From: mutantmonkey Date: Tue, 16 Feb 2016 01:30:53 +0000 (-0800) Subject: [KUSI] Add new extractor X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=199e72429106375218902102812e26c2fc6624b5;p=youtube-dl [KUSI] Add new extractor --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 537d25777..bfc2008be 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -338,6 +338,7 @@ from .konserthusetplay import KonserthusetPlayIE from .kontrtube import KontrTubeIE from .krasview import KrasViewIE from .ku6 import Ku6IE +from .kusi import KUSIIE from .kuwo import ( KuwoIE, KuwoAlbumIE, diff --git a/youtube_dl/extractor/kusi.py b/youtube_dl/extractor/kusi.py new file mode 100644 index 000000000..20407411b --- /dev/null +++ b/youtube_dl/extractor/kusi.py @@ -0,0 +1,61 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_urllib_parse_unquote_plus +from ..utils import int_or_none + + +class KUSIIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?kusi\.com/(?Pstory/.+|video\?clipId=(?P\d+))' + _TEST = { + 'url': 'http://www.kusi.com/story/31183873/turko-files-case-closed-put-on-hold', + 'md5': 'f926e7684294cf8cb7bdf8858e1b3988', + 'info_dict': { + 'id': '12203019', + 'ext': 'mp4', + 'title': 'Turko Files: Case Closed! & Put On Hold!', + 'duration': 231000, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + + if mobj.group('clipId') is not None: + video_id = mobj.group('clipId') + else: + webpage = self._download_webpage(url, mobj.group('path')) + video_id = self._html_search_regex(r'"clipId", "(\d+)"', webpage, + 'clipId') + + xml_url = 'http://www.kusi.com/build.asp?buildtype=buildfeaturexml'\ + 'request&featureType=Clip&featureid={0}&affiliateno=956&'\ + 'clientgroupid=1&rnd=562461'.format(video_id) + doc = self._download_xml(xml_url, video_id, + note='Downloading video info', + errnote='Failed to download video info') + + video_title = doc.find('HEADLINE').text + duration = int_or_none(doc.find('DURATION'), get_attr='text') + description = doc.find('ABSTRACT') + + quality_options = doc.find('{http://search.yahoo.com/mrss/}group').findall('{http://search.yahoo.com/mrss/}content') + formats = [] + for quality in quality_options: + if 'height' in quality.attrib: + formats.append({ + 'url': compat_urllib_parse_unquote_plus(quality.attrib['url']), + 'height': quality.attrib['height'], + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video_title, + 'description': description, + 'duration': duration, + 'formats': formats, + }