Python3之乱码\xe6\x97\xa0\xe6\xb3\x95处理方式

import chardet
response = chardet.detect(b'\xe5\xbd\x93\xe5\x89\x8d\xe7\x9b\xae\xe5\xbd\x95\xe4\xb8\x8b\xe6\x89\x80\xe6\x9c\x89\xe6\x96\x87\xe4\xbb\xb6\xe5\x90\x8d\xe6\xb1\x87\xe6\x80\xbb\xe5\x88\x97\xe8\xa1\xa8')
print(response)

{'encoding': 'utf-8', 'confidence': 0.99, 'language': ''}

response = b'\xe5\xbd\x93\xe5\x89\x8d\xe7\x9b\xae\xe5\xbd\x95\xe4\xb8\x8b\xe6\x89\x80\xe6\x9c\x89\xe6\x96\x87\xe4\xbb\xb6\xe5\x90\x8d\xe6\xb1\x87\xe6\x80\xbb\xe5\x88\x97\xe8\xa1\xa8'
print(response.decode('utf8'))

# def decode_char(*args):
#   response = args[0]
#   print(response.decode('utf8'))
#
# c = b'\a8\xe5\x90\xa7\xef\xbc\x81'
#
# decode_char(c)

s = '绝地求生'
ss = s.encode()
print(type(ss))
print(ss)

s = b'\xe7\xbb\x9d\xe5\x9c\xb0\xe6\xb1\x82\xe7\x94\x9f'
ss = s.decode()
print(type(ss))
print(ss)

s = '\xe7\xbb\x9d\xe5\x9c\xb0\xe6\xb1\x82\xe7\x94\x9f'
ss = s.encode('raw_unicode_escape')
print(type(ss))
print(ss)

sss = ss.decode()
print(sss)

s = b'\xe7\xbb\x9d\xe5\x9c\xb0\xe6\xb1\x82\xe7\x94\x9f'

print(type(s))
print(s)

ss = str(s, 'utf8')
print(ss)

import urllib.request
response = urllib.request.urlopen('http://www.baidu.com')
html = response.read()
print(html)

import urllib.request
response = urllib.request.urlopen('http://www.baidu.com')
html =str(response.read(),'utf-8')
print(html)