python分析三國演義中出現次數最多的詞作詞頻統計

import jieba
"""分析三國演義小說中名字出現次數最多的人物然后輸出"""
#第一步 讀取小說內容
fb=open('三國演義.txt','r',encoding='utf-8')# 'r'表示操作read
content=fb.read()
fb.close()
excludes = {"將軍", "卻說", "荊州", "二人", "不可", "不能", "如此", "商議", "如何", "主公",

            "軍士", "左右", "軍馬", "引兵", "次日", "大喜", "天下", "東吳", "於是", "今日",

            "不敢", "魏兵","人馬", "陛下", "一人", "不知", "漢中", "只見", "眾將","蜀兵","丞相"}  #排除
print('--------------------------------------------------------------------')
#第二步 分詞
words=jieba._lcut(content)
#3.統計 容器 數據{單詞：次數}
data={}#定義空字典
for word in words:
    if(len(word)==1):#去除符號和單字
        continue
    elif word=='孔明曰'or word=='諸葛亮':
        rename='孔明'
    elif word=='玄德曰'or word=='玄德':
        rename='劉備'
    elif word=='雲長'or word=='關公':
        rename='關羽'
    else:
        rename=word
    data[rename] = data.get(rename, 0) + 1

#2.去除干擾詞匯
for word in excludes:
   del(data[word])


#排序
list=list(data.items())#轉成列表以便排序
list.sort(key=lambda x:x[1],reverse=True)
fo=open('result.txt','w',encoding='utf-8')

for i in range(10):#返回序列
    print('{:<10}{:>5}'.format(list[i][0],list[i][1]))#輸出到控制台
    fo.write('{:<10}{:>5}{}'.format(list[i][0],list[i][1],'\n'))#寫入到文件
fo.close()

 

運行結果：