from ..compat import compat_HTTPError
from ..utils import (
determine_ext,
- dict_get,
int_or_none,
+ join_nonempty,
js_to_json,
+ orderedSet,
+ qualities,
str_or_none,
+ traverse_obj,
try_get,
urlencode_postdata,
ExtractorError,
)
-class FunimationPageIE(InfoExtractor):
+class FunimationBaseIE(InfoExtractor):
+ _NETRC_MACHINE = 'funimation'
+ _REGION = None
+ _TOKEN = None
+
+ def _get_region(self):
+ region_cookie = self._get_cookies('https://www.funimation.com').get('region')
+ region = region_cookie.value if region_cookie else self.get_param('geo_bypass_country')
+ return region or traverse_obj(
+ self._download_json(
+ 'https://geo-service.prd.funimationsvc.com/geo/v1/region/check', None, fatal=False,
+ note='Checking geo-location', errnote='Unable to fetch geo-location information'),
+ 'region') or 'US'
+
+ def _login(self):
+ username, password = self._get_login_info()
+ if username is None:
+ return
+ try:
+ data = self._download_json(
+ 'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
+ None, 'Logging in', data=urlencode_postdata({
+ 'username': username,
+ 'password': password,
+ }))
+ return data['token']
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+ error = self._parse_json(e.cause.read().decode(), None)['error']
+ raise ExtractorError(error, expected=True)
+ raise
+
+
+class FunimationPageIE(FunimationBaseIE):
IE_NAME = 'funimation:page'
- _VALID_URL = r'(?P<origin>https?://(?:www\.)?funimation(?:\.com|now\.uk))/(?P<lang>[^/]+/)?(?P<path>shows/(?P<id>[^/]+/[^/?#&]+).*$)'
+ _VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?:(?P<lang>[^/]+)/)?(?:shows|v)/(?P<show>[^/]+)/(?P<episode>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
}, {
'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
'only_matching': True,
+ }, {
+ 'url': 'https://www.funimation.com/v/a-certain-scientific-railgun/super-powered-level-5',
+ 'only_matching': True,
}]
+ def _real_initialize(self):
+ if not self._REGION:
+ FunimationBaseIE._REGION = self._get_region()
+ if not self._TOKEN:
+ FunimationBaseIE._TOKEN = self._login()
+
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- display_id = mobj.group('id').replace('/', '_')
- if not mobj.group('lang'):
- url = '%s/en/%s' % (mobj.group('origin'), mobj.group('path'))
-
- webpage = self._download_webpage(url, display_id)
- title_data = self._parse_json(self._search_regex(
- r'TITLE_DATA\s*=\s*({[^}]+})',
- webpage, 'title data', default=''),
- display_id, js_to_json, fatal=False) or {}
-
- video_id = (
- title_data.get('id')
- or self._search_regex(
- (r"KANE_customdimensions.videoID\s*=\s*'(\d+)';", r'<iframe[^>]+src="/player/(\d+)'),
- webpage, 'video_id', default=None)
- or self._search_regex(
- r'/player/(\d+)',
- self._html_search_meta(['al:web:url', 'og:video:url', 'og:video:secure_url'], webpage, fatal=True),
- 'video id'))
+ locale, show, episode = self._match_valid_url(url).group('lang', 'show', 'episode')
+
+ video_id = traverse_obj(self._download_json(
+ f'https://title-api.prd.funimationsvc.com/v1/shows/{show}/episodes/{episode}',
+ f'{show}_{episode}', query={
+ 'deviceType': 'web',
+ 'region': self._REGION,
+ 'locale': locale or 'en'
+ }), ('videoList', ..., 'id'), get_all=False)
+
return self.url_result(f'https://www.funimation.com/player/{video_id}', FunimationIE.ie_key(), video_id)
-class FunimationIE(InfoExtractor):
+class FunimationIE(FunimationBaseIE):
_VALID_URL = r'https?://(?:www\.)?funimation\.com/player/(?P<id>\d+)'
- _NETRC_MACHINE = 'funimation'
- _TOKEN = None
-
_TESTS = [{
'url': 'https://www.funimation.com/player/210051',
'info_dict': {
'season_number': 99,
'series': 'Attack on Titan: Junior High',
'description': '',
- 'duration': 154,
+ 'duration': 155,
},
'params': {
'skip_download': 'm3u8',
'season_number': 99,
'series': 'Attack on Titan: Junior High',
'description': '',
- 'duration': 154,
+ 'duration': 155,
},
'params': {
'skip_download': 'm3u8',
},
}]
- def _login(self):
- username, password = self._get_login_info()
- if username is None:
- return
- try:
- data = self._download_json(
- 'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
- None, 'Logging in', data=urlencode_postdata({
- 'username': username,
- 'password': password,
- }))
- self._TOKEN = data['token']
- except ExtractorError as e:
- if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
- error = self._parse_json(e.cause.read().decode(), None)['error']
- raise ExtractorError(error, expected=True)
- raise
-
def _real_initialize(self):
- self._login()
+ if not self._TOKEN:
+ FunimationBaseIE._TOKEN = self._login()
@staticmethod
def _get_experiences(episode):
formats, subtitles, thumbnails, duration = [], {}, [], 0
requested_languages, requested_versions = self._configuration_arg('language'), self._configuration_arg('version')
+ language_preference = qualities((requested_languages or [''])[::-1])
+ source_preference = qualities((requested_versions or ['uncut', 'simulcast'])[::-1])
only_initial_experience = 'seperate-video-versions' in self.get_param('compat_opts', [])
for lang, version, fmt in self._get_experiences(episode):
experience_id = str(fmt['experienceId'])
if (only_initial_experience and experience_id != initial_experience_id
- or requested_languages and lang not in requested_languages
- or requested_versions and version not in requested_versions):
+ or requested_languages and lang.lower() not in requested_languages
+ or requested_versions and version.lower() not in requested_versions):
continue
thumbnails.append({'url': fmt.get('poster')})
duration = max(duration, fmt.get('duration', 0))
})
for f in current_formats:
# TODO: Convert language to code
- f.update({'language': lang, 'format_note': version})
+ f.update({
+ 'language': lang,
+ 'format_note': version,
+ 'source_preference': source_preference(version.lower()),
+ 'language_preference': language_preference(lang.lower()),
+ })
formats.extend(current_formats)
self._remove_duplicate_formats(formats)
- self._sort_formats(formats)
+ self._sort_formats(formats, ('lang', 'source'))
return {
'id': initial_experience_id if only_initial_experience else episode_id,
def _get_subtitles(self, subtitles, experience_id, episode, display_id, format_name):
if isinstance(episode, str):
webpage = self._download_webpage(
- f'https://www.funimation.com/player/{experience_id}', display_id,
+ f'https://www.funimation.com/player/{experience_id}/', display_id,
fatal=False, note=f'Downloading player webpage for {format_name}')
episode, _, _ = self._get_episode(webpage, episode_id=episode, fatal=False)
sub_type = sub_type if sub_type != 'FULL' else None
current_sub = {
'url': text_track['src'],
- 'name': ' '.join(filter(None, (version, text_track.get('label'), sub_type)))
+ 'name': join_nonempty(version, text_track.get('label'), sub_type, delim=' ')
}
- lang = '_'.join(filter(None, (
- text_track.get('language', 'und'), version if version != 'Simulcast' else None, sub_type)))
+ lang = join_nonempty(text_track.get('language', 'und'),
+ version if version != 'Simulcast' else None,
+ sub_type, delim='_')
if current_sub not in subtitles.get(lang, []):
subtitles.setdefault(lang, []).append(current_sub)
return subtitles
-class FunimationShowIE(FunimationIE):
+class FunimationShowIE(FunimationBaseIE):
IE_NAME = 'funimation:show'
_VALID_URL = r'(?P<url>https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?P<locale>[^/]+)?/?shows/(?P<id>[^/?#&]+))/?(?:[?#]|$)'
},
}]
+ def _real_initialize(self):
+ if not self._REGION:
+ FunimationBaseIE._REGION = self._get_region()
+
def _real_extract(self, url):
- base_url, locale, display_id = re.match(self._VALID_URL, url).groups()
+ base_url, locale, display_id = self._match_valid_url(url).groups()
show_info = self._download_json(
- 'https://title-api.prd.funimationsvc.com/v2/shows/%s?region=US&deviceType=web&locale=%s'
- % (display_id, locale or 'en'), display_id)
- items = self._download_json(
+ 'https://title-api.prd.funimationsvc.com/v2/shows/%s?region=%s&deviceType=web&locale=%s'
+ % (display_id, self._REGION, locale or 'en'), display_id)
+ items_info = self._download_json(
'https://prod-api-funimationnow.dadcdigital.com/api/funimation/episodes/?limit=99999&title_id=%s'
- % show_info.get('id'), display_id).get('items')
- vod_items = map(lambda k: dict_get(k, ('mostRecentSvod', 'mostRecentAvod')).get('item'), items)
+ % show_info.get('id'), display_id)
+
+ vod_items = traverse_obj(items_info, ('items', ..., re.compile('(?i)mostRecent[AS]vod').match, 'item'))
return {
'_type': 'playlist',
'id': show_info['id'],
'title': show_info['name'],
- 'entries': [
+ 'entries': orderedSet(
self.url_result(
'%s/%s' % (base_url, vod_item.get('episodeSlug')), FunimationPageIE.ie_key(),
vod_item.get('episodeId'), vod_item.get('episodeName'))
- for vod_item in sorted(vod_items, key=lambda x: x.get('episodeOrder'))],
+ for vod_item in sorted(vod_items, key=lambda x: x.get('episodeOrder', -1))),
}