mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-02 19:36:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

[nrktv:episodes] Add support for episodes (#11571)

Browse source
This commit is contained in:
Sergey M․ 2017-01-01 21:25:25 +07:00
parent e5e19379be
commit 966815e139
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 51 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
youtube_dl/extractor/extractors.py
View file

@ -655,6 +655,7 @@
NRKSkoleIE, NRKSkoleIE,
NRKTVIE, NRKTVIE,
NRKTVDirekteIE, NRKTVDirekteIE,
NRKTVEpisodesIE,
) )
from .ntvde import NTVDeIE from .ntvde import NTVDeIE
from .ntvru import NTVRuIE from .ntvru import NTVRuIE

66
youtube_dl/extractor/nrk.py
View file

@ -207,7 +207,15 @@ class NRKIE(NRKBaseIE):
class NRKTVIE(NRKBaseIE): class NRKTVIE(NRKBaseIE):
IE_DESC = 'NRK TV and NRK Radio' IE_DESC = 'NRK TV and NRK Radio'
_VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?' _EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
_VALID_URL = r'''(?x)
https?://
(?:tv|radio)\.nrk(?:super)?\.no/
(?:serie/[^/]+|program)/
(?![Ee]pisodes)%s
(?:/\d{2}-\d{2}-\d{4})?
(?:\#del=(?P<part_id>\d+))?
''' % _EPISODE_RE
_API_HOST = 'psapi-we.nrk.no' _API_HOST = 'psapi-we.nrk.no'
_TESTS = [{ _TESTS = [{
@ -286,9 +294,30 @@ class NRKTVDirekteIE(NRKTVIE):
}] }]
class NRKPlaylistIE(InfoExtractor): class NRKPlaylistBaseIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)' def _extract_description(self, webpage):
pass
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
entries = [
self.url_result('nrk:%s' % video_id, NRKIE.ie_key())
for video_id in re.findall(self._ITEM_RE, webpage)
]
playlist_title = self. _extract_title(webpage)
playlist_description = self._extract_description(webpage)
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
class NRKPlaylistIE(NRKPlaylistBaseIE):
_VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
_ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'
_TESTS = [{ _TESTS = [{
'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763', 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
'info_dict': { 'info_dict': {
@ -307,23 +336,28 @@ class NRKPlaylistIE(InfoExtractor):
'playlist_count': 5, 'playlist_count': 5,
}] }]
def _real_extract(self, url): def _extract_title(self, webpage):
playlist_id = self._match_id(url) return self._og_search_title(webpage, fatal=False)
webpage = self._download_webpage(url, playlist_id) def _extract_description(self, webpage):
return self._og_search_description(webpage)
entries = [
self.url_result('nrk:%s' % video_id, 'NRK')
for video_id in re.findall(
r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
webpage)
]
playlist_title = self._og_search_title(webpage) class NRKTVEpisodesIE(NRKPlaylistBaseIE):
playlist_description = self._og_search_description(webpage) _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'
_ITEM_RE = r'data-episode=["\']%s' % NRKTVIE._EPISODE_RE
_TESTS = [{
'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031',
'info_dict': {
'id': '69031',
'title': 'Nytt på nytt, sesong: 201210',
},
'playlist_count': 4,
}]
return self.playlist_result( def _extract_title(self, webpage):
entries, playlist_id, playlist_title, playlist_description) return self._html_search_regex(
r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
class NRKSkoleIE(InfoExtractor): class NRKSkoleIE(InfoExtractor):