简单的小问题求解答（UnicodeDecodeError）

逍遥随风

#-*-coding:utf-8
import urllib.request
import re
import random
'''

'''
def open_url(url):
    opener = urllib.request.build_opener(proxy_support)
    opener.addheader = [('User-Agent' , 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36')]

    urllib.request.install_opener(opener)

    response = urllib.request.urlopen(url)
    html = response.read().decode('utf-8')

    return html

def get_img(html):
    p = r'(?:(?:[0,1]?\d?\d|2[0-4]\d|25[0-5])\.){3}(?:[0,1]?\d?\d|2[0-4]\d|25[0-5])'
    iplist = re.findall(p,html)
    return iplist

IPurl = 'https://www.xicidaili.com/nt/'
url =  'https://search.sina.com.cn/?q=习大大&c=news&from=channel&ie=utf-8'

req = urllib.request.Request(IPurl)
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36')
ipweb = urllib.request.urlopen(req)
ip = get_img(ipweb.read().decode('utf-8'))

proxy_support = urllib.request.ProxyHandler({'http':random.choice(ip)})

html = open_url(url)
print(html)

在上述程序在运行过程中总会出现UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd0 in position 400: invalid continuation byte这样的报错，怎么解决啊？是因为不能用utf-8来解码吗

松_HWI3H

html.encoding=html.apparent.encoding
加入这行代码试一下

wp231957

传说中的编码问题  最闹心的问题