paradizelost/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[nrktv:series] Improve extraction (closes #21926)

Browse Source
This commit is contained in:
Sergey M․ 2020-12-05 02:43:33 +07:00
parent 02b04785ee
commit 5d769860c3
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 26 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
youtube_dl/extractor/nrk.py
View File

@ -521,7 +521,8 @@ class NRKTVSerieBaseIE(InfoExtractor):
config = self._parse_json( config = self._parse_json(
self._search_regex( self._search_regex(
(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>',
r'PRELOADED_STATE_*\s*=\s*({.+?})\s*\n'),
webpage, 'config', default='{}' if not fatal else NO_DEFAULT), webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
display_id, fatal=False, transform_source=js_to_json) display_id, fatal=False, transform_source=js_to_json)
if not config: if not config:
@ -531,12 +532,26 @@ class NRKTVSerieBaseIE(InfoExtractor):
(lambda x: x['initialState']['series'], lambda x: x['series']), (lambda x: x['initialState']['series'], lambda x: x['series']),
dict) dict)
def _extract_seasons(self, seasons): def _extract_seasons(self, domain, series_id, seasons):
if isinstance(seasons, dict):
seasons = seasons.get('seasons')
if not isinstance(seasons, list): if not isinstance(seasons, list):
return [] return []
entries = [] entries = []
for season in seasons: for season in seasons:
entries.extend(self._extract_episodes(season)) if not isinstance(season, dict):
continue
episodes = self._extract_episodes(season)
if episodes:
entries.extend(episodes)
continue
season_name = season.get('name')
if season_name and isinstance(season_name, compat_str):
entries.append(self.url_result(
'https://%s.nrk.no/serie/%s/sesong/%s'
% (domain, series_id, season_name),
ie=NRKTVSeasonIE.ie_key(),
video_title=season.get('title')))
return entries return entries
def _extract_episodes(self, season): def _extract_episodes(self, season):
@ -713,6 +728,13 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
}, { }, {
'url': 'https://tv.nrk.no/serie/postmann-pat', 'url': 'https://tv.nrk.no/serie/postmann-pat',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://radio.nrk.no/serie/dickie-dick-dickens',
'info_dict': {
'id': 'dickie-dick-dickens',
},
'playlist_mincount': 8,
'expected_warnings': ['HTTP Error 404: Not Found'],
}] }]
@classmethod @classmethod
@ -748,7 +770,7 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
# New layout (e.g. https://tv.nrk.no/serie/backstage) # New layout (e.g. https://tv.nrk.no/serie/backstage)
if series: if series:
entries = [] entries = []
entries.extend(self._extract_seasons(series.get('seasons'))) entries.extend(self._extract_seasons(domain, series_id, series.get('seasons')))
entries.extend(self._extract_entries(series.get('instalments'))) entries.extend(self._extract_entries(series.get('instalments')))
entries.extend(self._extract_episodes(series.get('extraMaterial'))) entries.extend(self._extract_episodes(series.get('extraMaterial')))
return self.playlist_result(entries, series_id, title, description) return self.playlist_result(entries, series_id, title, description)