diff options
author | Sergey M․ <dstftw@gmail.com> | 2016-11-02 01:29:05 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2016-11-02 01:29:05 +0700 |
commit | 9c82bba05d5495d29be2ee20fc9cb690b37fcdce (patch) | |
tree | b287781362791d1e09e56dfbeb23145d9b49e7b1 | |
parent | e3577722b0bdb16e786eba8029d09ccc1983e0ce (diff) |
[nickde] Improve extraction
-rw-r--r-- | youtube_dl/extractor/nick.py | 13 |
1 files changed, 10 insertions, 3 deletions
diff --git a/youtube_dl/extractor/nick.py b/youtube_dl/extractor/nick.py index a96bb0ef5..36364bee9 100644 --- a/youtube_dl/extractor/nick.py +++ b/youtube_dl/extractor/nick.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .mtv import MTVServicesInfoExtractor from ..utils import update_url_query @@ -69,7 +71,7 @@ class NickIE(MTVServicesInfoExtractor): class NickDeIE(MTVServicesInfoExtractor): IE_NAME = 'nick.de' - _VALID_URL = r'https?://(?:www\.)?(?:nick\.de|nickelodeon\.(?:nl|at))/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?(?P<host>nick\.de|nickelodeon\.(?:nl|at))/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'http://www.nick.de/playlist/3773-top-videos/videos/episode/17306-zu-wasser-und-zu-land-rauchende-erdnusse', 'only_matching': True, @@ -79,16 +81,21 @@ class NickDeIE(MTVServicesInfoExtractor): }, { 'url': 'http://www.nickelodeon.nl/shows/474-spongebob/videos/17403-een-kijkje-in-de-keuken-met-sandy-van-binnenuit', 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.at/playlist/3773-top-videos/videos/episode/77993-das-letzte-gefecht', + 'only_matching': True, }] def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + host = mobj.group('host') webpage = self._download_webpage(url, video_id) mrss_url = update_url_query(self._search_regex( r'data-mrss=(["\'])(?P<url>http.+?)\1', webpage, 'mrss url', group='url'), - {'siteKey': 'nick.de'}) + {'siteKey': host}) return self._get_videos_info_from_url(mrss_url, video_id) |