python实现文本编码转换

python实现文本编码转换

下列python可以将当前目录及子目录内的 .h和.c文件的编码批量转换为utf-8 BOM

import chardet
import os

def get_encoding(file):
    with open(file, "rb") as f:
        data = f.read()
        return chardet.detect(data)["encoding"]


for root, dirs, files in os.walk("."):
    for name in files:
        if os.path.splitext(name)[-1] in (".c",".h"):
            file_name = os.path.join(root, name)
            decoding = get_encoding(file_name)
            print(file_name)
            data = None
            with open(file_name, "r", encoding = decoding) as f:
                data = f.read()
            with open(file_name, "w", encoding = "utf-8-sig") as f:
                f.write(data)