2022-01-29 00:33:51 +00:00
|
|
|
|
import base64
|
2022-06-24 08:10:17 +00:00
|
|
|
|
|
2018-09-01 09:04:10 +00:00
|
|
|
|
from .common import InfoExtractor
|
2023-07-09 07:53:02 +00:00
|
|
|
|
from ..networking.exceptions import HTTPError
|
2014-12-13 11:24:42 +00:00
|
|
|
|
from ..utils import (
|
|
|
|
|
ExtractorError,
|
2018-09-01 07:16:28 +00:00
|
|
|
|
float_or_none,
|
2022-01-29 00:33:51 +00:00
|
|
|
|
format_field,
|
2023-05-24 18:45:15 +00:00
|
|
|
|
int_or_none,
|
2022-01-29 00:33:51 +00:00
|
|
|
|
join_nonempty,
|
2023-05-24 18:45:15 +00:00
|
|
|
|
parse_age_limit,
|
|
|
|
|
parse_count,
|
2022-08-02 21:18:40 +00:00
|
|
|
|
parse_iso8601,
|
2021-11-04 18:04:37 +00:00
|
|
|
|
qualities,
|
2023-05-24 18:45:15 +00:00
|
|
|
|
remove_start,
|
|
|
|
|
time_seconds,
|
2022-01-29 00:33:51 +00:00
|
|
|
|
traverse_obj,
|
2023-05-24 18:45:15 +00:00
|
|
|
|
url_or_none,
|
|
|
|
|
urlencode_postdata,
|
2013-11-04 02:08:17 +00:00
|
|
|
|
)
|
|
|
|
|
|
2014-02-25 13:26:11 +00:00
|
|
|
|
|
2018-09-01 09:04:10 +00:00
|
|
|
|
class CrunchyrollBaseIE(InfoExtractor):
|
2023-05-24 18:45:15 +00:00
|
|
|
|
_BASE_URL = 'https://www.crunchyroll.com'
|
2022-01-31 20:01:17 +00:00
|
|
|
|
_API_BASE = 'https://api.crunchyroll.com'
|
2015-10-18 00:57:57 +00:00
|
|
|
|
_NETRC_MACHINE = 'crunchyroll'
|
2023-05-24 18:45:15 +00:00
|
|
|
|
_AUTH_HEADERS = None
|
|
|
|
|
_API_ENDPOINT = None
|
|
|
|
|
_BASIC_AUTH = None
|
2023-07-20 20:09:52 +00:00
|
|
|
|
_CLIENT_ID = ('cr_web', 'noaihdevm_6iyg0a8l0q')
|
|
|
|
|
_LOCALE_LOOKUP = {
|
|
|
|
|
'ar': 'ar-SA',
|
|
|
|
|
'de': 'de-DE',
|
|
|
|
|
'': 'en-US',
|
|
|
|
|
'es': 'es-419',
|
|
|
|
|
'es-es': 'es-ES',
|
|
|
|
|
'fr': 'fr-FR',
|
|
|
|
|
'it': 'it-IT',
|
|
|
|
|
'pt-br': 'pt-BR',
|
|
|
|
|
'pt-pt': 'pt-PT',
|
|
|
|
|
'ru': 'ru-RU',
|
|
|
|
|
'hi': 'hi-IN',
|
|
|
|
|
}
|
2017-11-13 18:15:16 +00:00
|
|
|
|
|
2023-02-13 19:36:38 +00:00
|
|
|
|
@property
|
|
|
|
|
def is_logged_in(self):
|
2023-07-20 20:09:52 +00:00
|
|
|
|
return bool(self._get_cookies(self._BASE_URL).get('etp_rt'))
|
2023-02-13 19:36:38 +00:00
|
|
|
|
|
2022-03-18 20:53:33 +00:00
|
|
|
|
def _perform_login(self, username, password):
|
2023-02-13 19:36:38 +00:00
|
|
|
|
if self.is_logged_in:
|
2016-09-15 14:53:35 +00:00
|
|
|
|
return
|
|
|
|
|
|
2022-01-31 20:01:17 +00:00
|
|
|
|
upsell_response = self._download_json(
|
|
|
|
|
f'{self._API_BASE}/get_upsell_data.0.json', None, 'Getting session id',
|
|
|
|
|
query={
|
|
|
|
|
'sess_id': 1,
|
|
|
|
|
'device_id': 'whatvalueshouldbeforweb',
|
|
|
|
|
'device_type': 'com.crunchyroll.static',
|
|
|
|
|
'access_token': 'giKq5eY27ny3cqz',
|
2023-05-24 18:45:15 +00:00
|
|
|
|
'referer': f'{self._BASE_URL}/welcome/login'
|
2022-01-31 20:01:17 +00:00
|
|
|
|
})
|
|
|
|
|
if upsell_response['code'] != 'ok':
|
|
|
|
|
raise ExtractorError('Could not get session id')
|
|
|
|
|
session_id = upsell_response['data']['session_id']
|
|
|
|
|
|
|
|
|
|
login_response = self._download_json(
|
|
|
|
|
f'{self._API_BASE}/login.1.json', None, 'Logging in',
|
2023-05-24 18:45:15 +00:00
|
|
|
|
data=urlencode_postdata({
|
2022-01-31 20:01:17 +00:00
|
|
|
|
'account': username,
|
|
|
|
|
'password': password,
|
|
|
|
|
'session_id': session_id
|
2023-05-24 18:45:15 +00:00
|
|
|
|
}))
|
2022-01-31 20:01:17 +00:00
|
|
|
|
if login_response['code'] != 'ok':
|
2022-03-04 11:27:35 +00:00
|
|
|
|
raise ExtractorError('Login failed. Server message: %s' % login_response['message'], expected=True)
|
2023-02-13 19:36:38 +00:00
|
|
|
|
if not self.is_logged_in:
|
2022-01-31 20:01:17 +00:00
|
|
|
|
raise ExtractorError('Login succeeded but did not set etp_rt cookie')
|
2015-10-18 00:57:57 +00:00
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
def _update_auth(self):
|
|
|
|
|
if CrunchyrollBaseIE._AUTH_HEADERS and CrunchyrollBaseIE._AUTH_REFRESH > time_seconds():
|
|
|
|
|
return
|
|
|
|
|
|
2023-07-20 20:09:52 +00:00
|
|
|
|
if not CrunchyrollBaseIE._BASIC_AUTH:
|
|
|
|
|
cx_api_param = self._CLIENT_ID[self.is_logged_in]
|
|
|
|
|
self.write_debug(f'Using cxApiParam={cx_api_param}')
|
|
|
|
|
CrunchyrollBaseIE._BASIC_AUTH = 'Basic ' + base64.b64encode(f'{cx_api_param}:'.encode()).decode()
|
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
grant_type = 'etp_rt_cookie' if self.is_logged_in else 'client_id'
|
2023-07-20 20:09:52 +00:00
|
|
|
|
try:
|
|
|
|
|
auth_response = self._download_json(
|
|
|
|
|
f'{self._BASE_URL}/auth/v1/token', None, note=f'Authenticating with grant_type={grant_type}',
|
|
|
|
|
headers={'Authorization': CrunchyrollBaseIE._BASIC_AUTH}, data=f'grant_type={grant_type}'.encode())
|
|
|
|
|
except ExtractorError as error:
|
|
|
|
|
if isinstance(error.cause, HTTPError) and error.cause.status == 403:
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
'Request blocked by Cloudflare; navigate to Crunchyroll in your browser, '
|
|
|
|
|
'then pass the fresh cookies (with --cookies-from-browser or --cookies) '
|
|
|
|
|
'and your browser\'s User-Agent (with --user-agent)', expected=True)
|
|
|
|
|
raise
|
2023-05-24 18:45:15 +00:00
|
|
|
|
|
|
|
|
|
CrunchyrollBaseIE._AUTH_HEADERS = {'Authorization': auth_response['token_type'] + ' ' + auth_response['access_token']}
|
|
|
|
|
CrunchyrollBaseIE._AUTH_REFRESH = time_seconds(seconds=traverse_obj(auth_response, ('expires_in', {float_or_none}), default=300) - 10)
|
|
|
|
|
|
2023-07-20 20:09:52 +00:00
|
|
|
|
def _locale_from_language(self, language):
|
|
|
|
|
config_locale = self._configuration_arg('metadata', ie_key=CrunchyrollBetaIE, casesense=True)
|
|
|
|
|
return config_locale[0] if config_locale else self._LOCALE_LOOKUP.get(language)
|
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
def _call_base_api(self, endpoint, internal_id, lang, note=None, query={}):
|
|
|
|
|
self._update_auth()
|
|
|
|
|
|
|
|
|
|
if not endpoint.startswith('/'):
|
|
|
|
|
endpoint = f'/{endpoint}'
|
|
|
|
|
|
2023-07-20 20:09:52 +00:00
|
|
|
|
query = query.copy()
|
|
|
|
|
locale = self._locale_from_language(lang)
|
|
|
|
|
if locale:
|
|
|
|
|
query['locale'] = locale
|
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
return self._download_json(
|
|
|
|
|
f'{self._BASE_URL}{endpoint}', internal_id, note or f'Calling API: {endpoint}',
|
2023-07-20 20:09:52 +00:00
|
|
|
|
headers=CrunchyrollBaseIE._AUTH_HEADERS, query=query)
|
2023-05-24 18:45:15 +00:00
|
|
|
|
|
|
|
|
|
def _call_api(self, path, internal_id, lang, note='api', query={}):
|
|
|
|
|
if not path.startswith(f'/content/v2/{self._API_ENDPOINT}/'):
|
|
|
|
|
path = f'/content/v2/{self._API_ENDPOINT}/{path}'
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
result = self._call_base_api(
|
|
|
|
|
path, internal_id, lang, f'Downloading {note} JSON ({self._API_ENDPOINT})', query=query)
|
|
|
|
|
except ExtractorError as error:
|
2023-07-09 07:53:02 +00:00
|
|
|
|
if isinstance(error.cause, HTTPError) and error.cause.status == 404:
|
2023-05-24 18:45:15 +00:00
|
|
|
|
return None
|
|
|
|
|
raise
|
|
|
|
|
|
|
|
|
|
if not result:
|
|
|
|
|
raise ExtractorError(f'Unexpected response when downloading {note} JSON')
|
|
|
|
|
return result
|
|
|
|
|
|
|
|
|
|
def _extract_formats(self, stream_response, display_id=None):
|
|
|
|
|
requested_formats = self._configuration_arg('format') or ['adaptive_hls']
|
|
|
|
|
available_formats = {}
|
|
|
|
|
for stream_type, streams in traverse_obj(
|
|
|
|
|
stream_response, (('streams', ('data', 0)), {dict.items}, ...)):
|
|
|
|
|
if stream_type not in requested_formats:
|
|
|
|
|
continue
|
|
|
|
|
for stream in traverse_obj(streams, lambda _, v: v['url']):
|
|
|
|
|
hardsub_lang = stream.get('hardsub_locale') or ''
|
|
|
|
|
format_id = join_nonempty(stream_type, format_field(stream, 'hardsub_locale', 'hardsub-%s'))
|
|
|
|
|
available_formats[hardsub_lang] = (stream_type, format_id, hardsub_lang, stream['url'])
|
|
|
|
|
|
|
|
|
|
requested_hardsubs = [('' if val == 'none' else val) for val in (self._configuration_arg('hardsub') or ['none'])]
|
|
|
|
|
if '' in available_formats and 'all' not in requested_hardsubs:
|
|
|
|
|
full_format_langs = set(requested_hardsubs)
|
|
|
|
|
self.to_screen(
|
|
|
|
|
'To get all formats of a hardsub language, use '
|
|
|
|
|
'"--extractor-args crunchyrollbeta:hardsub=<language_code or all>". '
|
|
|
|
|
'See https://github.com/yt-dlp/yt-dlp#crunchyrollbeta-crunchyroll for more info',
|
|
|
|
|
only_once=True)
|
|
|
|
|
else:
|
|
|
|
|
full_format_langs = set(map(str.lower, available_formats))
|
|
|
|
|
|
|
|
|
|
audio_locale = traverse_obj(stream_response, ((None, 'meta'), 'audio_locale'), get_all=False)
|
|
|
|
|
hardsub_preference = qualities(requested_hardsubs[::-1])
|
|
|
|
|
formats = []
|
|
|
|
|
for stream_type, format_id, hardsub_lang, stream_url in available_formats.values():
|
|
|
|
|
if stream_type.endswith('hls'):
|
|
|
|
|
if hardsub_lang.lower() in full_format_langs:
|
|
|
|
|
adaptive_formats = self._extract_m3u8_formats(
|
|
|
|
|
stream_url, display_id, 'mp4', m3u8_id=format_id,
|
|
|
|
|
fatal=False, note=f'Downloading {format_id} HLS manifest')
|
|
|
|
|
else:
|
|
|
|
|
adaptive_formats = (self._m3u8_meta_format(stream_url, ext='mp4', m3u8_id=format_id),)
|
|
|
|
|
elif stream_type.endswith('dash'):
|
|
|
|
|
adaptive_formats = self._extract_mpd_formats(
|
|
|
|
|
stream_url, display_id, mpd_id=format_id,
|
|
|
|
|
fatal=False, note=f'Downloading {format_id} MPD manifest')
|
2022-08-30 16:34:13 +00:00
|
|
|
|
else:
|
2023-05-24 18:45:15 +00:00
|
|
|
|
self.report_warning(f'Encountered unknown stream_type: {stream_type!r}', display_id, only_once=True)
|
|
|
|
|
continue
|
|
|
|
|
for f in adaptive_formats:
|
|
|
|
|
if f.get('acodec') != 'none':
|
|
|
|
|
f['language'] = audio_locale
|
|
|
|
|
f['quality'] = hardsub_preference(hardsub_lang.lower())
|
|
|
|
|
formats.extend(adaptive_formats)
|
|
|
|
|
|
|
|
|
|
return formats
|
|
|
|
|
|
|
|
|
|
def _extract_subtitles(self, data):
|
|
|
|
|
subtitles = {}
|
|
|
|
|
|
|
|
|
|
for locale, subtitle in traverse_obj(data, ((None, 'meta'), 'subtitles', {dict.items}, ...)):
|
|
|
|
|
subtitles[locale] = [traverse_obj(subtitle, {'url': 'url', 'ext': 'format'})]
|
|
|
|
|
|
|
|
|
|
return subtitles
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class CrunchyrollCmsBaseIE(CrunchyrollBaseIE):
|
|
|
|
|
_API_ENDPOINT = 'cms'
|
|
|
|
|
_CMS_EXPIRY = None
|
|
|
|
|
|
|
|
|
|
def _call_cms_api_signed(self, path, internal_id, lang, note='api'):
|
|
|
|
|
if not CrunchyrollCmsBaseIE._CMS_EXPIRY or CrunchyrollCmsBaseIE._CMS_EXPIRY <= time_seconds():
|
|
|
|
|
response = self._call_base_api('index/v2', None, lang, 'Retrieving signed policy')['cms_web']
|
|
|
|
|
CrunchyrollCmsBaseIE._CMS_QUERY = {
|
|
|
|
|
'Policy': response['policy'],
|
|
|
|
|
'Signature': response['signature'],
|
|
|
|
|
'Key-Pair-Id': response['key_pair_id'],
|
2022-04-05 10:51:12 +00:00
|
|
|
|
}
|
2023-05-24 18:45:15 +00:00
|
|
|
|
CrunchyrollCmsBaseIE._CMS_BUCKET = response['bucket']
|
|
|
|
|
CrunchyrollCmsBaseIE._CMS_EXPIRY = parse_iso8601(response['expires']) - 10
|
|
|
|
|
|
|
|
|
|
if not path.startswith('/cms/v2'):
|
|
|
|
|
path = f'/cms/v2{CrunchyrollCmsBaseIE._CMS_BUCKET}/{path}'
|
2022-04-05 10:51:12 +00:00
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
return self._call_base_api(
|
|
|
|
|
path, internal_id, lang, f'Downloading {note} JSON (signed cms)', query=CrunchyrollCmsBaseIE._CMS_QUERY)
|
2022-04-05 10:51:12 +00:00
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
|
|
|
|
|
class CrunchyrollBetaIE(CrunchyrollCmsBaseIE):
|
2022-11-06 18:48:55 +00:00
|
|
|
|
IE_NAME = 'crunchyroll'
|
2022-08-12 07:38:32 +00:00
|
|
|
|
_VALID_URL = r'''(?x)
|
2023-05-24 18:45:15 +00:00
|
|
|
|
https?://(?:beta\.|www\.)?crunchyroll\.com/
|
2023-07-20 20:09:52 +00:00
|
|
|
|
(?:(?P<lang>\w{2}(?:-\w{2})?)/)?
|
2023-05-24 18:45:15 +00:00
|
|
|
|
watch/(?!concert|musicvideo)(?P<id>\w+)'''
|
2021-10-17 11:46:05 +00:00
|
|
|
|
_TESTS = [{
|
2023-05-24 18:45:15 +00:00
|
|
|
|
# Premium only
|
2022-11-06 18:48:55 +00:00
|
|
|
|
'url': 'https://www.crunchyroll.com/watch/GY2P1Q98Y/to-the-future',
|
2021-10-17 11:46:05 +00:00
|
|
|
|
'info_dict': {
|
2022-08-02 21:18:40 +00:00
|
|
|
|
'id': 'GY2P1Q98Y',
|
2021-10-17 11:46:05 +00:00
|
|
|
|
'ext': 'mp4',
|
2022-08-02 21:18:40 +00:00
|
|
|
|
'duration': 1380.241,
|
|
|
|
|
'timestamp': 1459632600,
|
2021-10-17 11:46:05 +00:00
|
|
|
|
'description': 'md5:a022fbec4fbb023d43631032c91ed64b',
|
|
|
|
|
'title': 'World Trigger Episode 73 – To the Future',
|
|
|
|
|
'upload_date': '20160402',
|
2022-04-05 10:51:12 +00:00
|
|
|
|
'series': 'World Trigger',
|
2022-08-02 21:18:40 +00:00
|
|
|
|
'series_id': 'GR757DMKY',
|
2022-04-05 10:51:12 +00:00
|
|
|
|
'season': 'World Trigger',
|
2022-08-02 21:18:40 +00:00
|
|
|
|
'season_id': 'GR9P39NJ6',
|
2022-04-05 10:51:12 +00:00
|
|
|
|
'season_number': 1,
|
2022-08-02 21:18:40 +00:00
|
|
|
|
'episode': 'To the Future',
|
|
|
|
|
'episode_number': 73,
|
2023-05-24 18:45:15 +00:00
|
|
|
|
'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
|
2023-02-12 07:47:12 +00:00
|
|
|
|
'chapters': 'count:2',
|
2023-05-24 18:45:15 +00:00
|
|
|
|
'age_limit': 14,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'dislike_count': int,
|
2021-10-17 11:46:05 +00:00
|
|
|
|
},
|
2022-09-30 01:05:44 +00:00
|
|
|
|
'params': {'skip_download': 'm3u8', 'format': 'all[format_id~=hardsub]'},
|
|
|
|
|
}, {
|
2023-05-24 18:45:15 +00:00
|
|
|
|
# Premium only
|
2022-11-06 18:48:55 +00:00
|
|
|
|
'url': 'https://www.crunchyroll.com/watch/GYE5WKQGR',
|
2022-09-30 01:05:44 +00:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'GYE5WKQGR',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'duration': 366.459,
|
|
|
|
|
'timestamp': 1476788400,
|
|
|
|
|
'description': 'md5:74b67283ffddd75f6e224ca7dc031e76',
|
2023-05-24 18:45:15 +00:00
|
|
|
|
'title': 'SHELTER – Porter Robinson presents Shelter the Animation',
|
2022-09-30 01:05:44 +00:00
|
|
|
|
'upload_date': '20161018',
|
|
|
|
|
'series': 'SHELTER',
|
|
|
|
|
'series_id': 'GYGG09WWY',
|
|
|
|
|
'season': 'SHELTER',
|
|
|
|
|
'season_id': 'GR09MGK4R',
|
|
|
|
|
'season_number': 1,
|
|
|
|
|
'episode': 'Porter Robinson presents Shelter the Animation',
|
|
|
|
|
'episode_number': 0,
|
2023-05-24 18:45:15 +00:00
|
|
|
|
'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
|
|
|
|
|
'age_limit': 14,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'dislike_count': int,
|
2022-09-30 01:05:44 +00:00
|
|
|
|
},
|
|
|
|
|
'params': {'skip_download': True},
|
2023-05-24 18:45:15 +00:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.crunchyroll.com/watch/GJWU2VKK3/cherry-blossom-meeting-and-a-coming-blizzard',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'GJWU2VKK3',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'duration': 1420.054,
|
|
|
|
|
'description': 'md5:2d1c67c0ec6ae514d9c30b0b99a625cd',
|
|
|
|
|
'title': 'The Ice Guy and His Cool Female Colleague Episode 1 – Cherry Blossom Meeting and a Coming Blizzard',
|
|
|
|
|
'series': 'The Ice Guy and His Cool Female Colleague',
|
|
|
|
|
'series_id': 'GW4HM75NP',
|
|
|
|
|
'season': 'The Ice Guy and His Cool Female Colleague',
|
|
|
|
|
'season_id': 'GY9PC21VE',
|
|
|
|
|
'season_number': 1,
|
|
|
|
|
'episode': 'Cherry Blossom Meeting and a Coming Blizzard',
|
|
|
|
|
'episode_number': 1,
|
|
|
|
|
'chapters': 'count:2',
|
|
|
|
|
'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
|
|
|
|
|
'timestamp': 1672839000,
|
|
|
|
|
'upload_date': '20230104',
|
|
|
|
|
'age_limit': 14,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'dislike_count': int,
|
|
|
|
|
},
|
|
|
|
|
'params': {'skip_download': 'm3u8'},
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.crunchyroll.com/watch/GM8F313NQ',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'GM8F313NQ',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Garakowa -Restore the World-',
|
|
|
|
|
'description': 'md5:8d2f8b6b9dd77d87810882e7d2ee5608',
|
|
|
|
|
'duration': 3996.104,
|
|
|
|
|
'age_limit': 13,
|
|
|
|
|
'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
|
|
|
|
|
},
|
|
|
|
|
'params': {'skip_download': 'm3u8'},
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.crunchyroll.com/watch/G62PEZ2E6',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'G62PEZ2E6',
|
|
|
|
|
'description': 'md5:8d2f8b6b9dd77d87810882e7d2ee5608',
|
|
|
|
|
'age_limit': 13,
|
|
|
|
|
'duration': 65.138,
|
|
|
|
|
'title': 'Garakowa -Restore the World-',
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 5,
|
2022-04-05 10:51:12 +00:00
|
|
|
|
}, {
|
2023-07-20 20:09:52 +00:00
|
|
|
|
'url': 'https://www.crunchyroll.com/de/watch/GY2P1Q98Y',
|
2022-04-05 10:51:12 +00:00
|
|
|
|
'only_matching': True,
|
2022-07-27 10:41:15 +00:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://beta.crunchyroll.com/pt-br/watch/G8WUN8VKP/the-ruler-of-conspiracy',
|
|
|
|
|
'only_matching': True,
|
2021-10-17 11:46:05 +00:00
|
|
|
|
}]
|
2023-05-24 18:45:15 +00:00
|
|
|
|
# We want to support lazy playlist filtering and movie listings cannot be inside a playlist
|
|
|
|
|
_RETURN_TYPE = 'video'
|
2021-10-17 11:46:05 +00:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2023-05-24 18:45:15 +00:00
|
|
|
|
lang, internal_id = self._match_valid_url(url).group('lang', 'id')
|
2022-04-05 10:51:12 +00:00
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
# We need to use unsigned API call to allow ratings query string
|
|
|
|
|
response = traverse_obj(self._call_api(
|
|
|
|
|
f'objects/{internal_id}', internal_id, lang, 'object info', {'ratings': 'true'}), ('data', 0, {dict}))
|
|
|
|
|
if not response:
|
|
|
|
|
raise ExtractorError(f'No video with id {internal_id} could be found (possibly region locked?)', expected=True)
|
2022-01-29 00:33:51 +00:00
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
object_type = response.get('type')
|
|
|
|
|
if object_type == 'episode':
|
|
|
|
|
result = self._transform_episode_response(response)
|
2022-01-29 00:33:51 +00:00
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
elif object_type == 'movie':
|
|
|
|
|
result = self._transform_movie_response(response)
|
2022-01-29 00:33:51 +00:00
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
elif object_type == 'movie_listing':
|
|
|
|
|
first_movie_id = traverse_obj(response, ('movie_listing_metadata', 'first_movie_id'))
|
|
|
|
|
if not self._yes_playlist(internal_id, first_movie_id):
|
|
|
|
|
return self.url_result(f'{self._BASE_URL}/{lang}watch/{first_movie_id}', CrunchyrollBetaIE, first_movie_id)
|
|
|
|
|
|
|
|
|
|
def entries():
|
|
|
|
|
movies = self._call_api(f'movie_listings/{internal_id}/movies', internal_id, lang, 'movie list')
|
|
|
|
|
for movie_response in traverse_obj(movies, ('data', ...)):
|
|
|
|
|
yield self.url_result(
|
|
|
|
|
f'{self._BASE_URL}/{lang}watch/{movie_response["id"]}',
|
|
|
|
|
CrunchyrollBetaIE, **self._transform_movie_response(movie_response))
|
|
|
|
|
|
|
|
|
|
return self.playlist_result(entries(), **self._transform_movie_response(response))
|
2022-09-30 01:05:44 +00:00
|
|
|
|
|
|
|
|
|
else:
|
2023-05-24 18:45:15 +00:00
|
|
|
|
raise ExtractorError(f'Unknown object type {object_type}')
|
2022-09-30 01:05:44 +00:00
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
# There might be multiple audio languages for one object (`<object>_metadata.versions`),
|
|
|
|
|
# so we need to get the id from `streams_link` instead or we dont know which language to choose
|
|
|
|
|
streams_link = response.get('streams_link')
|
|
|
|
|
if not streams_link and traverse_obj(response, (f'{object_type}_metadata', 'is_premium_only')):
|
|
|
|
|
message = f'This {object_type} is for premium members only'
|
|
|
|
|
if self.is_logged_in:
|
|
|
|
|
raise ExtractorError(message, expected=True)
|
|
|
|
|
self.raise_login_required(message)
|
|
|
|
|
|
|
|
|
|
# We need go from unsigned to signed api to avoid getting soft banned
|
|
|
|
|
stream_response = self._call_cms_api_signed(remove_start(
|
|
|
|
|
streams_link, '/content/v2/cms/'), internal_id, lang, 'stream info')
|
|
|
|
|
result['formats'] = self._extract_formats(stream_response, internal_id)
|
|
|
|
|
result['subtitles'] = self._extract_subtitles(stream_response)
|
2022-01-29 00:33:51 +00:00
|
|
|
|
|
2023-02-12 07:47:12 +00:00
|
|
|
|
# if no intro chapter is available, a 403 without usable data is returned
|
2023-05-24 18:45:15 +00:00
|
|
|
|
intro_chapter = self._download_json(
|
|
|
|
|
f'https://static.crunchyroll.com/datalab-intro-v2/{internal_id}.json',
|
|
|
|
|
internal_id, note='Downloading chapter info', fatal=False, errnote=False)
|
2023-02-12 07:47:12 +00:00
|
|
|
|
if isinstance(intro_chapter, dict):
|
2023-05-24 18:45:15 +00:00
|
|
|
|
result['chapters'] = [{
|
2023-02-12 07:47:12 +00:00
|
|
|
|
'title': 'Intro',
|
|
|
|
|
'start_time': float_or_none(intro_chapter.get('startTime')),
|
2023-05-24 18:45:15 +00:00
|
|
|
|
'end_time': float_or_none(intro_chapter.get('endTime')),
|
2023-02-12 07:47:12 +00:00
|
|
|
|
}]
|
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
def calculate_count(item):
|
|
|
|
|
return parse_count(''.join((item['displayed'], item.get('unit') or '')))
|
|
|
|
|
|
|
|
|
|
result.update(traverse_obj(response, ('rating', {
|
|
|
|
|
'like_count': ('up', {calculate_count}),
|
|
|
|
|
'dislike_count': ('down', {calculate_count}),
|
|
|
|
|
})))
|
|
|
|
|
|
|
|
|
|
return result
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _transform_episode_response(data):
|
|
|
|
|
metadata = traverse_obj(data, (('episode_metadata', None), {dict}), get_all=False) or {}
|
2022-01-29 00:33:51 +00:00
|
|
|
|
return {
|
2023-05-24 18:45:15 +00:00
|
|
|
|
'id': data['id'],
|
|
|
|
|
'title': ' \u2013 '.join((
|
|
|
|
|
('%s%s' % (
|
|
|
|
|
format_field(metadata, 'season_title'),
|
|
|
|
|
format_field(metadata, 'episode', ' Episode %s'))),
|
|
|
|
|
format_field(data, 'title'))),
|
|
|
|
|
**traverse_obj(data, {
|
|
|
|
|
'episode': ('title', {str}),
|
|
|
|
|
'description': ('description', {str}, {lambda x: x.replace(r'\r\n', '\n')}),
|
|
|
|
|
'thumbnails': ('images', 'thumbnail', ..., ..., {
|
|
|
|
|
'url': ('source', {url_or_none}),
|
|
|
|
|
'width': ('width', {int_or_none}),
|
|
|
|
|
'height': ('height', {int_or_none}),
|
|
|
|
|
}),
|
|
|
|
|
}),
|
|
|
|
|
**traverse_obj(metadata, {
|
|
|
|
|
'duration': ('duration_ms', {lambda x: float_or_none(x, 1000)}),
|
|
|
|
|
'timestamp': ('upload_date', {parse_iso8601}),
|
|
|
|
|
'series': ('series_title', {str}),
|
|
|
|
|
'series_id': ('series_id', {str}),
|
|
|
|
|
'season': ('season_title', {str}),
|
|
|
|
|
'season_id': ('season_id', {str}),
|
|
|
|
|
'season_number': ('season_number', ({int}, {float_or_none})),
|
|
|
|
|
'episode_number': ('sequence_number', ({int}, {float_or_none})),
|
|
|
|
|
'age_limit': ('maturity_ratings', -1, {parse_age_limit}),
|
|
|
|
|
'language': ('audio_locale', {str}),
|
|
|
|
|
}, get_all=False),
|
2022-01-29 00:33:51 +00:00
|
|
|
|
}
|
2021-10-17 11:46:05 +00:00
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
@staticmethod
|
|
|
|
|
def _transform_movie_response(data):
|
|
|
|
|
metadata = traverse_obj(data, (('movie_metadata', 'movie_listing_metadata', None), {dict}), get_all=False) or {}
|
|
|
|
|
return {
|
|
|
|
|
'id': data['id'],
|
|
|
|
|
**traverse_obj(data, {
|
|
|
|
|
'title': ('title', {str}),
|
|
|
|
|
'description': ('description', {str}, {lambda x: x.replace(r'\r\n', '\n')}),
|
|
|
|
|
'thumbnails': ('images', 'thumbnail', ..., ..., {
|
|
|
|
|
'url': ('source', {url_or_none}),
|
|
|
|
|
'width': ('width', {int_or_none}),
|
|
|
|
|
'height': ('height', {int_or_none}),
|
|
|
|
|
}),
|
|
|
|
|
}),
|
|
|
|
|
**traverse_obj(metadata, {
|
|
|
|
|
'duration': ('duration_ms', {lambda x: float_or_none(x, 1000)}),
|
|
|
|
|
'age_limit': ('maturity_ratings', -1, {parse_age_limit}),
|
|
|
|
|
}),
|
|
|
|
|
}
|
2021-10-17 11:46:05 +00:00
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
|
|
|
|
|
class CrunchyrollBetaShowIE(CrunchyrollCmsBaseIE):
|
2022-11-06 18:48:55 +00:00
|
|
|
|
IE_NAME = 'crunchyroll:playlist'
|
2022-08-12 07:38:32 +00:00
|
|
|
|
_VALID_URL = r'''(?x)
|
2023-05-24 18:45:15 +00:00
|
|
|
|
https?://(?:beta\.|www\.)?crunchyroll\.com/
|
2022-08-12 07:38:32 +00:00
|
|
|
|
(?P<lang>(?:\w{2}(?:-\w{2})?/)?)
|
2023-05-24 18:45:15 +00:00
|
|
|
|
series/(?P<id>\w+)'''
|
2021-10-17 11:46:05 +00:00
|
|
|
|
_TESTS = [{
|
2022-11-06 18:48:55 +00:00
|
|
|
|
'url': 'https://www.crunchyroll.com/series/GY19NQ2QR/Girl-Friend-BETA',
|
2021-10-17 11:46:05 +00:00
|
|
|
|
'info_dict': {
|
2022-08-02 21:18:40 +00:00
|
|
|
|
'id': 'GY19NQ2QR',
|
2021-10-17 11:46:05 +00:00
|
|
|
|
'title': 'Girl Friend BETA',
|
2023-05-24 18:45:15 +00:00
|
|
|
|
'description': 'md5:99c1b22ee30a74b536a8277ced8eb750',
|
|
|
|
|
# XXX: `thumbnail` does not get set from `thumbnails` in playlist
|
|
|
|
|
# 'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
|
|
|
|
|
'age_limit': 14,
|
2021-10-17 11:46:05 +00:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 10,
|
|
|
|
|
}, {
|
2022-08-12 07:38:32 +00:00
|
|
|
|
'url': 'https://beta.crunchyroll.com/it/series/GY19NQ2QR',
|
2021-10-17 11:46:05 +00:00
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2023-05-24 18:45:15 +00:00
|
|
|
|
lang, internal_id = self._match_valid_url(url).group('lang', 'id')
|
|
|
|
|
|
|
|
|
|
def entries():
|
|
|
|
|
seasons_response = self._call_cms_api_signed(f'seasons?series_id={internal_id}', internal_id, lang, 'seasons')
|
|
|
|
|
for season in traverse_obj(seasons_response, ('items', ..., {dict})):
|
|
|
|
|
episodes_response = self._call_cms_api_signed(
|
|
|
|
|
f'episodes?season_id={season["id"]}', season["id"], lang, 'episode list')
|
|
|
|
|
for episode_response in traverse_obj(episodes_response, ('items', ..., {dict})):
|
|
|
|
|
yield self.url_result(
|
|
|
|
|
f'{self._BASE_URL}/{lang}watch/{episode_response["id"]}',
|
|
|
|
|
CrunchyrollBetaIE, **CrunchyrollBetaIE._transform_episode_response(episode_response))
|
|
|
|
|
|
|
|
|
|
return self.playlist_result(
|
|
|
|
|
entries(), internal_id,
|
|
|
|
|
**traverse_obj(self._call_api(f'series/{internal_id}', internal_id, lang, 'series'), ('data', 0, {
|
|
|
|
|
'title': ('title', {str}),
|
|
|
|
|
'description': ('description', {lambda x: x.replace(r'\r\n', '\n')}),
|
|
|
|
|
'age_limit': ('maturity_ratings', -1, {parse_age_limit}),
|
|
|
|
|
'thumbnails': ('images', ..., ..., ..., {
|
|
|
|
|
'url': ('source', {url_or_none}),
|
|
|
|
|
'width': ('width', {int_or_none}),
|
|
|
|
|
'height': ('height', {int_or_none}),
|
|
|
|
|
})
|
|
|
|
|
})))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class CrunchyrollMusicIE(CrunchyrollBaseIE):
|
|
|
|
|
IE_NAME = 'crunchyroll:music'
|
|
|
|
|
_VALID_URL = r'''(?x)
|
|
|
|
|
https?://(?:www\.)?crunchyroll\.com/
|
|
|
|
|
(?P<lang>(?:\w{2}(?:-\w{2})?/)?)
|
2023-06-27 20:28:23 +00:00
|
|
|
|
watch/(?P<type>concert|musicvideo)/(?P<id>\w+)'''
|
2023-05-24 18:45:15 +00:00
|
|
|
|
_TESTS = [{
|
2023-06-27 20:28:23 +00:00
|
|
|
|
'url': 'https://www.crunchyroll.com/de/watch/musicvideo/MV5B02C79',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'id': 'MV5B02C79',
|
|
|
|
|
'display_id': 'egaono-hana',
|
|
|
|
|
'title': 'Egaono Hana',
|
|
|
|
|
'track': 'Egaono Hana',
|
|
|
|
|
'artist': 'Goose house',
|
|
|
|
|
'thumbnail': r're:(?i)^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
|
2024-03-08 22:36:41 +00:00
|
|
|
|
'genres': ['J-Pop'],
|
2023-06-27 20:28:23 +00:00
|
|
|
|
},
|
|
|
|
|
'params': {'skip_download': 'm3u8'},
|
|
|
|
|
}, {
|
2023-05-24 18:45:15 +00:00
|
|
|
|
'url': 'https://www.crunchyroll.com/watch/musicvideo/MV88BB7F2C',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'id': 'MV88BB7F2C',
|
|
|
|
|
'display_id': 'crossing-field',
|
|
|
|
|
'title': 'Crossing Field',
|
|
|
|
|
'track': 'Crossing Field',
|
|
|
|
|
'artist': 'LiSA',
|
|
|
|
|
'thumbnail': r're:(?i)^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
|
2024-03-08 22:36:41 +00:00
|
|
|
|
'genres': ['Anime'],
|
2023-05-24 18:45:15 +00:00
|
|
|
|
},
|
|
|
|
|
'params': {'skip_download': 'm3u8'},
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.crunchyroll.com/watch/concert/MC2E2AC135',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'id': 'MC2E2AC135',
|
|
|
|
|
'display_id': 'live-is-smile-always-364joker-at-yokohama-arena',
|
|
|
|
|
'title': 'LiVE is Smile Always-364+JOKER- at YOKOHAMA ARENA',
|
|
|
|
|
'track': 'LiVE is Smile Always-364+JOKER- at YOKOHAMA ARENA',
|
|
|
|
|
'artist': 'LiSA',
|
|
|
|
|
'thumbnail': r're:(?i)^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
|
|
|
|
|
'description': 'md5:747444e7e6300907b7a43f0a0503072e',
|
2024-03-08 22:36:41 +00:00
|
|
|
|
'genres': ['J-Pop'],
|
2023-05-24 18:45:15 +00:00
|
|
|
|
},
|
|
|
|
|
'params': {'skip_download': 'm3u8'},
|
|
|
|
|
}, {
|
2023-06-27 20:28:23 +00:00
|
|
|
|
'url': 'https://www.crunchyroll.com/de/watch/musicvideo/MV5B02C79/egaono-hana',
|
2023-05-24 18:45:15 +00:00
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.crunchyroll.com/watch/concert/MC2E2AC135/live-is-smile-always-364joker-at-yokohama-arena',
|
|
|
|
|
'only_matching': True,
|
2023-06-27 20:28:23 +00:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.crunchyroll.com/watch/musicvideo/MV88BB7F2C/crossing-field',
|
|
|
|
|
'only_matching': True,
|
2023-05-24 18:45:15 +00:00
|
|
|
|
}]
|
|
|
|
|
_API_ENDPOINT = 'music'
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
lang, internal_id, object_type = self._match_valid_url(url).group('lang', 'id', 'type')
|
|
|
|
|
path, name = {
|
|
|
|
|
'concert': ('concerts', 'concert info'),
|
|
|
|
|
'musicvideo': ('music_videos', 'music video info'),
|
|
|
|
|
}[object_type]
|
|
|
|
|
response = traverse_obj(self._call_api(f'{path}/{internal_id}', internal_id, lang, name), ('data', 0, {dict}))
|
|
|
|
|
if not response:
|
|
|
|
|
raise ExtractorError(f'No video with id {internal_id} could be found (possibly region locked?)', expected=True)
|
2022-04-05 10:51:12 +00:00
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
streams_link = response.get('streams_link')
|
|
|
|
|
if not streams_link and response.get('isPremiumOnly'):
|
|
|
|
|
message = f'This {response.get("type") or "media"} is for premium members only'
|
|
|
|
|
if self.is_logged_in:
|
|
|
|
|
raise ExtractorError(message, expected=True)
|
|
|
|
|
self.raise_login_required(message)
|
|
|
|
|
|
|
|
|
|
result = self._transform_music_response(response)
|
|
|
|
|
stream_response = self._call_api(streams_link, internal_id, lang, 'stream info')
|
|
|
|
|
result['formats'] = self._extract_formats(stream_response, internal_id)
|
|
|
|
|
|
|
|
|
|
return result
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _transform_music_response(data):
|
|
|
|
|
return {
|
|
|
|
|
'id': data['id'],
|
|
|
|
|
**traverse_obj(data, {
|
|
|
|
|
'display_id': 'slug',
|
|
|
|
|
'title': 'title',
|
|
|
|
|
'track': 'title',
|
|
|
|
|
'artist': ('artist', 'name'),
|
|
|
|
|
'description': ('description', {str}, {lambda x: x.replace(r'\r\n', '\n') or None}),
|
|
|
|
|
'thumbnails': ('images', ..., ..., {
|
|
|
|
|
'url': ('source', {url_or_none}),
|
|
|
|
|
'width': ('width', {int_or_none}),
|
|
|
|
|
'height': ('height', {int_or_none}),
|
|
|
|
|
}),
|
2024-03-08 22:36:41 +00:00
|
|
|
|
'genres': ('genres', ..., 'displayValue'),
|
2023-05-24 18:45:15 +00:00
|
|
|
|
'age_limit': ('maturity_ratings', -1, {parse_age_limit}),
|
|
|
|
|
}),
|
|
|
|
|
}
|
2022-04-05 10:51:12 +00:00
|
|
|
|
|
2023-05-24 18:45:15 +00:00
|
|
|
|
|
|
|
|
|
class CrunchyrollArtistIE(CrunchyrollBaseIE):
|
|
|
|
|
IE_NAME = 'crunchyroll:artist'
|
|
|
|
|
_VALID_URL = r'''(?x)
|
|
|
|
|
https?://(?:www\.)?crunchyroll\.com/
|
|
|
|
|
(?P<lang>(?:\w{2}(?:-\w{2})?/)?)
|
|
|
|
|
artist/(?P<id>\w{10})'''
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'https://www.crunchyroll.com/artist/MA179CB50D',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'MA179CB50D',
|
|
|
|
|
'title': 'LiSA',
|
2024-03-08 22:36:41 +00:00
|
|
|
|
'genres': ['J-Pop', 'Anime', 'Rock'],
|
2023-05-24 18:45:15 +00:00
|
|
|
|
'description': 'md5:16d87de61a55c3f7d6c454b73285938e',
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 83,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.crunchyroll.com/artist/MA179CB50D/lisa',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
|
|
|
|
_API_ENDPOINT = 'music'
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
lang, internal_id = self._match_valid_url(url).group('lang', 'id')
|
|
|
|
|
response = traverse_obj(self._call_api(
|
|
|
|
|
f'artists/{internal_id}', internal_id, lang, 'artist info'), ('data', 0))
|
2022-04-05 10:51:12 +00:00
|
|
|
|
|
|
|
|
|
def entries():
|
2023-05-24 18:45:15 +00:00
|
|
|
|
for attribute, path in [('concerts', 'concert'), ('videos', 'musicvideo')]:
|
|
|
|
|
for internal_id in traverse_obj(response, (attribute, ...)):
|
|
|
|
|
yield self.url_result(f'{self._BASE_URL}/watch/{path}/{internal_id}', CrunchyrollMusicIE, internal_id)
|
|
|
|
|
|
|
|
|
|
return self.playlist_result(entries(), **self._transform_artist_response(response))
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _transform_artist_response(data):
|
|
|
|
|
return {
|
|
|
|
|
'id': data['id'],
|
|
|
|
|
**traverse_obj(data, {
|
|
|
|
|
'title': 'name',
|
|
|
|
|
'description': ('description', {str}, {lambda x: x.replace(r'\r\n', '\n')}),
|
|
|
|
|
'thumbnails': ('images', ..., ..., {
|
|
|
|
|
'url': ('source', {url_or_none}),
|
|
|
|
|
'width': ('width', {int_or_none}),
|
|
|
|
|
'height': ('height', {int_or_none}),
|
|
|
|
|
}),
|
2024-03-08 22:36:41 +00:00
|
|
|
|
'genres': ('genres', ..., 'displayValue'),
|
2023-05-24 18:45:15 +00:00
|
|
|
|
}),
|
|
|
|
|
}
|