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

# coding: utf-8
from __future__ import unicode_literals

import random
import re
import string

from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
    determine_ext,
    int_or_none,
    join_nonempty,
    js_to_json,
    orderedSet,
    qualities,
    str_or_none,
    traverse_obj,
    try_get,
    urlencode_postdata,
    ExtractorError,
)


class FunimationBaseIE(InfoExtractor):
    _NETRC_MACHINE = 'funimation'
    _REGION = None
    _TOKEN = None

    def _get_region(self):
        region_cookie = self._get_cookies('https://www.funimation.com').get('region')
        region = region_cookie.value if region_cookie else self.get_param('geo_bypass_country')
        return region or traverse_obj(
            self._download_json(
                'https://geo-service.prd.funimationsvc.com/geo/v1/region/check', None, fatal=False,
                note='Checking geo-location', errnote='Unable to fetch geo-location information'),
            'region') or 'US'

    def _login(self):
        username, password = self._get_login_info()
        if username is None:
            return
        try:
            data = self._download_json(
                'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
                None, 'Logging in', data=urlencode_postdata({
                    'username': username,
                    'password': password,
                }))
            return data['token']
        except ExtractorError as e:
            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
                error = self._parse_json(e.cause.read().decode(), None)['error']
                raise ExtractorError(error, expected=True)
            raise


class FunimationPageIE(FunimationBaseIE):
    IE_NAME = 'funimation:page'
    _VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?:(?P<lang>[^/]+)/)?(?:shows|v)/(?P<show>[^/]+)/(?P<episode>[^/?#&]+)'

    _TESTS = [{
        'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
        'info_dict': {
            'id': '210050',
            'ext': 'mp4',
            'title': 'Broadcast Dub Preview',
            # Other metadata is tested in FunimationIE
        },
        'params': {
            'skip_download': 'm3u8',
        },
        'add_ie': ['Funimation'],
    }, {
        # Not available in US
        'url': 'https://www.funimation.com/shows/hacksign/role-play/',
        'only_matching': True,
    }, {
        # with lang code
        'url': 'https://www.funimation.com/en/shows/hacksign/role-play/',
        'only_matching': True,
    }, {
        'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
        'only_matching': True,
    }, {
        'url': 'https://www.funimation.com/v/a-certain-scientific-railgun/super-powered-level-5',
        'only_matching': True,
    }]

    def _real_initialize(self):
        if not self._REGION:
            FunimationBaseIE._REGION = self._get_region()
        if not self._TOKEN:
            FunimationBaseIE._TOKEN = self._login()

    def _real_extract(self, url):
        locale, show, episode = self._match_valid_url(url).group('lang', 'show', 'episode')

        video_id = traverse_obj(self._download_json(
            f'https://title-api.prd.funimationsvc.com/v1/shows/{show}/episodes/{episode}',
            f'{show}_{episode}', query={
                'deviceType': 'web',
                'region': self._REGION,
                'locale': locale or 'en'
            }), ('videoList', ..., 'id'), get_all=False)

        return self.url_result(f'https://www.funimation.com/player/{video_id}', FunimationIE.ie_key(), video_id)


class FunimationIE(FunimationBaseIE):
    _VALID_URL = r'https?://(?:www\.)?funimation\.com/player/(?P<id>\d+)'

    _TESTS = [{
        'url': 'https://www.funimation.com/player/210051',
        'info_dict': {
            'id': '210050',
            'display_id': 'broadcast-dub-preview',
            'ext': 'mp4',
            'title': 'Broadcast Dub Preview',
            'thumbnail': r're:https?://.*\.(?:jpg|png)',
            'episode': 'Broadcast Dub Preview',
            'episode_id': '210050',
            'season': 'Extras',
            'season_id': '166038',
            'season_number': 99,
            'series': 'Attack on Titan: Junior High',
            'description': '',
            'duration': 155,
        },
        'params': {
            'skip_download': 'm3u8',
        },
    }, {
        'note': 'player_id should be extracted with the relevent compat-opt',
        'url': 'https://www.funimation.com/player/210051',
        'info_dict': {
            'id': '210051',
            'display_id': 'broadcast-dub-preview',
            'ext': 'mp4',
            'title': 'Broadcast Dub Preview',
            'thumbnail': r're:https?://.*\.(?:jpg|png)',
            'episode': 'Broadcast Dub Preview',
            'episode_id': '210050',
            'season': 'Extras',
            'season_id': '166038',
            'season_number': 99,
            'series': 'Attack on Titan: Junior High',
            'description': '',
            'duration': 155,
        },
        'params': {
            'skip_download': 'm3u8',
            'compat_opts': ['seperate-video-versions'],
        },
    }]

    def _real_initialize(self):
        if not self._TOKEN:
            FunimationBaseIE._TOKEN = self._login()

    @staticmethod
    def _get_experiences(episode):
        for lang, lang_data in episode.get('languages', {}).items():
            for video_data in lang_data.values():
                for version, f in video_data.items():
                    yield lang, version.title(), f

    def _get_episode(self, webpage, experience_id=None, episode_id=None, fatal=True):
        ''' Extract the episode, season and show objects given either episode/experience id '''
        show = self._parse_json(
            self._search_regex(
                r'show\s*=\s*({.+?})\s*;', webpage, 'show data', fatal=fatal),
            experience_id, transform_source=js_to_json, fatal=fatal) or []
        for season in show.get('seasons', []):
            for episode in season.get('episodes', []):
                if episode_id is not None:
                    if str(episode.get('episodePk')) == episode_id:
                        return episode, season, show
                    continue
                for _, _, f in self._get_experiences(episode):
                    if f.get('experienceId') == experience_id:
                        return episode, season, show
        if fatal:
            raise ExtractorError('Unable to find episode information')
        else:
            self.report_warning('Unable to find episode information')
        return {}, {}, {}

    def _real_extract(self, url):
        initial_experience_id = self._match_id(url)
        webpage = self._download_webpage(
            url, initial_experience_id, note=f'Downloading player webpage for {initial_experience_id}')
        episode, season, show = self._get_episode(webpage, experience_id=int(initial_experience_id))
        episode_id = str(episode['episodePk'])
        display_id = episode.get('slug') or episode_id

        formats, subtitles, thumbnails, duration = [], {}, [], 0
        requested_languages, requested_versions = self._configuration_arg('language'), self._configuration_arg('version')
        language_preference = qualities((requested_languages or [''])[::-1])
        source_preference = qualities((requested_versions or ['uncut', 'simulcast'])[::-1])
        only_initial_experience = 'seperate-video-versions' in self.get_param('compat_opts', [])

        for lang, version, fmt in self._get_experiences(episode):
            experience_id = str(fmt['experienceId'])
            if (only_initial_experience and experience_id != initial_experience_id
                    or requested_languages and lang.lower() not in requested_languages
                    or requested_versions and version.lower() not in requested_versions):
                continue
            thumbnails.append({'url': fmt.get('poster')})
            duration = max(duration, fmt.get('duration', 0))
            format_name = '%s %s (%s)' % (version, lang, experience_id)
            self.extract_subtitles(
                subtitles, experience_id, display_id=display_id, format_name=format_name,
                episode=episode if experience_id == initial_experience_id else episode_id)

            headers = {}
            if self._TOKEN:
                headers['Authorization'] = 'Token %s' % self._TOKEN
            page = self._download_json(
                'https://www.funimation.com/api/showexperience/%s/' % experience_id,
                display_id, headers=headers, expected_status=403, query={
                    'pinst_id': ''.join([random.choice(string.digits + string.ascii_letters) for _ in range(8)]),
                }, note=f'Downloading {format_name} JSON')
            sources = page.get('items') or []
            if not sources:
                error = try_get(page, lambda x: x['errors'][0], dict)
                if error:
                    self.report_warning('%s said: Error %s - %s' % (
                        self.IE_NAME, error.get('code'), error.get('detail') or error.get('title')))
                else:
                    self.report_warning('No sources found for format')

            current_formats = []
            for source in sources:
                source_url = source.get('src')
                source_type = source.get('videoType') or determine_ext(source_url)
                if source_type == 'm3u8':
                    current_formats.extend(self._extract_m3u8_formats(
                        source_url, display_id, 'mp4', m3u8_id='%s-%s' % (experience_id, 'hls'), fatal=False,
                        note=f'Downloading {format_name} m3u8 information'))
                else:
                    current_formats.append({
                        'format_id': '%s-%s' % (experience_id, source_type),
                        'url': source_url,
                    })
                for f in current_formats:
                    # TODO: Convert language to code
                    f.update({
                        'language': lang,
                        'format_note': version,
                        'source_preference': source_preference(version.lower()),
                        'language_preference': language_preference(lang.lower()),
                    })
                formats.extend(current_formats)
        self._remove_duplicate_formats(formats)
        self._sort_formats(formats, ('lang', 'source'))

        return {
            'id': initial_experience_id if only_initial_experience else episode_id,
            'display_id': display_id,
            'duration': duration,
            'title': episode['episodeTitle'],
            'description': episode.get('episodeSummary'),
            'episode': episode.get('episodeTitle'),
            'episode_number': int_or_none(episode.get('episodeId')),
            'episode_id': episode_id,
            'season': season.get('seasonTitle'),
            'season_number': int_or_none(season.get('seasonId')),
            'season_id': str_or_none(season.get('seasonPk')),
            'series': show.get('showTitle'),
            'formats': formats,
            'thumbnails': thumbnails,
            'subtitles': subtitles,
        }

    def _get_subtitles(self, subtitles, experience_id, episode, display_id, format_name):
        if isinstance(episode, str):
            webpage = self._download_webpage(
                f'https://www.funimation.com/player/{experience_id}', display_id,
                fatal=False, note=f'Downloading player webpage for {format_name}')
            episode, _, _ = self._get_episode(webpage, episode_id=episode, fatal=False)

        for _, version, f in self._get_experiences(episode):
            for source in f.get('sources'):
                for text_track in source.get('textTracks'):
                    if not text_track.get('src'):
                        continue
                    sub_type = text_track.get('type').upper()
                    sub_type = sub_type if sub_type != 'FULL' else None
                    current_sub = {
                        'url': text_track['src'],
                        'name': join_nonempty(version, text_track.get('label'), sub_type, delim=' ')
                    }
                    lang = join_nonempty(text_track.get('language', 'und'),
                                         version if version != 'Simulcast' else None,
                                         sub_type, delim='_')
                    if current_sub not in subtitles.get(lang, []):
                        subtitles.setdefault(lang, []).append(current_sub)
        return subtitles


class FunimationShowIE(FunimationBaseIE):
    IE_NAME = 'funimation:show'
    _VALID_URL = r'(?P<url>https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?P<locale>[^/]+)?/?shows/(?P<id>[^/?#&]+))/?(?:[?#]|$)'

    _TESTS = [{
        'url': 'https://www.funimation.com/en/shows/sk8-the-infinity',
        'info_dict': {
            'id': 1315000,
            'title': 'SK8 the Infinity'
        },
        'playlist_count': 13,
        'params': {
            'skip_download': True,
        },
    }, {
        # without lang code
        'url': 'https://www.funimation.com/shows/ouran-high-school-host-club/',
        'info_dict': {
            'id': 39643,
            'title': 'Ouran High School Host Club'
        },
        'playlist_count': 26,
        'params': {
            'skip_download': True,
        },
    }]

    def _real_initialize(self):
        if not self._REGION:
            FunimationBaseIE._REGION = self._get_region()

    def _real_extract(self, url):
        base_url, locale, display_id = self._match_valid_url(url).groups()

        show_info = self._download_json(
            'https://title-api.prd.funimationsvc.com/v2/shows/%s?region=%s&deviceType=web&locale=%s'
            % (display_id, self._REGION, locale or 'en'), display_id)
        items_info = self._download_json(
            'https://prod-api-funimationnow.dadcdigital.com/api/funimation/episodes/?limit=99999&title_id=%s'
            % show_info.get('id'), display_id)

        vod_items = traverse_obj(items_info, ('items', ..., re.compile('(?i)mostRecent[AS]vod').match, 'item'))

        return {
            '_type': 'playlist',
            'id': show_info['id'],
            'title': show_info['name'],
            'entries': orderedSet(
                self.url_result(
                    '%s/%s' % (base_url, vod_item.get('episodeSlug')), FunimationPageIE.ie_key(),
                    vod_item.get('episodeId'), vod_item.get('episodeName'))
                for vod_item in sorted(vod_items, key=lambda x: x.get('episodeOrder', -1))),
        }
Commit	Line	Data
ab4bdc91 MS	1	# coding: utf-8
ab4bdc91 MS	2	from __future__ import unicode_literals
f542a3d2	3
929ba399	4	import random
8cd69fc4	5	import re
929ba399 RA	6	import string
929ba399 RA	7
ab4bdc91	8	from .common import InfoExtractor
804181dd	9	from ..compat import compat_HTTPError
ab4bdc91	10	from ..utils import (
f542a3d2	11	determine_ext,
f377f44d	12	int_or_none,
34921b43	13	join_nonempty,
91399b2f	14	js_to_json,
8cd69fc4 J	15	orderedSet,
8cd69fc4 J	16	qualities,
3acf6d38	17	str_or_none,
8cd69fc4	18	traverse_obj,
3acf6d38	19	try_get,
29f63c96	20	urlencode_postdata,
ab4bdc91	21	ExtractorError,
ab4bdc91	22	)
ab4bdc91	23
b4c299ba	24
8cd69fc4 J	25	class FunimationBaseIE(InfoExtractor):
	26	_NETRC_MACHINE = 'funimation'
	27	_REGION = None
	28	_TOKEN = None
	29
	30	def _get_region(self):
	31	region_cookie = self._get_cookies('https://www.funimation.com').get('region')
	32	region = region_cookie.value if region_cookie else self.get_param('geo_bypass_country')
	33	return region or traverse_obj(
	34	self._download_json(
	35	'https://geo-service.prd.funimationsvc.com/geo/v1/region/check', None, fatal=False,
	36	note='Checking geo-location', errnote='Unable to fetch geo-location information'),
	37	'region') or 'US'
	38
	39	def _login(self):
	40	username, password = self._get_login_info()
	41	if username is None:
	42	return
	43	try:
	44	data = self._download_json(
	45	'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
	46	None, 'Logging in', data=urlencode_postdata({
	47	'username': username,
	48	'password': password,
	49	}))
	50	return data['token']
	51	except ExtractorError as e:
	52	if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
	53	error = self._parse_json(e.cause.read().decode(), None)['error']
	54	raise ExtractorError(error, expected=True)
	55	raise
	56
	57
	58	class FunimationPageIE(FunimationBaseIE):
3acf6d38	59	IE_NAME = 'funimation:page'
8cd69fc4	60	_VALID_URL = r'https?://(?:www\.)?funimation(?:\.com\|now\.uk)/(?:(?P<lang>[^/]+)/)?(?:shows\|v)/(?P<show>[^/]+)/(?P<episode>[^/?#&]+)'
3acf6d38	61
	62	_TESTS = [{
	63	'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
	64	'info_dict': {
	65	'id': '210050',
	66	'ext': 'mp4',
	67	'title': 'Broadcast Dub Preview',
	68	# Other metadata is tested in FunimationIE
	69	},
	70	'params': {
	71	'skip_download': 'm3u8',
	72	},
	73	'add_ie': ['Funimation'],
	74	}, {
	75	# Not available in US
	76	'url': 'https://www.funimation.com/shows/hacksign/role-play/',
	77	'only_matching': True,
	78	}, {
	79	# with lang code
	80	'url': 'https://www.funimation.com/en/shows/hacksign/role-play/',
	81	'only_matching': True,
	82	}, {
	83	'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
	84	'only_matching': True,
8cd69fc4 J	85	}, {
	86	'url': 'https://www.funimation.com/v/a-certain-scientific-railgun/super-powered-level-5',
	87	'only_matching': True,
3acf6d38	88	}]
3acf6d38	89
8cd69fc4 J	90	def _real_initialize(self):
	91	if not self._REGION:
	92	FunimationBaseIE._REGION = self._get_region()
	93	if not self._TOKEN:
	94	FunimationBaseIE._TOKEN = self._login()
	95
3acf6d38	96	def _real_extract(self, url):
8cd69fc4 J	97	locale, show, episode = self._match_valid_url(url).group('lang', 'show', 'episode')
	98
	99	video_id = traverse_obj(self._download_json(
	100	f'https://title-api.prd.funimationsvc.com/v1/shows/{show}/episodes/{episode}',
	101	f'{show}_{episode}', query={
	102	'deviceType': 'web',
	103	'region': self._REGION,
	104	'locale': locale or 'en'
	105	}), ('videoList', ..., 'id'), get_all=False)
	106
3acf6d38	107	return self.url_result(f'https://www.funimation.com/player/{video_id}', FunimationIE.ie_key(), video_id)
	108
	109
8cd69fc4	110	class FunimationIE(FunimationBaseIE):
3acf6d38	111	_VALID_URL = r'https?://(?:www\.)?funimation\.com/player/(?P<id>\d+)'
ab4bdc91	112
b59623ef	113	_TESTS = [{
3acf6d38	114	'url': 'https://www.funimation.com/player/210051',
ab4bdc91	115	'info_dict': {
3acf6d38	116	'id': '210050',
3acf6d38	117	'display_id': 'broadcast-dub-preview',
b59623ef	118	'ext': 'mp4',
3acf6d38	119	'title': 'Broadcast Dub Preview',
	120	'thumbnail': r're:https?://.*\.(?:jpg\|png)',
	121	'episode': 'Broadcast Dub Preview',
	122	'episode_id': '210050',
	123	'season': 'Extras',
	124	'season_id': '166038',
	125	'season_number': 99,
	126	'series': 'Attack on Titan: Junior High',
	127	'description': '',
8cd69fc4	128	'duration': 155,
b59623ef	129	},
91399b2f	130	'params': {
3acf6d38	131	'skip_download': 'm3u8',
91399b2f	132	},
b091529a	133	}, {
3acf6d38	134	'note': 'player_id should be extracted with the relevent compat-opt',
3acf6d38	135	'url': 'https://www.funimation.com/player/210051',
0b1bb1ac	136	'info_dict': {
804181dd	137	'id': '210051',
0b1bb1ac S	138	'display_id': 'broadcast-dub-preview',
0b1bb1ac S	139	'ext': 'mp4',
3acf6d38	140	'title': 'Broadcast Dub Preview',
ec85ded8	141	'thumbnail': r're:https?://.*\.(?:jpg\|png)',
3acf6d38	142	'episode': 'Broadcast Dub Preview',
	143	'episode_id': '210050',
	144	'season': 'Extras',
	145	'season_id': '166038',
	146	'season_number': 99,
	147	'series': 'Attack on Titan: Junior High',
	148	'description': '',
8cd69fc4	149	'duration': 155,
0b1bb1ac	150	},
804181dd	151	'params': {
3acf6d38	152	'skip_download': 'm3u8',
3acf6d38	153	'compat_opts': ['seperate-video-versions'],
804181dd	154	},
b59623ef	155	}]
f542a3d2	156
ab4bdc91	157	def _real_initialize(self):
8cd69fc4 J	158	if not self._TOKEN:
8cd69fc4 J	159	FunimationBaseIE._TOKEN = self._login()
ab4bdc91	160
3acf6d38	161	@staticmethod
	162	def _get_experiences(episode):
	163	for lang, lang_data in episode.get('languages', {}).items():
	164	for video_data in lang_data.values():
	165	for version, f in video_data.items():
	166	yield lang, version.title(), f
f542a3d2	167
3acf6d38	168	def _get_episode(self, webpage, experience_id=None, episode_id=None, fatal=True):
	169	''' Extract the episode, season and show objects given either episode/experience id '''
	170	show = self._parse_json(
	171	self._search_regex(
	172	r'show\s=\s({.+?})\s*;', webpage, 'show data', fatal=fatal),
	173	experience_id, transform_source=js_to_json, fatal=fatal) or []
	174	for season in show.get('seasons', []):
	175	for episode in season.get('episodes', []):
	176	if episode_id is not None:
	177	if str(episode.get('episodePk')) == episode_id:
	178	return episode, season, show
	179	continue
	180	for _, _, f in self._get_experiences(episode):
	181	if f.get('experienceId') == experience_id:
	182	return episode, season, show
	183	if fatal:
	184	raise ExtractorError('Unable to find episode information')
	185	else:
	186	self.report_warning('Unable to find episode information')
	187	return {}, {}, {}
91399b2f	188
3acf6d38	189	def _real_extract(self, url):
	190	initial_experience_id = self._match_id(url)
	191	webpage = self._download_webpage(
	192	url, initial_experience_id, note=f'Downloading player webpage for {initial_experience_id}')
	193	episode, season, show = self._get_episode(webpage, experience_id=int(initial_experience_id))
	194	episode_id = str(episode['episodePk'])
	195	display_id = episode.get('slug') or episode_id
91399b2f	196
3acf6d38	197	formats, subtitles, thumbnails, duration = [], {}, [], 0
3acf6d38	198	requested_languages, requested_versions = self._configuration_arg('language'), self._configuration_arg('version')
e919569e	199	language_preference = qualities((requested_languages or [''])[::-1])
e919569e	200	source_preference = qualities((requested_versions or ['uncut', 'simulcast'])[::-1])
3acf6d38	201	only_initial_experience = 'seperate-video-versions' in self.get_param('compat_opts', [])
	202
	203	for lang, version, fmt in self._get_experiences(episode):
	204	experience_id = str(fmt['experienceId'])
	205	if (only_initial_experience and experience_id != initial_experience_id
4bb6b02f	206	or requested_languages and lang.lower() not in requested_languages
4bb6b02f	207	or requested_versions and version.lower() not in requested_versions):
3acf6d38	208	continue
	209	thumbnails.append({'url': fmt.get('poster')})
	210	duration = max(duration, fmt.get('duration', 0))
	211	format_name = '%s %s (%s)' % (version, lang, experience_id)
	212	self.extract_subtitles(
	213	subtitles, experience_id, display_id=display_id, format_name=format_name,
	214	episode=episode if experience_id == initial_experience_id else episode_id)
f542a3d2	215
8fa17117 RA	216	headers = {}
	217	if self._TOKEN:
	218	headers['Authorization'] = 'Token %s' % self._TOKEN
3acf6d38	219	page = self._download_json(
	220	'https://www.funimation.com/api/showexperience/%s/' % experience_id,
	221	display_id, headers=headers, expected_status=403, query={
929ba399	222	'pinst_id': ''.join([random.choice(string.digits + string.ascii_letters) for _ in range(8)]),
3acf6d38	223	}, note=f'Downloading {format_name} JSON')
	224	sources = page.get('items') or []
	225	if not sources:
	226	error = try_get(page, lambda x: x['errors'][0], dict)
	227	if error:
	228	self.report_warning('%s said: Error %s - %s' % (
	229	self.IE_NAME, error.get('code'), error.get('detail') or error.get('title')))
	230	else:
	231	self.report_warning('No sources found for format')
f542a3d2	232
3acf6d38	233	current_formats = []
	234	for source in sources:
	235	source_url = source.get('src')
	236	source_type = source.get('videoType') or determine_ext(source_url)
	237	if source_type == 'm3u8':
	238	current_formats.extend(self._extract_m3u8_formats(
	239	source_url, display_id, 'mp4', m3u8_id='%s-%s' % (experience_id, 'hls'), fatal=False,
	240	note=f'Downloading {format_name} m3u8 information'))
	241	else:
	242	current_formats.append({
	243	'format_id': '%s-%s' % (experience_id, source_type),
	244	'url': source_url,
	245	})
	246	for f in current_formats:
	247	# TODO: Convert language to code
e919569e	248	f.update({
	249	'language': lang,
	250	'format_note': version,
	251	'source_preference': source_preference(version.lower()),
	252	'language_preference': language_preference(lang.lower()),
	253	})
3acf6d38	254	formats.extend(current_formats)
3acf6d38	255	self._remove_duplicate_formats(formats)
e919569e	256	self._sort_formats(formats, ('lang', 'source'))
b59623ef	257
ab4bdc91	258	return {
3acf6d38	259	'id': initial_experience_id if only_initial_experience else episode_id,
f542a3d2	260	'display_id': display_id,
3acf6d38	261	'duration': duration,
	262	'title': episode['episodeTitle'],
	263	'description': episode.get('episodeSummary'),
	264	'episode': episode.get('episodeTitle'),
	265	'episode_number': int_or_none(episode.get('episodeId')),
	266	'episode_id': episode_id,
	267	'season': season.get('seasonTitle'),
	268	'season_number': int_or_none(season.get('seasonId')),
	269	'season_id': str_or_none(season.get('seasonPk')),
	270	'series': show.get('showTitle'),
ab4bdc91	271	'formats': formats,
3acf6d38	272	'thumbnails': thumbnails,
3acf6d38	273	'subtitles': subtitles,
ab4bdc91	274	}
29f63c96	275
3acf6d38	276	def _get_subtitles(self, subtitles, experience_id, episode, display_id, format_name):
	277	if isinstance(episode, str):
	278	webpage = self._download_webpage(
	279	f'https://www.funimation.com/player/{experience_id}', display_id,
	280	fatal=False, note=f'Downloading player webpage for {format_name}')
	281	episode, _, _ = self._get_episode(webpage, episode_id=episode, fatal=False)
	282
	283	for _, version, f in self._get_experiences(episode):
	284	for source in f.get('sources'):
	285	for text_track in source.get('textTracks'):
	286	if not text_track.get('src'):
	287	continue
	288	sub_type = text_track.get('type').upper()
	289	sub_type = sub_type if sub_type != 'FULL' else None
	290	current_sub = {
	291	'url': text_track['src'],
34921b43	292	'name': join_nonempty(version, text_track.get('label'), sub_type, delim=' ')
3acf6d38	293	}
34921b43	294	lang = join_nonempty(text_track.get('language', 'und'),
	295	version if version != 'Simulcast' else None,
	296	sub_type, delim='_')
3acf6d38	297	if current_sub not in subtitles.get(lang, []):
3acf6d38	298	subtitles.setdefault(lang, []).append(current_sub)
29f63c96	299	return subtitles
125728b0 M	300
125728b0 M	301
8cd69fc4	302	class FunimationShowIE(FunimationBaseIE):
125728b0 M	303	IE_NAME = 'funimation:show'
	304	_VALID_URL = r'(?P<url>https?://(?:www\.)?funimation(?:\.com\|now\.uk)/(?P<locale>[^/]+)?/?shows/(?P<id>[^/?#&]+))/?(?:[?#]\|$)'
	305
	306	_TESTS = [{
	307	'url': 'https://www.funimation.com/en/shows/sk8-the-infinity',
	308	'info_dict': {
	309	'id': 1315000,
	310	'title': 'SK8 the Infinity'
	311	},
	312	'playlist_count': 13,
	313	'params': {
	314	'skip_download': True,
	315	},
	316	}, {
	317	# without lang code
	318	'url': 'https://www.funimation.com/shows/ouran-high-school-host-club/',
	319	'info_dict': {
	320	'id': 39643,
	321	'title': 'Ouran High School Host Club'
	322	},
	323	'playlist_count': 26,
	324	'params': {
	325	'skip_download': True,
	326	},
	327	}]
	328
ad226b1d	329	def _real_initialize(self):
8cd69fc4 J	330	if not self._REGION:
8cd69fc4 J	331	FunimationBaseIE._REGION = self._get_region()
ad226b1d	332
125728b0	333	def _real_extract(self, url):
5ad28e7f	334	base_url, locale, display_id = self._match_valid_url(url).groups()
125728b0 M	335
125728b0 M	336	show_info = self._download_json(
ad226b1d	337	'https://title-api.prd.funimationsvc.com/v2/shows/%s?region=%s&deviceType=web&locale=%s'
8cd69fc4 J	338	% (display_id, self._REGION, locale or 'en'), display_id)
8cd69fc4 J	339	items_info = self._download_json(
125728b0	340	'https://prod-api-funimationnow.dadcdigital.com/api/funimation/episodes/?limit=99999&title_id=%s'
8cd69fc4 J	341	% show_info.get('id'), display_id)
	342
	343	vod_items = traverse_obj(items_info, ('items', ..., re.compile('(?i)mostRecent[AS]vod').match, 'item'))
125728b0 M	344
	345	return {
	346	'_type': 'playlist',
	347	'id': show_info['id'],
	348	'title': show_info['name'],
8cd69fc4	349	'entries': orderedSet(
125728b0	350	self.url_result(
3acf6d38	351	'%s/%s' % (base_url, vod_item.get('episodeSlug')), FunimationPageIE.ie_key(),
125728b0	352	vod_item.get('episodeId'), vod_item.get('episodeName'))
8cd69fc4	353	for vod_item in sorted(vod_items, key=lambda x: x.get('episodeOrder', -1))),
125728b0	354	}