From 1da19488f906841cbfa285ad5ea378003c68ddf2 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Thu, 21 Apr 2016 23:29:51 +0800 Subject: [PATCH] [mgtv] Add new extractor (closes #9212) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/mgtv.py | 62 ++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+) create mode 100644 youtube_dl/extractor/mgtv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 84bdf5e97..d28f9e863 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -407,6 +407,7 @@ from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mgoon import MgoonIE +from .mgtv import MGTVIE from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE from .minoto import MinotoIE diff --git a/youtube_dl/extractor/mgtv.py b/youtube_dl/extractor/mgtv.py new file mode 100644 index 000000000..8f16a8f4c --- /dev/null +++ b/youtube_dl/extractor/mgtv.py @@ -0,0 +1,62 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import int_or_none + + +class MGTVIE(InfoExtractor): + _VALID_URL = r'https?://www\.mgtv\.com/v/(?:[^/]+/)*(?P\d+).html' + + _TEST = { + 'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html', + 'md5': '', + 'info_dict': { + 'id': '3116640', + 'ext': 'mp4', + 'title': '我是歌手第四季双年巅峰会:韩红李玟“双王”领军对抗', + 'description': '我是歌手第四季双年巅峰会', + 'duration': 7461, + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, # m3u8 download + }, + } + + _FORMAT_MAP = { + '标清': ('Standard', 0), + '高清': ('High', 1), + '超清': ('SuperHigh', 2), + } + + def _real_extract(self, url): + video_id = self._match_id(url) + api_data = self._download_json( + 'http://v.api.mgtv.com/player/video', video_id, + query={'video_id': video_id})['data'] + info = api_data['info'] + + formats = [] + for idx, stream in enumerate(api_data['stream']): + format_name = stream.get('name') + format_id, preference = self._FORMAT_MAP.get(format_name, (None, None)) + format_info = self._download_json( + stream['url'], video_id, + note='Download video info for format %s' % format_id or '#%d' % idx) + formats.append({ + 'format_id': format_id, + 'url': format_info['info'], + 'ext': 'mp4', # These are m3u8 playlists + 'preference': preference, + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': info['title'].strip(), + 'formats': formats, + 'description': info.get('desc'), + 'duration': int_or_none(info.get('duration')), + 'thumbnail': info.get('thumb'), + }