-# coding: utf-8
-from __future__ import unicode_literals
+import base64
-import re
-import json
-import zlib
-
-from hashlib import sha1
-from math import pow, sqrt, floor
from .common import InfoExtractor
-from .vrv import VRVIE
-from ..compat import (
- compat_b64decode,
- compat_etree_Element,
- compat_etree_fromstring,
- compat_str,
- compat_urllib_parse_urlencode,
- compat_urllib_request,
- compat_urlparse,
-)
+from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
- bytes_to_intlist,
- extract_attributes,
float_or_none,
- intlist_to_bytes,
+ format_field,
int_or_none,
- lowercase_escape,
- merge_dicts,
- remove_end,
- sanitized_Request,
- try_get,
+ join_nonempty,
+ parse_age_limit,
+ parse_count,
+ parse_iso8601,
+ qualities,
+ remove_start,
+ time_seconds,
+ traverse_obj,
+ url_or_none,
urlencode_postdata,
- xpath_text,
-)
-from ..aes import (
- aes_cbc_decrypt,
)
class CrunchyrollBaseIE(InfoExtractor):
- _LOGIN_URL = 'https://www.crunchyroll.com/login'
- _LOGIN_FORM = 'login_form'
+ _BASE_URL = 'https://www.crunchyroll.com'
+ _API_BASE = 'https://api.crunchyroll.com'
_NETRC_MACHINE = 'crunchyroll'
+ _AUTH_HEADERS = None
+ _API_ENDPOINT = None
+ _BASIC_AUTH = None
+ _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',
+ }
- def _call_rpc_api(self, method, video_id, note=None, data=None):
- data = data or {}
- data['req'] = 'RpcApi' + method
- data = compat_urllib_parse_urlencode(data).encode('utf-8')
- return self._download_xml(
- 'https://www.crunchyroll.com/xml/',
- video_id, note, fatal=False, data=data, headers={
- 'Content-Type': 'application/x-www-form-urlencoded',
- })
+ @property
+ def is_logged_in(self):
+ return bool(self._get_cookies(self._BASE_URL).get('etp_rt'))
+
+ def _perform_login(self, username, password):
+ if self.is_logged_in:
+ return
- def _login(self):
- username, password = self._get_login_info()
- if username is None:
+ 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',
+ 'referer': f'{self._BASE_URL}/welcome/login'
+ })
+ 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',
+ data=urlencode_postdata({
+ 'account': username,
+ 'password': password,
+ 'session_id': session_id
+ }))
+ if login_response['code'] != 'ok':
+ raise ExtractorError('Login failed. Server message: %s' % login_response['message'], expected=True)
+ if not self.is_logged_in:
+ raise ExtractorError('Login succeeded but did not set etp_rt cookie')
+
+ def _update_auth(self):
+ if CrunchyrollBaseIE._AUTH_HEADERS and CrunchyrollBaseIE._AUTH_REFRESH > time_seconds():
return
- login_page = self._download_webpage(
- self._LOGIN_URL, None, 'Downloading login page')
+ 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()
+
+ grant_type = 'etp_rt_cookie' if self.is_logged_in else 'client_id'
+ 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
+
+ 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)
+
+ 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)
+
+ def _call_base_api(self, endpoint, internal_id, lang, note=None, query={}):
+ self._update_auth()
+
+ if not endpoint.startswith('/'):
+ endpoint = f'/{endpoint}'
+
+ query = query.copy()
+ locale = self._locale_from_language(lang)
+ if locale:
+ query['locale'] = locale
+
+ return self._download_json(
+ f'{self._BASE_URL}{endpoint}', internal_id, note or f'Calling API: {endpoint}',
+ headers=CrunchyrollBaseIE._AUTH_HEADERS, query=query)
+
+ 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:
+ if isinstance(error.cause, HTTPError) and error.cause.status == 404:
+ 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))
- def is_logged(webpage):
- return 'href="/logout"' in webpage
+ 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')
+ else:
+ 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)
- # Already logged in
- if is_logged(login_page):
- return
+ return formats
- login_form_str = self._search_regex(
- r'(?P<form><form[^>]+?id=(["\'])%s\2[^>]*>)' % self._LOGIN_FORM,
- login_page, 'login form', group='form')
+ def _extract_subtitles(self, data):
+ subtitles = {}
- post_url = extract_attributes(login_form_str).get('action')
- if not post_url:
- post_url = self._LOGIN_URL
- elif not post_url.startswith('http'):
- post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
+ for locale, subtitle in traverse_obj(data, ((None, 'meta'), 'subtitles', {dict.items}, ...)):
+ subtitles[locale] = [traverse_obj(subtitle, {'url': 'url', 'ext': 'format'})]
- login_form = self._form_hidden_inputs(self._LOGIN_FORM, login_page)
+ return subtitles
- login_form.update({
- 'login_form[name]': username,
- 'login_form[password]': password,
- })
- response = self._download_webpage(
- post_url, None, 'Logging in', 'Wrong login info',
- data=urlencode_postdata(login_form),
- headers={'Content-Type': 'application/x-www-form-urlencoded'})
+class CrunchyrollCmsBaseIE(CrunchyrollBaseIE):
+ _API_ENDPOINT = 'cms'
+ _CMS_EXPIRY = None
- # Successful login
- if is_logged(response):
- return
+ 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'],
+ }
+ CrunchyrollCmsBaseIE._CMS_BUCKET = response['bucket']
+ CrunchyrollCmsBaseIE._CMS_EXPIRY = parse_iso8601(response['expires']) - 10
- error = self._html_search_regex(
- '(?s)<ul[^>]+class=["\']messages["\'][^>]*>(.+?)</ul>',
- response, 'error message', default=None)
- if error:
- raise ExtractorError('Unable to login: %s' % error, expected=True)
+ if not path.startswith('/cms/v2'):
+ path = f'/cms/v2{CrunchyrollCmsBaseIE._CMS_BUCKET}/{path}'
- raise ExtractorError('Unable to log in')
+ return self._call_base_api(
+ path, internal_id, lang, f'Downloading {note} JSON (signed cms)', query=CrunchyrollCmsBaseIE._CMS_QUERY)
- def _real_initialize(self):
- self._login()
- @staticmethod
- def _add_skip_wall(url):
- parsed_url = compat_urlparse.urlparse(url)
- qs = compat_urlparse.parse_qs(parsed_url.query)
- # Always force skip_wall to bypass maturity wall, namely 18+ confirmation message:
- # > This content may be inappropriate for some people.
- # > Are you sure you want to continue?
- # since it's not disabled by default in crunchyroll account's settings.
- # See https://github.com/ytdl-org/youtube-dl/issues/7202.
- qs['skip_wall'] = ['1']
- return compat_urlparse.urlunparse(
- parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
-
-
-class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
+class CrunchyrollBetaIE(CrunchyrollCmsBaseIE):
IE_NAME = 'crunchyroll'
- _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|(?:[^/]*/){1,2}[^/?&]*?)(?P<id>[0-9]+))(?:[/?&]|$)'
+ _VALID_URL = r'''(?x)
+ https?://(?:beta\.|www\.)?crunchyroll\.com/
+ (?:(?P<lang>\w{2}(?:-\w{2})?)/)?
+ watch/(?!concert|musicvideo)(?P<id>\w+)'''
_TESTS = [{
- 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
+ # Premium only
+ 'url': 'https://www.crunchyroll.com/watch/GY2P1Q98Y/to-the-future',
'info_dict': {
- 'id': '645513',
+ 'id': 'GY2P1Q98Y',
'ext': 'mp4',
- 'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
- 'description': 'md5:2d17137920c64f2f49981a7797d275ef',
- 'thumbnail': r're:^https?://.*\.jpg$',
- 'uploader': 'Yomiuri Telecasting Corporation (YTV)',
- 'upload_date': '20131013',
- 'url': 're:(?!.*&)',
- },
- 'params': {
- # rtmp
- 'skip_download': True,
- },
- 'skip': 'Video gone',
- }, {
- 'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
- 'info_dict': {
- 'id': '589804',
- 'ext': 'flv',
- 'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
- 'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
- 'thumbnail': r're:^https?://.*\.jpg$',
- 'uploader': 'Danny Choo Network',
- 'upload_date': '20120213',
- },
- 'params': {
- # rtmp
- 'skip_download': True,
+ 'duration': 1380.241,
+ 'timestamp': 1459632600,
+ 'description': 'md5:a022fbec4fbb023d43631032c91ed64b',
+ 'title': 'World Trigger Episode 73 – To the Future',
+ 'upload_date': '20160402',
+ 'series': 'World Trigger',
+ 'series_id': 'GR757DMKY',
+ 'season': 'World Trigger',
+ 'season_id': 'GR9P39NJ6',
+ 'season_number': 1,
+ 'episode': 'To the Future',
+ 'episode_number': 73,
+ 'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
+ 'chapters': 'count:2',
+ 'age_limit': 14,
+ 'like_count': int,
+ 'dislike_count': int,
},
- 'skip': 'Video gone',
+ 'params': {'skip_download': 'm3u8', 'format': 'all[format_id~=hardsub]'},
}, {
- 'url': 'http://www.crunchyroll.com/rezero-starting-life-in-another-world-/episode-5-the-morning-of-our-promise-is-still-distant-702409',
+ # Premium only
+ 'url': 'https://www.crunchyroll.com/watch/GYE5WKQGR',
'info_dict': {
- 'id': '702409',
+ 'id': 'GYE5WKQGR',
'ext': 'mp4',
- 'title': compat_str,
- 'description': compat_str,
- 'thumbnail': r're:^https?://.*\.jpg$',
- 'uploader': 'Re:Zero Partners',
- 'timestamp': 1462098900,
- 'upload_date': '20160501',
- },
- 'params': {
- # m3u8 download
- 'skip_download': True,
+ 'duration': 366.459,
+ 'timestamp': 1476788400,
+ 'description': 'md5:74b67283ffddd75f6e224ca7dc031e76',
+ 'title': 'SHELTER – Porter Robinson presents Shelter the Animation',
+ 'upload_date': '20161018',
+ 'series': 'SHELTER',
+ 'series_id': 'GYGG09WWY',
+ 'season': 'SHELTER',
+ 'season_id': 'GR09MGK4R',
+ 'season_number': 1,
+ 'episode': 'Porter Robinson presents Shelter the Animation',
+ 'episode_number': 0,
+ 'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
+ 'age_limit': 14,
+ 'like_count': int,
+ 'dislike_count': int,
},
+ 'params': {'skip_download': True},
}, {
- 'url': 'http://www.crunchyroll.com/konosuba-gods-blessing-on-this-wonderful-world/episode-1-give-me-deliverance-from-this-judicial-injustice-727589',
+ 'url': 'https://www.crunchyroll.com/watch/GJWU2VKK3/cherry-blossom-meeting-and-a-coming-blizzard',
'info_dict': {
- 'id': '727589',
+ 'id': 'GJWU2VKK3',
'ext': 'mp4',
- 'title': compat_str,
- 'description': compat_str,
- 'thumbnail': r're:^https?://.*\.jpg$',
- 'uploader': 'Kadokawa Pictures Inc.',
- 'timestamp': 1484130900,
- 'upload_date': '20170111',
- 'series': compat_str,
- 'season': "KONOSUBA -God's blessing on this wonderful world! 2",
- 'season_number': 2,
- 'episode': 'Give Me Deliverance From This Judicial Injustice!',
+ 'duration': 1420.054,
+ 'description': 'md5:2d1c67c0ec6ae514d9c30b0b99a625cd',
+ 'title': 'The Ice Guy and His Cool Female Colleague Episode 1 – Cherry Blossom Meeting and a Coming Blizzard',
+ 'series': 'The Ice Guy and His Cool Female Colleague',
+ 'series_id': 'GW4HM75NP',
+ 'season': 'The Ice Guy and His Cool Female Colleague',
+ 'season_id': 'GY9PC21VE',
+ 'season_number': 1,
+ 'episode': 'Cherry Blossom Meeting and a Coming Blizzard',
'episode_number': 1,
+ 'chapters': 'count:2',
+ 'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
+ 'timestamp': 1672839000,
+ 'upload_date': '20230104',
+ 'age_limit': 14,
+ 'like_count': int,
+ 'dislike_count': int,
},
- 'params': {
- # m3u8 download
- 'skip_download': True,
- },
- }, {
- 'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
- 'only_matching': True,
- }, {
- # geo-restricted (US), 18+ maturity wall, non-premium available
- 'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617',
- 'only_matching': True,
- }, {
- # A description with double quotes
- 'url': 'http://www.crunchyroll.com/11eyes/episode-1-piros-jszaka-red-night-535080',
- 'info_dict': {
- 'id': '535080',
- 'ext': 'mp4',
- 'title': compat_str,
- 'description': compat_str,
- 'uploader': 'Marvelous AQL Inc.',
- 'timestamp': 1255512600,
- 'upload_date': '20091014',
- },
- 'params': {
- # Just test metadata extraction
- 'skip_download': True,
- },
+ 'params': {'skip_download': 'm3u8'},
}, {
- # make sure we can extract an uploader name that's not a link
- 'url': 'http://www.crunchyroll.com/hakuoki-reimeiroku/episode-1-dawn-of-the-divine-warriors-606899',
+ 'url': 'https://www.crunchyroll.com/watch/GM8F313NQ',
'info_dict': {
- 'id': '606899',
+ 'id': 'GM8F313NQ',
'ext': 'mp4',
- 'title': 'Hakuoki Reimeiroku Episode 1 – Dawn of the Divine Warriors',
- 'description': 'Ryunosuke was left to die, but Serizawa-san asked him a simple question "Do you want to live?"',
- 'uploader': 'Geneon Entertainment',
- 'upload_date': '20120717',
+ 'title': 'Garakowa -Restore the World-',
+ 'description': 'md5:8d2f8b6b9dd77d87810882e7d2ee5608',
+ 'duration': 3996.104,
+ 'age_limit': 13,
+ 'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
},
- 'params': {
- # just test metadata extraction
- 'skip_download': True,
- },
- 'skip': 'Video gone',
+ 'params': {'skip_download': 'm3u8'},
}, {
- # A video with a vastly different season name compared to the series name
- 'url': 'http://www.crunchyroll.com/nyarko-san-another-crawling-chaos/episode-1-test-590532',
+ 'url': 'https://www.crunchyroll.com/watch/G62PEZ2E6',
'info_dict': {
- 'id': '590532',
- 'ext': 'mp4',
- 'title': compat_str,
- 'description': compat_str,
- 'uploader': 'TV TOKYO',
- 'timestamp': 1330956000,
- 'upload_date': '20120305',
- 'series': 'Nyarko-san: Another Crawling Chaos',
- 'season': 'Haiyoru! Nyaruani (ONA)',
- },
- 'params': {
- # Just test metadata extraction
- 'skip_download': True,
+ 'id': 'G62PEZ2E6',
+ 'description': 'md5:8d2f8b6b9dd77d87810882e7d2ee5608',
+ 'age_limit': 13,
+ 'duration': 65.138,
+ 'title': 'Garakowa -Restore the World-',
},
+ 'playlist_mincount': 5,
}, {
- 'url': 'http://www.crunchyroll.com/media-723735',
+ 'url': 'https://www.crunchyroll.com/de/watch/GY2P1Q98Y',
'only_matching': True,
}, {
- 'url': 'https://www.crunchyroll.com/en-gb/mob-psycho-100/episode-2-urban-legends-encountering-rumors-780921',
+ 'url': 'https://beta.crunchyroll.com/pt-br/watch/G8WUN8VKP/the-ruler-of-conspiracy',
'only_matching': True,
}]
+ # We want to support lazy playlist filtering and movie listings cannot be inside a playlist
+ _RETURN_TYPE = 'video'
- _FORMAT_IDS = {
- '360': ('60', '106'),
- '480': ('61', '106'),
- '720': ('62', '106'),
- '1080': ('80', '108'),
- }
+ def _real_extract(self, url):
+ lang, internal_id = self._match_valid_url(url).group('lang', 'id')
- def _download_webpage(self, url_or_request, *args, **kwargs):
- request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
- else sanitized_Request(url_or_request))
- # Accept-Language must be set explicitly to accept any language to avoid issues
- # similar to https://github.com/ytdl-org/youtube-dl/issues/6797.
- # Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
- # should be imposed or not (from what I can see it just takes the first language
- # ignoring the priority and requires it to correspond the IP). By the way this causes
- # Crunchyroll to not work in georestriction cases in some browsers that don't place
- # the locale lang first in header. However allowing any language seems to workaround the issue.
- request.add_header('Accept-Language', '*')
- return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)
-
- def _decrypt_subtitles(self, data, iv, id):
- data = bytes_to_intlist(compat_b64decode(data))
- iv = bytes_to_intlist(compat_b64decode(iv))
- id = int(id)
-
- def obfuscate_key_aux(count, modulo, start):
- output = list(start)
- for _ in range(count):
- output.append(output[-1] + output[-2])
- # cut off start values
- output = output[2:]
- output = list(map(lambda x: x % modulo + 33, output))
- return output
-
- def obfuscate_key(key):
- num1 = int(floor(pow(2, 25) * sqrt(6.9)))
- num2 = (num1 ^ key) << 5
- num3 = key ^ num1
- num4 = num3 ^ (num3 >> 3) ^ num2
- prefix = intlist_to_bytes(obfuscate_key_aux(20, 97, (1, 2)))
- shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
- # Extend 160 Bit hash to 256 Bit
- return shaHash + [0] * 12
-
- key = obfuscate_key(id)
-
- decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
- return zlib.decompress(decrypted_data)
-
- def _convert_subtitles_to_srt(self, sub_root):
- output = ''
-
- for i, event in enumerate(sub_root.findall('./events/event'), 1):
- start = event.attrib['start'].replace('.', ',')
- end = event.attrib['end'].replace('.', ',')
- text = event.attrib['text'].replace('\\N', '\n')
- output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
- return output
-
- def _convert_subtitles_to_ass(self, sub_root):
- output = ''
-
- def ass_bool(strvalue):
- assvalue = '0'
- if strvalue == '1':
- assvalue = '-1'
- return assvalue
-
- output = '[Script Info]\n'
- output += 'Title: %s\n' % sub_root.attrib['title']
- output += 'ScriptType: v4.00+\n'
- output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style']
- output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x']
- output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y']
- output += """
-[V4+ Styles]
-Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
-"""
- for style in sub_root.findall('./styles/style'):
- output += 'Style: ' + style.attrib['name']
- output += ',' + style.attrib['font_name']
- output += ',' + style.attrib['font_size']
- output += ',' + style.attrib['primary_colour']
- output += ',' + style.attrib['secondary_colour']
- output += ',' + style.attrib['outline_colour']
- output += ',' + style.attrib['back_colour']
- output += ',' + ass_bool(style.attrib['bold'])
- output += ',' + ass_bool(style.attrib['italic'])
- output += ',' + ass_bool(style.attrib['underline'])
- output += ',' + ass_bool(style.attrib['strikeout'])
- output += ',' + style.attrib['scale_x']
- output += ',' + style.attrib['scale_y']
- output += ',' + style.attrib['spacing']
- output += ',' + style.attrib['angle']
- output += ',' + style.attrib['border_style']
- output += ',' + style.attrib['outline']
- output += ',' + style.attrib['shadow']
- output += ',' + style.attrib['alignment']
- output += ',' + style.attrib['margin_l']
- output += ',' + style.attrib['margin_r']
- output += ',' + style.attrib['margin_v']
- output += ',' + style.attrib['encoding']
- output += '\n'
-
- output += """
-[Events]
-Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
-"""
- for event in sub_root.findall('./events/event'):
- output += 'Dialogue: 0'
- output += ',' + event.attrib['start']
- output += ',' + event.attrib['end']
- output += ',' + event.attrib['style']
- output += ',' + event.attrib['name']
- output += ',' + event.attrib['margin_l']
- output += ',' + event.attrib['margin_r']
- output += ',' + event.attrib['margin_v']
- output += ',' + event.attrib['effect']
- output += ',' + event.attrib['text']
- output += '\n'
-
- return output
-
- def _extract_subtitles(self, subtitle):
- sub_root = compat_etree_fromstring(subtitle)
- return [{
- 'ext': 'srt',
- 'data': self._convert_subtitles_to_srt(sub_root),
- }, {
- 'ext': 'ass',
- 'data': self._convert_subtitles_to_ass(sub_root),
- }]
-
- def _get_subtitles(self, video_id, webpage):
- subtitles = {}
- for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage):
- sub_doc = self._call_rpc_api(
- 'Subtitle_GetXml', video_id,
- 'Downloading subtitles for ' + sub_name, data={
- 'subtitle_script_id': sub_id,
- })
- if not isinstance(sub_doc, compat_etree_Element):
- continue
- sid = sub_doc.get('id')
- iv = xpath_text(sub_doc, 'iv', 'subtitle iv')
- data = xpath_text(sub_doc, 'data', 'subtitle data')
- if not sid or not iv or not data:
- continue
- subtitle = self._decrypt_subtitles(data, iv, sid).decode('utf-8')
- lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
- if not lang_code:
- continue
- subtitles[lang_code] = self._extract_subtitles(subtitle)
- return subtitles
+ # 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)
- def _real_extract(self, url):
- mobj = self._match_valid_url(url)
- video_id = mobj.group('id')
+ object_type = response.get('type')
+ if object_type == 'episode':
+ result = self._transform_episode_response(response)
+
+ elif object_type == 'movie':
+ result = self._transform_movie_response(response)
+
+ 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))
- if mobj.group('prefix') == 'm':
- mobile_webpage = self._download_webpage(url, video_id, 'Downloading mobile webpage')
- webpage_url = self._search_regex(r'<link rel="canonical" href="([^"]+)" />', mobile_webpage, 'webpage_url')
else:
- webpage_url = 'http://www.' + mobj.group('url')
-
- webpage = self._download_webpage(
- self._add_skip_wall(webpage_url), video_id,
- headers=self.geo_verification_headers())
- note_m = self._html_search_regex(
- r'<div class="showmedia-trailer-notice">(.+?)</div>',
- webpage, 'trailer-notice', default='')
- if note_m:
- raise ExtractorError(note_m, expected=True)
-
- mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage)
- if mobj:
- msg = json.loads(mobj.group('msg'))
- if msg.get('type') == 'error':
- raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)
-
- if 'To view this, please log in to verify you are 18 or older.' in webpage:
- self.raise_login_required()
-
- media = self._parse_json(self._search_regex(
- r'vilos\.config\.media\s*=\s*({.+?});',
- webpage, 'vilos media', default='{}'), video_id)
- media_metadata = media.get('metadata') or {}
-
- language = self._search_regex(
- r'(?:vilos\.config\.player\.language|LOCALE)\s*=\s*(["\'])(?P<lang>(?:(?!\1).)+)\1',
- webpage, 'language', default=None, group='lang')
-
- video_title = self._html_search_regex(
- (r'(?s)<h1[^>]*>((?:(?!<h1).)*?<(?:span[^>]+itemprop=["\']title["\']|meta[^>]+itemprop=["\']position["\'])[^>]*>(?:(?!<h1).)+?)</h1>',
- r'<title>(.+?),\s+-\s+.+? Crunchyroll'),
- webpage, 'video_title', default=None)
- if not video_title:
- video_title = re.sub(r'^Watch\s+', '', self._og_search_description(webpage))
- video_title = re.sub(r' {2,}', ' ', video_title)
- video_description = (self._parse_json(self._html_search_regex(
- r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id,
- webpage, 'description', default='{}'), video_id) or media_metadata).get('description')
-
- thumbnails = []
- thumbnail_url = (self._parse_json(self._html_search_regex(
- r'<script type="application\/ld\+json">\n\s*(.+?)<\/script>',
- webpage, 'thumbnail_url', default='{}'), video_id)).get('image')
- if thumbnail_url:
- thumbnails.append({
- 'url': thumbnail_url,
- 'width': 1920,
- 'height': 1080
- })
+ raise ExtractorError(f'Unknown object type {object_type}')
+
+ # 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)
+
+ # if no intro chapter is available, a 403 without usable data is returned
+ 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)
+ if isinstance(intro_chapter, dict):
+ result['chapters'] = [{
+ 'title': 'Intro',
+ 'start_time': float_or_none(intro_chapter.get('startTime')),
+ 'end_time': float_or_none(intro_chapter.get('endTime')),
+ }]
+
+ 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
- if video_description:
- video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
- video_uploader = self._html_search_regex(
- # try looking for both an uploader that's a link and one that's not
- [r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', r'<div>\s*Publisher:\s*<span>\s*(.+?)\s*</span>\s*</div>'],
- webpage, 'video_uploader', default=False)
+ @staticmethod
+ def _transform_episode_response(data):
+ metadata = traverse_obj(data, (('episode_metadata', None), {dict}), get_all=False) or {}
+ return {
+ '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),
+ }
- formats = []
- for stream in media.get('streams', []):
- audio_lang = stream.get('audio_lang')
- hardsub_lang = stream.get('hardsub_lang')
- vrv_formats = self._extract_vrv_formats(
- stream.get('url'), video_id, stream.get('format'),
- audio_lang, hardsub_lang)
- for f in vrv_formats:
- f['language_preference'] = 1 if audio_lang == language else 0
- f['quality'] = (
- 1 if not hardsub_lang
- else 0 if hardsub_lang == language
- else -1)
- formats.extend(vrv_formats)
- if not formats:
- available_fmts = []
- for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):
- attrs = extract_attributes(a)
- href = attrs.get('href')
- if href and '/freetrial' in href:
- continue
- available_fmts.append(fmt)
- if not available_fmts:
- for p in (r'token=["\']showmedia\.([0-9]{3,4})p"', r'showmedia\.([0-9]{3,4})p'):
- available_fmts = re.findall(p, webpage)
- if available_fmts:
- break
- if not available_fmts:
- available_fmts = self._FORMAT_IDS.keys()
- video_encode_ids = []
-
- for fmt in available_fmts:
- stream_quality, stream_format = self._FORMAT_IDS[fmt]
- video_format = fmt + 'p'
- stream_infos = []
- streamdata = self._call_rpc_api(
- 'VideoPlayer_GetStandardConfig', video_id,
- 'Downloading media info for %s' % video_format, data={
- 'media_id': video_id,
- 'video_format': stream_format,
- 'video_quality': stream_quality,
- 'current_page': url,
- })
- if isinstance(streamdata, compat_etree_Element):
- stream_info = streamdata.find('./{default}preload/stream_info')
- if stream_info is not None:
- stream_infos.append(stream_info)
- stream_info = self._call_rpc_api(
- 'VideoEncode_GetStreamInfo', video_id,
- 'Downloading stream info for %s' % video_format, data={
- 'media_id': video_id,
- 'video_format': stream_format,
- 'video_encode_quality': stream_quality,
- })
- if isinstance(stream_info, compat_etree_Element):
- stream_infos.append(stream_info)
- for stream_info in stream_infos:
- video_encode_id = xpath_text(stream_info, './video_encode_id')
- if video_encode_id in video_encode_ids:
- continue
- video_encode_ids.append(video_encode_id)
-
- video_file = xpath_text(stream_info, './file')
- if not video_file:
- continue
- if video_file.startswith('http'):
- formats.extend(self._extract_m3u8_formats(
- video_file, video_id, 'mp4', entry_protocol='m3u8_native',
- m3u8_id='hls', fatal=False))
- continue
-
- video_url = xpath_text(stream_info, './host')
- if not video_url:
- continue
- metadata = stream_info.find('./metadata')
- format_info = {
- 'format': video_format,
- 'height': int_or_none(xpath_text(metadata, './height')),
- 'width': int_or_none(xpath_text(metadata, './width')),
- }
-
- if '.fplive.net/' in video_url:
- video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip())
- parsed_video_url = compat_urlparse.urlparse(video_url)
- direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
- netloc='v.lvlt.crcdn.net',
- path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))
- if self._is_valid_url(direct_video_url, video_id, video_format):
- format_info.update({
- 'format_id': 'http-' + video_format,
- 'url': direct_video_url,
- })
- formats.append(format_info)
- continue
-
- format_info.update({
- 'format_id': 'rtmp-' + video_format,
- 'url': video_url,
- 'play_path': video_file,
- 'ext': 'flv',
- })
- formats.append(format_info)
- self._sort_formats(formats)
-
- metadata = self._call_rpc_api(
- 'VideoPlayer_GetMediaMetadata', video_id,
- note='Downloading media info', data={
- 'media_id': video_id,
- })
+ @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}),
+ }),
+ }
- subtitles = {}
- for subtitle in media.get('subtitles', []):
- subtitle_url = subtitle.get('url')
- if not subtitle_url:
- continue
- subtitles.setdefault(subtitle.get('language', 'enUS'), []).append({
- 'url': subtitle_url,
- 'ext': subtitle.get('format', 'ass'),
- })
- if not subtitles:
- subtitles = self.extract_subtitles(video_id, webpage)
-
- # webpage provide more accurate data than series_title from XML
- series = self._html_search_regex(
- r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d',
- webpage, 'series', fatal=False)
-
- season = episode = episode_number = duration = None
-
- if isinstance(metadata, compat_etree_Element):
- season = xpath_text(metadata, 'series_title')
- episode = xpath_text(metadata, 'episode_title')
- episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
- duration = float_or_none(media_metadata.get('duration'), 1000)
-
- if not episode:
- episode = media_metadata.get('title')
- if not episode_number:
- episode_number = int_or_none(media_metadata.get('episode_number'))
- thumbnail_url = try_get(media, lambda x: x['thumbnail']['url'])
- if thumbnail_url:
- thumbnails.append({
- 'url': thumbnail_url,
- 'width': 640,
- 'height': 360
- })
- season_number = int_or_none(self._search_regex(
- r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)',
- webpage, 'season number', default=None))
-
- info = self._search_json_ld(webpage, video_id, default={})
-
- return merge_dicts({
- 'id': video_id,
- 'title': video_title,
- 'description': video_description,
- 'duration': duration,
- 'thumbnails': thumbnails,
- 'uploader': video_uploader,
- 'series': series,
- 'season': season,
- 'season_number': season_number,
- 'episode': episode,
- 'episode_number': episode_number,
- 'subtitles': subtitles,
- 'formats': formats,
- }, info)
-
-
-class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
+class CrunchyrollBetaShowIE(CrunchyrollCmsBaseIE):
IE_NAME = 'crunchyroll:playlist'
- _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:\w{1,2}/)?(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login|media-\d+))(?P<id>[\w\-]+))/?(?:\?|$)'
+ _VALID_URL = r'''(?x)
+ https?://(?:beta\.|www\.)?crunchyroll\.com/
+ (?P<lang>(?:\w{2}(?:-\w{2})?/)?)
+ series/(?P<id>\w+)'''
+ _TESTS = [{
+ 'url': 'https://www.crunchyroll.com/series/GY19NQ2QR/Girl-Friend-BETA',
+ 'info_dict': {
+ 'id': 'GY19NQ2QR',
+ 'title': 'Girl Friend BETA',
+ 'description': 'md5:99c1b22ee30a74b536a8277ced8eb750',
+ # XXX: `thumbnail` does not get set from `thumbnails` in playlist
+ # 'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
+ 'age_limit': 14,
+ },
+ 'playlist_mincount': 10,
+ }, {
+ 'url': 'https://beta.crunchyroll.com/it/series/GY19NQ2QR',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ 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})?/)?)
+ watch/(?P<type>concert|musicvideo)/(?P<id>\w+)'''
_TESTS = [{
- 'url': 'https://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
+ 'url': 'https://www.crunchyroll.com/de/watch/musicvideo/MV5B02C79',
'info_dict': {
- 'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
- 'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
+ '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?$',
+ 'genre': ['J-Pop'],
},
- 'playlist_count': 13,
+ 'params': {'skip_download': 'm3u8'},
}, {
- # geo-restricted (US), 18+ maturity wall, non-premium available
- 'url': 'http://www.crunchyroll.com/cosplay-complex-ova',
+ 'url': 'https://www.crunchyroll.com/watch/musicvideo/MV88BB7F2C',
'info_dict': {
- 'id': 'cosplay-complex-ova',
- 'title': 'Cosplay Complex OVA'
+ 'ext': 'mp4',
+ 'id': 'MV88BB7F2C',
+ 'display_id': 'crossing-field',
+ 'title': 'Crossing Field',
+ 'track': 'Crossing Field',
+ 'artist': 'LiSA',
+ 'thumbnail': r're:(?i)^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$',
+ 'genre': ['Anime'],
},
- 'playlist_count': 3,
- 'skip': 'Georestricted',
+ 'params': {'skip_download': 'm3u8'},
}, {
- # geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14
- 'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1',
+ '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',
+ 'genre': ['J-Pop'],
+ },
+ 'params': {'skip_download': 'm3u8'},
+ }, {
+ 'url': 'https://www.crunchyroll.com/de/watch/musicvideo/MV5B02C79/egaono-hana',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.crunchyroll.com/watch/concert/MC2E2AC135/live-is-smile-always-364joker-at-yokohama-arena',
'only_matching': True,
}, {
- 'url': 'http://www.crunchyroll.com/fr/ladies-versus-butlers',
+ 'url': 'https://www.crunchyroll.com/watch/musicvideo/MV88BB7F2C/crossing-field',
'only_matching': True,
}]
+ _API_ENDPOINT = 'music'
def _real_extract(self, url):
- show_id = self._match_id(url)
-
- webpage = self._download_webpage(
- # https:// gives a 403, but http:// does not
- self._add_skip_wall(url).replace('https://', 'http://'), show_id,
- headers=self.geo_verification_headers())
- title = self._html_search_meta('name', webpage, default=None)
-
- episode_paths = re.findall(
- r'(?s)<li id="showview_videos_media_(\d+)"[^>]+>.*?<a href="([^"]+)"',
- webpage)
- entries = [
- self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll', ep_id)
- for ep_id, ep in episode_paths
- ]
- entries.reverse()
+ 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)
+
+ 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 {
- '_type': 'playlist',
- 'id': show_id,
- 'title': title,
- 'entries': entries,
+ '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}),
+ }),
+ 'genre': ('genres', ..., 'displayValue'),
+ 'age_limit': ('maturity_ratings', -1, {parse_age_limit}),
+ }),
}
-class CrunchyrollBetaIE(CrunchyrollBaseIE):
- IE_NAME = 'crunchyroll:beta'
- _VALID_URL = r'https?://beta\.crunchyroll\.com/(?P<lang>(?:\w{1,2}/)?)watch/(?P<internal_id>\w+)/(?P<id>[\w\-]+)/?(?:\?|$)'
+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://beta.crunchyroll.com/watch/GY2P1Q98Y/to-the-future',
+ 'url': 'https://www.crunchyroll.com/artist/MA179CB50D',
'info_dict': {
- 'id': '696363',
- 'ext': 'mp4',
- 'timestamp': 1459610100,
- 'description': 'md5:a022fbec4fbb023d43631032c91ed64b',
- 'uploader': 'Toei Animation',
- 'title': 'World Trigger Episode 73 – To the Future',
- 'upload_date': '20160402',
+ 'id': 'MA179CB50D',
+ 'title': 'LiSA',
+ 'genre': ['J-Pop', 'Anime', 'Rock'],
+ 'description': 'md5:16d87de61a55c3f7d6c454b73285938e',
},
- 'params': {'skip_download': 'm3u8'},
- 'expected_warnings': ['Unable to download XML']
- }]
-
- def _real_extract(self, url):
- lang, internal_id, display_id = self._match_valid_url(url).group('lang', 'internal_id', 'id')
- webpage = self._download_webpage(url, display_id)
- episode_data = self._parse_json(
- self._search_regex(r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'episode data'),
- display_id)['content']['byId'][internal_id]
- video_id = episode_data['external_id'].split('.')[1]
- series_id = episode_data['episode_metadata']['series_slug_title']
- return self.url_result(f'https://www.crunchyroll.com/{lang}{series_id}/{display_id}-{video_id}',
- CrunchyrollIE.ie_key(), video_id)
-
-
-class CrunchyrollBetaShowIE(CrunchyrollBaseIE):
- IE_NAME = 'crunchyroll:playlist:beta'
- _VALID_URL = r'https?://beta\.crunchyroll\.com/(?P<lang>(?:\w{1,2}/)?)series/\w+/(?P<id>[\w\-]+)/?(?:\?|$)'
- _TESTS = [{
- 'url': 'https://beta.crunchyroll.com/series/GY19NQ2QR/Girl-Friend-BETA',
- 'info_dict': {
- 'id': 'girl-friend-beta',
- 'title': 'Girl Friend BETA',
- },
- 'playlist_mincount': 10,
+ 'playlist_mincount': 83,
}, {
- 'url': 'https://beta.crunchyroll.com/it/series/GY19NQ2QR/Girl-Friend-BETA',
+ 'url': 'https://www.crunchyroll.com/artist/MA179CB50D/lisa',
'only_matching': True,
}]
+ _API_ENDPOINT = 'music'
def _real_extract(self, url):
- lang, series_id = self._match_valid_url(url).group('lang', 'id')
- return self.url_result(f'https://www.crunchyroll.com/{lang}{series_id.lower()}',
- CrunchyrollShowPlaylistIE.ie_key(), series_id)
+ 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))
+
+ def entries():
+ 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}),
+ }),
+ 'genre': ('genres', ..., 'displayValue'),
+ }),
+ }