聊斋相关分词

import jieba
text=open('E:/聊斋志异/聊斋志异.txt',"r",encoding='utf-8').read()
words=jieba.lcut(text)
counts={}
for word in words:
   if len(word)==1:  #排除带个字符的分词效果
      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))

结果：