commit 79fd7320e24596b39d81c2a364fb5b41c2f57b41
parent 0685d9727b9657fc8a31c96cb52c4155de29fcfc
Author: Sergey M․ <dstftw@gmail.com>
Date:   Mon,  9 Jul 2018 23:44:05 +0700

[nrktv] Add support for new episode URL schema (closes #16909)

Diffstat:
Myoutube_dl/extractor/extractors.py | 1+
Myoutube_dl/extractor/nrk.py | 38+++++++++++++++++++++++++++++++++++++-
2 files changed, 38 insertions(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py @@ -768,6 +768,7 @@ from .nrk import ( NRKSkoleIE, NRKTVIE, NRKTVDirekteIE, + NRKTVEpisodeIE, NRKTVEpisodesIE, NRKTVSeriesIE, ) diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py @@ -8,6 +8,7 @@ from ..compat import compat_urllib_parse_unquote from ..utils import ( ExtractorError, int_or_none, + JSON_LD_RE, parse_age_limit, parse_duration, ) @@ -359,6 +360,40 @@ class NRKTVIE(NRKBaseIE): }] +class NRKTVEpisodeIE(InfoExtractor): + _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/\d+/episode/\d+)' + _TEST = { + 'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8', + 'info_dict': { + 'id': 'MSUI14000816AA', + 'ext': 'mp4', + 'title': 'Backstage 8:30', + 'description': 'md5:de6ca5d5a2d56849e4021f2bf2850df4', + 'duration': 1320, + 'series': 'Backstage', + 'season_number': 1, + 'episode_number': 8, + 'episode': '8:30', + }, + 'params': { + 'skip_download': True, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + nrk_id = self._parse_json( + self._search_regex(JSON_LD_RE, webpage, 'JSON-LD', group='json_ld'), + display_id)['@id'] + + assert re.match(NRKTVIE._EPISODE_RE, nrk_id) + return self.url_result( + 'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id) + + class NRKTVDirekteIE(NRKTVIE): IE_DESC = 'NRK TV Direkte and NRK Radio Direkte' _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)' @@ -470,7 +505,8 @@ class NRKTVSeriesIE(InfoExtractor): @classmethod def suitable(cls, url): - return False if NRKTVIE.suitable(url) else super(NRKTVSeriesIE, cls).suitable(url) + return (False if NRKTVIE.suitable(url) or NRKTVEpisodeIE.suitable(url) + else super(NRKTVSeriesIE, cls).suitable(url)) def _real_extract(self, url): series_id = self._match_id(url)