fork(1) download
  1. # -*- coding: utf-8 -*-
  2. import re
  3. s = u"中国,中,。》%国foo中¥国bar@中123=国%中国12-34中国"
  4. pat_block = u'[^\u4e00-\u9fff0-9a-zA-Z]+';
  5. pattern = u'([0-9]+{0}[0-9]+)|{0}'.format(pat_block)
  6. res = re.sub(pattern, lambda x: x.group(1) if x.group(1) else u"" ,s)
  7. print(res.encode("utf8"))
Success #stdin #stdout 0s 25400KB
stdin
Standard input is empty
stdout
中国中国foo中国bar中123国中国12-34中国