yt-dlp/youtube_dl/extractor/douyutv.py

109 lines
3.5 KiB
Python
Raw Normal View History

2015-03-07 06:05:56 +00:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
2016-08-26 17:16:39 +00:00
from ..utils import (
ExtractorError,
unescapeHTML,
)
2015-03-07 06:05:56 +00:00
class DouyuTVIE(InfoExtractor):
2015-07-10 16:50:45 +00:00
IE_DESC = '斗鱼'
_VALID_URL = r'https?://(?:www\.)?douyu(?:tv)?\.com/(?:[^/]+/)*(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
2015-03-07 06:05:56 +00:00
'url': 'http://www.douyutv.com/iseven',
'info_dict': {
'id': '17732',
'display_id': 'iseven',
'ext': 'mp4',
'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}$',
'description': r're:.*m7show@163\.com.*',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '7师傅',
2015-03-07 06:05:56 +00:00
'is_live': True,
},
'params': {
'skip_download': True,
2016-03-04 05:36:29 +00:00
},
}, {
'url': 'http://www.douyutv.com/85982',
'info_dict': {
'id': '85982',
'display_id': '85982',
'ext': 'mp4',
'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}$',
'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'douyu小漠',
'is_live': True,
},
'params': {
'skip_download': True,
2016-03-04 05:36:29 +00:00
},
'skip': 'Room not found',
2016-03-04 05:36:29 +00:00
}, {
'url': 'http://www.douyutv.com/17732',
'info_dict': {
'id': '17732',
'display_id': '17732',
'ext': 'mp4',
'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}$',
'description': r're:.*m7show@163\.com.*',
'thumbnail': r're:^https?://.*\.jpg$',
2016-03-04 05:36:29 +00:00
'uploader': '7师傅',
'is_live': True,
},
'params': {
'skip_download': True,
},
2016-03-25 07:43:29 +00:00
}, {
'url': 'http://www.douyu.com/xiaocang',
'only_matching': True,
}, {
# \"room_id\"
'url': 'http://www.douyu.com/t/lpl',
'only_matching': True,
}]
2015-03-07 06:05:56 +00:00
2016-08-26 17:16:39 +00:00
# Decompile core.swf in webpage by ffdec "Search SWFs in memory". core.swf
# is encrypted originally, but ffdec can dump memory to get the decrypted one.
_API_KEY = 'A12Svb&%1UUmf@hC'
2015-03-07 06:05:56 +00:00
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')
2016-08-26 17:16:39 +00:00
room = self._download_json(
'http://m.douyu.com/html5/live?roomId=%s' % room_id, video_id,
note='Downloading room info')['data']
# 1 = live, 2 = offline
2016-08-26 17:16:39 +00:00
if room.get('show_status') == '2':
raise ExtractorError('Live stream is offline', expected=True)
formats = self._extract_m3u8_formats(
room['hls_url'], video_id, ext='mp4')
title = self._live_title(unescapeHTML(room['room_name']))
description = room.get('show_details')
thumbnail = room.get('room_src')
uploader = room.get('nickname')
2015-03-07 06:05:56 +00:00
return {
'id': room_id,
'display_id': video_id,
'formats': formats,
2015-03-07 06:05:56 +00:00
'title': title,
'description': description,
2015-03-07 06:05:56 +00:00
'thumbnail': thumbnail,
'uploader': uploader,
2015-03-07 06:05:56 +00:00
'is_live': True,
}