0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 03:33:02 +00:00
yt-dlp/youtube_dlc/extractor/douyutv.py

202 lines
6.7 KiB
Python
Raw Normal View History

2015-03-07 06:05:56 +00:00
# coding: utf-8
from __future__ import unicode_literals
import time
import hashlib
import re
2015-03-07 06:05:56 +00:00
from .common import InfoExtractor
2016-08-26 17:16:39 +00:00
from ..utils import (
ExtractorError,
unescapeHTML,
unified_strdate,
urljoin,
2016-08-26 17:16:39 +00:00
)
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': 'flv',
2017-05-01 19:29:34 +00:00
'title': 're:^清晨醒脑!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': '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}$',
'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
'thumbnail': r're:^https?://.*\.jpg$',
'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': 'flv',
2017-05-01 19:29:34 +00:00
'title': 're:^清晨醒脑!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
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')
# Grab metadata from mobile API
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)
# Grab the URL from PC client API
# The m3u8 url from mobile API requires re-authentication every 5 minutes
tt = int(time.time())
signContent = 'lapi/live/thirdPart/getPlay/%s?aid=pcclient&rate=0&time=%d9TUk5fjjUjg9qIMH3sdnh' % (room_id, tt)
sign = hashlib.md5(signContent.encode('ascii')).hexdigest()
video_url = self._download_json(
'http://coapi.douyucdn.cn/lapi/live/thirdPart/getPlay/' + room_id,
video_id, note='Downloading video URL info',
query={'rate': 0}, headers={
'auth': sign,
'time': str(tt),
'aid': 'pcclient'
})['data']['live_url']
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,
'url': video_url,
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,
}
class DouyuShowIE(InfoExtractor):
_VALID_URL = r'https?://v(?:mobile)?\.douyu\.com/show/(?P<id>[0-9a-zA-Z]+)'
_TESTS = [{
'url': 'https://v.douyu.com/show/rjNBdvnVXNzvE2yw',
'md5': '0c2cfd068ee2afe657801269b2d86214',
'info_dict': {
'id': 'rjNBdvnVXNzvE2yw',
'ext': 'mp4',
'title': '陈一发儿:砒霜 我有个室友系列04-01 22点场',
'duration': 7150.08,
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '陈一发儿',
'uploader_id': 'XrZwYelr5wbK',
'uploader_url': 'https://v.douyu.com/author/XrZwYelr5wbK',
'upload_date': '20170402',
},
}, {
'url': 'https://vmobile.douyu.com/show/rjNBdvnVXNzvE2yw',
'only_matching': True,
}]
def _real_extract(self, url):
url = url.replace('vmobile.', 'v.')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
room_info = self._parse_json(self._search_regex(
r'var\s+\$ROOM\s*=\s*({.+});', webpage, 'room info'), video_id)
video_info = None
for trial in range(5):
# Sometimes Douyu rejects our request. Let's try it more times
try:
video_info = self._download_json(
'https://vmobile.douyu.com/video/getInfo', video_id,
query={'vid': video_id},
headers={
'Referer': url,
'x-requested-with': 'XMLHttpRequest',
})
break
except ExtractorError:
self._sleep(1, video_id)
if not video_info:
raise ExtractorError('Can\'t fetch video info')
formats = self._extract_m3u8_formats(
video_info['data']['video_url'], video_id,
entry_protocol='m3u8_native', ext='mp4')
upload_date = unified_strdate(self._html_search_regex(
r'<em>上传时间:</em><span>([^<]+)</span>', webpage,
'upload date', fatal=False))
uploader = uploader_id = uploader_url = None
mobj = re.search(
r'(?m)<a[^>]+href="/author/([0-9a-zA-Z]+)".+?<strong[^>]+title="([^"]+)"',
webpage)
if mobj:
uploader_id, uploader = mobj.groups()
uploader_url = urljoin(url, '/author/' + uploader_id)
return {
'id': video_id,
'title': room_info['name'],
'formats': formats,
'duration': room_info.get('duration'),
'thumbnail': room_info.get('pic'),
'upload_date': upload_date,
'uploader': uploader,
'uploader_id': uploader_id,
'uploader_url': uploader_url,
}