[yt-dlp.git] / yt_dlp / extractor / zee5.py

# coding: utf-8
from __future__ import unicode_literals

import json

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    ExtractorError,
    int_or_none,
    parse_age_limit,
    str_or_none,
    try_get,
    unified_strdate,
    unified_timestamp,
    url_or_none,
)


class Zee5IE(InfoExtractor):
    _VALID_URL = r'''(?x)
                     (?:
                        zee5:|
                        https?://(?:www\.)?zee5\.com/(?:[^#?]+/)?
                        (?:
                            (?:tv-shows|kids|web-series|zee5originals)(?:/[^#/?]+){3}
                            |movies/[^#/?]+
                        )/(?P<display_id>[^#/?]+)/
                     )
                     (?P<id>[^#/?]+)/?(?:$|[?#])
                     '''
    _TESTS = [{
        'url': 'https://www.zee5.com/movies/details/krishna-the-birth/0-0-63098',
        'info_dict': {
            'id': '0-0-63098',
            'ext': 'mp4',
            'display_id': 'krishna-the-birth',
            'title': 'Krishna - The Birth',
            'duration': 4368,
            'description': compat_str,
            'alt_title': 'Krishna - The Birth',
            'uploader': 'Zee Entertainment Enterprises Ltd',
            'release_date': '20060101',
            'upload_date': '20060101',
            'timestamp': 1136073600,
            'thumbnail': r're:^https?://.*\.jpg$',
            'episode_number': 0,
            'episode': 'Episode 0',
            'tags': list
        },
        'params': {
            'format': 'bv',
        },
    }, {
        'url': 'https://www.zee5.com/kids/kids-shows/bandbudh-aur-budbak/0-6-1899/yoga-se-hoga-bandbudh-aur-budbak/0-1-239839',
        'info_dict': {
            'id': '0-1-239839',
            'ext': 'mp4',
            'display_id': 'yoga-se-hoga-bandbudh-aur-budbak',
            'title': 'Yoga Se Hoga-Bandbudh aur Budbak',
            'duration': 659,
            'description': compat_str,
            'alt_title': 'Yoga Se Hoga-Bandbudh aur Budbak',
            'uploader': 'Zee Entertainment Enterprises Ltd',
            'release_date': '20150101',
            'upload_date': '20150101',
            'timestamp': 1420070400,
            'thumbnail': r're:^https?://.*\.jpg$',
            'series': 'Bandbudh Aur Budbak',
            'season_number': 1,
            'episode_number': 1,
            'episode': 'Episode 1',
            'season': 'Season 1',
            'tags': list,
        },
        'params': {
            'format': 'bv',
        },
    }, {
        'url': 'https://www.zee5.com/hi/tv-shows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730?country=IN',
        'only_matching': True
    }, {
        'url': 'https://www.zee5.com/global/hi/tv-shows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730',
        'only_matching': True
    }, {
        'url': 'https://www.zee5.com/web-series/details/mithya/0-6-4z587408/maine-dekhi-hai-uski-mrityu/0-1-6z587412',
        'only_matching': True
    }]
    _DETAIL_API_URL = 'https://spapi.zee5.com/singlePlayback/getDetails?content_id={}&device_id={}&platform_name=desktop_web&country=IN&check_parental_control=false'
    _DEVICE_ID = 'iIxsxYf40cqO3koIkwzKHZhnJzHN13zb'
    _USER_TOKEN = None
    _LOGIN_HINT = 'Use "--username <mobile_number>" to login using otp or "--username token" and "--password <user_token>" to login using user token.'
    _NETRC_MACHINE = 'zee5'
    _GEO_COUNTRIES = ['IN']

    def _perform_login(self, username, password):
        if len(username) == 10 and username.isdigit() and self._USER_TOKEN is None:
            self.report_login()
            otp_request_json = self._download_json('https://b2bapi.zee5.com/device/sendotp_v1.php?phoneno=91{}'.format(username),
                                                   None, note='Sending OTP')
            if otp_request_json['code'] == 0:
                self.to_screen(otp_request_json['message'])
            else:
                raise ExtractorError(otp_request_json['message'], expected=True)
            otp_code = self._get_tfa_info('OTP')
            otp_verify_json = self._download_json('https://b2bapi.zee5.com/device/verifyotp_v1.php?phoneno=91{}&otp={}&guest_token={}&platform=web'.format(username, otp_code, self._DEVICE_ID),
                                                  None, note='Verifying OTP', fatal=False)
            if not otp_verify_json:
                raise ExtractorError('Unable to verify OTP.', expected=True)
            self._USER_TOKEN = otp_verify_json.get('token')
            if not self._USER_TOKEN:
                raise ExtractorError(otp_request_json['message'], expected=True)
        elif username.lower() == 'token' and len(password) > 1198:
            self._USER_TOKEN = password
        else:
            raise ExtractorError(self._LOGIN_HINT, expected=True)

    def _real_extract(self, url):
        video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
        access_token_request = self._download_json(
            'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
            video_id, note='Downloading access token')
        data = {
            'x-access-token': access_token_request['token']
        }
        if self._USER_TOKEN:
            data['Authorization'] = 'bearer %s' % self._USER_TOKEN
        else:
            data['X-Z5-Guest-Token'] = self._DEVICE_ID

        json_data = self._download_json(
            self._DETAIL_API_URL.format(video_id, self._DEVICE_ID),
            video_id, headers={'content-type': 'application/json'}, data=json.dumps(data).encode('utf-8'))
        asset_data = json_data['assetDetails']
        show_data = json_data.get('showDetails', {})
        if 'premium' in asset_data['business_type']:
            raise ExtractorError('Premium content is DRM protected.', expected=True)
        if not asset_data.get('hls_url'):
            self.raise_login_required(self._LOGIN_HINT, metadata_available=True, method=None)
        formats, m3u8_subs = self._extract_m3u8_formats_and_subtitles(asset_data['hls_url'], video_id, 'mp4', fatal=False)
        self._sort_formats(formats)

        subtitles = {}
        for sub in asset_data.get('subtitle_url', []):
            sub_url = sub.get('url')
            if not sub_url:
                continue
            subtitles.setdefault(sub.get('language', 'en'), []).append({
                'url': self._proto_relative_url(sub_url),
            })
        subtitles = self._merge_subtitles(subtitles, m3u8_subs)
        return {
            'id': video_id,
            'display_id': display_id,
            'title': asset_data['title'],
            'formats': formats,
            'subtitles': subtitles,
            'duration': int_or_none(asset_data.get('duration')),
            'description': str_or_none(asset_data.get('description')),
            'alt_title': str_or_none(asset_data.get('original_title')),
            'uploader': str_or_none(asset_data.get('content_owner')),
            'age_limit': parse_age_limit(asset_data.get('age_rating')),
            'release_date': unified_strdate(asset_data.get('release_date')),
            'timestamp': unified_timestamp(asset_data.get('release_date')),
            'thumbnail': url_or_none(asset_data.get('image_url')),
            'series': str_or_none(asset_data.get('tvshow_name')),
            'season': try_get(show_data, lambda x: x['seasons']['title'], str),
            'season_number': int_or_none(try_get(show_data, lambda x: x['seasons'][0]['orderid'])),
            'episode_number': int_or_none(try_get(asset_data, lambda x: x['orderid'])),
            'tags': try_get(asset_data, lambda x: x['tags'], list)
        }


class Zee5SeriesIE(InfoExtractor):
    IE_NAME = 'zee5:series'
    _VALID_URL = r'''(?x)
                     (?:
                        zee5:series:|
                        https?://(?:www\.)?zee5\.com/(?:[^#?]+/)?
                        (?:tv-shows|web-series|kids|zee5originals)(?:/[^#/?]+){2}/
                     )
                     (?P<id>[^#/?]+)(?:/episodes)?/?(?:$|[?#])
                     '''
    _TESTS = [{
        'url': 'https://www.zee5.com/kids/kids-shows/bandbudh-aur-budbak/0-6-1899',
        'playlist_mincount': 156,
        'info_dict': {
            'id': '0-6-1899',
        },
    }, {
        'url': 'https://www.zee5.com/tv-shows/details/bhabi-ji-ghar-par-hai/0-6-199',
        'playlist_mincount': 1500,
        'info_dict': {
            'id': '0-6-199',
        },
    }, {
        'url': 'https://www.zee5.com/tv-shows/details/agent-raghav-crime-branch/0-6-965',
        'playlist_mincount': 24,
        'info_dict': {
            'id': '0-6-965',
        },
    }, {
        'url': 'https://www.zee5.com/ta/tv-shows/details/nagabhairavi/0-6-3201',
        'playlist_mincount': 3,
        'info_dict': {
            'id': '0-6-3201',
        },
    }, {
        'url': 'https://www.zee5.com/global/hi/tv-shows/details/khwaabon-ki-zamin-par/0-6-270',
        'playlist_mincount': 150,
        'info_dict': {
            'id': '0-6-270',
        },
    }, {
        'url': 'https://www.zee5.com/tv-shows/details/chala-hawa-yeu-dya-ladies-zindabaad/0-6-2943/episodes',
        'only_matching': True,
    }, {
        'url': 'https://www.zee5.com/web-series/details/mithya/0-6-4z587408',
        'only_matching': True,
    }]

    def _entries(self, show_id):
        access_token_request = self._download_json(
            'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
            show_id, note='Downloading access token')
        headers = {
            'X-Access-Token': access_token_request['token'],
            'Referer': 'https://www.zee5.com/',
        }
        show_url = 'https://gwapi.zee5.com/content/tvshow/{}?translation=en&country=IN'.format(show_id)

        page_num = 0
        show_json = self._download_json(show_url, video_id=show_id, headers=headers)
        for season in show_json.get('seasons') or []:
            season_id = try_get(season, lambda x: x['id'], compat_str)
            next_url = 'https://gwapi.zee5.com/content/tvshow/?season_id={}&type=episode&translation=en&country=IN&on_air=false&asset_subtype=tvshow&page=1&limit=100'.format(season_id)
            while next_url:
                page_num += 1
                episodes_json = self._download_json(
                    next_url, video_id=show_id, headers=headers,
                    note='Downloading JSON metadata page %d' % page_num)
                for episode in try_get(episodes_json, lambda x: x['episode'], list) or []:
                    video_id = episode.get('id')
                    yield self.url_result(
                        'zee5:%s' % video_id,
                        ie=Zee5IE.ie_key(), video_id=video_id)
                next_url = url_or_none(episodes_json.get('next_episode_api'))

    def _real_extract(self, url):
        show_id = self._match_id(url)
        return self.playlist_result(self._entries(show_id), playlist_id=show_id)
Commit	Line	Data
da6dcbad A	1	# coding: utf-8
	2	from __future__ import unicode_literals
	3
96c23f3b	4	import json
da6dcbad A	5
da6dcbad A	6	from .common import InfoExtractor
d488e254	7	from ..compat import compat_str
da6dcbad	8	from ..utils import (
96c23f3b	9	ExtractorError,
da6dcbad A	10	int_or_none,
	11	parse_age_limit,
	12	str_or_none,
	13	try_get,
	14	unified_strdate,
	15	unified_timestamp,
	16	url_or_none,
	17	)
	18
	19
	20	class Zee5IE(InfoExtractor):
d488e254 A	21	_VALID_URL = r'''(?x)
	22	(?:
	23	zee5:\|
73f035e1	24	https?://(?:www\.)?zee5\.com/(?:[^#?]+/)?
d488e254	25	(?:
4d4f9a02	26	(?:tv-shows\|kids\|web-series\|zee5originals)(?:/[^#/?]+){3}
d488e254 A	27	\|movies/[^#/?]+
	28	)/(?P<display_id>[^#/?]+)/
	29	)
	30	(?P<id>[^#/?]+)/?(?:$\|[?#])
	31	'''
da6dcbad A	32	_TESTS = [{
	33	'url': 'https://www.zee5.com/movies/details/krishna-the-birth/0-0-63098',
	34	'info_dict': {
d488e254 A	35	'id': '0-0-63098',
	36	'ext': 'mp4',
	37	'display_id': 'krishna-the-birth',
	38	'title': 'Krishna - The Birth',
	39	'duration': 4368,
1815d102	40	'description': compat_str,
d488e254 A	41	'alt_title': 'Krishna - The Birth',
	42	'uploader': 'Zee Entertainment Enterprises Ltd',
	43	'release_date': '20060101',
	44	'upload_date': '20060101',
	45	'timestamp': 1136073600,
ee7b9bdf AG	46	'thumbnail': r're:^https?://.*\.jpg$',
	47	'episode_number': 0,
	48	'episode': 'Episode 0',
d488e254	49	'tags': list
da6dcbad A	50	},
	51	'params': {
	52	'format': 'bv',
	53	},
	54	}, {
ee7b9bdf	55	'url': 'https://www.zee5.com/kids/kids-shows/bandbudh-aur-budbak/0-6-1899/yoga-se-hoga-bandbudh-aur-budbak/0-1-239839',
da6dcbad	56	'info_dict': {
ee7b9bdf	57	'id': '0-1-239839',
d488e254	58	'ext': 'mp4',
ee7b9bdf AG	59	'display_id': 'yoga-se-hoga-bandbudh-aur-budbak',
	60	'title': 'Yoga Se Hoga-Bandbudh aur Budbak',
	61	'duration': 659,
1815d102	62	'description': compat_str,
ee7b9bdf	63	'alt_title': 'Yoga Se Hoga-Bandbudh aur Budbak',
96c23f3b	64	'uploader': 'Zee Entertainment Enterprises Ltd',
ee7b9bdf AG	65	'release_date': '20150101',
	66	'upload_date': '20150101',
	67	'timestamp': 1420070400,
	68	'thumbnail': r're:^https?://.*\.jpg$',
	69	'series': 'Bandbudh Aur Budbak',
d488e254 A	70	'season_number': 1,
d488e254 A	71	'episode_number': 1,
ee7b9bdf AG	72	'episode': 'Episode 1',
ee7b9bdf AG	73	'season': 'Season 1',
d488e254	74	'tags': list,
da6dcbad A	75	},
	76	'params': {
	77	'format': 'bv',
	78	},
54759df5	79	}, {
ee7b9bdf	80	'url': 'https://www.zee5.com/hi/tv-shows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730?country=IN',
54759df5	81	'only_matching': True
d488e254	82	}, {
ee7b9bdf	83	'url': 'https://www.zee5.com/global/hi/tv-shows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730',
d488e254	84	'only_matching': True
4d4f9a02 AJ	85	}, {
	86	'url': 'https://www.zee5.com/web-series/details/mithya/0-6-4z587408/maine-dekhi-hai-uski-mrityu/0-1-6z587412',
	87	'only_matching': True
da6dcbad	88	}]
96c23f3b A	89	_DETAIL_API_URL = 'https://spapi.zee5.com/singlePlayback/getDetails?content_id={}&device_id={}&platform_name=desktop_web&country=IN&check_parental_control=false'
	90	_DEVICE_ID = 'iIxsxYf40cqO3koIkwzKHZhnJzHN13zb'
	91	_USER_TOKEN = None
	92	_LOGIN_HINT = 'Use "--username <mobile_number>" to login using otp or "--username token" and "--password <user_token>" to login using user token.'
	93	_NETRC_MACHINE = 'zee5'
fdeab99e	94	_GEO_COUNTRIES = ['IN']
96c23f3b	95
52efa4b3	96	def _perform_login(self, username, password):
	97	if len(username) == 10 and username.isdigit() and self._USER_TOKEN is None:
	98	self.report_login()
	99	otp_request_json = self._download_json('https://b2bapi.zee5.com/device/sendotp_v1.php?phoneno=91{}'.format(username),
	100	None, note='Sending OTP')
	101	if otp_request_json['code'] == 0:
	102	self.to_screen(otp_request_json['message'])
9e907ebd	103	else:
52efa4b3	104	raise ExtractorError(otp_request_json['message'], expected=True)
	105	otp_code = self._get_tfa_info('OTP')
	106	otp_verify_json = self._download_json('https://b2bapi.zee5.com/device/verifyotp_v1.php?phoneno=91{}&otp={}&guest_token={}&platform=web'.format(username, otp_code, self._DEVICE_ID),
	107	None, note='Verifying OTP', fatal=False)
	108	if not otp_verify_json:
	109	raise ExtractorError('Unable to verify OTP.', expected=True)
	110	self._USER_TOKEN = otp_verify_json.get('token')
	111	if not self._USER_TOKEN:
	112	raise ExtractorError(otp_request_json['message'], expected=True)
	113	elif username.lower() == 'token' and len(password) > 1198:
	114	self._USER_TOKEN = password
	115	else:
	116	raise ExtractorError(self._LOGIN_HINT, expected=True)
da6dcbad A	117
da6dcbad A	118	def _real_extract(self, url):
5ad28e7f	119	video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
da6dcbad A	120	access_token_request = self._download_json(
da6dcbad A	121	'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
d488e254	122	video_id, note='Downloading access token')
96c23f3b A	123	data = {
	124	'x-access-token': access_token_request['token']
	125	}
	126	if self._USER_TOKEN:
	127	data['Authorization'] = 'bearer %s' % self._USER_TOKEN
	128	else:
	129	data['X-Z5-Guest-Token'] = self._DEVICE_ID
da6dcbad	130
96c23f3b A	131	json_data = self._download_json(
	132	self._DETAIL_API_URL.format(video_id, self._DEVICE_ID),
	133	video_id, headers={'content-type': 'application/json'}, data=json.dumps(data).encode('utf-8'))
	134	asset_data = json_data['assetDetails']
	135	show_data = json_data.get('showDetails', {})
	136	if 'premium' in asset_data['business_type']:
	137	raise ExtractorError('Premium content is DRM protected.', expected=True)
	138	if not asset_data.get('hls_url'):
	139	self.raise_login_required(self._LOGIN_HINT, metadata_available=True, method=None)
	140	formats, m3u8_subs = self._extract_m3u8_formats_and_subtitles(asset_data['hls_url'], video_id, 'mp4', fatal=False)
da6dcbad	141	self._sort_formats(formats)
96c23f3b A	142
	143	subtitles = {}
	144	for sub in asset_data.get('subtitle_url', []):
	145	sub_url = sub.get('url')
	146	if not sub_url:
	147	continue
	148	subtitles.setdefault(sub.get('language', 'en'), []).append({
	149	'url': self._proto_relative_url(sub_url),
	150	})
	151	subtitles = self._merge_subtitles(subtitles, m3u8_subs)
da6dcbad A	152	return {
	153	'id': video_id,
	154	'display_id': display_id,
96c23f3b	155	'title': asset_data['title'],
da6dcbad	156	'formats': formats,
96c23f3b A	157	'subtitles': subtitles,
96c23f3b A	158	'duration': int_or_none(asset_data.get('duration')),
96c23f3b A	159	'description': str_or_none(asset_data.get('description')),
	160	'alt_title': str_or_none(asset_data.get('original_title')),
	161	'uploader': str_or_none(asset_data.get('content_owner')),
	162	'age_limit': parse_age_limit(asset_data.get('age_rating')),
	163	'release_date': unified_strdate(asset_data.get('release_date')),
	164	'timestamp': unified_timestamp(asset_data.get('release_date')),
	165	'thumbnail': url_or_none(asset_data.get('image_url')),
	166	'series': str_or_none(asset_data.get('tvshow_name')),
	167	'season': try_get(show_data, lambda x: x['seasons']['title'], str),
	168	'season_number': int_or_none(try_get(show_data, lambda x: x['seasons'][0]['orderid'])),
	169	'episode_number': int_or_none(try_get(asset_data, lambda x: x['orderid'])),
	170	'tags': try_get(asset_data, lambda x: x['tags'], list)
da6dcbad	171	}
d488e254 A	172
	173
	174	class Zee5SeriesIE(InfoExtractor):
	175	IE_NAME = 'zee5:series'
	176	_VALID_URL = r'''(?x)
	177	(?:
	178	zee5:series:\|
73f035e1	179	https?://(?:www\.)?zee5\.com/(?:[^#?]+/)?
4d4f9a02	180	(?:tv-shows\|web-series\|kids\|zee5originals)(?:/[^#/?]+){2}/
d488e254	181	)
b3a5115f	182	(?P<id>[^#/?]+)(?:/episodes)?/?(?:$\|[?#])
d488e254 A	183	'''
d488e254 A	184	_TESTS = [{
ee7b9bdf AG	185	'url': 'https://www.zee5.com/kids/kids-shows/bandbudh-aur-budbak/0-6-1899',
ee7b9bdf AG	186	'playlist_mincount': 156,
d488e254	187	'info_dict': {
ee7b9bdf	188	'id': '0-6-1899',
d488e254 A	189	},
d488e254 A	190	}, {
ee7b9bdf	191	'url': 'https://www.zee5.com/tv-shows/details/bhabi-ji-ghar-par-hai/0-6-199',
d488e254 A	192	'playlist_mincount': 1500,
	193	'info_dict': {
	194	'id': '0-6-199',
	195	},
	196	}, {
ee7b9bdf	197	'url': 'https://www.zee5.com/tv-shows/details/agent-raghav-crime-branch/0-6-965',
96c23f3b	198	'playlist_mincount': 24,
d488e254 A	199	'info_dict': {
	200	'id': '0-6-965',
	201	},
	202	}, {
ee7b9bdf	203	'url': 'https://www.zee5.com/ta/tv-shows/details/nagabhairavi/0-6-3201',
d488e254 A	204	'playlist_mincount': 3,
	205	'info_dict': {
	206	'id': '0-6-3201',
	207	},
	208	}, {
ee7b9bdf	209	'url': 'https://www.zee5.com/global/hi/tv-shows/details/khwaabon-ki-zamin-par/0-6-270',
d488e254 A	210	'playlist_mincount': 150,
	211	'info_dict': {
	212	'id': '0-6-270',
	213	},
b3a5115f	214	}, {
ee7b9bdf	215	'url': 'https://www.zee5.com/tv-shows/details/chala-hawa-yeu-dya-ladies-zindabaad/0-6-2943/episodes',
b3a5115f	216	'only_matching': True,
4d4f9a02 AJ	217	}, {
	218	'url': 'https://www.zee5.com/web-series/details/mithya/0-6-4z587408',
	219	'only_matching': True,
b3a5115f	220	}]
d488e254 A	221
	222	def _entries(self, show_id):
	223	access_token_request = self._download_json(
	224	'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
	225	show_id, note='Downloading access token')
	226	headers = {
	227	'X-Access-Token': access_token_request['token'],
	228	'Referer': 'https://www.zee5.com/',
	229	}
	230	show_url = 'https://gwapi.zee5.com/content/tvshow/{}?translation=en&country=IN'.format(show_id)
	231
	232	page_num = 0
	233	show_json = self._download_json(show_url, video_id=show_id, headers=headers)
	234	for season in show_json.get('seasons') or []:
	235	season_id = try_get(season, lambda x: x['id'], compat_str)
	236	next_url = 'https://gwapi.zee5.com/content/tvshow/?season_id={}&type=episode&translation=en&country=IN&on_air=false&asset_subtype=tvshow&page=1&limit=100'.format(season_id)
	237	while next_url:
	238	page_num += 1
	239	episodes_json = self._download_json(
	240	next_url, video_id=show_id, headers=headers,
	241	note='Downloading JSON metadata page %d' % page_num)
	242	for episode in try_get(episodes_json, lambda x: x['episode'], list) or []:
	243	video_id = episode.get('id')
	244	yield self.url_result(
	245	'zee5:%s' % video_id,
	246	ie=Zee5IE.ie_key(), video_id=video_id)
	247	next_url = url_or_none(episodes_json.get('next_episode_api'))
	248
	249	def _real_extract(self, url):
	250	show_id = self._match_id(url)
	251	return self.playlist_result(self._entries(show_id), playlist_id=show_id)