From: Tobias Bell Date: Sat, 17 May 2014 12:47:23 +0000 (+0200) Subject: [gameone] Add new extractor gameone X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=412f356e04b0daaa1a862f8fdc155ae63376e7d2;p=youtube-dl [gameone] Add new extractor gameone Currently only usable for downloading tv episodes residing under http://www.gameone.de/tv/ --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 3503c76b7..a294f66ae 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -103,6 +103,7 @@ from .freesound import FreesoundIE from .freespeech import FreespeechIE from .funnyordie import FunnyOrDieIE from .gamekings import GamekingsIE +from .gameone import GameOneIE from .gamespot import GameSpotIE from .gametrailers import GametrailersIE from .gdcvault import GDCVaultIE diff --git a/youtube_dl/extractor/gameone.py b/youtube_dl/extractor/gameone.py new file mode 100644 index 000000000..a8a290477 --- /dev/null +++ b/youtube_dl/extractor/gameone.py @@ -0,0 +1,62 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import xpath_with_ns + +NAMESPACE_MAP = { + 'media': 'http://search.yahoo.com/mrss/', +} + +RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/' + +class GameOneIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P\d+)' + _TESTS = { + 'url': 'http://www.gameone.de/tv/288', + 'md5': '136656b7fb4c9cb4a8e2d500651c499b', + 'info_dict': { + 'id': '288', + 'ext': 'mp4', + 'title': 'Game One - Folge 288', + 'duration': 1238, + 'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + og_video = self._og_search_video_url(webpage, secure=False) + mrss_url = self._search_regex(r'mrss=([^&]+)', og_video, 'mrss') + + mrss = self._download_xml(mrss_url, video_id, 'Downloading mrss') + title = mrss.find('.//item/title').text + thumbnail = mrss.find('.//item/image').get('url') + content = mrss.find(xpath_with_ns('.//media:content', NAMESPACE_MAP)) + content_url = content.get('url') + + content = self._download_xml(content_url, video_id, 'Downloading media:content') + rendition_items = content.findall('.//rendition') + duration = int(rendition_items[0].get('duration')) + formats = [ + { + 'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text), + 'width': int(r.get('width')), + 'height': int(r.get('height')), + 'tbr': int(r.get('bitrate')), + } + for r in rendition_items + ] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + }