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

# coding: utf-8
from __future__ import unicode_literals

import re
import time

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    js_to_json,
    urlencode_postdata,
    ExtractorError,
    parse_qs
)


class IPrimaIE(InfoExtractor):
    _VALID_URL = r'https?://(?!cnn)(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
    _GEO_BYPASS = False
    _NETRC_MACHINE = 'iprima'
    _LOGIN_URL = 'https://auth.iprima.cz/oauth2/login'
    _TOKEN_URL = 'https://auth.iprima.cz/oauth2/token'
    access_token = None

    _TESTS = [{
        'url': 'https://prima.iprima.cz/particka/92-epizoda',
        'info_dict': {
            'id': 'p51388',
            'ext': 'mp4',
            'title': 'Partička (92)',
            'description': 'md5:859d53beae4609e6dd7796413f1b6cac',
            'upload_date': '20201103',
            'timestamp': 1604437480,
        },
        'params': {
            'skip_download': True,  # m3u8 download
        },
    }, {
        'url': 'http://play.iprima.cz/particka/particka-92',
        'only_matching': True,
    }, {
        # geo restricted
        'url': 'http://play.iprima.cz/closer-nove-pripady/closer-nove-pripady-iv-1',
        'only_matching': True,
    }, {
        'url': 'https://prima.iprima.cz/my-little-pony/mapa-znameni-2-2',
        'only_matching': True,
    }, {
        'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha',
        'only_matching': True,
    }, {
        'url': 'http://www.iprima.cz/filmy/desne-rande',
        'only_matching': True,
    }, {
        'url': 'https://zoom.iprima.cz/10-nejvetsich-tajemstvi-zahad/posvatna-mista-a-stavby',
        'only_matching': True,
    }, {
        'url': 'https://krimi.iprima.cz/mraz-0/sebevrazdy',
        'only_matching': True,
    }, {
        'url': 'https://cool.iprima.cz/derava-silnice-nevadi',
        'only_matching': True,
    }, {
        'url': 'https://love.iprima.cz/laska-az-za-hrob/slib-dany-bratrovi',
        'only_matching': True,
    }]

    def _login(self):
        username, password = self._get_login_info()

        if username is None or password is None:
            self.raise_login_required('Login is required to access any iPrima content', method='password')

        login_page = self._download_webpage(
            self._LOGIN_URL, None, note='Downloading login page',
            errnote='Downloading login page failed')

        login_form = self._hidden_inputs(login_page)

        login_form.update({
            '_email': username,
            '_password': password})

        _, login_handle = self._download_webpage_handle(
            self._LOGIN_URL, None, data=urlencode_postdata(login_form),
            note='Logging in')

        code = parse_qs(login_handle.geturl()).get('code')[0]
        if not code:
            raise ExtractorError('Login failed', expected=True)

        token_request_data = {
            'scope': 'openid+email+profile+phone+address+offline_access',
            'client_id': 'prima_sso',
            'grant_type': 'authorization_code',
            'code': code,
            'redirect_uri': 'https://auth.iprima.cz/sso/auth-check'}

        token_data = self._download_json(
            self._TOKEN_URL, None,
            note='Downloading token', errnote='Downloading token failed',
            data=urlencode_postdata(token_request_data))

        self.access_token = token_data.get('access_token')
        if self.access_token is None:
            raise ExtractorError('Getting token failed', expected=True)

    def _raise_access_error(self, error_code):
        if error_code == 'PLAY_GEOIP_DENIED':
            self.raise_geo_restricted(countries=['CZ'], metadata_available=True)
        elif error_code is not None:
            self.raise_no_formats('Access to stream infos forbidden', expected=True)

    def _real_initialize(self):
        if not self.access_token:
            self._login()

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

        webpage = self._download_webpage(url, video_id)

        title = self._html_search_meta(
            ['og:title', 'twitter:title'],
            webpage, 'title', default=None)

        video_id = self._search_regex((
            r'productId\s*=\s*([\'"])(?P<id>p\d+)\1',
            r'pproduct_id\s*=\s*([\'"])(?P<id>p\d+)\1'),
            webpage, 'real id', group='id')

        metadata = self._download_json(
            f'https://api.play-backend.iprima.cz/api/v1//products/id-{video_id}/play',
            video_id, note='Getting manifest URLs', errnote='Failed to get manifest URLs',
            headers={'X-OTT-Access-Token': self.access_token},
            expected_status=403)

        self._raise_access_error(metadata.get('errorCode'))

        stream_infos = metadata.get('streamInfos')
        formats = []
        if stream_infos is None:
            self.raise_no_formats('Reading stream infos failed', expected=True)
        else:
            for manifest in stream_infos:
                manifest_type = manifest.get('type')
                manifest_url = manifest.get('url')
                ext = determine_ext(manifest_url)
                if manifest_type == 'HLS' or ext == 'm3u8':
                    formats += self._extract_m3u8_formats(
                        manifest_url, video_id, 'mp4', entry_protocol='m3u8_native',
                        m3u8_id='hls', fatal=False)
                elif manifest_type == 'DASH' or ext == 'mpd':
                    formats += self._extract_mpd_formats(
                        manifest_url, video_id, mpd_id='dash', fatal=False)
            self._sort_formats(formats)

        final_result = self._search_json_ld(webpage, video_id) or {}
        final_result.update({
            'id': video_id,
            'title': title,
            'thumbnail': self._html_search_meta(
                ['thumbnail', 'og:image', 'twitter:image'],
                webpage, 'thumbnail', default=None),
            'formats': formats,
            'description': self._html_search_meta(
                ['description', 'og:description', 'twitter:description'],
                webpage, 'description', default=None)})

        return final_result


class IPrimaCNNIE(InfoExtractor):
    _VALID_URL = r'https?://cnn\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
    _GEO_BYPASS = False

    _TESTS = [{
        'url': 'https://cnn.iprima.cz/porady/strunc/24072020-koronaviru-mam-plne-zuby-strasit-druhou-vlnou-je-absurdni-rika-senatorka-dernerova',
        'info_dict': {
            'id': 'p716177',
            'ext': 'mp4',
            'title': 'md5:277c6b1ed0577e51b40ddd35602ff43e',
        },
        'params': {
            'skip_download': 'm3u8'
        }
    }]

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

        self._set_cookie('play.iprima.cz', 'ott_adult_confirmed', '1')

        webpage = self._download_webpage(url, video_id)

        title = self._og_search_title(
            webpage, default=None) or self._search_regex(
            r'<h1>([^<]+)', webpage, 'title')

        video_id = self._search_regex(
            (r'<iframe[^>]+\bsrc=["\'](?:https?:)?//(?:api\.play-backend\.iprima\.cz/prehravac/embedded|prima\.iprima\.cz/[^/]+/[^/]+)\?.*?\bid=(p\d+)',
             r'data-product="([^"]+)">',
             r'id=["\']player-(p\d+)"',
             r'playerId\s*:\s*["\']player-(p\d+)',
             r'\bvideos\s*=\s*["\'](p\d+)'),
            webpage, 'real id')

        playerpage = self._download_webpage(
            'http://play.iprima.cz/prehravac/init',
            video_id, note='Downloading player', query={
                '_infuse': 1,
                '_ts': round(time.time()),
                'productId': video_id,
            }, headers={'Referer': url})

        formats = []

        def extract_formats(format_url, format_key=None, lang=None):
            ext = determine_ext(format_url)
            new_formats = []
            if format_key == 'hls' or ext == 'm3u8':
                new_formats = self._extract_m3u8_formats(
                    format_url, video_id, 'mp4', entry_protocol='m3u8_native',
                    m3u8_id='hls', fatal=False)
            elif format_key == 'dash' or ext == 'mpd':
                return
                new_formats = self._extract_mpd_formats(
                    format_url, video_id, mpd_id='dash', fatal=False)
            if lang:
                for f in new_formats:
                    if not f.get('language'):
                        f['language'] = lang
            formats.extend(new_formats)

        options = self._parse_json(
            self._search_regex(
                r'(?s)(?:TDIPlayerOptions|playerOptions)\s*=\s*({.+?});\s*\]\]',
                playerpage, 'player options', default='{}'),
            video_id, transform_source=js_to_json, fatal=False)
        if options:
            for key, tracks in options.get('tracks', {}).items():
                if not isinstance(tracks, list):
                    continue
                for track in tracks:
                    src = track.get('src')
                    if src:
                        extract_formats(src, key.lower(), track.get('lang'))

        if not formats:
            for _, src in re.findall(r'src["\']\s*:\s*(["\'])(.+?)\1', playerpage):
                extract_formats(src)

        if not formats and '>GEO_IP_NOT_ALLOWED<' in playerpage:
            self.raise_geo_restricted(countries=['CZ'], metadata_available=True)

        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': title,
            'thumbnail': self._og_search_thumbnail(webpage, default=None),
            'formats': formats,
            'description': self._og_search_description(webpage, default=None),
        }
Commit	Line	Data
369e7e3f	1	# coding: utf-8
7881a644	2	from __future__ import unicode_literals
	3
	4	import re
f406c787	5	import time
7881a644	6
7881a644	7	from .common import InfoExtractor
1cc79574	8	from ..utils import (
369e7e3f S	9	determine_ext,
369e7e3f S	10	js_to_json,
e1b7c54d	11	urlencode_postdata,
	12	ExtractorError,
	13	parse_qs
82642235	14	)
7881a644	15
	16
	17	class IPrimaIE(InfoExtractor):
e1b7c54d	18	_VALID_URL = r'https?://(?!cnn)(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
da42ff06	19	_GEO_BYPASS = False
e1b7c54d	20	_NETRC_MACHINE = 'iprima'
	21	_LOGIN_URL = 'https://auth.iprima.cz/oauth2/login'
	22	_TOKEN_URL = 'https://auth.iprima.cz/oauth2/token'
	23	access_token = None
7881a644	24
7881a644	25	_TESTS = [{
30fa5c60	26	'url': 'https://prima.iprima.cz/particka/92-epizoda',
7881a644	27	'info_dict': {
30fa5c60	28	'id': 'p51388',
f406c787	29	'ext': 'mp4',
30fa5c60 S	30	'title': 'Partička (92)',
30fa5c60 S	31	'description': 'md5:859d53beae4609e6dd7796413f1b6cac',
e1b7c54d	32	'upload_date': '20201103',
e1b7c54d	33	'timestamp': 1604437480,
7881a644	34	},
7881a644	35	'params': {
f406c787	36	'skip_download': True, # m3u8 download
7881a644	37	},
973f2532	38	}, {
f406c787	39	'url': 'http://play.iprima.cz/particka/particka-92',
bc03e585	40	'only_matching': True,
da42ff06 S	41	}, {
	42	# geo restricted
	43	'url': 'http://play.iprima.cz/closer-nove-pripady/closer-nove-pripady-iv-1',
	44	'only_matching': True,
a2637a2d	45	}, {
a2637a2d S	46	'url': 'https://prima.iprima.cz/my-little-pony/mapa-znameni-2-2',
	47	'only_matching': True,
	48	}, {
a2637a2d S	49	'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha',
a2637a2d S	50	'only_matching': True,
9235b509 S	51	}, {
	52	'url': 'http://www.iprima.cz/filmy/desne-rande',
	53	'only_matching': True,
90046d77	54	}, {
	55	'url': 'https://zoom.iprima.cz/10-nejvetsich-tajemstvi-zahad/posvatna-mista-a-stavby',
	56	'only_matching': True,
	57	}, {
	58	'url': 'https://krimi.iprima.cz/mraz-0/sebevrazdy',
	59	'only_matching': True,
	60	}, {
	61	'url': 'https://cool.iprima.cz/derava-silnice-nevadi',
	62	'only_matching': True,
	63	}, {
	64	'url': 'https://love.iprima.cz/laska-az-za-hrob/slib-dany-bratrovi',
	65	'only_matching': True,
e1b7c54d	66	}]
	67
	68	def _login(self):
	69	username, password = self._get_login_info()
	70
	71	if username is None or password is None:
	72	self.raise_login_required('Login is required to access any iPrima content', method='password')
	73
	74	login_page = self._download_webpage(
	75	self._LOGIN_URL, None, note='Downloading login page',
	76	errnote='Downloading login page failed')
	77
	78	login_form = self._hidden_inputs(login_page)
	79
	80	login_form.update({
	81	'_email': username,
	82	'_password': password})
	83
	84	_, login_handle = self._download_webpage_handle(
	85	self._LOGIN_URL, None, data=urlencode_postdata(login_form),
	86	note='Logging in')
	87
	88	code = parse_qs(login_handle.geturl()).get('code')[0]
	89	if not code:
	90	raise ExtractorError('Login failed', expected=True)
	91
	92	token_request_data = {
	93	'scope': 'openid+email+profile+phone+address+offline_access',
	94	'client_id': 'prima_sso',
	95	'grant_type': 'authorization_code',
	96	'code': code,
d54c6003	97	'redirect_uri': 'https://auth.iprima.cz/sso/auth-check'}
e1b7c54d	98
	99	token_data = self._download_json(
	100	self._TOKEN_URL, None,
	101	note='Downloading token', errnote='Downloading token failed',
	102	data=urlencode_postdata(token_request_data))
	103
	104	self.access_token = token_data.get('access_token')
	105	if self.access_token is None:
	106	raise ExtractorError('Getting token failed', expected=True)
	107
	108	def _raise_access_error(self, error_code):
	109	if error_code == 'PLAY_GEOIP_DENIED':
	110	self.raise_geo_restricted(countries=['CZ'], metadata_available=True)
	111	elif error_code is not None:
	112	self.raise_no_formats('Access to stream infos forbidden', expected=True)
	113
	114	def _real_initialize(self):
	115	if not self.access_token:
	116	self._login()
	117
	118	def _real_extract(self, url):
	119	video_id = self._match_id(url)
	120
	121	webpage = self._download_webpage(url, video_id)
	122
	123	title = self._html_search_meta(
	124	['og:title', 'twitter:title'],
	125	webpage, 'title', default=None)
	126
	127	video_id = self._search_regex((
	128	r'productId\s=\s([\'"])(?P<id>p\d+)\1',
	129	r'pproduct_id\s=\s([\'"])(?P<id>p\d+)\1'),
	130	webpage, 'real id', group='id')
	131
	132	metadata = self._download_json(
	133	f'https://api.play-backend.iprima.cz/api/v1//products/id-{video_id}/play',
	134	video_id, note='Getting manifest URLs', errnote='Failed to get manifest URLs',
	135	headers={'X-OTT-Access-Token': self.access_token},
	136	expected_status=403)
	137
	138	self._raise_access_error(metadata.get('errorCode'))
	139
	140	stream_infos = metadata.get('streamInfos')
	141	formats = []
	142	if stream_infos is None:
	143	self.raise_no_formats('Reading stream infos failed', expected=True)
	144	else:
	145	for manifest in stream_infos:
	146	manifest_type = manifest.get('type')
	147	manifest_url = manifest.get('url')
	148	ext = determine_ext(manifest_url)
	149	if manifest_type == 'HLS' or ext == 'm3u8':
	150	formats += self._extract_m3u8_formats(
	151	manifest_url, video_id, 'mp4', entry_protocol='m3u8_native',
	152	m3u8_id='hls', fatal=False)
	153	elif manifest_type == 'DASH' or ext == 'mpd':
	154	formats += self._extract_mpd_formats(
	155	manifest_url, video_id, mpd_id='dash', fatal=False)
	156	self._sort_formats(formats)
	157
	158	final_result = self._search_json_ld(webpage, video_id) or {}
	159	final_result.update({
	160	'id': video_id,
	161	'title': title,
162	'thumbnail': self._html_search_meta(
163	['thumbnail', 'og:image', 'twitter:image'],
164	webpage, 'thumbnail', default=None),
165	'formats': formats,
166	'description': self._html_search_meta(
167	['description', 'og:description', 'twitter:description'],
168	webpage, 'description', default=None)})
169
170	return final_result
171
172
173	class IPrimaCNNIE(InfoExtractor):
174	_VALID_URL = r'https?://cnn\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
175	_GEO_BYPASS = False
176
177	_TESTS = [{
178	'url': 'https://cnn.iprima.cz/porady/strunc/24072020-koronaviru-mam-plne-zuby-strasit-druhou-vlnou-je-absurdni-rika-senatorka-dernerova',
179	'info_dict': {
180	'id': 'p716177',
181	'ext': 'mp4',
182	'title': 'md5:277c6b1ed0577e51b40ddd35602ff43e',
183	},
184	'params': {
185	'skip_download': 'm3u8'
186	}
973f2532	187	}]
7881a644	188
7881a644	189	def _real_extract(self, url):
369e7e3f	190	video_id = self._match_id(url)
7881a644	191
09322ccc S	192	self._set_cookie('play.iprima.cz', 'ott_adult_confirmed', '1')
09322ccc S	193
7881a644	194	webpage = self._download_webpage(url, video_id)
7881a644	195
30fa5c60 S	196	title = self._og_search_title(
	197	webpage, default=None) or self._search_regex(
	198	r'<h1>([^<]+)', webpage, 'title')
	199
a2637a2d S	200	video_id = self._search_regex(
a2637a2d S	201	(r'<iframe[^>]+\bsrc=["\'](?:https?:)?//(?:api\.play-backend\.iprima\.cz/prehravac/embedded\|prima\.iprima\.cz/[^/]+/[^/]+)\?.*?\bid=(p\d+)',
30fa5c60 S	202	r'data-product="([^"]+)">',
30fa5c60 S	203	r'id=["\']player-(p\d+)"',
b7770046 U	204	r'playerId\s:\s["\']player-(p\d+)',
b7770046 U	205	r'\bvideos\s=\s["\'](p\d+)'),
a2637a2d	206	webpage, 'real id')
82642235	207
82f66218 S	208	playerpage = self._download_webpage(
	209	'http://play.iprima.cz/prehravac/init',
	210	video_id, note='Downloading player', query={
	211	'_infuse': 1,
	212	'_ts': round(time.time()),
	213	'productId': video_id,
	214	}, headers={'Referer': url})
7881a644	215
369e7e3f	216	formats = []
7881a644	217
369e7e3f S	218	def extract_formats(format_url, format_key=None, lang=None):
	219	ext = determine_ext(format_url)
	220	new_formats = []
	221	if format_key == 'hls' or ext == 'm3u8':
	222	new_formats = self._extract_m3u8_formats(
	223	format_url, video_id, 'mp4', entry_protocol='m3u8_native',
	224	m3u8_id='hls', fatal=False)
	225	elif format_key == 'dash' or ext == 'mpd':
	226	return
	227	new_formats = self._extract_mpd_formats(
	228	format_url, video_id, mpd_id='dash', fatal=False)
	229	if lang:
	230	for f in new_formats:
	231	if not f.get('language'):
	232	f['language'] = lang
	233	formats.extend(new_formats)
	234
	235	options = self._parse_json(
	236	self._search_regex(
0bbcc8a1	237	r'(?s)(?:TDIPlayerOptions\|playerOptions)\s=\s({.+?});\s*\]\]',
369e7e3f S	238	playerpage, 'player options', default='{}'),
	239	video_id, transform_source=js_to_json, fatal=False)
	240	if options:
	241	for key, tracks in options.get('tracks', {}).items():
	242	if not isinstance(tracks, list):
	243	continue
	244	for track in tracks:
	245	src = track.get('src')
	246	if src:
	247	extract_formats(src, key.lower(), track.get('lang'))
	248
	249	if not formats:
	250	for _, src in re.findall(r'src["\']\s:\s(["\'])(.+?)\1', playerpage):
	251	extract_formats(src)
91264ce5	252
3c6b3bf2	253	if not formats and '>GEO_IP_NOT_ALLOWED<' in playerpage:
b7da73eb	254	self.raise_geo_restricted(countries=['CZ'], metadata_available=True)
3c6b3bf2	255
91264ce5	256	self._sort_formats(formats)
7881a644	257
7881a644	258	return {
f406c787	259	'id': video_id,
30fa5c60 S	260	'title': title,
30fa5c60 S	261	'thumbnail': self._og_search_thumbnail(webpage, default=None),
7881a644	262	'formats': formats,
30fa5c60	263	'description': self._og_search_description(webpage, default=None),
91264ce5	264	}