- 帖子
- 11
- 精华
- 0
- 积分
- 55
- 阅读权限
- 20
- 注册时间
- 2018-1-28
- 最后登录
- 2018-4-12
|
代码:
import jieba
excludes={"将军","却说","荆州","二人","不可","不能","如此"}
txt=open("三国演义.txt","r",encoding='utf-8').read()
words=jieba.lcut(txt)
couts={}
for word in words:
if len(word)==1:
continue
elif word=="诸葛亮" or word=="孔明曰":
rword="孔明"
elif word=="玄德" or word=="玄德曰":
rword="刘备"
elif word=="关公" or word=="云长":
rword="关羽"
elif word=="丞相" or word=="孟德":
rword="曹操"
else:
rword=word
couts[rword]=couts.get(rword,0)+1
for word in excludes:
del(couts[word])
items=list(couts.items)
items.sort(key=lambda x:x[1],reverse=Ture)
for i in items:
m,n=items
print("{0:<10}{1:>5}".format(m,n))
|
|