Separates low-ASCII characters from everything else.

mixed.txt

欢迎来到Mifos管理区域

separate.py

#!/usr/bin/python

import codecs

# see http://stackoverflow.com/questions/5179042/vim-deleting-non-roman-characters

mixedInput = codecs.open('mixed.txt', 'r', 'utf-8')
lowAsciiOutput = codecs.open('lowAscii.txt', 'w', 'utf-8')
otherOutput = codecs.open('other.txt', 'w', 'utf-8')

for rawline in mixedInput:
    line = rawline.rstrip()
    for c in line:
        if ord(c) < 2**7:
            lowAsciiOutput.write(c)
        else:
            otherOutput.write(c)
    otherOutput.write('\n')
    lowAsciiOutput.write('\n')

mixedInput.close()
lowAsciiOutput.close()
otherOutput.close()