From 9e68f9fdf1efa6b6afe141feb27d9626e40c3056 Mon Sep 17 00:00:00 2001 From: David Wagner Date: Wed, 26 Feb 2014 22:25:04 +0000 Subject: [PATCH] Extractor for non-password protected GDC Vault videos --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/gdcvault.py | 61 ++++++++++++++++++++++++++++++++ 2 files changed, 62 insertions(+) create mode 100644 youtube_dl/extractor/gdcvault.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index e16bbd969..60aa97636 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -89,6 +89,7 @@ from .funnyordie import FunnyOrDieIE from .gamekings import GamekingsIE from .gamespot import GameSpotIE from .gametrailers import GametrailersIE +from .gdcvault import GDCVaultIE from .generic import GenericIE from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py new file mode 100644 index 000000000..a1e4c3221 --- /dev/null +++ b/youtube_dl/extractor/gdcvault.py @@ -0,0 +1,61 @@ +from __future__ import unicode_literals + +import re +import json +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import unified_strdate + + +class GDCVaultIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P\d+)/(?P(\w|-)+)' + + _TEST = { + u'url': u'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple', + u'md5': u'7ce8388f544c88b7ac11c7ab1b593704', + u'info_dict': { + u"id": u"1019721", + u"ext": u"mp4", + u"title": u"Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)" + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + + video_id = mobj.group('id') + webpage_url = 'http://www.gdcvault.com/play/' + video_id + + start_page = self._download_webpage(webpage_url, video_id) + + self.report_extraction(video_id) + + xml_root = self._html_search_regex(r'', start_page, 'xml filename') + xml_decription_url = xml_root + 'xml/' + xml_name + + xml_description = self._download_xml(xml_decription_url, video_id) + + video_title = xml_description.find('./metadata/title').text + + mp4_video = xml_description.find('./metadata/mp4video').text + mobj = re.match(r'(?Phttps?://.*?/).*', mp4_video) + video_root = mobj.group('root') + + formats = xml_description.findall('./metadata/MBRVideos/MBRVideo') + video_formats = [] + for format in formats: + mobj = re.match(r'mp4\:(?P.*)', format.find('streamName').text) + url = video_root + mobj.group('path') + vbr = format.find('bitrate').text + video_formats.append({ + 'url': url, + 'vbr': int(vbr), + }) + + return [{ + 'id': video_id, + 'formats': video_formats, + 'title': video_title, + }]