From 33898fb19c1af161c503ebce8f9a4774fecee45e Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 6 Oct 2016 10:45:57 +0100 Subject: [PATCH] [nzz] Add new extractor(#4407) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/nzz.py | 36 ++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) create mode 100644 youtube_dl/extractor/nzz.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index feee060049..72bc4f57ce 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -638,6 +638,7 @@ NYTimesArticleIE, ) from .nuvid import NuvidIE +from .nzz import NZZIE from .odatv import OdaTVIE from .odnoklassniki import OdnoklassnikiIE from .oktoberfesttv import OktoberfestTVIE diff --git a/youtube_dl/extractor/nzz.py b/youtube_dl/extractor/nzz.py new file mode 100644 index 0000000000..2d352f53f2 --- /dev/null +++ b/youtube_dl/extractor/nzz.py @@ -0,0 +1,36 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + extract_attributes, +) + + +class NZZIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?nzz\.ch/(?:[^/]+/)*[^/?#]+-ld\.(?P\d+)' + _TEST = { + 'url': 'http://www.nzz.ch/zuerich/gymizyte/gymizyte-schreiben-schueler-heute-noch-diktate-ld.9153', + 'info_dict': { + 'id': '9153', + }, + 'playlist_mincount': 6, + } + + def _real_extract(self, url): + page_id = self._match_id(url) + webpage = self._download_webpage(url, page_id) + + entries = [] + for player_element in re.findall(r'(<[^>]+class="kalturaPlayer"[^>]*>)', webpage): + player_params = extract_attributes(player_element) + if player_params.get('data-type') not in ('kaltura_singleArticle',): + self.report_warning('Unsupported player type') + continue + entry_id = player_params['data-id'] + entries.append(self.url_result( + 'kaltura:1750922:' + entry_id, 'Kaltura', entry_id)) + + return self.playlist_result(entries, page_id)