From 9195ef745aba88a08e351af6405a87b5f355c026 Mon Sep 17 00:00:00 2001 From: mutantmonkey Date: Mon, 15 Feb 2016 17:07:13 -0800 Subject: [PATCH] [uStudio] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/ustudio.py | 58 ++++++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+) create mode 100644 youtube_dl/extractor/ustudio.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1ae606f1e..5386747f1 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -813,6 +813,7 @@ from .digiteka import DigitekaIE from .unistra import UnistraIE from .urort import UrortIE from .ustream import UstreamIE, UstreamChannelIE +from .ustudio import UstudioIE from .varzesh3 import Varzesh3IE from .vbox7 import Vbox7IE from .veehd import VeeHDIE diff --git a/youtube_dl/extractor/ustudio.py b/youtube_dl/extractor/ustudio.py new file mode 100644 index 000000000..0f837ad73 --- /dev/null +++ b/youtube_dl/extractor/ustudio.py @@ -0,0 +1,58 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import int_or_none + + +class UstudioIE(InfoExtractor): + IE_NAME = 'uStudio' + _VALID_URL = r'http://(?:www\.|v1\.)?ustudio.com/video/(?P[\w\d]+)/.+' + _TESTS = [ + { + 'url': 'http://ustudio.com/video/Uxu2my9bgSph/san_francisco_golden_gate_bridge', + 'md5': '58bbfca62125378742df01fc2abbdef6', + 'info_dict': { + 'id': 'Uxu2my9bgSph', + 'ext': 'mp4', + 'title': 'San Francisco: Golden Gate Bridge', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'md5:23925500697f2c6d4830e387ba51a9be', + 'uploader': 'Tony Farley', + } + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + doc = self._download_xml( + 'http://v1.ustudio.com/embed/{0}/ustudio/config.xml'.format( + video_id), + video_id, + note='Downloading video info', + errnote='Failed to download video info') + + formats = [ + { + 'url': quality.attrib['url'], + 'width': int_or_none(quality.attrib.get('width')), + 'height': int_or_none(quality.attrib.get('height')), + } for quality in doc.findall('./qualities/quality/video') + ] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'formats': formats, + 'description': self._og_search_description(webpage), + 'uploader': self._html_search_regex( + r'(.+) on', + webpage, + 'uploader', + fatal=False), + }