Jieba分词——三国演义上卷节选

Posted 2021-03-02 glzt

import jieba
path = ‘C:UsersAdministratorDesktop3国演义.txt‘
text = open(path,‘r‘,encoding=‘utf-8‘).read()
words = jieba.lcut(text)
excludes = [‘将军‘,‘却说‘,‘二人‘,‘不可‘,‘商议‘,‘天下‘,‘军士‘,‘次日‘,‘徐州‘,‘天子‘,‘如何‘,‘引兵‘,‘引军‘,‘军马‘,‘太守‘,‘朝廷‘,‘不能‘,‘诸侯‘,‘出马‘,‘太师‘]
counts = {}
for word in words:
    if len(word) == 1:
        continue
    elif word == ‘诸葛亮‘or word == ‘孔明曰‘:
        rword = ‘孔明‘
    elif word == ‘玄德‘or word == ‘玄德曰‘:
        rword = ‘刘备‘
    elif word == ‘孟德‘or word == ‘丞相‘:
        rword = ‘曹操‘
    elif word == ‘关公‘or word == ‘云长‘:
        rword = ‘关羽‘
    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(15):
    word,count = items[i]   
    print("{0:<10}{1:>5}".format(word,count))