ytdl-nightly/youtube_dl/extractor/douyutv.py

134 lines
4.4 KiB
Python
Raw Normal View History

2015-03-07 07:05:56 +01:00
# coding: utf-8
from __future__ import unicode_literals
import hashlib
import time
2015-03-07 07:05:56 +01:00
from .common import InfoExtractor
from ..utils import (ExtractorError, unescapeHTML)
from ..compat import (compat_str, compat_basestring)
2015-03-07 07:05:56 +01:00
class DouyuTVIE(InfoExtractor):
2015-07-10 18:50:45 +02:00
IE_DESC = '斗鱼'
2016-03-25 08:43:29 +01:00
_VALID_URL = r'https?://(?:www\.)?douyu(?:tv)?\.com/(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
2015-03-07 07:05:56 +01:00
'url': 'http://www.douyutv.com/iseven',
'info_dict': {
'id': '17732',
'display_id': 'iseven',
2015-03-07 07:05:56 +01:00
'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}$',
2016-03-04 06:36:29 +01:00
'description': 'md5:f34981259a03e980a3c6404190a3ed61',
2015-03-07 07:05:56 +01:00
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': '7师傅',
'uploader_id': '431925',
2015-03-07 07:05:56 +01:00
'is_live': True,
},
'params': {
'skip_download': True,
2016-03-04 06:36:29 +01:00
},
}, {
'url': 'http://www.douyutv.com/85982',
'info_dict': {
'id': '85982',
'display_id': '85982',
'ext': 'flv',
'title': 're:^小漠从零单排记——CSOL2躲猫猫 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'douyu小漠',
'uploader_id': '3769985',
'is_live': True,
},
'params': {
'skip_download': True,
2016-03-04 06:36:29 +01:00
},
'skip': 'Romm not found',
}, {
'url': 'http://www.douyutv.com/17732',
'info_dict': {
'id': '17732',
'display_id': '17732',
'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}$',
'description': 'md5:f34981259a03e980a3c6404190a3ed61',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': '7师傅',
'uploader_id': '431925',
'is_live': True,
},
'params': {
'skip_download': True,
},
2016-03-25 08:43:29 +01:00
}, {
'url': 'http://www.douyu.com/xiaocang',
'only_matching': True,
}]
2015-03-07 07:05:56 +01:00
def _real_extract(self, url):
video_id = self._match_id(url)
if video_id.isdigit():
room_id = video_id
else:
page = self._download_webpage(url, video_id)
room_id = self._html_search_regex(
r'"room_id"\s*:\s*(\d+),', page, 'room id')
prefix = 'room/%s?aid=android&client_sys=android&time=%d' % (
room_id, int(time.time()))
auth = hashlib.md5((prefix + '1231').encode('ascii')).hexdigest()
config = self._download_json(
'http://www.douyutv.com/api/v1/%s&auth=%s' % (prefix, auth),
video_id)
2015-03-07 07:05:56 +01:00
data = config['data']
error_code = config.get('error', 0)
2015-03-07 07:05:56 +01:00
if error_code is not 0:
error_desc = 'Server reported error %i' % error_code
2015-03-29 12:17:48 +02:00
if isinstance(data, (compat_str, compat_basestring)):
error_desc += ': ' + data
raise ExtractorError(error_desc, expected=True)
2015-03-07 07:05:56 +01:00
show_status = data.get('show_status')
# 1 = live, 2 = offline
2015-03-07 07:05:56 +01:00
if show_status == '2':
raise ExtractorError(
'Live stream is offline', expected=True)
base_url = data['rtmp_url']
live_path = data['rtmp_live']
2015-03-07 07:05:56 +01:00
title = self._live_title(unescapeHTML(data['room_name']))
description = data.get('show_details')
thumbnail = data.get('room_src')
2015-03-07 07:05:56 +01:00
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)
2015-03-07 07:05:56 +01:00
return {
'id': room_id,
'display_id': video_id,
2015-03-07 07:05:56 +01:00
'title': title,
'description': description,
2015-03-07 07:05:56 +01:00
'thumbnail': thumbnail,
'uploader': uploader,
'uploader_id': uploader_id,
'formats': formats,
2015-03-07 07:05:56 +01:00
'is_live': True,
}