From 375696b1b160227b488cfc5c3ca92079bc0b4df8 Mon Sep 17 00:00:00 2001 From: pulpe Date: Sun, 18 May 2014 14:56:35 +0200 Subject: [PATCH] [SWRMediathek] add support for swrmediathek.de --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/swrmediathek.py | 74 ++++++++++++++++++++++++++++ 2 files changed, 75 insertions(+) create mode 100644 youtube_dl/extractor/swrmediathek.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 3503c76b7c..4a4eb4b747 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -260,6 +260,7 @@ from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE +from .swrmediathek import SWRMediathekIE from .syfy import SyfyIE from .sztvhu import SztvHuIE from .teamcoco import TeamcocoIE diff --git a/youtube_dl/extractor/swrmediathek.py b/youtube_dl/extractor/swrmediathek.py new file mode 100644 index 0000000000..5ba3f3504c --- /dev/null +++ b/youtube_dl/extractor/swrmediathek.py @@ -0,0 +1,74 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class SWRMediathekIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/player\.htm\?show=(?P[^?#&]+)' + + _TESTS = [{ + 'url': 'http://swrmediathek.de/player.htm?show=849790d0-dab8-11e3-a953-0026b975f2e6', + 'info_dict': { + 'id': '849790d0-dab8-11e3-a953-0026b975f2e6', + 'ext': 'flv', + 'title': 'SWR odysso', + 'description': 'md5:2012e31baad36162e97ce9eb3f157b8a', + 'thumbnail': 're:^http:.*\.jpg$', + }, + 'params': { + 'skip_download': True, # requires rtmpdump + }, + }, { + 'url': 'http://swrmediathek.de/player.htm?show=0e1a8510-ddf2-11e3-9be3-0026b975f2e6', + 'info_dict': { + 'id': '0e1a8510-ddf2-11e3-9be3-0026b975f2e6', + 'ext': 'flv', + 'title': 'Nachtcafé - Alltagsdroge Alkohol - zwischen Sektempfang und Komasaufen', + 'description': 'md5:e0a3adc17e47db2c23aab9ebc36dbee2', + 'thumbnail': 're:http://.*\.jpg', + }, + 'params': { + 'skip_download': True, # requires rtmpdump + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('videoid') + + webpage = self._download_webpage(url, video_id) + + smilurl = 'http://swrmediathek.de/rtmpQuals/%s/clips.smil' + smildoc = self._download_xml(smilurl % video_id, video_id, note='Downloading SMIL page') + + baseurl = smildoc.find('.//meta').attrib['base'] + + formats = [] + for video in smildoc.findall('.//video'): + vbr = video.attrib.get('system-bitrate') + if vbr: + vbr = int(vbr) / 1000 + + formats.append({ + 'format_id': video.attrib['height'] + 'p', + 'width': int_or_none(video.attrib['width']), + 'height': int_or_none(video.attrib['height']), + 'vbr': vbr, + 'url': baseurl, + 'play_path': 'mp4:' + video.attrib['src'], + 'ext': 'flv', + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': self._html_search_regex(r'', webpage, 'title'), + 'thumbnail': self._search_regex(r'', webpage, 'thumbnail'), + 'formats': formats, + 'description': self._html_search_regex(r'', webpage, 'description'), + }