# -*- coding: utf-8 -*-
"""
Created on Sun Feb 23 16:53:08 2020
@author: 15389
"""
#Calthreekingdoms.py
import jieba
txt = open("threekingdoms.txt","r",encoding="utf-8").read()
excludes = ("将军", "却说", "荆州", "二人", "不可", "不能", "如此")
words = jieba.lcut(txt)
counts = {}
for word in words:
if len(word) == 1:
continue
elif word == "诸葛亮" or "孔明曰":
rword = "孔明"
elif word == "关公" or "云长":
rword = "关羽"
elif word == "玄德" or "玄德曰":
rword = "刘备"
elif word == "孟德" or "丞相曰":
rword = "曹操"
else:
rword = word
counts[rword] = counts.get(rword, 0)+1
for word in excludes:
del counts[word]
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True)
for i in range(10):
word, count = items[i]
print("{0:<10}{1:>5}".format(word, count))
练习(三国演义字频统计)
最新推荐文章于 2022-12-05 21:17:09 发布