三国演义人物出场次数统计

统计中文词频需要用到python中的jieba库，用cmd模式下的pip install jieba命令安装好jieba库，下载好三国演义的文档并保存。注意，三国演义文档要保存为以下编码，否则出现错误。（用的python3.6 64位）
代码如下：

#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",#排除不是人名的词语
            "商议","如何","主公","军士","左右","军马","引兵",
            "次日","大喜","天下","东吴","于是","今日","不敢",
            "魏兵","陛下","一人","不知","都督","人马","汉中","大军",
            "众将","只见","后主","蜀兵","上马","大叫","太守","何不",
            "此人","夫人","先主","后人","背后","城中","天子","一面"}

words = jieba.lcut(txt)
counts = {}
for word in words:             #合并指代同一人的不同词语出现次数
    if len(word) == 1:
        continue
    elif word == "诸葛亮" or word =="孔明曰":
        reord = "孔明"
    elif word =="关公" or word =="云长":
        rword = "关羽"
    elif word =="玄德" or word =="玄德曰":
        rword = "刘备"
    elif word =="孟德" or word =="丞相":
        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(14):    #使用字典表达词频
    word,count = items[i]
    print("{0:<10}{1:>5}".format(word,count))