X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fnpo.py;h=fa4ef20c52959240af41a0c8a7b08c02fd3eb54c;hb=b14b2283a0b9f66f54e862641b5b1cd22c07bd62;hp=38fefe492b5f60f3952023d17c41721b7c6df412;hpb=4f06c1c9fcbfbc74b81b5fa89a616914b5ce5aad;p=youtube-dl diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index 38fefe492..fa4ef20c5 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -28,17 +28,17 @@ class NPOBaseIE(InfoExtractor): class NPOIE(NPOBaseIE): IE_NAME = 'npo' - IE_DESC = 'npo.nl and ntr.nl' + IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl' _VALID_URL = r'''(?x) (?: npo:| https?:// (?:www\.)? (?: - npo\.nl/(?!live|radio)(?:[^/]+/){2}| + npo\.nl/(?!(?:live|radio)/)(?:[^/]+/){2}| ntr\.nl/(?:[^/]+/){2,}| omroepwnl\.nl/video/fragment/[^/]+__| - zapp\.nl/[^/]+/[^/]+/ + (?:zapp|npo3)\.nl/(?:[^/]+/){2} ) ) (?P[^/?#]+) @@ -146,10 +146,16 @@ class NPOIE(NPOBaseIE): }, { 'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990', 'only_matching': True, + }, { + 'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870', + 'only_matching': True, }, { # live stream 'url': 'npo:LI_NL1_4188102', 'only_matching': True, + }, { + 'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373', + 'only_matching': True, }] def _real_extract(self, url): @@ -313,9 +319,9 @@ class NPOIE(NPOBaseIE): class NPOLiveIE(NPOBaseIE): IE_NAME = 'npo.nl:live' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/live/(?P[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?npo\.nl/live(?:/(?P[^/?#&]+))?' - _TEST = { + _TESTS = [{ 'url': 'http://www.npo.nl/live/npo-1', 'info_dict': { 'id': 'LI_NL1_4188102', @@ -327,15 +333,18 @@ class NPOLiveIE(NPOBaseIE): 'params': { 'skip_download': True, } - } + }, { + 'url': 'http://www.npo.nl/live', + 'only_matching': True, + }] def _real_extract(self, url): - display_id = self._match_id(url) + display_id = self._match_id(url) or 'npo-1' webpage = self._download_webpage(url, display_id) live_id = self._search_regex( - r'data-prid="([^"]+)"', webpage, 'live id') + [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id') return { '_type': 'url_transparent',