From a172d96292abda037b23b1f2b14dd2c6e65b56bb Mon Sep 17 00:00:00 2001 From: bonfy Date: Sat, 7 Mar 2015 14:05:56 +0800 Subject: [PATCH 1/2] [douyutv] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/douyutv.py | 59 ++++++++++++++++++++++++++++++++ 2 files changed, 60 insertions(+) create mode 100644 youtube_dl/extractor/douyutv.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index ffcc7d9ab..7d0798176 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -106,6 +106,7 @@ from .dctp import DctpTvIE from .deezer import DeezerPlaylistIE from .dfb import DFBIE from .dotsub import DotsubIE +from .douyutv import DouyutvIE from .dreisat import DreiSatIE from .drbonanza import DRBonanzaIE from .drtuber import DrTuberIE diff --git a/youtube_dl/extractor/douyutv.py b/youtube_dl/extractor/douyutv.py new file mode 100644 index 000000000..e9b92eb3b --- /dev/null +++ b/youtube_dl/extractor/douyutv.py @@ -0,0 +1,59 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + +from ..utils import ( + ExtractorError, +) + +class DouyutvIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P[A-Za-z0-9]+)' + + ''' + show_status: 1 直播中 ，2 没有直播 + ''' + + _TEST = { + 'url': 'http://www.douyutv.com/iseven', + 'info_dict': { + 'id': 'iseven', + 'title': '清晨醒脑！T-ara根本停不下来！', + 'ext': 'flv', + 'thumbnail': 're:^https?://.*\.jpg$', + 'is_live': True, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + info_url = 'http://www.douyutv.com/api/client/room/' + video_id + + config = self._download_json(info_url, video_id) + + error_code = config.get('error') + show_status = config['data'].get('show_status') + if error_code is not 0: + raise ExtractorError('Server reported error %i' % error_code, + expected=True) + + if show_status == '2': + raise ExtractorError('The live show has not yet started', + expected=True) + + title = config['data'].get('room_name') + rtmp_url = config['data'].get('rtmp_url') + rtmp_live = config['data'].get('rtmp_live') + thumbnail = config['data'].get('room_src') + + url = rtmp_url+'/'+rtmp_live + + return { + 'id': video_id, + 'title': title, + 'ext':'flv', + 'url': url, + 'thumbnail': thumbnail, + 'is_live': True, + # TODO more properties (see youtube_dl/extractor/common.py) + } \ No newline at end of file From 2ca1c5aa9f8d7db08608de0bd99f6c994ab496d3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 17 Mar 2015 22:27:33 +0600 Subject: [PATCH 2/2] [douyutv] Improve and extract all formats --- youtube_dl/extractor/__init__.py | 2 +- youtube_dl/extractor/douyutv.py | 72 ++++++++++++++++++++------------ 2 files changed, 46 insertions(+), 28 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index f3901bfc3..73c17aa84 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -107,7 +107,7 @@ from .dctp import DctpTvIE from .deezer import DeezerPlaylistIE from .dfb import DFBIE from .dotsub import DotsubIE -from .douyutv import DouyutvIE +from .douyutv import DouyuTVIE from .dreisat import DreiSatIE from .drbonanza import DRBonanzaIE from .drtuber import DrTuberIE diff --git a/youtube_dl/extractor/douyutv.py b/youtube_dl/extractor/douyutv.py index e9b92eb3b..d7956e6e4 100644 --- a/youtube_dl/extractor/douyutv.py +++ b/youtube_dl/extractor/douyutv.py @@ -2,58 +2,76 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import ExtractorError -from ..utils import ( - ExtractorError, -) -class DouyutvIE(InfoExtractor): +class DouyuTVIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P[A-Za-z0-9]+)' - - ''' - show_status: 1 直播中 ，2 没有直播 - ''' - _TEST = { 'url': 'http://www.douyutv.com/iseven', 'info_dict': { 'id': 'iseven', - 'title': '清晨醒脑！T-ara根本停不下来！', 'ext': 'flv', + 'title': 're:^清晨醒脑！T-ara根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'description': 'md5:9e525642c25a0a24302869937cf69d17', 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': '7师傅', + 'uploader_id': '431925', 'is_live': True, + }, + 'params': { + 'skip_download': True, } } def _real_extract(self, url): video_id = self._match_id(url) - info_url = 'http://www.douyutv.com/api/client/room/' + video_id - config = self._download_json(info_url, video_id) + config = self._download_json( + 'http://www.douyutv.com/api/client/room/%s' % video_id, video_id) - error_code = config.get('error') - show_status = config['data'].get('show_status') + data = config['data'] + + error_code = config.get('error', 0) + show_status = data.get('show_status') if error_code is not 0: - raise ExtractorError('Server reported error %i' % error_code, - expected=True) + raise ExtractorError( + 'Server reported error %i' % error_code, expected=True) + # 1 = live, 2 = offline if show_status == '2': - raise ExtractorError('The live show has not yet started', - expected=True) + raise ExtractorError( + 'Live stream is offline', expected=True) + + base_url = data['rtmp_url'] + live_path = data['rtmp_live'] - title = config['data'].get('room_name') - rtmp_url = config['data'].get('rtmp_url') - rtmp_live = config['data'].get('rtmp_live') - thumbnail = config['data'].get('room_src') + title = self._live_title(data['room_name']) + description = data.get('show_details') + thumbnail = data.get('room_src') - url = rtmp_url+'/'+rtmp_live + uploader = data.get('nickname') + uploader_id = data.get('owner_uid') + + multi_formats = data.get('rtmp_multi_bitrate') + if not isinstance(multi_formats, dict): + multi_formats = {} + multi_formats['live'] = live_path + + formats = [{ + 'url': '%s/%s' % (base_url, format_path), + 'format_id': format_id, + 'preference': 1 if format_id == 'live' else 0, + } for format_id, format_path in multi_formats.items()] + self._sort_formats(formats) return { 'id': video_id, 'title': title, - 'ext':'flv', - 'url': url, + 'description': description, 'thumbnail': thumbnail, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'formats': formats, 'is_live': True, - # TODO more properties (see youtube_dl/extractor/common.py) - } \ No newline at end of file + }