[nrktv:seriebase] Fix extraction (closes #23625) (#23537)

This commit is contained in:
Roxedus 2020-01-06 00:34:36 +01:00 committed by Sergey M
parent 233826f68f
commit 0d2306d02b

View File

@ -12,6 +12,7 @@ from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
JSON_LD_RE, JSON_LD_RE,
js_to_json,
NO_DEFAULT, NO_DEFAULT,
parse_age_limit, parse_age_limit,
parse_duration, parse_duration,
@ -105,6 +106,7 @@ class NRKBaseIE(InfoExtractor):
MESSAGES = { MESSAGES = {
'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet', 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
'ProgramRightsHasExpired': 'Programmet har gått ut', 'ProgramRightsHasExpired': 'Programmet har gått ut',
'NoProgramRights': 'Ikke tilgjengelig',
'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge', 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
} }
message_type = data.get('messageType', '') message_type = data.get('messageType', '')
@ -255,6 +257,17 @@ class NRKTVIE(NRKBaseIE):
''' % _EPISODE_RE ''' % _EPISODE_RE
_API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no') _API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
_TESTS = [{ _TESTS = [{
'url': 'https://tv.nrk.no/program/MDDP12000117',
'md5': '8270824df46ec629b66aeaa5796b36fb',
'info_dict': {
'id': 'MDDP12000117AA',
'ext': 'mp4',
'title': 'Alarm Trolltunga',
'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
'duration': 2223,
'age_limit': 6,
},
}, {
'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
'md5': '9a167e54d04671eb6317a37b7bc8a280', 'md5': '9a167e54d04671eb6317a37b7bc8a280',
'info_dict': { 'info_dict': {
@ -266,6 +279,7 @@ class NRKTVIE(NRKBaseIE):
'series': '20 spørsmål', 'series': '20 spørsmål',
'episode': '23.05.2014', 'episode': '23.05.2014',
}, },
'skip': 'NoProgramRights',
}, { }, {
'url': 'https://tv.nrk.no/program/mdfp15000514', 'url': 'https://tv.nrk.no/program/mdfp15000514',
'info_dict': { 'info_dict': {
@ -370,7 +384,24 @@ class NRKTVIE(NRKBaseIE):
class NRKTVEpisodeIE(InfoExtractor): class NRKTVEpisodeIE(InfoExtractor):
_VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/\d+/episode/\d+)' _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/\d+/episode/\d+)'
_TEST = { _TESTS = [{
'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2',
'info_dict': {
'id': 'MUHH36005220BA',
'ext': 'mp4',
'title': 'Kro, krig og kjærlighet 2:6',
'description': 'md5:b32a7dc0b1ed27c8064f58b97bda4350',
'duration': 1563,
'series': 'Hellums kro',
'season_number': 1,
'episode_number': 2,
'episode': '2:6',
'age_limit': 6,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8', 'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8',
'info_dict': { 'info_dict': {
'id': 'MSUI14000816AA', 'id': 'MSUI14000816AA',
@ -386,7 +417,8 @@ class NRKTVEpisodeIE(InfoExtractor):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
} 'skip': 'ProgramRightsHasExpired',
}]
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
@ -409,7 +441,7 @@ class NRKTVSerieBaseIE(InfoExtractor):
(r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;', (r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;',
r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'), r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'),
webpage, 'config', default='{}' if not fatal else NO_DEFAULT), webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
display_id, fatal=False) display_id, fatal=False, transform_source=js_to_json)
if not config: if not config:
return return
return try_get( return try_get(
@ -479,6 +511,14 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
_VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)' _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
_ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)' _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'https://tv.nrk.no/serie/blank',
'info_dict': {
'id': 'blank',
'title': 'Blank',
'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e',
},
'playlist_mincount': 30,
}, {
# new layout, seasons # new layout, seasons
'url': 'https://tv.nrk.no/serie/backstage', 'url': 'https://tv.nrk.no/serie/backstage',
'info_dict': { 'info_dict': {
@ -648,7 +688,7 @@ class NRKSkoleIE(InfoExtractor):
_TESTS = [{ _TESTS = [{
'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099', 'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6', 'md5': '18c12c3d071953c3bf8d54ef6b2587b7',
'info_dict': { 'info_dict': {
'id': '6021', 'id': '6021',
'ext': 'mp4', 'ext': 'mp4',