X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/af478477605bdf3f5d57562035885cfee905f379..d904ce9fca517ea1b6310e731acddcdd05dda618:/youtube_dl/extractor/ndr.py diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index 0650f95..79a1395 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 = [ - { - 'url': 'http://www.ndr.de/fernsehen/sendungen/markt/markt7959.html', - 'md5': 'e7a6079ca39d3568f4996cb858dd6708', - 'note': 'Video file', - 'info_dict': { - 'id': '7959', - 'ext': 'mp4', - 'title': 'Markt - die ganze Sendung', - 'description': 'md5:af9179cf07f67c5c12dc6d9997e05725', - 'duration': 2655, - }, - }, - { - 'url': 'http://www.ndr.de/info/audio51535.html', - 'md5': 'bb3cd38e24fbcc866d13b50ca59307b8', - 'note': 'Audio file', - 'info_dict': { - 'id': '51535', - 'ext': 'mp3', - 'title': 'La Valette entgeht der Hinrichtung', - 'description': 'md5:22f9541913a40fe50091d5cdd7c9f536', - 'duration': 884, - } - } - ] - +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