X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fnpo.py;h=87f5675c7ff8b14169291420feb9bcf85edf894d;hb=175c2e9ec326f9ef820413837608eb4f5c8c5961;hp=583ed3e142ddd5e3aaf012b0b5a28c24a3c7046f;hpb=574f42d79a8596ceda681b205e19e766e7bab046;p=youtube-dl diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index 583ed3e14..87f5675c7 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -3,17 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_request, - compat_urllib_parse, -) from ..utils import ( fix_xml_ampersands, parse_duration, qualities, strip_jsonp, unified_strdate, - url_basename, ) @@ -77,7 +72,7 @@ class NPOIE(NPOBaseIE): 'info_dict': { 'id': 'VARA_101191800', 'ext': 'm4v', - 'title': 'De Mega Mike & Mega Thomas show', + 'title': 'De Mega Mike & Mega Thomas show: The best of.', 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4', 'upload_date': '20090227', 'duration': 2400, @@ -89,7 +84,7 @@ class NPOIE(NPOBaseIE): 'info_dict': { 'id': 'VPWON_1169289', 'ext': 'm4v', - 'title': 'Tegenlicht', + 'title': 'Tegenlicht: De toekomst komt uit Afrika', 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea', 'upload_date': '20130225', 'duration': 3000, @@ -162,6 +157,13 @@ class NPOIE(NPOBaseIE): # video id is POMS_WNL_853698 but prid is POW_00996502) video_id = metadata.get('prid') or video_id + # titel is too generic in some cases so utilize aflevering_titel as well + # when available (e.g. http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html) + title = metadata['titel'] + sub_title = metadata.get('aflevering_titel') + if sub_title and sub_title != title: + title += ': %s' % sub_title + token = self._get_token(video_id) formats = [] @@ -187,7 +189,7 @@ class NPOIE(NPOBaseIE): if not video_url: continue if format_id == 'adaptive': - formats.extend(self._extract_m3u8_formats(video_url, video_id)) + formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4')) else: formats.append({ 'url': video_url, @@ -234,9 +236,7 @@ class NPOIE(NPOBaseIE): return { 'id': video_id, - # prefer aflevering_titel if any since titel may be too generic, e.g. - # http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html - 'title': metadata.get('aflevering_titel') or metadata['titel'], + 'title': title, 'description': metadata.get('info'), 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'], 'upload_date': unified_strdate(metadata.get('gidsdatum')), @@ -406,7 +406,40 @@ class NPORadioFragmentIE(InfoExtractor): } +class SchoolTVIE(InfoExtractor): + IE_NAME = 'schooltv' + _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P[^/?#&]+)' + + _TEST = { + 'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/', + 'info_dict': { + 'id': 'WO_NTR_429477', + 'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam', + 'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?', + 'ext': 'mp4', + 'description': 'md5:abfa0ff690adb73fd0297fd033aaa631' + }, + 'params': { + # Skip because of m3u8 download + 'skip_download': True + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._search_regex( + r'data-mid=(["\'])(?P.+?)\1', webpage, 'video_id', group='id') + return { + '_type': 'url_transparent', + 'ie_key': 'NPO', + 'url': 'npo:%s' % video_id, + 'display_id': display_id + } + + class VPROIE(NPOIE): + IE_NAME = 'vpro' _VALID_URL = r'https?://(?:www\.)?(?:tegenlicht\.)?vpro\.nl/(?:[^/]+/){2,}(?P[^/]+)\.html' _TESTS = [