结巴分词

import jieba
import re
word = "aaddaweh大大的无ausdy五千股qeas华盛顿哈刚过去而过千万股ads"
cleaned_data = re.findall(u"[\u4e00-\u9fa5]+",word)
r = ''
for i in cleaned_data:
    b = str(cleaned_data)
    i = str(i)
    r += i
a = jieba.lcut(r)
print(a)
>>>['大大的', '无', '五千股', '华盛顿', '哈', '刚过去', '而', '过', '千万', '股']