From c6129feb7f8313941a4d2044fa4b45ceaa0a91c7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 9 Sep 2016 23:20:45 +0700 Subject: [PATCH] [ketnet] Add extractor (Closes #10343) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/ketnet.py | 52 ++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+) create mode 100644 youtube_dl/extractor/ketnet.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index b7b630e9d..38dc33674 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -407,6 +407,7 @@ from .kankan import KankanIE from .karaoketv import KaraoketvIE from .karrierevideos import KarriereVideosIE from .keezmovies import KeezMoviesIE +from .ketnet import KetnetIE from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE from .keek import KeekIE diff --git a/youtube_dl/extractor/ketnet.py b/youtube_dl/extractor/ketnet.py new file mode 100644 index 000000000..aaf3f807a --- /dev/null +++ b/youtube_dl/extractor/ketnet.py @@ -0,0 +1,52 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class KetnetIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ketnet\.be/(?:[^/]+/)*(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.ketnet.be/kijken/zomerse-filmpjes', + 'md5': 'd907f7b1814ef0fa285c0475d9994ed7', + 'info_dict': { + 'id': 'zomerse-filmpjes', + 'ext': 'mp4', + 'title': 'Gluur mee op de filmset en op Pennenzakkenrock', + 'description': 'Gluur mee met Ghost Rockers op de filmset', + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, { + 'url': 'https://www.ketnet.be/kijken/karrewiet/uitzending-8-september-2016', + 'only_matching': True, + }, { + 'url': 'https://www.ketnet.be/achter-de-schermen/sien-repeteert-voor-stars-for-life', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + config = self._parse_json( + self._search_regex( + r'(?s)playerConfig\s*=\s*({.+?})\s*;', webpage, + 'player config'), + video_id) + + title = config['title'] + + formats = self._extract_m3u8_formats( + config['source']['hls'], video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls') + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': config.get('description'), + 'thumbnail': config.get('image'), + 'series': config.get('program'), + 'episode': config.get('episode'), + 'formats': formats, + }