JUKUAN/Lib/utils/read_log.py

import chardet

def detect_file_encoding(file_path):
    """
    检测文件编码
    
    Args:
        file_path: 文件路径
        
    Returns:
        检测到的编码类型和置信度
    """
    # 读取文件的二进制内容
    with open(file_path, 'rb') as file:
        raw_data = file.read()
    
    # 使用chardet检测编码
    result = chardet.detect(raw_data)
    
    return result

def read_file_with_encoding(file_path, encoding=None):
    """
    使用指定编码读取文件，如果没有指定编码则先检测编码
    
    Args:
        file_path: 文件路径
        encoding: 指定的编码类型（可选）
        
    Returns:
        文件内容
    """
    if not encoding:
        detected = detect_file_encoding(file_path)
        encoding = detected['encoding']
        print(f"检测到的编码: {detected}")
    
    try:
        with open(file_path, 'r', encoding=encoding) as file:
            content = file.read()
        return content
    except UnicodeDecodeError as e:
        print(f"使用 {encoding} 解码失败: {e}")
        return None

file_path = '/Users/maxfeng/Downloads/log.txt'
# 先检测编码
result = detect_file_encoding(file_path)
print(f"文件编码检测结果: {result}")

code = result['encoding']

# 然后用检测到的编码读取文件
content = read_file_with_encoding(file_path, code)
print("\n文件内容:")
print(content)

# with open('/Users/maxfeng/Downloads/log.txt', 'r', encoding='GB2312') as f:
#     content = f.read()
    
with open('/Users/maxfeng/Downloads/log2.txt', 'w', encoding='utf-8') as f:
    f.write(content)