[ie/tubitv:series] Fix extractor (#10116)

Closes #8563
Authored by: bashonly
This commit is contained in:
bashonly 2024-06-13 16:59:17 -05:00 committed by GitHub
parent 46c1b7cfec
commit d7d861811c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 41 additions and 16 deletions

View File

@ -13,6 +13,7 @@
class TubiTvIE(InfoExtractor): class TubiTvIE(InfoExtractor):
IE_NAME = 'tubitv'
_VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?P<type>video|movies|tv-shows)/(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?P<type>video|movies|tv-shows)/(?P<id>\d+)'
_LOGIN_URL = 'http://tubitv.com/login' _LOGIN_URL = 'http://tubitv.com/login'
_NETRC_MACHINE = 'tubitv' _NETRC_MACHINE = 'tubitv'
@ -148,30 +149,54 @@ def _real_extract(self, url):
class TubiTvShowIE(InfoExtractor): class TubiTvShowIE(InfoExtractor):
_WORKING = False IE_NAME = 'tubitv:series'
_VALID_URL = r'https?://(?:www\.)?tubitv\.com/series/[0-9]+/(?P<show_name>[^/?#]+)' _VALID_URL = r'https?://(?:www\.)?tubitv\.com/series/\d+/(?P<show_name>[^/?#]+)(?:/season-(?P<season>\d+))?'
_TESTS = [{ _TESTS = [{
'url': 'https://tubitv.com/series/3936/the-joy-of-painting-with-bob-ross?start=true', 'url': 'https://tubitv.com/series/3936/the-joy-of-painting-with-bob-ross?start=true',
'playlist_mincount': 390, 'playlist_mincount': 389,
'info_dict': { 'info_dict': {
'id': 'the-joy-of-painting-with-bob-ross', 'id': 'the-joy-of-painting-with-bob-ross',
}, },
}, {
'url': 'https://tubitv.com/series/2311/the-saddle-club/season-1',
'playlist_count': 26,
'info_dict': {
'id': 'the-saddle-club-season-1',
},
}, {
'url': 'https://tubitv.com/series/2311/the-saddle-club/season-3',
'playlist_count': 19,
'info_dict': {
'id': 'the-saddle-club-season-3',
},
}, {
'url': 'https://tubitv.com/series/2311/the-saddle-club/',
'playlist_mincount': 71,
'info_dict': {
'id': 'the-saddle-club',
},
}] }]
def _entries(self, show_url, show_name): def _entries(self, show_url, playlist_id, selected_season):
show_webpage = self._download_webpage(show_url, show_name) webpage = self._download_webpage(show_url, playlist_id)
show_json = self._parse_json(self._search_regex( data = self._search_json(
r'window\.__data\s*=\s*({[^<]+});\s*</script>', r'window\.__data\s*=', webpage, 'data', playlist_id,
show_webpage, 'data'), show_name, transform_source=js_to_json)['video'] transform_source=js_to_json)['video']
for episode_id in show_json['fullContentById']: # v['number'] is already a decimal string, but stringify to protect against API changes
if traverse_obj(show_json, ('byId', episode_id, 'type')) == 's': path = [lambda _, v: str(v['number']) == selected_season] if selected_season else [..., {dict}]
continue
for season in traverse_obj(data, ('byId', lambda _, v: v['type'] == 's', 'seasons', *path)):
season_number = int_or_none(season.get('number'))
for episode in traverse_obj(season, ('episodes', lambda _, v: v['id'])):
episode_id = episode['id']
yield self.url_result( yield self.url_result(
f'https://tubitv.com/tv-shows/{episode_id}/', f'https://tubitv.com/tv-shows/{episode_id}/', TubiTvIE, episode_id,
ie=TubiTvIE.ie_key(), video_id=episode_id) season_number=season_number, episode_number=int_or_none(episode.get('num')))
def _real_extract(self, url): def _real_extract(self, url):
show_name = self._match_valid_url(url).group('show_name') playlist_id, selected_season = self._match_valid_url(url).group('show_name', 'season')
return self.playlist_result(self._entries(url, show_name), playlist_id=show_name) if selected_season:
playlist_id = f'{playlist_id}-season-{selected_season}'
return self.playlist_result(self._entries(url, playlist_id, selected_season), playlist_id)