From: Sergey M. Date: Thu, 6 Feb 2014 17:35:26 +0000 (+0700) Subject: [ndr] Add support for ndr.de (Closes #2325) X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=e9ea0bf12347b785b352236cd0d0e0f25a8f26c5;p=youtube-dl [ndr] Add support for ndr.de (Closes #2325) --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 7a97c3279..a13b5cfb8 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -142,6 +142,7 @@ from .myvideo import MyVideoIE from .naver import NaverIE from .nba import NBAIE from .nbc import NBCNewsIE +from .ndr import NDRIE from .ndtv import NDTVIE from .newgrounds import NewgroundsIE from .nfb import NFBIE diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py new file mode 100644 index 000000000..bf6782d7d --- /dev/null +++ b/youtube_dl/extractor/ndr.py @@ -0,0 +1,89 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ExtractorError + + +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, + } + } + ] + + 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) + description = self._og_search_description(page) + + mobj = re.search( + r'
(?P\d+):(?P\d+)
', + page) + duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None + + formats = [] + + mp3_url = re.search(r'''{src:'(?P