From 74aa18f68ffe5a721fae1149193c8b6401076d63 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Thu, 17 Jul 2014 10:07:51 +0200 Subject: [PATCH] [dfb] Add extractor (closes #3280) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/dfb.py | 44 ++++++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) create mode 100644 youtube_dl/extractor/dfb.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 3e3b5d44a..03d2e446d 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -63,6 +63,7 @@ DailymotionUserIE, ) from .daum import DaumIE +from .dfb import DFBIE from .dotsub import DotsubIE from .dreisat import DreiSatIE from .drtv import DRTVIE diff --git a/youtube_dl/extractor/dfb.py b/youtube_dl/extractor/dfb.py new file mode 100644 index 000000000..cb8e06822 --- /dev/null +++ b/youtube_dl/extractor/dfb.py @@ -0,0 +1,44 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class DFBIE(InfoExtractor): + IE_NAME = 'tv.dfb.de' + _VALID_URL = r'https?://tv\.dfb\.de/video/[^/]+/(?P\d+)' + + _TEST = { + 'url': 'http://tv.dfb.de/video/highlights-des-empfangs-in-berlin/9070/', + # The md5 is different each time + 'info_dict': { + 'id': '9070', + 'ext': 'flv', + 'title': 'Highlights des Empfangs in Berlin', + 'upload_date': '20140716', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + player_info = self._download_xml( + 'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id, + video_id) + video_info = player_info.find('video') + + f4m_info = self._download_xml(video_info.find('url').text, video_id) + token_el = f4m_info.find('token') + manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0' + + return { + 'id': video_id, + 'title': video_info.find('title').text, + 'url': manifest_url, + 'ext': 'flv', + 'thumbnail': self._og_search_thumbnail(webpage), + 'upload_date': ''.join(video_info.find('time_date').text.split('.')[::-1]), + }