-sarvagun-sampanna/s-2116/janhvi-targets-suman/1000234847',
        'info_dict': {
            'id': '1000234847',
            'ext': 'mp4',
            'title': 'Janhvi Targets Suman',
            'description': 'md5:78a85509348910bd1ca31be898c5796b',
            'timestamp': 1556670600,
            'upload_date': '20190501',
            'duration': 1219,
            'channel': 'StarPlus',
            'channel_id': 3,
            'series': 'Ek Bhram - Sarvagun Sampanna',
            'season': 'Chapter 1',
            'season_number': 1,
            'season_id': 6771,
            'episode': 'Janhvi Targets Suman',
            'episode_number': 8,
        }
    }, {
        'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/anupama-anuj-share-a-moment/1000282843',
        'info_dict': {
            'id': '1000282843',
            'ext': 'mp4',
            'title': 'Anupama, Anuj Share a Moment',
            'season': 'Chapter 1',
            'description': 'md5:8d74ed2248423b8b06d5c8add4d7a0c0',
            'timestamp': 1678149000,
            'channel': 'StarPlus',
            'series': 'Anupama',
            'season_number': 1,
            'season_id': 7399,
            'upload_date': '20230307',
            'episode': 'Anupama, Anuj Share a Moment',
            'episode_number': 853,
            'duration': 1272,
            'channel_id': 3,
        },
    }, {
        'url': 'https://www.hotstar.com/in/clips/e3-sairat-kahani-pyaar-ki/1000262286',
        'info_dict': {
            'id': '1000262286',
            'ext': 'mp4',
            'title': 'E3 - SaiRat, Kahani Pyaar Ki',
            'description': 'md5:e3b4b3203bc0c5396fe7d0e4948a6385',
            'episode': 'E3 - SaiRat, Kahani Pyaar Ki',
            'upload_date': '20210606',
            'timestamp': 1622943900,
            'duration': 5395,
        },
    }, {
        'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
        'only_matching': True,
    }, {
        'url': 'https://www.hotstar.com/in/sports/cricket/follow-the-blues-2021/recap-eng-fight-back-on-day-2/1260066104',
        'only_matching': True,
    }, {
        'url': 'https://www.hotstar.com/in/sports/football/most-costly-pl-transfers-ft-grealish/1260065956',
        'only_matching': True,
    }]
    _GEO_BYPASS = False

    _TYPE = {
        'movies': 'movie',
        'sports': 'match',
        'episode': 'episode',
        'tv': 'episode',
        'shows': 'episode',
        'clips': 'content',
        None: 'content',
    }

    _IGNORE_MAP = {
        'res': 'resolution',
        'vcodec': 'video_codec',
        'dr': 'dynamic_range',
    }

    _TAG_FIELDS = {
        'language': 'language',
        'acodec': 'audio_codec',
        'vcodec': 'video_codec',
    }

    @classmethod
    def _video_url(cls, video_id, video_type=None, *, slug='ignore_me', root=None):
        assert None in (video_type, root)
        if not root:
            root = join_nonempty(cls._BASE_URL, video_type, delim='/')
        return f'{root}/{slug}/{video_id}'

    def _real_extract(self, url):
        video_id, video_type = self._match_valid_url(url).group('id', 'type')
        video_type = self._TYPE.get(video_type, video_type)
        cookies = self._get_cookies(url)  # Cookies before any request

        video_data = self._call_api_v1(f'{video_type}/detail', video_id,
                                       query={'tas': 10000, 'contentId': video_id})['body']['results']['item']
        if not self.get_param('allow_unplayable_formats') and video_data.get('drmProtected'):
            self.report_drm(video_id)

        # See https://github.com/yt-dlp/yt-dlp/issues/396
        st = self._download_webpage_handle(f'{self._BASE_URL}/in', video_id)[1].headers.get('x-origin-date')

        geo_restricted = False
        formats, subs = [], {}
        headers = {'Referer': f'{self._BASE_URL}/in'}

        # change to v2 in the future
        playback_sets = self._call_api_v2('play/v1/playback', video_id, st=st, cookies=cookies)['playBackSets']
        for playback_set in playback_sets:
            if not isinstance(playback_set, dict):
                continue
            tags = str_or_none(playback_set.get('tagsCombination')) or ''
            if any(f'{prefix}:{ignore}' in tags
                   for key, prefix in self._IGNORE_MAP.items()
                   for ignore in self._configuration_arg(key)):
                continue
            tag_dict = dict((t.split(':', 1) + [None])[:2] for t in tags.split(';'))

            format_url = url_or_none(playback_set.get('playbackUrl'))
            if not format_url:
                continue
            format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', format_url)
            ext = determine_ext(format_url)

            current_formats, current_subs = [], {}
            try:
                if 'package:hls' in tags or ext == 'm3u8':
                    current_formats, current_subs = self._extract_m3u8_formats_and_subtitles(
                        format_url, video_id, ext='mp4', headers=headers)
                elif 'package:dash' in tags or ext == 'mpd':
                    current_formats, current_subs = self._extract_mpd_formats_and_subtitles(
                        format_url, video_id, headers=headers)
                elif ext == 'f4m':
                    pass  # XXX: produce broken files
                else:
                    current_formats = [{
                        'url': format_url,
                        'width': int_or_none(playback_set.get('width')),
                        'height': int_or_none(playback_set.get('height')),
                    }]
            except ExtractorError as e:
                if isinstance(e.cause, HTTPError) and e.cause.status == 403:
                    geo_restricted = True
                continue

            if tag_dict.get('encryption') not in ('plain', None):
                for f in current_formats:
                    f['has_drm'] = True
            for f in current_formats:
                for k, v in self._TAG_FIELDS.items():
                    if not f.get(k):
                        f[k] = tag_dict.get(v)
                if f.get('vcodec') != 'none' and not f.get('dynamic_range'):
                    f['dynamic_range'] = tag_dict.get('dynamic_range')
                if f.get('acodec') != 'none' and not f.get('audio_channels'):
                    f['audio_channels'] = {
                        'stereo': 2,
                        'dolby51': 6,
                    }.get(tag_dict.get('audio_channel'))
                f['format_note'] = join_nonempty(
                    tag_dict.get('ladder'),
                    tag_dict.get('audio_channel') if f.get('acodec') != 'none' else None,
                    f.get('format_note'),
                    delim=', ')

            formats.extend(current_formats)
            subs = self._merge_subtitles(subs, current_subs)

        if not formats and geo_restricted:
            self.raise_geo_restricted(countries=['IN'], metadata_available=True)
        self._remove_duplicate_formats(formats)
        for f in formats:
            f.setdefault('http_headers', {}).update(headers)

        return {
            'id': video_id,
            'title': video_data.get('title'),
            'description': video_data.get('description'),
            'duration': int_or_none(video_data.get('duration')),
            'timestamp': int_or_none(traverse_obj(video_data, 'broadcastDate', 'startDate')),
            'formats': formats,
            'subtitles': subs,
            'channel': video_data.get('channelName'),
            'channel_id': video_data.get('channelId'),
            'series': video_data.get('showName'),
            'season': video_data.get('seasonName'),
            'season_number': int_or_none(video_data.get('seasonNo')),
            'season_id': video_data.get('seasonId'),
            'episode': video_data.get('title'),
            'episode_number': int_or_none(video_data.get('episodeNo')),
        }


class HotStarPrefixIE(InfoExtractor):
    """ The "hotstar:" prefix is no longer in use, but this is kept for backward compatibility """
    IE_DESC = False
    _VALID_URL = r'hotstar:(?:(?P<type>\w+):)?(?P<id>\d+)$'
    _TESTS = [{
        'url': 'hotstar:1000076273',
        'only_matching': True,
    }, {
        'url': 'hotstar:movies:1260009879',
        'info_dict': {
            'id': '1260009879',
            'ext': 'mp4',
            'title': 'Nuvvu Naaku Nachav',
            'description': 'md5:d43701b1314e6f8233ce33523c043b7d',
            'timestamp': 1567525674,
            'upload_date': '20190903',
            'duration': 10787,
            'episode': 'Nuvvu Naaku Nachav',
        },
    }, {
        'url': 'hotstar:episode:1000234847',
        'only_matching': True,
    }, {
        # contentData
        'url': 'hotstar:sports:1260065956',
        'only_matching': True,
    }, {
        # contentData
        'url': 'hotstar:sports:1260066104',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        video_id, video_type = self._match_valid_url(url).group('id', 'type')
        return self.url_result(HotStarIE._video_url(video_id, video_type), HotStarIE, video_id)


class HotStarPlaylistIE(HotStarBaseIE):
    IE_NAME = 'hotstar:playlist'
    _VALID_URL = r'https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)(?:/[^/]+){2}/list/[^/]+/t-(?P<id>\w+)'
    _TESTS = [{
        'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
        'info_dict': {
            'id': '3_2_26',
        },
        'playlist_mincount': 20,
    }, {
        'url': 'https://www.hotstar.com/shows/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
        'only_matching': True,
    }, {
        'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
        'only_matching': True,
    }, {
        'url': 'https://www.hotstar.com/in/tv/karthika-deepam/15457/list/popular-clips/t-3_2_1272',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        id_ = self._match_id(url)
        return self.playlist_result(
            self._playlist_entries('tray/find', id_, query={'tas': 10000, 'uqId': id_}), id_)


class HotStarSeasonIE(HotStarBaseIE):
    IE_NAME = 'hotstar:season'
    _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)/[^/]+/\w+)/seasons/[^/]+/ss-(?P<id>\w+)'
    _TESTS = [{
        'url': 'https://www.hotstar.com/tv/radhakrishn/1260000646/seasons/season-2/ss-8028',
        'info_dict': {
            'id': '8028',
        },
        'playlist_mincount': 35,
    }, {
        'url': 'https://www.hotstar.com/in/tv/ishqbaaz/9567/seasons/season-2/ss-4357',
        'info_dict': {
            'id': '4357',
        },
        'playlist_mincount': 30,
    }, {
        'url': 'https://www.hotstar.com/in/tv/bigg-boss/14714/seasons/season-4/ss-8208/',
        'info_dict': {
            'id': '8208',
        },
        'playlist_mincount': 19,
    }, {
        'url': 'https://www.hotstar.com/in/shows/bigg-boss/14714/seasons/season-4/ss-8208/',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        url, season_id = self._match_valid_url(url).groups()
        return self.playlist_result(self._playlist_entries(
            'season/asset', season_id, url, query={'tao': 0, 'tas': 0, 'size': 10000, 'id': season_id}), season_id)


class HotStarSeriesIE(HotStarBaseIE):
    IE_NAME = 'hotstar:series'
    _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)/[^/]+/(?P<id>\d+))/?(?:[#?]|$)'
    _TESTS = [{
        'url': 'https://www.hotstar.com/in/tv/radhakrishn/1260000646',
        'info_dict': {
            'id': '1260000646',
        },
        'playlist_mincount': 690,
    }, {
        'url': 'https://www.hotstar.com/tv/dancee-/1260050431',
        'info_dict': {
            'id': '1260050431',
        },
        'playlist_mincount': 43,
    }, {
        'url': 'https://www.hotstar.com/in/tv/mahabharat/435/',
        'info_dict': {
            'id': '435',
        },
        'playlist_mincount': 267,
    }, {
        'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/',
        'info_dict': {
            'id': '1260022017',
        },
        'playlist_mincount': 940,
    }]

    def _real_extract(self, url):
        url, series_id = self._match_valid_url(url).groups()
        id_ = self._call_api_v1(
            'show/detail', series_id, query={'contentId': series_id})['body']['results']['item']['id']

        return self.playlist_result(self._playlist_entries(
            'tray/g/1/items', series_id, url, query={'tao': 0, 'tas': 10000, 'etid': 0, 'eid': id_}), series_id)
Commit	Line	Data
85cd69ad RA	1	import hashlib
85cd69ad RA	2	import hmac
fad689c7	3	import json
1cb812d3	4	import re
85cd69ad	5	import time
2533f5b6	6	import uuid
909191de	7
fb8e402a	8	from .common import InfoExtractor
3d2623a8	9	from ..compat import compat_str
3d2623a8	10	from ..networking.exceptions import HTTPError
fb8e402a	11	from ..utils import (
909191de	12	ExtractorError,
fad689c7	13	determine_ext,
fb8e402a	14	int_or_none,
a1ddaa89	15	join_nonempty,
2533f5b6	16	str_or_none,
fad689c7	17	traverse_obj,
2533f5b6	18	url_or_none,
fb8e402a	19	)
	20
	21
909191de	22	class HotStarBaseIE(InfoExtractor):
a1ddaa89	23	_BASE_URL = 'https://www.hotstar.com'
a1ddaa89	24	_API_URL = 'https://api.hotstar.com'
85cd69ad RA	25	_AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
85cd69ad RA	26
fad689c7	27	def _call_api_v1(self, path, args, *kwargs):
	28	return self._download_json(
	29	f'{self._API_URL}/o/v1/{path}', args, *kwargs,
	30	headers={'x-country-code': 'IN', 'x-platform-code': 'PCTV'})
	31
fe07e2c6	32	def _call_api_impl(self, path, video_id, query, st=None, cookies=None):
9fc0de57	33	st = int_or_none(st) or int(time.time())
85cd69ad RA	34	exp = st + 6000
	35	auth = 'st=%d~exp=%d~acl=/*' % (st, exp)
	36	auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
6923b538	37
b6a35ad8	38	if cookies and cookies.get('userUP'):
fe07e2c6 A	39	token = cookies.get('userUP').value
	40	else:
	41	token = self._download_json(
a1ddaa89	42	f'{self._API_URL}/um/v3/users',
fe07e2c6 A	43	video_id, note='Downloading token',
	44	data=json.dumps({"device_ids": [{"id": compat_str(uuid.uuid4()), "type": "device_id"}]}).encode('utf-8'),
	45	headers={
	46	'hotstarauth': auth,
	47	'x-hs-platform': 'PCTV', # or 'web'
	48	'Content-Type': 'application/json',
	49	})['user_identity']
6923b538	50
85cd69ad	51	response = self._download_json(
a1ddaa89	52	f'{self._API_URL}/{path}', video_id, query=query,
a1ddaa89	53	headers={
85cd69ad	54	'hotstarauth': auth,
7078ec64 N	55	'x-hs-appversion': '6.72.2',
	56	'x-hs-platform': 'web',
	57	'x-hs-usertoken': token,
a1ddaa89	58	})
6923b538	59
7078ec64	60	if response['message'] != "Playback URL's fetched successfully":
85cd69ad	61	raise ExtractorError(
7078ec64 N	62	response['message'], expected=True)
7078ec64 N	63	return response['data']
909191de	64
5d5c0f7e	65	def _call_api_v2(self, path, video_id, st=None, cookies=None):
2533f5b6	66	return self._call_api_impl(
a1ddaa89	67	f'{path}/content/{video_id}', video_id, st=st, cookies=cookies, query={
a64907d0	68	'desired-config': 'audio_channel:stereo\|container:fmp4\|dynamic_range:hdr\|encryption:plain\|ladder:tv\|package:dash\|resolution:fhd\|subs-tag:HotstarVIP\|video_codec:h265',
fe07e2c6	69	'device-id': cookies.get('device_id').value if cookies.get('device_id') else compat_str(uuid.uuid4()),
7078ec64 N	70	'os-name': 'Windows',
7078ec64 N	71	'os-version': '10',
2533f5b6 S	72	})
2533f5b6 S	73
fad689c7	74	def _playlist_entries(self, path, item_id, root=None, **kwargs):
	75	results = self._call_api_v1(path, item_id, **kwargs)['body']['results']
	76	for video in traverse_obj(results, (('assets', None), 'items', ...)):
	77	if video.get('contentId'):
	78	yield self.url_result(
	79	HotStarIE._video_url(video['contentId'], root=root), HotStarIE, video['contentId'])
	80
909191de S	81
909191de S	82	class HotStarIE(HotStarBaseIE):
85cd69ad	83	IE_NAME = 'hotstar'
6e639032	84	_VALID_URL = r'''(?x)
a1ddaa89	85	https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/)
a1ddaa89	86	(?:
86eeb044	87	(?P<type>movies\|sports\|clips\|episode\|(?P<tv>tv\|shows))/
a1ddaa89	88	(?(tv)(?:[^/?#]+/){2}\|[^?#]*)
	89	)?
	90	[^/?#]+/
	91	(?P<id>\d{10})
	92	'''
	93
89d23f37	94	_TESTS = [{
85cd69ad	95	'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273',
fb8e402a	96	'info_dict': {
	97	'id': '1000076273',
	98	'ext': 'mp4',
85cd69ad	99	'title': 'Can You Not Spread Rumours?',
fb8e402a	100	'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
85cd69ad	101	'timestamp': 1447248600,
fb8e402a	102	'upload_date': '20151111',
fb8e402a	103	'duration': 381,
a1ddaa89	104	'episode': 'Can You Not Spread Rumours?',
fb8e402a	105	},
fad689c7	106	'params': {'skip_download': 'm3u8'},
2533f5b6	107	}, {
2533f5b6	108	'url': 'https://www.hotstar.com/tv/ek-bhram-sarvagun-sampanna/s-2116/janhvi-targets-suman/1000234847',
b6a35ad8 A	109	'info_dict': {
	110	'id': '1000234847',
	111	'ext': 'mp4',
	112	'title': 'Janhvi Targets Suman',
	113	'description': 'md5:78a85509348910bd1ca31be898c5796b',
	114	'timestamp': 1556670600,
	115	'upload_date': '20190501',
	116	'duration': 1219,
	117	'channel': 'StarPlus',
	118	'channel_id': 3,
	119	'series': 'Ek Bhram - Sarvagun Sampanna',
	120	'season': 'Chapter 1',
	121	'season_number': 1,
	122	'season_id': 6771,
	123	'episode': 'Janhvi Targets Suman',
	124	'episode_number': 8,
a1ddaa89	125	}
7f8ddebb	126	}, {
	127	'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/anupama-anuj-share-a-moment/1000282843',
	128	'info_dict': {
	129	'id': '1000282843',
	130	'ext': 'mp4',
	131	'title': 'Anupama, Anuj Share a Moment',
	132	'season': 'Chapter 1',
	133	'description': 'md5:8d74ed2248423b8b06d5c8add4d7a0c0',
	134	'timestamp': 1678149000,
	135	'channel': 'StarPlus',
	136	'series': 'Anupama',
	137	'season_number': 1,
	138	'season_id': 7399,
	139	'upload_date': '20230307',
	140	'episode': 'Anupama, Anuj Share a Moment',
	141	'episode_number': 853,
	142	'duration': 1272,
	143	'channel_id': 3,
	144	},
86eeb044	145	}, {
	146	'url': 'https://www.hotstar.com/in/clips/e3-sairat-kahani-pyaar-ki/1000262286',
	147	'info_dict': {
	148	'id': '1000262286',
	149	'ext': 'mp4',
	150	'title': 'E3 - SaiRat, Kahani Pyaar Ki',
	151	'description': 'md5:e3b4b3203bc0c5396fe7d0e4948a6385',
	152	'episode': 'E3 - SaiRat, Kahani Pyaar Ki',
	153	'upload_date': '20210606',
	154	'timestamp': 1622943900,
	155	'duration': 5395,
	156	},
b6a35ad8	157	}, {
a1ddaa89	158	'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
	159	'only_matching': True,
	160	}, {
	161	'url': 'https://www.hotstar.com/in/sports/cricket/follow-the-blues-2021/recap-eng-fight-back-on-day-2/1260066104',
	162	'only_matching': True,
	163	}, {
	164	'url': 'https://www.hotstar.com/in/sports/football/most-costly-pl-transfers-ft-grealish/1260065956',
2533f5b6	165	'only_matching': True,
89d23f37	166	}]
85cd69ad	167	_GEO_BYPASS = False
a1ddaa89	168
b6a35ad8 A	169	_TYPE = {
	170	'movies': 'movie',
	171	'sports': 'match',
	172	'episode': 'episode',
	173	'tv': 'episode',
7f8ddebb	174	'shows': 'episode',
86eeb044	175	'clips': 'content',
b6a35ad8 A	176	None: 'content',
b6a35ad8 A	177	}
fb8e402a	178
a1ddaa89	179	_IGNORE_MAP = {
	180	'res': 'resolution',
	181	'vcodec': 'video_codec',
	182	'dr': 'dynamic_range',
	183	}
	184
e74a3c6d	185	_TAG_FIELDS = {
	186	'language': 'language',
	187	'acodec': 'audio_codec',
	188	'vcodec': 'video_codec',
	189	}
	190
a1ddaa89	191	@classmethod
	192	def _video_url(cls, video_id, video_type=None, *, slug='ignore_me', root=None):
	193	assert None in (video_type, root)
	194	if not root:
	195	root = join_nonempty(cls._BASE_URL, video_type, delim='/')
	196	return f'{root}/{slug}/{video_id}'
	197
fb8e402a	198	def _real_extract(self, url):
a1ddaa89	199	video_id, video_type = self._match_valid_url(url).group('id', 'type')
b6a35ad8	200	video_type = self._TYPE.get(video_type, video_type)
5d5c0f7e	201	cookies = self._get_cookies(url) # Cookies before any request
0dac7cbb	202
fad689c7	203	video_data = self._call_api_v1(f'{video_type}/detail', video_id,
fad689c7	204	query={'tas': 10000, 'contentId': video_id})['body']['results']['item']
a06916d9	205	if not self.get_param('allow_unplayable_formats') and video_data.get('drmProtected'):
88acdbc2	206	self.report_drm(video_id)
88acdbc2	207
a1ddaa89	208	# See https://github.com/yt-dlp/yt-dlp/issues/396
	209	st = self._download_webpage_handle(f'{self._BASE_URL}/in', video_id)[1].headers.get('x-origin-date')
	210
2533f5b6	211	geo_restricted = False
a1ddaa89	212	formats, subs = [], {}
	213	headers = {'Referer': f'{self._BASE_URL}/in'}
	214
6923b538	215	# change to v2 in the future
5d5c0f7e	216	playback_sets = self._call_api_v2('play/v1/playback', video_id, st=st, cookies=cookies)['playBackSets']
2533f5b6 S	217	for playback_set in playback_sets:
	218	if not isinstance(playback_set, dict):
	219	continue
a1ddaa89	220	tags = str_or_none(playback_set.get('tagsCombination')) or ''
	221	if any(f'{prefix}:{ignore}' in tags
	222	for key, prefix in self._IGNORE_MAP.items()
	223	for ignore in self._configuration_arg(key)):
	224	continue
e74a3c6d	225	tag_dict = dict((t.split(':', 1) + [None])[:2] for t in tags.split(';'))
a1ddaa89	226
2533f5b6 S	227	format_url = url_or_none(playback_set.get('playbackUrl'))
	228	if not format_url:
	229	continue
a1ddaa89	230	format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', format_url)
2533f5b6	231	ext = determine_ext(format_url)
a1ddaa89	232
6ff34542	233	current_formats, current_subs = [], {}
85cd69ad	234	try:
2533f5b6	235	if 'package:hls' in tags or ext == 'm3u8':
6ff34542	236	current_formats, current_subs = self._extract_m3u8_formats_and_subtitles(
e74a3c6d	237	format_url, video_id, ext='mp4', headers=headers)
2533f5b6	238	elif 'package:dash' in tags or ext == 'mpd':
6ff34542	239	current_formats, current_subs = self._extract_mpd_formats_and_subtitles(
e74a3c6d	240	format_url, video_id, headers=headers)
2533f5b6	241	elif ext == 'f4m':
a1ddaa89	242	pass # XXX: produce broken files
2533f5b6	243	else:
6ff34542	244	current_formats = [{
2533f5b6 S	245	'url': format_url,
	246	'width': int_or_none(playback_set.get('width')),
	247	'height': int_or_none(playback_set.get('height')),
6ff34542	248	}]
85cd69ad	249	except ExtractorError as e:
3d2623a8	250	if isinstance(e.cause, HTTPError) and e.cause.status == 403:
2533f5b6 S	251	geo_restricted = True
2533f5b6 S	252	continue
a1ddaa89	253
e74a3c6d	254	if tag_dict.get('encryption') not in ('plain', None):
6ff34542 AG	255	for f in current_formats:
6ff34542 AG	256	f['has_drm'] = True
e74a3c6d	257	for f in current_formats:
	258	for k, v in self._TAG_FIELDS.items():
	259	if not f.get(k):
	260	f[k] = tag_dict.get(v)
	261	if f.get('vcodec') != 'none' and not f.get('dynamic_range'):
	262	f['dynamic_range'] = tag_dict.get('dynamic_range')
	263	if f.get('acodec') != 'none' and not f.get('audio_channels'):
	264	f['audio_channels'] = {
	265	'stereo': 2,
	266	'dolby51': 6,
	267	}.get(tag_dict.get('audio_channel'))
	268	f['format_note'] = join_nonempty(
	269	tag_dict.get('ladder'),
	270	tag_dict.get('audio_channel') if f.get('acodec') != 'none' else None,
	271	f.get('format_note'),
	272	delim=', ')
a1ddaa89	273
6ff34542 AG	274	formats.extend(current_formats)
6ff34542 AG	275	subs = self._merge_subtitles(subs, current_subs)
a1ddaa89	276
2533f5b6	277	if not formats and geo_restricted:
b7da73eb	278	self.raise_geo_restricted(countries=['IN'], metadata_available=True)
e74a3c6d	279	self._remove_duplicate_formats(formats)
d7def23d RA	280	for f in formats:
	281	f.setdefault('http_headers', {}).update(headers)
	282
fb8e402a	283	return {
fb8e402a	284	'id': video_id,
a1ddaa89	285	'title': video_data.get('title'),
fb8e402a	286	'description': video_data.get('description'),
fb8e402a	287	'duration': int_or_none(video_data.get('duration')),
e74a3c6d	288	'timestamp': int_or_none(traverse_obj(video_data, 'broadcastDate', 'startDate')),
fb8e402a	289	'formats': formats,
b6a35ad8	290	'subtitles': subs,
85cd69ad RA	291	'channel': video_data.get('channelName'),
	292	'channel_id': video_data.get('channelId'),
	293	'series': video_data.get('showName'),
	294	'season': video_data.get('seasonName'),
	295	'season_number': int_or_none(video_data.get('seasonNo')),
	296	'season_id': video_data.get('seasonId'),
a1ddaa89	297	'episode': video_data.get('title'),
85cd69ad	298	'episode_number': int_or_none(video_data.get('episodeNo')),
fb8e402a	299	}
477c97f8 AV	300
477c97f8 AV	301
a1ddaa89	302	class HotStarPrefixIE(InfoExtractor):
	303	""" The "hotstar:" prefix is no longer in use, but this is kept for backward compatibility """
	304	IE_DESC = False
	305	_VALID_URL = r'hotstar:(?:(?P<type>\w+):)?(?P<id>\d+)$'
	306	_TESTS = [{
	307	'url': 'hotstar:1000076273',
	308	'only_matching': True,
	309	}, {
db6fa696	310	'url': 'hotstar:movies:1260009879',
a1ddaa89	311	'info_dict': {
db6fa696	312	'id': '1260009879',
a1ddaa89	313	'ext': 'mp4',
db6fa696	314	'title': 'Nuvvu Naaku Nachav',
	315	'description': 'md5:d43701b1314e6f8233ce33523c043b7d',
	316	'timestamp': 1567525674,
	317	'upload_date': '20190903',
	318	'duration': 10787,
	319	'episode': 'Nuvvu Naaku Nachav',
a1ddaa89	320	},
	321	}, {
	322	'url': 'hotstar:episode:1000234847',
	323	'only_matching': True,
	324	}, {
	325	# contentData
	326	'url': 'hotstar:sports:1260065956',
	327	'only_matching': True,
	328	}, {
	329	# contentData
	330	'url': 'hotstar:sports:1260066104',
	331	'only_matching': True,
	332	}]
	333
	334	def _real_extract(self, url):
	335	video_id, video_type = self._match_valid_url(url).group('id', 'type')
	336	return self.url_result(HotStarIE._video_url(video_id, video_type), HotStarIE, video_id)
	337
	338
909191de	339	class HotStarPlaylistIE(HotStarBaseIE):
477c97f8	340	IE_NAME = 'hotstar:playlist'
7f8ddebb	341	_VALID_URL = r'https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv\|shows)(?:/[^/]+){2}/list/[^/]+/t-(?P<id>\w+)'
477c97f8	342	_TESTS = [{
85cd69ad	343	'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
477c97f8	344	'info_dict': {
85cd69ad	345	'id': '3_2_26',
477c97f8	346	},
85cd69ad	347	'playlist_mincount': 20,
7f8ddebb	348	}, {
	349	'url': 'https://www.hotstar.com/shows/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
	350	'only_matching': True,
477c97f8	351	}, {
85cd69ad	352	'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
477c97f8	353	'only_matching': True,
db6fa696	354	}, {
	355	'url': 'https://www.hotstar.com/in/tv/karthika-deepam/15457/list/popular-clips/t-3_2_1272',
	356	'only_matching': True,
477c97f8	357	}]
477c97f8 AV	358
477c97f8 AV	359	def _real_extract(self, url):
fad689c7	360	id_ = self._match_id(url)
	361	return self.playlist_result(
	362	self._playlist_entries('tray/find', id_, query={'tas': 10000, 'uqId': id_}), id_)
6e639032 A	363
6e639032 A	364
db6fa696	365	class HotStarSeasonIE(HotStarBaseIE):
db6fa696	366	IE_NAME = 'hotstar:season'
7f8ddebb	367	_VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv\|shows)/[^/]+/\w+)/seasons/[^/]+/ss-(?P<id>\w+)'
db6fa696	368	_TESTS = [{
	369	'url': 'https://www.hotstar.com/tv/radhakrishn/1260000646/seasons/season-2/ss-8028',
	370	'info_dict': {
	371	'id': '8028',
	372	},
	373	'playlist_mincount': 35,
	374	}, {
	375	'url': 'https://www.hotstar.com/in/tv/ishqbaaz/9567/seasons/season-2/ss-4357',
	376	'info_dict': {
	377	'id': '4357',
	378	},
	379	'playlist_mincount': 30,
	380	}, {
	381	'url': 'https://www.hotstar.com/in/tv/bigg-boss/14714/seasons/season-4/ss-8208/',
	382	'info_dict': {
	383	'id': '8208',
	384	},
	385	'playlist_mincount': 19,
7f8ddebb	386	}, {
	387	'url': 'https://www.hotstar.com/in/shows/bigg-boss/14714/seasons/season-4/ss-8208/',
	388	'only_matching': True,
db6fa696	389	}]
	390
	391	def _real_extract(self, url):
	392	url, season_id = self._match_valid_url(url).groups()
fad689c7	393	return self.playlist_result(self._playlist_entries(
fad689c7	394	'season/asset', season_id, url, query={'tao': 0, 'tas': 0, 'size': 10000, 'id': season_id}), season_id)
db6fa696	395
db6fa696	396
6e639032 A	397	class HotStarSeriesIE(HotStarBaseIE):
6e639032 A	398	IE_NAME = 'hotstar:series'
7f8ddebb	399	_VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv\|shows)/[^/]+/(?P<id>\d+))/?(?:[#?]\|$)'
6e639032 A	400	_TESTS = [{
	401	'url': 'https://www.hotstar.com/in/tv/radhakrishn/1260000646',
	402	'info_dict': {
	403	'id': '1260000646',
	404	},
	405	'playlist_mincount': 690,
	406	}, {
	407	'url': 'https://www.hotstar.com/tv/dancee-/1260050431',
	408	'info_dict': {
	409	'id': '1260050431',
	410	},
	411	'playlist_mincount': 43,
8242bf22 A	412	}, {
	413	'url': 'https://www.hotstar.com/in/tv/mahabharat/435/',
	414	'info_dict': {
	415	'id': '435',
	416	},
db6fa696	417	'playlist_mincount': 267,
7f8ddebb	418	}, {
	419	'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/',
	420	'info_dict': {
	421	'id': '1260022017',
	422	},
	423	'playlist_mincount': 940,
6e639032 A	424	}]
	425
	426	def _real_extract(self, url):
81bcd43a	427	url, series_id = self._match_valid_url(url).groups()
fad689c7	428	id_ = self._call_api_v1(
	429	'show/detail', series_id, query={'contentId': series_id})['body']['results']['item']['id']
	430
	431	return self.playlist_result(self._playlist_entries(
	432	'tray/g/1/items', series_id, url, query={'tao': 0, 'tas': 10000, 'etid': 0, 'eid': id_}), series_id)