Python进阶指南之文本文件读写与编码格式选择详解

# ❌ 错误示例：尝试用 ASCII 保存中文
with open("product_desc.txt", "w", encoding="ascii") as f:
    f.write("这是一条中文商品描述")

# 写入文件
with open("example.txt", "w", encoding="utf-8") as file:
    file.write("Hello, 世界！\n")
    file.write("This is a test.")

# 读取文件
with open("example.txt", "r", encoding="utf-8") as file:
    content = file.read()
    print(content)

# config.ini
language = zh-CN
greeting = 你好，世界！
welcome = Hello, World!
message = こんにちは、世界！

def read_multilingual_config(filename):
    try:
        with open(filename, "r", encoding="utf-8") as f:
            lines = f.readlines()
        
        config = {}
        for line in lines:
            if '=' in line:
                key, value = line.strip().split('=', 1)
                config[key.strip()] = value.strip()
        
        return config
    except UnicodeDecodeError as e:
        print(f"❌ 文件解码失败：{e}")
        return None

# 调用
config = read_multilingual_config("config.ini")
print(config)
# 输出：
# {'language': 'zh-CN', 'greeting': '你好，世界！', 'welcome': 'Hello, World!', 'message': 'こんにちは、世界！'}

# ❌ 错误示范：用 UTF-8 读取 GBK 编码文件
with open("wrong_encoding.txt", "r", encoding="utf-8") as f:
    content = f.read()

# ✅ 使用正确的编码读取
with open("wrong_encoding.txt", "r", encoding="gbk") as f:
    content = f.read()
print(content)  # 正常显示中文内容

pip install chardet

import chardet

def detect_encoding(filename):
    with open(filename, "rb") as f:
        raw_data = f.read()
        result = chardet.detect(raw_data)
        return result['encoding']

# 使用
encoding = detect_encoding("unknown_file.txt")
print(f"检测到的编码：{encoding}")  # 例如：'GBK' 或 'UTF-8'

import chardet

def safe_read_file(filename, fallback_encodings=["utf-8", "gbk", "latin1"]):
    """
    安全读取文件，支持多种编码尝试
    """
    # 尝试预读前 1024 字节以检测编码
    with open(filename, "rb") as f:
        raw_data = f.read(1024)
    
    # 尝试自动检测
    detected = chardet.detect(raw_data)
    encoding = detected['encoding']
    
    # 若检测不到或不可靠，按备选列表尝试
    if encoding is None or detected['confidence'] < 0.7:
        for enc in fallback_encodings:
            try:
                with open(filename, "r", encoding=enc) as f:
                    return f.read(), enc
            except UnicodeDecodeError:
                continue
        raise ValueError(f"无法解析 {filename} 的编码格式")
    
    # 使用检测到的编码读取
    try:
        with open(filename, "r", encoding=encoding) as f:
            return f.read(), encoding
    except UnicodeDecodeError:
        # 如果检测结果也不对，尝试备选
        for enc in fallback_encodings:
            if enc == encoding:
                continue
            try:
                with open(filename, "r", encoding=enc) as f:
                    return f.read(), enc
            except UnicodeDecodeError:
                continue
        raise ValueError(f"所有编码均失败：{filename}")

# 测试
try:
    content, used_encoding = safe_read_file("mixed_encoding.txt")
    print(f"✅ 成功读取，使用编码：{used_encoding}")
    print(content)
except Exception as e:
    print(f"❌ 读取失败：{e}")

2024-05-20 10:30:15 INFO 用户登录成功：张三
2024-05-20 10:31:22 ERROR 登录失败：用户名不存在
2024-05-20 10:32:01 DEBUG 手机号验证通过

def analyze_log_errors(log_filename):
    errors = []
    keywords = {}

    with open(log_filename, "r", encoding="utf-8") as f:
        for line in f:
            if "ERROR" in line:
                errors.append(line.strip())
                
                # 提取中文部分
                import re
                chinese_match = re.search(r'：([^：]+)', line)
                if chinese_match:
                    text = chinese_match.group(1)
                    keywords[text] = keywords.get(text, 0) + 1
    
    return errors, keywords

# 执行分析
error_logs, keyword_count = analyze_log_errors("app.log")

print(f"🔍 发现 {len(error_logs)} 条错误日志：")
for log in error_logs:
    print(f"  - {log}")

print("\n📊 关键词统计：")
for word, count in keyword_count.items():
    print(f"  - '{word}' 出现 {count} 次")

# 危险！依赖系统默认编码
with open("data.txt", "w") as f:
    f.write("测试中文")

with open("data.txt", "w", encoding="utf-8") as f:
    f.write("测试中文")

# 错误：先用 UTF-8 写，再用 GBK 写
with open("mixed.txt", "w", encoding="utf-8") as f:
    f.write("你好\n")

with open("mixed.txt", "a", encoding="gbk") as f:
    f.write("你好\n")

with open("clean.txt", "w", encoding="utf-8") as f:
    f.write("你好\n")
    f.write("你好\n")

# 写入带 BOM 的 UTF-8
with open("bom_utf8.txt", "w", encoding="utf-8-sig") as f:
    f.write("Hello, 世界！\n")

# 写入无 BOM 的 UTF-8
with open("no_bom.txt", "w", encoding="utf-8") as f:
    f.write("Hello, 世界！\n")