From 37c1e4025c6df834e93a64c1c13eebac23e90942 Mon Sep 17 00:00:00 2001 From: ping Date: Mon, 6 Jul 2015 15:26:49 +0800 Subject: [PATCH] [yinyuetai] New extractor for yinyuetai.com --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/yinyuetai.py | 47 +++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) create mode 100644 youtube_dl/extractor/yinyuetai.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index aba62db532..8665855eb3 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -733,6 +733,7 @@ YandexMusicPlaylistIE, ) from .yesjapan import YesJapanIE +from .yinyuetai import YinYueTaiIE from .ynet import YnetIE from .youjizz import YouJizzIE from .youku import YoukuIE diff --git a/youtube_dl/extractor/yinyuetai.py b/youtube_dl/extractor/yinyuetai.py new file mode 100644 index 0000000000..661c346027 --- /dev/null +++ b/youtube_dl/extractor/yinyuetai.py @@ -0,0 +1,47 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class YinYueTaiIE(InfoExtractor): + IE_NAME = 'yinyuetai:video' + _VALID_URL = r'https?://v\.yinyuetai\.com/video(/h5)?/(?P[0-9]+)' + _TEST = { + 'url': 'http://v.yinyuetai.com/video/2322376', + 'md5': '6e3abe28d38e3a54b591f9f040595ce0', + 'info_dict': { + 'id': '2322376', + 'ext': 'mp4', + 'title': '少女时代_PARTY_Music Video Teaser', + 'creator': '少女时代', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + info = self._download_json( + 'http://ext.yinyuetai.com/main/get-h-mv-info?json=true&videoId=%s' % video_id, video_id, + 'Downloading mv info')['videoInfo']['coreVideoInfo'] + + if info['error']: + raise ExtractorError(info['errorMsg'], expected=True) + + formats = [ + {'url': format_info['videoUrl'], 'format_id': format_info['qualityLevel'], + 'format': format_info['qualityLevelName'], 'filesize': format_info['fileSize'], + 'ext': 'mp4', 'preference': format_info['bitrate']} + for format_info in info['videoUrlModels'] + ] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': info['videoName'], + 'thumbnail': info['bigHeadImage'], + 'creator': info['artistNames'], + 'duration': info['duration'], + 'formats': formats, + }