使用批处理命令和python将当前文件夹下的csv文件转换成UTF-8格式

批处理命令

// An highlighted block
echo off
setlocal enabledelayedexpansion 
set DIR="%cd%"
for /R %DIR% %%f in (*.csv) do ( 
echo %%f
set "FILE_FULLNAME=%%~nxf"
python ToUTF8.py !FILE_FULLNAME!
echo change to UTF-8 completed
)
pause

python脚本

// An highlighted block
import sys
import os
import codecs
def handleEncoding(original_file):
    #newfile=original_file[0:original_file.rfind(.)]+'_copy.csv'
    newfile = original_file.replace(".csv","_copy.csv")
    f=open(original_file,'rb+')
    content=f.read()
    source_encoding='utf-8'
    try:
        content.decode('utf-8').encode('utf-8')
        source_encoding='utf-8'
    except:
        try:
            content.decode('gbk').encode('utf-8')
            source_encoding='gbk'
        except:
            try:
                content.decode('gb2312').encode('utf-8')
                source_encoding='gb2312'
            except:
                try:
                    content.decode('gb18030').encode('utf-8')
                    source_encoding='gb18030'
                except:
                    try:
                        content.decode('big5').encode('utf-8')
                        source_encoding='gb18030'
                    except:
                        content.decode('cp936').encode('utf-8')
                        source_encoding='cp936'
    f.close()
    block_size=4096
    with codecs.open(original_file,'r',source_encoding) as f:
        with codecs.open(newfile,'w','utf-8') as f2:
            while True:
                content=f.read(block_size)
                if not content:
                    break
                f2.write(content)
    os.replace(newfile ,original_file)
# dirs = os.listdir()
# for file in dirs:
#     if '.csv' in file:
#         handleEncoding(file)
if __name__ == '__main__':
    handleEncoding(sys.argv[1])