import string txt = "我是个日本人。我毎天六点半起床。我学习Python。我总在好奇" wrk = [x for x in txt if not x in string.ascii_letters] aset = set(wrk) print(aset)
Standard input is empty
{'点', '。', '六', '天', '本', '学', '在', '奇', '好', '习', '起', '床', '总', '日', '我', '毎', '人', '个', '是', '半'}