add_bom.py

# coding: utf-8
"""
@Createtime: 2025/04/07 12:00
@Updatetime: 2025/04/07 12:00
@Author: s1g0day
@Description: 为目录下所有CSV文件添加BOM头
"""
import os
import sys

def has_bom(file_path):
    """检查文件是否包含UTF-8 BOM头"""
    try:
        with open(file_path, 'rb') as f:
            return f.read(3) == b'\xef\xbb\xbf'
    except IOError as e:
        print(f"无法读取文件 {file_path}: {e}")
        return False

def add_bom_to_csv(directory):
    """为目录下所有CSV文件添加BOM头"""
    modified_files = 0
    skipped_files = 0
    error_files = 0

    for root, dirs, files in os.walk(directory):
        for file in files:
            if file.lower().endswith('.csv'):
                file_path = os.path.join(root, file)
                
                if has_bom(file_path):
                    print(f"跳过已包含BOM的文件: {file_path}")
                    skipped_files += 1
                    continue
                
                try:
                    # 读取原始内容
                    with open(file_path, 'rb') as f:
                        content = f.read()
                    
                    # 添加BOM头并写入新内容
                    with open(file_path, 'wb') as f:
                        f.write(b'\xef\xbb\xbf' + content)
                    
                    print(f"已添加BOM头: {file_path}")
                    modified_files += 1
                except Exception as e:
                    print(f"处理文件失败 {file_path}: {e}")
                    error_files += 1

    print("\n处理完成:")
    print(f"修改文件: {modified_files}")
    print(f"跳过文件: {skipped_files}")
    print(f"失败文件: {error_files}")

if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("使用方法: python add_bom.py <目录路径>")
        sys.exit(1)
    
    target_dir = sys.argv[1]
    if not os.path.isdir(target_dir):
        print(f"错误: {target_dir} 不是有效目录")
        sys.exit(1)
    
    add_bom_to_csv(target_dir)