Windows/Linux文本文件中文编码乱码问题解决方案

gbk_utf8_transformation.py

#!/usr/bin/env python
import sys, codecs

def transform(enc1, enc2, f1, f2):
    infile = codecs.open(f1, 'rU', enc1)
    outfile = codecs.open(f2, 'w', enc2, errors='ignore')
    if enc1 == 'utf-8' and enc2 == 'gbk':
        for line in infile.readlines():
            outfile.write(line[:-1] + '\r\n')
    elif enc1 == 'gbk' and enc2 == 'utf-8':
        for line in infile.readlines():
            outfile.write(line[:-2] + '\n')
    infile.close()
    outfile.close()
    print 'Transform {} file {} to {} file {} done.'.format(enc1,f1,enc2,f2)

if __name__ == '__main__':
    if len(sys.argv) == 4:
        if sys.argv[1] == '-2gbk':
            transform('utf-8', 'gbk', sys.argv[2], sys.argv[3])
        elif sys.argv[1] == '-2utf8':
            transform('gbk', 'utf-8', sys.argv[2], sys.argv[3])
    else:
        print "Invalid command"

Use python transform.py -2utf8 mygbkfile.txt myutf8file.txt to convert gbk encoded file to utf-8 encoded file
Use python transform.py -2gbk myutf8file.txt mygbkfile.txt to convert utf-8 encoded file to gbk encoded file