如何将Python库自动检测并实现GBK转UTF-8编码转换？

本文共计411个文字，预计阅读时间需要2分钟。

原文内容较长，以下是对其进行简化后的版本：

原文文件支持GBK、UTF8及ASCII编码。自动检测GBK编码转为不带BOM的UTF-8。题外话：Python格式乱，tab问题很烦。安装基础工具：apt-get install python3 pip3 pip3 install chardet /debug/gbk2u8.py /src/

原来文件只有GBK,UTF8以及ASCII

自动检测GBK转码成不带BOM的UTF-8

题外话

Python的格式经常乱tab，就很烦

安装基础工具

apt-get install python3
apt-get install pip3
pip3 install chardet

+./debug/gbk2u8.py +./src/ +./inc/

cd debug
python gbk2u8.py

gbk2u8.py 文件代码

#-*- coding:utf-8 -*-
import os
import operator
import chardet

def strequal(a, b):
return operator.eq(str(a), str(b))
def getFileencode(filename):
with open(filename, 'rb') as f:
en=chardet.detect(f.read())
##print(en)
return en['encoding']
def fileGb2312ToUtf8(filename):
file_en=getFileencode(filename)

if strequal(file_en,'GB2312'):
print(filename+"gbk ",file_en)
content = open(filename,'rb').read()
new_content = content.decode('GB18030').encode('utf-8')
open(filename, 'wb').write(new_content)
elif strequal(file_en,'UTF-8-SIG'):
s = open(filename, mode='r', encoding='UTF-8-SIG').read()
open(filename, mode='w', encoding='utf-8').write(s)
else:
print(filename+"other ",file_en)


def fileExtension(filename):
return os.path.splitext(filename)[1]



def isCodeFile(filename):
extension = fileExtension(filename)
return (strequal(extension, '.h') ) or (strequal(extension, '.c')) \
or (strequal(extension, '.ini') ) or (strequal(extension, '.md')) or (strequal(extension, '.sh') )



def dirGb2312ToUtf8(dir):
list = []
for path,dirs,fs in os.walk(dir):
for f in fs:
fullPath = os.path.join(path,f)
list.append(fullPath)

for i, filename in enumerate(list):
if (isCodeFile(filename)):
fileGb2312ToUtf8(filename)


dirGb2312ToUtf8('../')