X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/99b46abf79266c2bf5eabc291dc4f366e61b5dde..39393b81acfaf4045fb7f20454a0226f0dc9142e:/youtube_dl/extractor/nick.py?ds=sidebyside diff --git a/youtube_dl/extractor/nick.py b/youtube_dl/extractor/nick.py index 9c54846..2e8b302 100644 --- a/youtube_dl/extractor/nick.py +++ b/youtube_dl/extractor/nick.py @@ -1,16 +1,18 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .mtv import MTVServicesInfoExtractor -from ..compat import compat_urllib_parse_urlencode from ..utils import update_url_query class NickIE(MTVServicesInfoExtractor): # None of videos on the website are still alive? IE_NAME = 'nick.com' - _VALID_URL = r'https?://(?:www\.)?nick(?:jr)?\.com/(?:videos/clip|[^/]+/videos)/(?P[^/?#.]+)' + _VALID_URL = r'https?://(?P(?:(?:www|beta)\.)?nick(?:jr)?\.com)/(?:[^/]+/)?(?:videos/clip|[^/]+/videos)/(?P[^/?#.]+)' _FEED_URL = 'http://udat.mtvnservices.com/service1/dispatch.htm' + _GEO_COUNTRIES = ['US'] _TESTS = [{ 'url': 'http://www.nick.com/videos/clip/alvinnn-and-the-chipmunks-112-full-episode.html', 'playlist': [ @@ -56,36 +58,192 @@ class NickIE(MTVServicesInfoExtractor): }, { 'url': 'http://www.nickjr.com/paw-patrol/videos/pups-save-a-goldrush-s3-ep302-full-episode/', 'only_matching': True, + }, { + 'url': 'http://beta.nick.com/nicky-ricky-dicky-and-dawn/videos/nicky-ricky-dicky-dawn-301-full-episode/', + 'only_matching': True, }] def _get_feed_query(self, uri): - return compat_urllib_parse_urlencode({ + return { 'feed': 'nick_arc_player_prime', 'mgid': uri, - }) + } + + def _real_extract(self, url): + domain, display_id = re.match(self._VALID_URL, url).groups() + video_data = self._download_json( + 'http://%s/data/video.endLevel.json' % domain, + display_id, query={ + 'urlKey': display_id, + }) + return self._get_videos_info(video_data['player'] + video_data['id']) + + +class NickBrIE(MTVServicesInfoExtractor): + IE_NAME = 'nickelodeon:br' + _VALID_URL = r'''(?x) + https?:// + (?: + (?P(?:www\.)?nickjr|mundonick\.uol)\.com\.br| + (?:www\.)?nickjr\.[a-z]{2}| + (?:www\.)?nickelodeonjunior\.fr + ) + /(?:programas/)?[^/]+/videos/(?:episodios/)?(?P[^/?\#.]+) + ''' + _TESTS = [{ + 'url': 'http://www.nickjr.com.br/patrulha-canina/videos/210-labirinto-de-pipoca/', + 'only_matching': True, + }, { + 'url': 'http://mundonick.uol.com.br/programas/the-loud-house/videos/muitas-irmas/7ljo9j', + 'only_matching': True, + }, { + 'url': 'http://www.nickjr.nl/paw-patrol/videos/311-ge-wol-dig-om-terug-te-zijn/', + 'only_matching': True, + }, { + 'url': 'http://www.nickjr.de/blaze-und-die-monster-maschinen/videos/f6caaf8f-e4e8-4cc1-b489-9380d6dcd059/', + 'only_matching': True, + }, { + 'url': 'http://www.nickelodeonjunior.fr/paw-patrol-la-pat-patrouille/videos/episode-401-entier-paw-patrol/', + 'only_matching': True, + }] - def _extract_mgid(self, webpage): - return self._search_regex(r'data-contenturi="([^"]+)', webpage, 'mgid') + def _real_extract(self, url): + domain, display_id = re.match(self._VALID_URL, url).groups() + webpage = self._download_webpage(url, display_id) + uri = self._search_regex( + r'data-(?:contenturi|mgid)="([^"]+)', webpage, 'mgid') + video_id = self._id_from_uri(uri) + config = self._download_json( + 'http://media.mtvnservices.com/pmt/e1/access/index.html', + video_id, query={ + 'uri': uri, + 'configtype': 'edge', + }, headers={ + 'Referer': url, + }) + info_url = self._remove_template_parameter(config['feedWithQueryParams']) + if info_url == 'None': + if domain.startswith('www.'): + domain = domain[4:] + content_domain = { + 'mundonick.uol': 'mundonick.com.br', + 'nickjr': 'br.nickelodeonjunior.tv', + }[domain] + query = { + 'mgid': uri, + 'imageEp': content_domain, + 'arcEp': content_domain, + } + if domain == 'nickjr.com.br': + query['ep'] = 'c4b16088' + info_url = update_url_query( + 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed', query) + return self._get_videos_info_from_url(info_url, video_id) class NickDeIE(MTVServicesInfoExtractor): IE_NAME = 'nick.de' - _VALID_URL = r'https?://(?:www\.)?nick\.de/(?:playlist|shows)/(?:[^/]+/)*(?P[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?(?Pnick\.(?:de|com\.pl|ch)|nickelodeon\.(?:nl|be|at|dk|no|se))/[^/]+/(?:[^/]+/)*(?P[^/?#&]+)' _TESTS = [{ 'url': 'http://www.nick.de/playlist/3773-top-videos/videos/episode/17306-zu-wasser-und-zu-land-rauchende-erdnusse', 'only_matching': True, }, { 'url': 'http://www.nick.de/shows/342-icarly', 'only_matching': True, + }, { + '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, + }, { + 'url': 'http://www.nick.com.pl/seriale/474-spongebob-kanciastoporty/wideo/17412-teatr-to-jest-to-rodeo-oszolom', + 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.no/program/2626-bulderhuset/videoer/90947-femteklasse-veronica-vs-vanzilla', + 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.dk/serier/2626-hojs-hus/videoer/761-tissepause', + 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.se/serier/2626-lugn-i-stormen/videos/998-', + 'only_matching': True, + }, { + 'url': 'http://www.nick.ch/shows/2304-adventure-time-abenteuerzeit-mit-finn-und-jake', + 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.be/afspeellijst/4530-top-videos/videos/episode/73917-inval-broodschapper-lariekoek-arie', + 'only_matching': True, }] + def _extract_mrss_url(self, webpage, host): + return update_url_query(self._search_regex( + r'data-mrss=(["\'])(?Phttp.+?)\1', webpage, 'mrss url', group='url'), + {'siteKey': host}) + 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=(["\'])(?Phttp.+?)\1', webpage, 'mrss url', group='url'), - {'siteKey': 'nick.de'}) + mrss_url = self._extract_mrss_url(webpage, host) return self._get_videos_info_from_url(mrss_url, video_id) + + +class NickNightIE(NickDeIE): + IE_NAME = 'nicknight' + _VALID_URL = r'https?://(?:www\.)(?Pnicknight\.(?:de|at|tv))/(?:playlist|shows)/(?:[^/]+/)*(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'http://www.nicknight.at/shows/977-awkward/videos/85987-nimmer-beste-freunde', + 'only_matching': True, + }, { + 'url': 'http://www.nicknight.at/shows/977-awkward', + 'only_matching': True, + }, { + 'url': 'http://www.nicknight.at/shows/1900-faking-it', + 'only_matching': True, + }] + + def _extract_mrss_url(self, webpage, *args): + return self._search_regex( + r'mrss\s*:\s*(["\'])(?Phttp.+?)\1', webpage, + 'mrss url', group='url') + + +class NickRuIE(MTVServicesInfoExtractor): + IE_NAME = 'nickelodeonru' + _VALID_URL = r'https?://(?:www\.)nickelodeon\.(?:ru|fr|es|pt|ro|hu|com\.tr)/[^/]+/(?:[^/]+/)*(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'http://www.nickelodeon.ru/shows/henrydanger/videos/episodes/3-sezon-15-seriya-licenziya-na-polyot/pmomfb#playlist/7airc6', + 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.ru/videos/smotri-na-nickelodeon-v-iyule/g9hvh7', + 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.fr/programmes/bob-l-eponge/videos/le-marathon-de-booh-kini-bottom-mardi-31-octobre/nfn7z0', + 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.es/videos/nickelodeon-consejos-tortitas/f7w7xy', + 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.pt/series/spongebob-squarepants/videos/a-bolha-de-tinta-gigante/xutq1b', + 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.ro/emisiuni/shimmer-si-shine/video/nahal-din-bomboane/uw5u2k', + 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.hu/musorok/spongyabob-kockanadrag/videok/episodes/buborekfujas-az-elszakadt-nadrag/q57iob#playlist/k6te4y', + 'only_matching': True, + }, { + 'url': 'http://www.nickelodeon.com.tr/programlar/sunger-bob/videolar/kayip-yatak/mgqbjy', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + mgid = self._extract_mgid(webpage) + return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)