jieba分词

import jieba
txt = open("D:\python-learn\lianxi\聊斋志异.txt","r",encoding = 'utf-8').read()
words = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    else:
        counts[word] = counts.get(word,0)+1
        items = list(counts.items())
        items.sort(key = lambda x:x[1],reverse = True)
for i in range(20):
    word,count = items[i]
    print("{0:<10}{1:>5}".format(word,count))

print("学号后两位30")

 

jieba分词