jcgruenhage/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[nicknight] Improve extraction (closes #10769)

Browse source
This commit is contained in:
Sergey M․ 2016-11-02 01:35:53 +07:00
parent 9c82bba05d
commit f449c061d0
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 14 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
youtube_dl/extractor/extractors.py
View file

@ -596,7 +596,7 @@ from .nhl import (
from .nick import ( from .nick import (
NickIE, NickIE,
NickDeIE, NickDeIE,
NickNightAtIE, NickNightIE,
) )
from .niconico import NiconicoIE, NiconicoPlaylistIE from .niconico import NiconicoIE, NiconicoPlaylistIE
from .ninecninemedia import ( from .ninecninemedia import (

28
youtube_dl/extractor/nick.py
View file

@ -86,6 +86,11 @@ class NickDeIE(MTVServicesInfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
def _extract_mrss_url(self, webpage, host):
return update_url_query(self._search_regex(
r'data-mrss=(["\'])(?P<url>http.+?)\1', webpage, 'mrss url', group='url'),
{'siteKey': host})
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
@ -93,16 +98,14 @@ class NickDeIE(MTVServicesInfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
mrss_url = update_url_query(self._search_regex( mrss_url = self._extract_mrss_url(webpage, host)
r'data-mrss=(["\'])(?P<url>http.+?)\1', webpage, 'mrss url', group='url'),
{'siteKey': host})
return self._get_videos_info_from_url(mrss_url, video_id) return self._get_videos_info_from_url(mrss_url, video_id)
class NickNightAtIE(MTVServicesInfoExtractor): class NickNightIE(NickDeIE):
IE_NAME = 'nicknight.de' IE_NAME = 'nicknight'
_VALID_URL = r'https?://(?:www\.)nicknight\.(?:de|at|tv)/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)(?P<host>nicknight\.(?:de|at|tv))/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.nicknight.at/shows/977-awkward/videos/85987-nimmer-beste-freunde', 'url': 'http://www.nicknight.at/shows/977-awkward/videos/85987-nimmer-beste-freunde',
'only_matching': True, 'only_matching': True,
@ -114,12 +117,7 @@ class NickNightAtIE(MTVServicesInfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
def _real_extract(self, url): def _extract_mrss_url(self, webpage, *args):
video_id = self._match_id(url) return self._search_regex(
r'mrss\s*:\s*(["\'])(?P<url>http.+?)\1', webpage,
webpage = self._download_webpage(url, video_id) 'mrss url', group='url')
mrss_url = self._search_regex(
r'mrss: (["\'])(?P<url>http.+?)\1', webpage, 'mrss url', group='url')
return self._get_videos_info_from_url(mrss_url, video_id)