Python出现中文乱码问题的全面解决方案

# -*- coding: utf-8 -*-

# 将字符串编码为字节
text = "中文内容"
encoded = text.encode('utf-8')  # 输出: b'\xe4\xb8\xad\xe6\x96\x87\xe5\x86\x85\xe5\xae\xb9'

# 将字节解码为字符串
decoded = encoded.decode('utf-8')  # 输出: '中文内容'

# 写入文件（使用UTF-8编码）
with open('file.txt', 'w', encoding='utf-8') as f:
    f.write("这是中文内容")

# 读取文件（使用UTF-8编码）
with open('file.txt', 'r', encoding='utf-8') as f:
    content = f.read()
    print(content)  # 正确显示: 这是中文内容

import requests

response = requests.get('https://example.com/chinese-page')
# 自动根据响应头确定编码
response.encoding = response.apparent_encoding  
print(response.text)  # 正确显示中文

import sys, io

# 对于标准输出
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')

# 对于标准错误
sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding='utf-8')

# Python 2中必须添加文件编码声明
# -*- coding: utf-8 -*-

# 使用unicode字符串前缀
text = u"中文内容"

# 解码字节字符串
byte_data = "中文内容".decode('utf-8')

# 编码为字节字符串
utf8_data = u"中文内容".encode('utf-8')

import chardet

# 检测字节数据的编码
raw_data = b'\xe4\xb8\xad\xe6\x96\x87'
result = chardet.detect(raw_data)
encoding = result['encoding']  # 输出: 'utf-8'

text = raw_data.decode(encoding)
print(text)  # 输出: 中文

# 忽略无法解码的字符
text = b'mixed \xe4\xb8\xad encoding'.decode('utf-8', errors='ignore')

# 替换无法解码的字符
text = b'mixed \xe4\xb8\xad encoding'.decode('utf-8', errors='replace')

import pymysql

connection = pymysql.connect(
    host='localhost',
    user='user',
    password='password',
    db='database',
    charset='utf8mb4',  # 支持4字节的UTF-8编码
    cursorclass=pymysql.cursors.DictCursor
)