[Python] 解析乱码HTML并转换为UTF-8编码

import chardet
from urllib.request import urlopen

# 网址
url = ""

# 请求网页
response=urlopen(url,timeout=3)
html_byte=response.read()

# 读取网页编码类型
chardit1 = chardet.detect(html_byte)
print("编码: "+chardit1['encoding'])
print("语言: "+chardit1['language'])

# 显示正确解码后的网页数据
# print(html_byte.decode(chardit1['encoding']))

# 写入文件
file = open('index.html', 'wb')
html_string=html_byte.decode(chardit1['encoding']).encode('utf-8')
file.write(html_string)
file.close()