# -*- coding:utf-8 -*- import re korean = u'崔雪莉(최진리)' line = [u'x', u'y', u'z', u'쭌', u'a'] if any([re.search(u'[\uAC00-\uD7A3]', x) for x in line[3:]]): print "found character" #[\uAC00-\uD7A3]基本包括所有的韩文,https://en.wikipedia.org/wiki/Template:Unicode_chart_Hangul_Syllables print re.sub(u'[\uAC00-\uD7A3]+','',korean) japan = u"不二周助ふじしゅうすけ" print re.sub(u'[\u0800-\u4e00]+','',japan)