[crunchyroll] Add support for beta.crunchyroll URLs

and fix series URLs with language code
This commit is contained in:
pukkandan 2021-10-17 17:16:05 +05:30
parent 71ce444a3f
commit dd078970ba
No known key found for this signature in database
GPG key ID: 0F00D95A001F4698
2 changed files with 58 additions and 2 deletions

View file

@ -650,7 +650,7 @@ def _real_extract(self, url):
class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE): class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
IE_NAME = 'crunchyroll:playlist' IE_NAME = 'crunchyroll:playlist'
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login|media-\d+))(?P<id>[\w\-]+))/?(?:\?|$)' _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:\w{1,2}/)?(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login|media-\d+))(?P<id>[\w\-]+))/?(?:\?|$)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', 'url': 'https://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
@ -672,6 +672,9 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
# geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14 # 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': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1',
'only_matching': True, 'only_matching': True,
}, {
'url': 'http://www.crunchyroll.com/fr/ladies-versus-butlers',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -698,3 +701,54 @@ def _real_extract(self, url):
'title': title, 'title': title,
'entries': entries, 'entries': entries,
} }
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\-]+)/?(?:\?|$)'
_TESTS = [{
'url': 'https://beta.crunchyroll.com/watch/GY2P1Q98Y/to-the-future',
'info_dict': {
'id': '696363',
'ext': 'mp4',
'timestamp': 1459610100,
'description': 'md5:a022fbec4fbb023d43631032c91ed64b',
'uploader': 'Toei Animation',
'title': 'World Trigger Episode 73 To the Future',
'upload_date': '20160402',
},
'params': {'skip_download': 'm3u8'},
'expected_warnings': ['Unable to download XML']
}]
def _real_extract(self, url):
lang, internal_id, display_id = self._match_valid_url(url).group('lang', 'internal_id', 'id')
webpage = self._download_webpage(url, display_id)
episode_data = self._parse_json(
self._search_regex(r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'episode data'),
display_id)['content']['byId'][internal_id]
video_id = episode_data['external_id'].split('.')[1]
series_id = episode_data['episode_metadata']['series_slug_title']
return self.url_result(f'https://www.crunchyroll.com/{lang}{series_id}/{display_id}-{video_id}',
CrunchyrollIE.ie_key(), video_id)
class CrunchyrollBetaShowIE(CrunchyrollBaseIE):
IE_NAME = 'crunchyroll:playlist:beta'
_VALID_URL = r'https?://beta\.crunchyroll\.com/(?P<lang>(?:\w{1,2}/)?)series/\w+/(?P<id>[\w\-]+)/?(?:\?|$)'
_TESTS = [{
'url': 'https://beta.crunchyroll.com/series/GY19NQ2QR/Girl-Friend-BETA',
'info_dict': {
'id': 'girl-friend-beta',
'title': 'Girl Friend BETA',
},
'playlist_mincount': 10,
}, {
'url': 'https://beta.crunchyroll.com/it/series/GY19NQ2QR/Girl-Friend-BETA',
'only_matching': True,
}]
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)

View file

@ -298,7 +298,9 @@
from .crooksandliars import CrooksAndLiarsIE from .crooksandliars import CrooksAndLiarsIE
from .crunchyroll import ( from .crunchyroll import (
CrunchyrollIE, CrunchyrollIE,
CrunchyrollShowPlaylistIE CrunchyrollShowPlaylistIE,
CrunchyrollBetaIE,
CrunchyrollBetaShowIE,
) )
from .cspan import CSpanIE from .cspan import CSpanIE
from .ctsnews import CtsNewsIE from .ctsnews import CtsNewsIE