mirror of
https://github.com/l1ving/youtube-dl
synced 2024-12-22 10:15:14 +08:00
[nrk:playlist] Relax video id regex and improve _VALID_URL
This commit is contained in:
parent
5379a2d40d
commit
a09141548a
@ -77,17 +77,25 @@ class NRKIE(InfoExtractor):
|
|||||||
|
|
||||||
|
|
||||||
class NRKPlaylistIE(InfoExtractor):
|
class NRKPlaylistIE(InfoExtractor):
|
||||||
_VALID_URL = r'http://(?:www\.)?nrk\.no/(?!video)[^/]+/(?P<id>[^/]+)'
|
_VALID_URL = r'http://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
|
||||||
|
|
||||||
_TEST = {
|
_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': {
|
||||||
'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
|
'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
|
||||||
'title': 'Gjenopplev den historiske solformørkelsen',
|
'title': 'Gjenopplev den historiske solformørkelsen',
|
||||||
'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
|
'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
|
||||||
},
|
},
|
||||||
'playlist_mincount': 2,
|
'playlist_count': 2,
|
||||||
}
|
}, {
|
||||||
|
'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'rivertonprisen-til-karin-fossum-1.12266449',
|
||||||
|
'title': 'Rivertonprisen til Karin Fossum',
|
||||||
|
'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
|
||||||
|
},
|
||||||
|
'playlist_count': 5,
|
||||||
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
playlist_id = self._match_id(url)
|
playlist_id = self._match_id(url)
|
||||||
@ -97,7 +105,8 @@ class NRKPlaylistIE(InfoExtractor):
|
|||||||
entries = [
|
entries = [
|
||||||
self.url_result('nrk:%s' % video_id, 'NRK')
|
self.url_result('nrk:%s' % video_id, 'NRK')
|
||||||
for video_id in re.findall(
|
for video_id in re.findall(
|
||||||
r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="(\d+)"', webpage)
|
r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
|
||||||
|
webpage)
|
||||||
]
|
]
|
||||||
|
|
||||||
playlist_title = self._og_search_title(webpage)
|
playlist_title = self._og_search_title(webpage)
|
||||||
|
Loading…
Reference in New Issue
Block a user