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

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

from .common import InfoExtractor
from ..compat import (
    compat_HTTPError,
    compat_str
)
from ..utils import (
    determine_ext,
    ExtractorError,
    int_or_none,
    join_nonempty,
    str_or_none,
    try_get,
    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_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(self, path, video_id, query_name='contentId'):
        return self._download_json(
            f'{self._API_URL}/{path}', video_id=video_id,
            query={
                query_name: video_id,
                'tas': 10000,
            }, headers={
                'x-country-code': 'IN',
                'x-platform-code': 'PCTV',
            })

    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',
            })


class HotStarIE(HotStarBaseIE):
    IE_NAME = 'hotstar'
    _VALID_URL = r'''(?x)
        https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/)
        (?:
            (?P<type>movies|sports|episode|(?P<tv>tv))/
            (?(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?',
        },
    }, {
        '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/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',
        None: 'content',
    }

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

    @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(f'o/v1/{video_type}/detail', 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

            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)
            dr = re.search(r'dynamic_range:(?P<dr>[a-z]+)', playback_set.get('tagsCombination')).group('dr')
            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, 'mp4',
                        entry_protocol='m3u8_native',
                        m3u8_id=f'{dr}-hls', headers=headers)
                elif 'package:dash' in tags or ext == 'mpd':
                    current_formats, current_subs = self._extract_mpd_formats_and_subtitles(
                        format_url, video_id, mpd_id=f'{dr}-dash', 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, compat_HTTPError) and e.cause.code == 403:
                    geo_restricted = True
                continue

            if tags and 'encryption:plain' not in tags:
                for f in current_formats:
                    f['has_drm'] = True
            if tags and 'language' in tags:
                lang = re.search(r'language:(?P<lang>[a-z]+)', tags).group('lang')
                for f in current_formats:
                    if not f.get('langauge'):
                        f['language'] = lang

            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._sort_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(video_data.get('broadcastDate') or video_data.get('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:1000057157',
        'info_dict': {
            'id': '1000057157',
            'ext': 'mp4',
            'title': 'Radha Gopalam',
            'description': 'md5:be3bc342cc120bbc95b3b0960e2b0d22',
            'timestamp': 1140805800,
            'upload_date': '20060224',
            'duration': 9182,
            'episode': 'Radha Gopalam',
        },
    }, {
        '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/tv/[^/]+/s-\w+/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/tv/savdhaan-india/s-26/list/extras/t-2480',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        playlist_id = self._match_id(url)

        collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId')['body']['results']
        entries = [
            self.url_result(HotStarIE._video_url(video['contentId']), HotStarIE, video['contentId'])
            for video in collection['assets']['items'] if video.get('contentId')]

        return self.playlist_result(entries, playlist_id)


class HotStarSeriesIE(HotStarBaseIE):
    IE_NAME = 'hotstar:series'
    _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/tv/[^/]+/(?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': 269,
    }]

    def _real_extract(self, url):
        url, series_id = self._match_valid_url(url).groups()
        headers = {
            'x-country-code': 'IN',
            'x-platform-code': 'PCTV',
        }
        detail_json = self._download_json(
            f'{self._API_URL}/o/v1/show/detail?contentId={series_id}', series_id, headers=headers)
        id = try_get(detail_json, lambda x: x['body']['results']['item']['id'], int)
        item_json = self._download_json(
            f'{self._API_URL}/o/v1/tray/g/1/items?etid=0&tao=0&tas=10000&eid={id}', series_id, headers=headers)

        return self.playlist_result([
            self.url_result(HotStarIE._video_url(video['contentId'], root=url), HotStarIE, video['contentId'])
            for video in item_json['body']['results']['items'] if video.get('contentId')
        ], series_id)
Commit	Line	Data
85cd69ad RA	1	import hashlib
85cd69ad RA	2	import hmac
1cb812d3	3	import re
85cd69ad	4	import time
2533f5b6	5	import uuid
7078ec64	6	import json
909191de	7
fb8e402a	8	from .common import InfoExtractor
2533f5b6 S	9	from ..compat import (
2533f5b6 S	10	compat_HTTPError,
6923b538	11	compat_str
2533f5b6	12	)
fb8e402a	13	from ..utils import (
fb8e402a	14	determine_ext,
909191de	15	ExtractorError,
fb8e402a	16	int_or_none,
a1ddaa89	17	join_nonempty,
2533f5b6	18	str_or_none,
05e7c184	19	try_get,
2533f5b6	20	url_or_none,
fb8e402a	21	)
	22
	23
909191de	24	class HotStarBaseIE(InfoExtractor):
a1ddaa89	25	_BASE_URL = 'https://www.hotstar.com'
a1ddaa89	26	_API_URL = 'https://api.hotstar.com'
85cd69ad RA	27	_AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
85cd69ad RA	28
fe07e2c6	29	def _call_api_impl(self, path, video_id, query, st=None, cookies=None):
9fc0de57	30	st = int_or_none(st) or int(time.time())
85cd69ad RA	31	exp = st + 6000
	32	auth = 'st=%d~exp=%d~acl=/*' % (st, exp)
	33	auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
6923b538	34
b6a35ad8	35	if cookies and cookies.get('userUP'):
fe07e2c6 A	36	token = cookies.get('userUP').value
	37	else:
	38	token = self._download_json(
a1ddaa89	39	f'{self._API_URL}/um/v3/users',
fe07e2c6 A	40	video_id, note='Downloading token',
	41	data=json.dumps({"device_ids": [{"id": compat_str(uuid.uuid4()), "type": "device_id"}]}).encode('utf-8'),
	42	headers={
	43	'hotstarauth': auth,
	44	'x-hs-platform': 'PCTV', # or 'web'
	45	'Content-Type': 'application/json',
	46	})['user_identity']
6923b538	47
85cd69ad	48	response = self._download_json(
a1ddaa89	49	f'{self._API_URL}/{path}', video_id, query=query,
a1ddaa89	50	headers={
85cd69ad	51	'hotstarauth': auth,
7078ec64 N	52	'x-hs-appversion': '6.72.2',
	53	'x-hs-platform': 'web',
	54	'x-hs-usertoken': token,
a1ddaa89	55	})
6923b538	56
7078ec64	57	if response['message'] != "Playback URL's fetched successfully":
85cd69ad	58	raise ExtractorError(
7078ec64 N	59	response['message'], expected=True)
7078ec64 N	60	return response['data']
909191de	61
2533f5b6	62	def _call_api(self, path, video_id, query_name='contentId'):
a1ddaa89	63	return self._download_json(
	64	f'{self._API_URL}/{path}', video_id=video_id,
	65	query={
	66	query_name: video_id,
	67	'tas': 10000,
	68	}, headers={
	69	'x-country-code': 'IN',
	70	'x-platform-code': 'PCTV',
	71	})
2533f5b6	72
5d5c0f7e	73	def _call_api_v2(self, path, video_id, st=None, cookies=None):
2533f5b6	74	return self._call_api_impl(
a1ddaa89	75	f'{path}/content/{video_id}', video_id, st=st, cookies=cookies, query={
a64907d0	76	'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	77	'device-id': cookies.get('device_id').value if cookies.get('device_id') else compat_str(uuid.uuid4()),
7078ec64 N	78	'os-name': 'Windows',
7078ec64 N	79	'os-version': '10',
2533f5b6 S	80	})
2533f5b6 S	81
909191de S	82
909191de S	83	class HotStarIE(HotStarBaseIE):
85cd69ad	84	IE_NAME = 'hotstar'
6e639032	85	_VALID_URL = r'''(?x)
a1ddaa89	86	https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/)
	87	(?:
	88	(?P<type>movies\|sports\|episode\|(?P<tv>tv))/
	89	(?(tv)(?:[^/?#]+/){2}\|[^?#]*)
	90	)?
	91	[^/?#]+/
	92	(?P<id>\d{10})
	93	'''
	94
89d23f37	95	_TESTS = [{
85cd69ad	96	'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273',
fb8e402a	97	'info_dict': {
	98	'id': '1000076273',
	99	'ext': 'mp4',
85cd69ad	100	'title': 'Can You Not Spread Rumours?',
fb8e402a	101	'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
85cd69ad	102	'timestamp': 1447248600,
fb8e402a	103	'upload_date': '20151111',
fb8e402a	104	'duration': 381,
a1ddaa89	105	'episode': 'Can You Not Spread Rumours?',
fb8e402a	106	},
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	}
b6a35ad8	126	}, {
a1ddaa89	127	'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
	128	'only_matching': True,
	129	}, {
	130	'url': 'https://www.hotstar.com/in/sports/cricket/follow-the-blues-2021/recap-eng-fight-back-on-day-2/1260066104',
	131	'only_matching': True,
	132	}, {
	133	'url': 'https://www.hotstar.com/in/sports/football/most-costly-pl-transfers-ft-grealish/1260065956',
2533f5b6	134	'only_matching': True,
89d23f37	135	}]
85cd69ad	136	_GEO_BYPASS = False
a1ddaa89	137
b6a35ad8 A	138	_TYPE = {
	139	'movies': 'movie',
	140	'sports': 'match',
	141	'episode': 'episode',
	142	'tv': 'episode',
	143	None: 'content',
	144	}
fb8e402a	145
a1ddaa89	146	_IGNORE_MAP = {
	147	'res': 'resolution',
	148	'vcodec': 'video_codec',
	149	'dr': 'dynamic_range',
	150	}
	151
	152	@classmethod
	153	def _video_url(cls, video_id, video_type=None, *, slug='ignore_me', root=None):
	154	assert None in (video_type, root)
	155	if not root:
	156	root = join_nonempty(cls._BASE_URL, video_type, delim='/')
	157	return f'{root}/{slug}/{video_id}'
	158
fb8e402a	159	def _real_extract(self, url):
a1ddaa89	160	video_id, video_type = self._match_valid_url(url).group('id', 'type')
b6a35ad8	161	video_type = self._TYPE.get(video_type, video_type)
5d5c0f7e	162	cookies = self._get_cookies(url) # Cookies before any request
0dac7cbb	163
a1ddaa89	164	video_data = self._call_api(f'o/v1/{video_type}/detail', video_id)['body']['results']['item']
a06916d9	165	if not self.get_param('allow_unplayable_formats') and video_data.get('drmProtected'):
88acdbc2	166	self.report_drm(video_id)
88acdbc2	167
a1ddaa89	168	# See https://github.com/yt-dlp/yt-dlp/issues/396
	169	st = self._download_webpage_handle(f'{self._BASE_URL}/in', video_id)[1].headers.get('x-origin-date')
	170
2533f5b6	171	geo_restricted = False
a1ddaa89	172	formats, subs = [], {}
	173	headers = {'Referer': f'{self._BASE_URL}/in'}
	174
6923b538	175	# change to v2 in the future
5d5c0f7e	176	playback_sets = self._call_api_v2('play/v1/playback', video_id, st=st, cookies=cookies)['playBackSets']
2533f5b6 S	177	for playback_set in playback_sets:
	178	if not isinstance(playback_set, dict):
	179	continue
a1ddaa89	180	tags = str_or_none(playback_set.get('tagsCombination')) or ''
	181	if any(f'{prefix}:{ignore}' in tags
	182	for key, prefix in self._IGNORE_MAP.items()
	183	for ignore in self._configuration_arg(key)):
	184	continue
	185
2533f5b6 S	186	format_url = url_or_none(playback_set.get('playbackUrl'))
	187	if not format_url:
	188	continue
a1ddaa89	189	format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', format_url)
a1ddaa89	190	dr = re.search(r'dynamic_range:(?P<dr>[a-z]+)', playback_set.get('tagsCombination')).group('dr')
2533f5b6	191	ext = determine_ext(format_url)
a1ddaa89	192
6ff34542	193	current_formats, current_subs = [], {}
85cd69ad	194	try:
2533f5b6	195	if 'package:hls' in tags or ext == 'm3u8':
6ff34542	196	current_formats, current_subs = self._extract_m3u8_formats_and_subtitles(
d9d30986	197	format_url, video_id, 'mp4',
d7def23d	198	entry_protocol='m3u8_native',
a64907d0	199	m3u8_id=f'{dr}-hls', headers=headers)
2533f5b6	200	elif 'package:dash' in tags or ext == 'mpd':
6ff34542	201	current_formats, current_subs = self._extract_mpd_formats_and_subtitles(
a64907d0	202	format_url, video_id, mpd_id=f'{dr}-dash', headers=headers)
2533f5b6	203	elif ext == 'f4m':
a1ddaa89	204	pass # XXX: produce broken files
2533f5b6	205	else:
6ff34542	206	current_formats = [{
2533f5b6 S	207	'url': format_url,
	208	'width': int_or_none(playback_set.get('width')),
	209	'height': int_or_none(playback_set.get('height')),
6ff34542	210	}]
85cd69ad RA	211	except ExtractorError as e:
85cd69ad RA	212	if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
2533f5b6 S	213	geo_restricted = True
2533f5b6 S	214	continue
a1ddaa89	215
6ff34542 AG	216	if tags and 'encryption:plain' not in tags:
	217	for f in current_formats:
	218	f['has_drm'] = True
525d9e0c AG	219	if tags and 'language' in tags:
	220	lang = re.search(r'language:(?P<lang>[a-z]+)', tags).group('lang')
	221	for f in current_formats:
	222	if not f.get('langauge'):
	223	f['language'] = lang
a1ddaa89	224
6ff34542 AG	225	formats.extend(current_formats)
6ff34542 AG	226	subs = self._merge_subtitles(subs, current_subs)
a1ddaa89	227
2533f5b6	228	if not formats and geo_restricted:
b7da73eb	229	self.raise_geo_restricted(countries=['IN'], metadata_available=True)
fb8e402a	230	self._sort_formats(formats)
d7def23d RA	231	for f in formats:
	232	f.setdefault('http_headers', {}).update(headers)
	233
fb8e402a	234	return {
fb8e402a	235	'id': video_id,
a1ddaa89	236	'title': video_data.get('title'),
fb8e402a	237	'description': video_data.get('description'),
fb8e402a	238	'duration': int_or_none(video_data.get('duration')),
85cd69ad	239	'timestamp': int_or_none(video_data.get('broadcastDate') or video_data.get('startDate')),
fb8e402a	240	'formats': formats,
b6a35ad8	241	'subtitles': subs,
85cd69ad RA	242	'channel': video_data.get('channelName'),
	243	'channel_id': video_data.get('channelId'),
	244	'series': video_data.get('showName'),
	245	'season': video_data.get('seasonName'),
	246	'season_number': int_or_none(video_data.get('seasonNo')),
	247	'season_id': video_data.get('seasonId'),
a1ddaa89	248	'episode': video_data.get('title'),
85cd69ad	249	'episode_number': int_or_none(video_data.get('episodeNo')),
fb8e402a	250	}
477c97f8 AV	251
477c97f8 AV	252
a1ddaa89	253	class HotStarPrefixIE(InfoExtractor):
	254	""" The "hotstar:" prefix is no longer in use, but this is kept for backward compatibility """
	255	IE_DESC = False
	256	_VALID_URL = r'hotstar:(?:(?P<type>\w+):)?(?P<id>\d+)$'
	257	_TESTS = [{
	258	'url': 'hotstar:1000076273',
	259	'only_matching': True,
	260	}, {
	261	'url': 'hotstar:movies:1000057157',
	262	'info_dict': {
	263	'id': '1000057157',
	264	'ext': 'mp4',
	265	'title': 'Radha Gopalam',
	266	'description': 'md5:be3bc342cc120bbc95b3b0960e2b0d22',
	267	'timestamp': 1140805800,
	268	'upload_date': '20060224',
	269	'duration': 9182,
	270	'episode': 'Radha Gopalam',
	271	},
	272	}, {
	273	'url': 'hotstar:episode:1000234847',
	274	'only_matching': True,
	275	}, {
	276	# contentData
	277	'url': 'hotstar:sports:1260065956',
	278	'only_matching': True,
	279	}, {
	280	# contentData
	281	'url': 'hotstar:sports:1260066104',
	282	'only_matching': True,
	283	}]
	284
	285	def _real_extract(self, url):
	286	video_id, video_type = self._match_valid_url(url).group('id', 'type')
	287	return self.url_result(HotStarIE._video_url(video_id, video_type), HotStarIE, video_id)
	288
	289
909191de	290	class HotStarPlaylistIE(HotStarBaseIE):
477c97f8	291	IE_NAME = 'hotstar:playlist'
85cd69ad	292	_VALID_URL = r'https?://(?:www\.)?hotstar\.com/tv/[^/]+/s-\w+/list/[^/]+/t-(?P<id>\w+)'
477c97f8	293	_TESTS = [{
85cd69ad	294	'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
477c97f8	295	'info_dict': {
85cd69ad	296	'id': '3_2_26',
477c97f8	297	},
85cd69ad	298	'playlist_mincount': 20,
477c97f8	299	}, {
85cd69ad	300	'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
477c97f8 AV	301	'only_matching': True,
477c97f8 AV	302	}]
477c97f8 AV	303
477c97f8 AV	304	def _real_extract(self, url):
85cd69ad RA	305	playlist_id = self._match_id(url)
85cd69ad RA	306
b6a35ad8	307	collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId')['body']['results']
477c97f8	308	entries = [
a1ddaa89	309	self.url_result(HotStarIE._video_url(video['contentId']), HotStarIE, video['contentId'])
a1ddaa89	310	for video in collection['assets']['items'] if video.get('contentId')]
909191de S	311
909191de S	312	return self.playlist_result(entries, playlist_id)
6e639032 A	313
	314
	315	class HotStarSeriesIE(HotStarBaseIE):
	316	IE_NAME = 'hotstar:series'
73f035e1	317	_VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/tv/[^/]+/(?P<id>\d+))'
6e639032 A	318	_TESTS = [{
	319	'url': 'https://www.hotstar.com/in/tv/radhakrishn/1260000646',
	320	'info_dict': {
	321	'id': '1260000646',
	322	},
	323	'playlist_mincount': 690,
	324	}, {
	325	'url': 'https://www.hotstar.com/tv/dancee-/1260050431',
	326	'info_dict': {
	327	'id': '1260050431',
	328	},
	329	'playlist_mincount': 43,
8242bf22 A	330	}, {
	331	'url': 'https://www.hotstar.com/in/tv/mahabharat/435/',
	332	'info_dict': {
	333	'id': '435',
	334	},
	335	'playlist_mincount': 269,
6e639032 A	336	}]
	337
	338	def _real_extract(self, url):
81bcd43a	339	url, series_id = self._match_valid_url(url).groups()
6e639032 A	340	headers = {
	341	'x-country-code': 'IN',
	342	'x-platform-code': 'PCTV',
	343	}
a1ddaa89	344	detail_json = self._download_json(
	345	f'{self._API_URL}/o/v1/show/detail?contentId={series_id}', series_id, headers=headers)
	346	id = try_get(detail_json, lambda x: x['body']['results']['item']['id'], int)
	347	item_json = self._download_json(
	348	f'{self._API_URL}/o/v1/tray/g/1/items?etid=0&tao=0&tas=10000&eid={id}', series_id, headers=headers)
6e639032	349
a1ddaa89	350	return self.playlist_result([
	351	self.url_result(HotStarIE._video_url(video['contentId'], root=url), HotStarIE, video['contentId'])
	352	for video in item_json['body']['results']['items'] if video.get('contentId')
	353	], series_id)