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

# coding: utf-8
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
    ExtractorError,
    int_or_none,
    join_nonempty,
    LazyList,
    parse_qs,
    str_or_none,
    traverse_obj,
    url_or_none,
    urlencode_postdata,
    urljoin,
    update_url_query,
)


class RoosterTeethBaseIE(InfoExtractor):
    _NETRC_MACHINE = 'roosterteeth'
    _API_BASE = 'https://svod-be.roosterteeth.com'
    _API_BASE_URL = f'{_API_BASE}/api/v1'

    def _login(self):
        username, password = self._get_login_info()
        if username is None:
            return
        if self._get_cookies(self._API_BASE_URL).get('rt_access_token'):
            return

        try:
            self._download_json(
                'https://auth.roosterteeth.com/oauth/token',
                None, 'Logging in', data=urlencode_postdata({
                    'client_id': '4338d2b4bdc8db1239360f28e72f0d9ddb1fd01e7a38fbb07b4b1f4ba4564cc5',
                    'grant_type': 'password',
                    'username': username,
                    'password': password,
                }))
        except ExtractorError as e:
            msg = 'Unable to login'
            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
                resp = self._parse_json(e.cause.read().decode(), None, fatal=False)
                if resp:
                    error = resp.get('extra_info') or resp.get('error_description') or resp.get('error')
                    if error:
                        msg += ': ' + error
            self.report_warning(msg)

    def _real_initialize(self):
        self._login()

    def _extract_video_info(self, data):
        thumbnails = []
        for image in traverse_obj(data, ('included', 'images')):
            if image.get('type') not in ('episode_image', 'bonus_feature_image'):
                continue
            thumbnails.extend([{
                'id': name,
                'url': url,
            } for name, url in (image.get('attributes') or {}).items() if url_or_none(url)])

        attributes = data.get('attributes') or {}
        title = traverse_obj(attributes, 'title', 'display_title')
        sub_only = attributes.get('is_sponsors_only')

        return {
            'id': str(data.get('id')),
            'display_id': attributes.get('slug'),
            'title': title,
            'description': traverse_obj(attributes, 'description', 'caption'),
            'series': attributes.get('show_title'),
            'season_number': int_or_none(attributes.get('season_number')),
            'season_id': attributes.get('season_id'),
            'episode': title,
            'episode_number': int_or_none(attributes.get('number')),
            'episode_id': str_or_none(data.get('uuid')),
            'channel_id': attributes.get('channel_id'),
            'duration': int_or_none(attributes.get('length')),
            'thumbnails': thumbnails,
            'availability': self._availability(
                needs_premium=sub_only, needs_subscription=sub_only, needs_auth=sub_only,
                is_private=False, is_unlisted=False),
            'tags': attributes.get('genres')
        }


class RoosterTeethIE(RoosterTeethBaseIE):
    _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/(?:episode|watch)/(?P<id>[^/?#&]+)'
    _TESTS = [{
        'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
        'info_dict': {
            'id': '9156',
            'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement',
            'ext': 'mp4',
            'title': 'Million Dollars, But... The Game Announcement',
            'description': 'md5:168a54b40e228e79f4ddb141e89fe4f5',
            'thumbnail': r're:^https?://.*\.png$',
            'series': 'Million Dollars, But...',
            'episode': 'Million Dollars, But... The Game Announcement',
        },
        'params': {'skip_download': True},
    }, {
        'url': 'https://roosterteeth.com/watch/rwby-bonus-25',
        'info_dict': {
            'id': '40432',
            'display_id': 'rwby-bonus-25',
            'title': 'Grimm',
            'description': 'md5:f30ff570741213418a8d2c19868b93ab',
            'episode': 'Grimm',
            'channel_id': '92f780eb-ebfe-4bf5-a3b5-c6ad5460a5f1',
            'thumbnail': r're:^https?://.*\.(png|jpe?g)$',
            'ext': 'mp4',
        },
        'params': {'skip_download': True},
    }, {
        'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
        'only_matching': True,
    }, {
        'url': 'http://funhaus.roosterteeth.com/episode/funhaus-shorts-2016-austin-sucks-funhaus-shorts',
        'only_matching': True,
    }, {
        'url': 'http://screwattack.roosterteeth.com/episode/death-battle-season-3-mewtwo-vs-shadow',
        'only_matching': True,
    }, {
        'url': 'http://theknow.roosterteeth.com/episode/the-know-game-news-season-1-boring-steam-sales-are-better',
        'only_matching': True,
    }, {
        # only available for FIRST members
        'url': 'http://roosterteeth.com/episode/rt-docs-the-world-s-greatest-head-massage-the-world-s-greatest-head-massage-an-asmr-journey-part-one',
        'only_matching': True,
    }, {
        'url': 'https://roosterteeth.com/watch/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        display_id = self._match_id(url)
        api_episode_url = f'{self._API_BASE_URL}/watch/{display_id}'

        try:
            video_data = self._download_json(
                api_episode_url + '/videos', display_id,
                'Downloading video JSON metadata')['data'][0]
            m3u8_url = video_data['attributes']['url']
            # XXX: additional URL at video_data['links']['download']
        except ExtractorError as e:
            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
                if self._parse_json(e.cause.read().decode(), display_id).get('access') is False:
                    self.raise_login_required(
                        '%s is only available for FIRST members' % display_id)
            raise

        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
            m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls')
        self._sort_formats(formats)

        episode = self._download_json(
            api_episode_url, display_id,
            'Downloading episode JSON metadata')['data'][0]

        return {
            'display_id': display_id,
            'formats': formats,
            'subtitles': subtitles,
            **self._extract_video_info(episode)
        }


class RoosterTeethSeriesIE(RoosterTeethBaseIE):
    _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/series/(?P<id>[^/?#&]+)'
    _TESTS = [{
        'url': 'https://roosterteeth.com/series/rwby?season=7',
        'playlist_count': 13,
        'info_dict': {
            'id': 'rwby-7',
            'title': 'RWBY - Season 7',
        }
    }, {
        'url': 'https://roosterteeth.com/series/role-initiative',
        'playlist_mincount': 16,
        'info_dict': {
            'id': 'role-initiative',
            'title': 'Role Initiative',
        }
    }, {
        'url': 'https://roosterteeth.com/series/let-s-play-minecraft?season=9',
        'playlist_mincount': 50,
        'info_dict': {
            'id': 'let-s-play-minecraft-9',
            'title': 'Let\'s Play Minecraft - Season 9',
        }
    }]

    def _entries(self, series_id, season_number):
        display_id = join_nonempty(series_id, season_number)
        # TODO: extract bonus material
        for data in self._download_json(
                f'{self._API_BASE_URL}/shows/{series_id}/seasons?order=asc&order_by', display_id)['data']:
            idx = traverse_obj(data, ('attributes', 'number'))
            if season_number and idx != season_number:
                continue
            season_url = update_url_query(urljoin(self._API_BASE, data['links']['episodes']), {'per_page': 1000})
            season = self._download_json(season_url, display_id, f'Downloading season {idx} JSON metadata')['data']
            for episode in season:
                yield self.url_result(
                    f'https://www.roosterteeth.com{episode["canonical_links"]["self"]}',
                    RoosterTeethIE.ie_key(),
                    **self._extract_video_info(episode))

    def _real_extract(self, url):
        series_id = self._match_id(url)
        season_number = traverse_obj(parse_qs(url), ('season', 0), expected_type=int_or_none)

        entries = LazyList(self._entries(series_id, season_number))
        return self.playlist_result(
            entries,
            join_nonempty(series_id, season_number),
            join_nonempty(entries[0].get('series'), season_number, delim=' - Season '))
Commit	Line	Data
3121b256	1	# coding: utf-8
3121b256	2	from .common import InfoExtractor
244644c0	3	from ..compat import compat_HTTPError
3121b256 NP	4	from ..utils import (
3121b256 NP	5	ExtractorError,
865b0872	6	int_or_none,
244644c0	7	join_nonempty,
	8	LazyList,
	9	parse_qs,
c72dc20d	10	str_or_none,
244644c0	11	traverse_obj,
244644c0	12	url_or_none,
3121b256	13	urlencode_postdata,
244644c0	14	urljoin,
df03de2c	15	update_url_query,
3121b256 NP	16	)
	17
	18
244644c0	19	class RoosterTeethBaseIE(InfoExtractor):
3121b256	20	_NETRC_MACHINE = 'roosterteeth'
244644c0	21	_API_BASE = 'https://svod-be.roosterteeth.com'
	22	_API_BASE_URL = f'{_API_BASE}/api/v1'
	23
	24	def _login(self):
	25	username, password = self._get_login_info()
	26	if username is None:
	27	return
	28	if self._get_cookies(self._API_BASE_URL).get('rt_access_token'):
	29	return
	30
	31	try:
	32	self._download_json(
	33	'https://auth.roosterteeth.com/oauth/token',
	34	None, 'Logging in', data=urlencode_postdata({
	35	'client_id': '4338d2b4bdc8db1239360f28e72f0d9ddb1fd01e7a38fbb07b4b1f4ba4564cc5',
	36	'grant_type': 'password',
	37	'username': username,
	38	'password': password,
	39	}))
	40	except ExtractorError as e:
	41	msg = 'Unable to login'
	42	if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
	43	resp = self._parse_json(e.cause.read().decode(), None, fatal=False)
	44	if resp:
	45	error = resp.get('extra_info') or resp.get('error_description') or resp.get('error')
	46	if error:
	47	msg += ': ' + error
	48	self.report_warning(msg)
	49
	50	def _real_initialize(self):
	51	self._login()
	52
	53	def _extract_video_info(self, data):
	54	thumbnails = []
	55	for image in traverse_obj(data, ('included', 'images')):
	56	if image.get('type') not in ('episode_image', 'bonus_feature_image'):
	57	continue
	58	thumbnails.extend([{
	59	'id': name,
	60	'url': url,
	61	} for name, url in (image.get('attributes') or {}).items() if url_or_none(url)])
	62
	63	attributes = data.get('attributes') or {}
	64	title = traverse_obj(attributes, 'title', 'display_title')
	65	sub_only = attributes.get('is_sponsors_only')
	66
	67	return {
	68	'id': str(data.get('id')),
	69	'display_id': attributes.get('slug'),
	70	'title': title,
	71	'description': traverse_obj(attributes, 'description', 'caption'),
	72	'series': attributes.get('show_title'),
	73	'season_number': int_or_none(attributes.get('season_number')),
	74	'season_id': attributes.get('season_id'),
	75	'episode': title,
	76	'episode_number': int_or_none(attributes.get('number')),
	77	'episode_id': str_or_none(data.get('uuid')),
	78	'channel_id': attributes.get('channel_id'),
	79	'duration': int_or_none(attributes.get('length')),
	80	'thumbnails': thumbnails,
	81	'availability': self._availability(
	82	needs_premium=sub_only, needs_subscription=sub_only, needs_auth=sub_only,
	83	is_private=False, is_unlisted=False),
	84	'tags': attributes.get('genres')
85	}
86
87
88	class RoosterTeethIE(RoosterTeethBaseIE):
89	_VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/(?:episode\|watch)/(?P<id>[^/?#&]+)'
3121b256 NP	90	_TESTS = [{
	91	'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
	92	'info_dict': {
c72dc20d	93	'id': '9156',
865b0872	94	'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement',
3121b256	95	'ext': 'mp4',
c72dc20d RA	96	'title': 'Million Dollars, But... The Game Announcement',
c72dc20d RA	97	'description': 'md5:168a54b40e228e79f4ddb141e89fe4f5',
ec85ded8	98	'thumbnail': r're:^https?://.*\.png$',
3121b256 NP	99	'series': 'Million Dollars, But...',
3121b256 NP	100	'episode': 'Million Dollars, But... The Game Announcement',
3121b256	101	},
b69fd25c	102	'params': {'skip_download': True},
b4d10440 FS	103	}, {
b4d10440 FS	104	'url': 'https://roosterteeth.com/watch/rwby-bonus-25',
b4d10440	105	'info_dict': {
244644c0	106	'id': '40432',
b4d10440	107	'display_id': 'rwby-bonus-25',
244644c0	108	'title': 'Grimm',
	109	'description': 'md5:f30ff570741213418a8d2c19868b93ab',
	110	'episode': 'Grimm',
	111	'channel_id': '92f780eb-ebfe-4bf5-a3b5-c6ad5460a5f1',
b4d10440 FS	112	'thumbnail': r're:^https?://.*\.(png\|jpe?g)$',
	113	'ext': 'mp4',
	114	},
b69fd25c	115	'params': {'skip_download': True},
3121b256 NP	116	}, {
	117	'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
	118	'only_matching': True,
	119	}, {
	120	'url': 'http://funhaus.roosterteeth.com/episode/funhaus-shorts-2016-austin-sucks-funhaus-shorts',
	121	'only_matching': True,
	122	}, {
	123	'url': 'http://screwattack.roosterteeth.com/episode/death-battle-season-3-mewtwo-vs-shadow',
	124	'only_matching': True,
	125	}, {
	126	'url': 'http://theknow.roosterteeth.com/episode/the-know-game-news-season-1-boring-steam-sales-are-better',
	127	'only_matching': True,
865b0872 S	128	}, {
	129	# only available for FIRST members
	130	'url': 'http://roosterteeth.com/episode/rt-docs-the-world-s-greatest-head-massage-the-world-s-greatest-head-massage-an-asmr-journey-part-one',
	131	'only_matching': True,
5efbc136 RA	132	}, {
	133	'url': 'https://roosterteeth.com/watch/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
	134	'only_matching': True,
3121b256	135	}]
3121b256 NP	136
3121b256 NP	137	def _real_extract(self, url):
865b0872	138	display_id = self._match_id(url)
244644c0	139	api_episode_url = f'{self._API_BASE_URL}/watch/{display_id}'
c72dc20d RA	140
c72dc20d RA	141	try:
dfd14aad	142	video_data = self._download_json(
c72dc20d	143	api_episode_url + '/videos', display_id,
dfd14aad SS	144	'Downloading video JSON metadata')['data'][0]
dfd14aad SS	145	m3u8_url = video_data['attributes']['url']
015c10ae	146	# XXX: additional URL at video_data['links']['download']
c72dc20d RA	147	except ExtractorError as e:
	148	if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
	149	if self._parse_json(e.cause.read().decode(), display_id).get('access') is False:
	150	self.raise_login_required(
	151	'%s is only available for FIRST members' % display_id)
	152	raise
865b0872	153
015c10ae	154	formats, subtitles = self._extract_m3u8_formats_and_subtitles(
c72dc20d	155	m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls')
3121b256 NP	156	self._sort_formats(formats)
3121b256 NP	157
c72dc20d RA	158	episode = self._download_json(
	159	api_episode_url, display_id,
	160	'Downloading episode JSON metadata')['data'][0]
865b0872	161
3121b256	162	return {
865b0872	163	'display_id': display_id,
865b0872	164	'formats': formats,
244644c0	165	'subtitles': subtitles,
244644c0	166	**self._extract_video_info(episode)
3121b256	167	}
244644c0	168
	169
	170	class RoosterTeethSeriesIE(RoosterTeethBaseIE):
	171	_VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/series/(?P<id>[^/?#&]+)'
	172	_TESTS = [{
	173	'url': 'https://roosterteeth.com/series/rwby?season=7',
	174	'playlist_count': 13,
	175	'info_dict': {
	176	'id': 'rwby-7',
	177	'title': 'RWBY - Season 7',
	178	}
	179	}, {
	180	'url': 'https://roosterteeth.com/series/role-initiative',
	181	'playlist_mincount': 16,
	182	'info_dict': {
	183	'id': 'role-initiative',
	184	'title': 'Role Initiative',
	185	}
df03de2c M	186	}, {
	187	'url': 'https://roosterteeth.com/series/let-s-play-minecraft?season=9',
	188	'playlist_mincount': 50,
	189	'info_dict': {
	190	'id': 'let-s-play-minecraft-9',
	191	'title': 'Let\'s Play Minecraft - Season 9',
	192	}
244644c0	193	}]
	194
	195	def _entries(self, series_id, season_number):
	196	display_id = join_nonempty(series_id, season_number)
	197	# TODO: extract bonus material
	198	for data in self._download_json(
	199	f'{self._API_BASE_URL}/shows/{series_id}/seasons?order=asc&order_by', display_id)['data']:
	200	idx = traverse_obj(data, ('attributes', 'number'))
	201	if season_number and idx != season_number:
	202	continue
df03de2c	203	season_url = update_url_query(urljoin(self._API_BASE, data['links']['episodes']), {'per_page': 1000})
244644c0	204	season = self._download_json(season_url, display_id, f'Downloading season {idx} JSON metadata')['data']
	205	for episode in season:
	206	yield self.url_result(
	207	f'https://www.roosterteeth.com{episode["canonical_links"]["self"]}',
	208	RoosterTeethIE.ie_key(),
	209	**self._extract_video_info(episode))
	210
	211	def _real_extract(self, url):
	212	series_id = self._match_id(url)
	213	season_number = traverse_obj(parse_qs(url), ('season', 0), expected_type=int_or_none)
	214
	215	entries = LazyList(self._entries(series_id, season_number))
	216	return self.playlist_result(
	217	entries,
	218	join_nonempty(series_id, season_number),
	219	join_nonempty(entries[0].get('series'), season_number, delim=' - Season '))