Python3 UTF-8编码转换教程 - 完全指南与实例 | Python编程技术

# 字符串编码示例
text = "你好，世界！ Hello, world! 😊"
utf8_bytes = text.encode('utf-8')  # 编码为UTF-8字节

print("原始字符串:", text)
print("UTF-8字节:", utf8_bytes)
print("字节类型:", type(utf8_bytes))
print("十六进制表示:", utf8_bytes.hex(' '))

# 字节解码示例
# 从十六进制创建bytes对象
hex_bytes = bytes.fromhex('e4bda0 e5a5bd efbc8c e4b896 e7958c efbc81 20 48656c6c6f2c20776f726c642120f09f988a')

decoded_text = hex_bytes.decode('utf-8')  # 解码为字符串

print("字节数据:", hex_bytes)
print("解码结果:", decoded_text)
print("字符串类型:", type(decoded_text))

# 写入UTF-8编码文件
with open('multilingual.txt', 'w', encoding='utf-8') as f:
    f.write("Python3 UTF-8文件操作示例\n")
    f.write("English: Hello World!\n")
    f.write("中文: 你好世界！\n")
    f.write("日本語: こんにちは世界！\n")
    f.write("Emoji: 🐍⭐🚀\n")

print("文件写入成功！")

# 读取UTF-8编码文件
with open('multilingual.txt', 'r', encoding='utf-8') as f:
    content = f.read()
    print("\n文件内容:")
    print(content)

# 处理解码错误
invalid_bytes = b'\xe4\xb8\x96\xff\xe7\x95\x8c'  # 包含无效字节

try:
    # 尝试解码可能无效的字节
    decoded = invalid_bytes.decode('utf-8')
except UnicodeDecodeError as e:
    print(f"解码错误: {e}")
    # 使用错误处理策略
    decoded_replace = invalid_bytes.decode('utf-8', errors='replace')
    print("替换无效字符结果:", decoded_replace)  # 输出: 世�界

# 使用chardet检测编码（需要安装：pip install chardet）
import chardet

def detect_encoding(file_path):
    with open(file_path, 'rb') as f:
        raw_data = f.read(1000)  # 读取部分内容用于检测
        result = chardet.detect(raw_data)
        return result['encoding']

file_encoding = detect_encoding('multilingual.txt')
print(f"检测到的文件编码: {file_encoding}")

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

def main():
    """UTF-8编码转换完整示例"""
    # 1. 字符串编码
    text = "Python3 UTF-8编码转换示例 ★"
    encoded = text.encode('utf-8')
    print(f"编码结果: {encoded}")
    
    # 2. 字节解码
    decoded = encoded.decode('utf-8')
    print(f"解码结果: {decoded}")
    
    # 3. 文件操作
    with open('demo_utf8.txt', 'w', encoding='utf-8') as f:
        f.write(text + "\n第二行内容")
    
    with open('demo_utf8.txt', 'r', encoding='utf-8') as f:
        content = f.read()
        print(f"文件内容: {content}")
    
    # 4. 错误处理
    try:
        invalid = b'Invalid\xffsequence'.decode('utf-8')
    except UnicodeDecodeError:
        print("捕获到解码错误，使用替换策略:")
        valid = b'Invalid\xffsequence'.decode('utf-8', errors='replace')
        print(valid)

if __name__ == "__main__":
    main()