X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fndr.py;h=79a13958b05e25a1c9e586168bb3a10742fbe01f;hb=c3124c3085e6a9a83ee31ace3a7d528a324c42da;hp=bf6782d7d83bf5173fc0aa1ce939513a08d853b8;hpb=9f31be70004d7a34fd8f9dee33a534156327aa01;p=youtube-dl diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index bf6782d7d..79a13958b 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -4,58 +4,35 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + int_or_none, + qualities, + parse_duration, +) -class NDRIE(InfoExtractor): - IE_NAME = 'ndr' - IE_DESC = 'NDR.de - Mediathek' - _VALID_URL = r'https?://www\.ndr\.de/.+?(?P\d+)\.html' - - _TESTS = [ - # video - { - 'url': 'http://www.ndr.de/fernsehen/sendungen/hallo_niedersachsen/media/hallonds19925.html', - 'md5': '20eba151ff165f386643dad9c1da08f7', - 'info_dict': { - 'id': '19925', - 'ext': 'mp4', - 'title': 'Hallo Niedersachsen ', - 'description': 'Bei Hallo Niedersachsen um 19:30 Uhr erfahren Sie alles, was am Tag in Niedersachsen los war.', - 'duration': 1722, - }, - }, - # audio - { - 'url': 'http://www.ndr.de/903/audio191719.html', - 'md5': '41ed601768534dd18a9ae34d84798129', - 'info_dict': { - 'id': '191719', - 'ext': 'mp3', - 'title': '"Es war schockierend"', - 'description': 'md5:ed7ff8364793545021a6355b97e95f10', - 'duration': 112, - } - } - ] - +class NDRBaseIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') page = self._download_webpage(url, video_id, 'Downloading page') - title = self._og_search_title(page) + title = self._og_search_title(page).strip() description = self._og_search_description(page) + if description: + description = description.strip() - mobj = re.search( - r'
(?P\d+):(?P\d+)
', - page) - duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None + duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', default=None)) + if not duration: + duration = parse_duration(self._html_search_regex( + r'(\d+:\d+)', + page, 'duration', default=None)) formats = [] - mp3_url = re.search(r'''{src:'(?P