运用结巴库分析三国演义的人物出场次数

Posted 2021-03-01 hayhong

 

import  jieba

txt = open("D:三国演义.txt", "r", encoding=‘ANSI‘).read()
words = jieba.lcut(txt)     # 使用精确模式对文本进行分词
counts = {}     # 通过键值对的形式存储词语及其出现的次数
for word in words:
    if  len(word) == 1:    # 单个词语不计算在内
        continue
    elif word == "诸葛亮" or word == "孔明曰":         #把相同的人合在一起
        rword = "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:
        counts[word] = counts.get(word, 0) + 1    # 遍历所有词语，每出现一次其对应的值加 1
excludes = {"将军","却说","荆州","二人","不可","不能","如此","商议","如何","主公","军士"}     #找出不是人物的词语  
for word in excludes:
    del(counts[word])       #删除不是人物的词雨 
items = list(counts.items())#将键值对转换成列表
items.sort(key=lambda x: x[1], reverse=True)    # 根据词语出现的次数进行从大到小排序
for i in range(15):
    word, count = items[i]
    print("{0:<5}{1:>5}".format(word, count))