From 8a7a2089050957c942bde0b9ab70963b2dea8f35 Mon Sep 17 00:00:00 2001 From: slangangular Date: Sun, 12 Jul 2015 10:30:51 +0200 Subject: [PATCH] [sportschau] Add support for sportschau.de Closes #6199. --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/sportschau.py | 43 ++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+) create mode 100644 youtube_dl/extractor/sportschau.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 06f21064b..d70de7690 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -552,6 +552,7 @@ from .sportbox import ( SportBoxEmbedIE, ) from .sportdeutschland import SportDeutschlandIE +from .sportschau import SportschauIE from .srf import SrfIE from .srmediathek import SRMediathekIE from .ssa import SSAIE diff --git a/youtube_dl/extractor/sportschau.py b/youtube_dl/extractor/sportschau.py new file mode 100644 index 000000000..ff30e1f0e --- /dev/null +++ b/youtube_dl/extractor/sportschau.py @@ -0,0 +1,43 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class SportschauIE(InfoExtractor): + IE_NAME = 'Sportschau' + _VALID_URL = r'https?://(?:www\.)?sportschau\.de/\w+(?:/\w+)?/video(?P\w+)\.html' + _TEST = { + 'url': 'http://www.sportschau.de/tourdefrance/videoseppeltkokainhatnichtsmitklassischemdopingzutun100.html', + 'md5': 'a6ef460ab9f4089b079832e06d554cec', + 'info_dict': { + 'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100', + 'ext': 'mp4', + 'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun" - Tour de France - sportschau.de', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + ext = '-mc_defaultQuality-h.json' + json_url = url[:-5] + ext + + json = self._download_json(json_url, video_id) + thumb_url = json['_previewImage'] + + m3u8_url = json['_mediaArray'][1]['_mediaStreamArray'][0]['_stream'][0] + m3u8_formats = self._extract_m3u8_formats(m3u8_url, video_id, ext="mp4") + + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex(r'(.*?)', webpage, 'title') + desc = self._html_search_meta('description', webpage) + + return { + 'id': video_id, + 'title': title, + 'formats': m3u8_formats, + 'description': desc, + 'thumbnail': thumb_url, + }