統計《三國演義》中出現次數較高的人物。

import jieba
excludes={"先主","將軍","卻說","荊州","二人","不可","不能","如此","忽然","下馬","喊聲","馬岱","心中","大驚","以為","不得","下文","糧草","追趕","報知","一聲","回報","分解","三千","分付","出馬","只得","之兵","曹兵","隨后","大將","一齊","許都","且說","眾官","洛陽","商議","如何","主公","軍士","左右","軍馬","引兵","次日","大喜","天下","于是","東吳","今日","不敢","魏兵","陛下","人馬","不知","漢中","一人","眾將","只見","蜀兵","大叫","上馬","天子","此人","一面","太守","后人","背后","何不","城中","忽報","先鋒","大軍","先生","然后","何故","夫人","不如","令人","趕來","原來","江東","正是","成都","徐州","因此","未知","大敗","百姓","大事","一軍","起兵","之后","接應","不見","進兵","可以","引軍","軍中","大怒"}
txt=open("G:\study\Python\三國演義.txt","r",encoding="utf-8").read()#讀取文件《三國演義》
words=jieba.lcut(txt)#通過jieba庫中的精確模式把文本精確分開不存在冗余詞組
counts={}#用于記錄出現的次數
for word in words:if len(word)==1:continueelif word=="諸葛亮" or word=="孔明曰":rword="孔明"elif word=="關公" or word=="云長":rword="關羽"elif word=="玄德" or word=="玄德曰":rword="劉備"elif word=="孟德" or word=="丞相":rword="曹操"elif word=="后主" or word=="阿斗":rword="劉禪"elif word=="都督" or word=="公瑾":rword="周瑜"elif word=="子龍" :rword="趙云"else:rword=wordcounts[rword]=counts.get(rword,0)+1
for word in excludes:#若存在上述excludes里面的詞組都不是詞組，然后減一del(counts[word])
items=list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)#通過出現的次數降序排序輸出
for i in range(50):word,count=items[i]print("{0:<10}{1:>5}".format(word,count))#進行格式的調整