通过读取文件头(前8个字节)判断文件的类型并添加后缀

遍历目录及所有文件, 读取前8个字节判断文件的类型并添加后缀

import os
import shutil

# 魔数与文件类型的映射
MAGIC_NUMBERS = {
    b'\xff\xd8\xff': 'jpg',  # JPEG
    b'\x89PNG\r\n\x1a\n': 'png',  # PNG
    b'GIF87a': 'gif',  # GIF 87a
    b'GIF89a': 'gif',  # GIF 89a
    b'\x42\x4d': 'bmp',  # BMP
    b'\x25\x50\x44\x46': 'pdf',  # PDF
    b'\x50\x4b\x03\x04': 'zip',  # ZIP
    b'\x52\x61\x72\x21': 'rar',  # RAR
    b'\x37\x7a\xbc\xaf\x27\x1c': '7z',  # 7-Zip
    b'\x49\x44\x33': 'mp3',  # MP3
    b'\x66\x74\x79\x70': 'mp4',  # MP4
    b'\x52\x49\x46\x46': 'avi',  # AVI or WAV, 需进一步区分
    b'\x4d\x5a': 'exe',  # EXE
    b'\x75\x73\x74\x61\x72': 'tar',  # TAR
    b'\x7f\x45\x4c\x46': 'elf',  # ELF
    b'\x46\x4c\x56': 'flv',  # FLV
    b'\x49\x49\x2a\x00': 'tif',  # TIFF (Little Endian)
    b'\x4d\x4d\x00\x2a': 'tif',  # TIFF (Big Endian)
    b'\x52\x49\x46\x46': 'webp',  # WebP 需结合文件内容进一步区分
    b'\x56\x31\x4d\x4d': 'vmdk',  # 存储虚拟机的数据
    # 根据需要扩展
}


def get_file_type(file_path):
    with open(file_path, 'rb') as f:
        file_start = f.read(8)  # 读取前8个字节
    for magic, filetype in MAGIC_NUMBERS.items():
        if file_start.startswith(magic):
            return filetype
    return None

def rename_file(file_path, new_extension):
    base = os.path.splitext(file_path)[0]
    new_file_path = f"{base}.{new_extension}"
    shutil.move(file_path, new_file_path)
    return new_file_path

def process_directory(directory):
    for root, dirs, files in os.walk(directory):
        for filename in files:
            file_path = os.path.join(root, filename)
            
            # 获取文件类型
            file_type = get_file_type(file_path)
            
            if file_type:
                new_file_path = rename_file(file_path, file_type)
                print(f"Renamed: {file_path} -> {new_file_path}")
            else:
                print(f"Could not determine file type for: {file_path}")

if __name__ == "__main__":
    directory_to_process = r"C:\Users\Administrator\Desktop\data"
    process_directory(directory_to_process)