#三国人物用词统计
#1、打开文本文件,并read后把read的结果放到txt中
txt=open("threekingdoms.txt","r",encoding="utf-8").read()
#2、英文分词里习惯将将符号替换为空格，但是中文分词用jieba库就不需要替换操作了。进行分词操作将分词放入words列表
import jieba
words=jieba.lcut(txt)
#3、建立words,抽取长度不为1的字符，组成新的字典dicwords
exp=["却说","锦州","二人","将军","不可","不能","如此"]
dicwords={}
for i in words:
    if len(i)==1:#排除字符长度为1的
        continue
    elif i in exp:
        continue
    elif i=="孔明曰" or i=="孔明":
        dicwords["孔明"]=dicwords.get("孔明",0)+1
    elif i == "玄德曰" or i == "玄德":
        dicwords["玄德"] = dicwords.get("玄德", 0) + 1
    else:
        dicwords[i]=dicwords.get(i,0)+1
#4、对列表中字符与出现的次数进行排序
lsdicwords=list(dicwords.items())
lsdicwords.sort(key=lambda x:x[1],reverse=True)

#找出前十名用的高频词汇
n=0
for i in lsdicwords:
     name,times=i
     #print(name,times)
     n=n+1
     if n==10:
        break
#也可以这样写
for i in range(15):
    name,tiems=lsdicwords[i]
    print(name,times)