python批量转换xml文件编码为utf-8

# coding utf-8
import os
import chardet


# 获得所有.xml文件的路径,传入根目录路径
def find_all_file(path: str) -> str:
    for root, dirs, files in os.walk(path):
        for f in files:
            if f.endswith('.xml'):
                fullname = os.path.join(root, f)
                yield fullname
            pass
        pass
    pass


# 判断是不是utf-8编码方式
def judge_coding(path: str) -> dict:

    with open(path, 'rb') as f:
        c = chardet.detect(f.read())

    if c != 'utf-8':
        return c


# 修改文件编码方式
def change_to_utf_file(path: str):
    for i in find_all_file(path):
        c = judge_coding(i)
        if c:
            change(i, c['encoding'])
            print("{} 编码方式已从{}改为 utf-8".format(i, c['encoding']))


def change(path: str, coding: str):
    with open(path, 'r', encoding=coding) as f:
        text = f.read()

    with open(path, 'w', encoding='utf-8') as f:
        f.write(text)


# 查看所有文件编码方式
def check(path: str):
    for i in find_all_file(path):
        with open(i, 'rb') as f:
            print(chardet.detect(f.read())['encoding'], ': ', i)


def main():
    my_path = './all_xml'  # 存放xml文件的路径
    change_to_utf_file(my_path)
    # check(my_path)


if __name__ == '__main__':
    main()

  • 0
    点赞
  • 6
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值