其他分享
首页 > 其他分享> > jieba分词 西游记

jieba分词 西游记

作者:互联网

import  jieba
 
txt = open("D:\\西游记.txt", "r", encoding='gb18030').read()
words = jieba.lcut(txt)     
counts = {}     
 
for word in words:
    if len(word) == 1:
        continue   
    elif word == "大圣" or word=="老孙" or word=="行者" or word=="孙大圣" or word=="孙行者" or word=="猴王" or word=="悟空" or word=="齐天大圣" or word=="猴子":
        rword = "孙悟空"
    elif word == "师父" or word == "三藏" or word=="圣僧":
        rword = "唐僧"
    elif word == "呆子" or word=="八戒" or word=="老猪":
        rword = "猪八戒"
    elif word=="沙和尚":
        rword="沙僧"
    elif word == "妖精" or word=="妖魔" or word=="妖道":
        rword = "妖怪"
    elif word=="佛祖":
        rword="如来"
    elif word=="三太子":
        rword="白马"
    else:
        rword = word
    counts[rword] = counts.get(rword,0) + 1
         
items = list(counts.items())
items.sort(key=lambda x: x[1], reverse=True)    
 
for i in range(20):
    word, count = items[i]
    print("{0:<10}{1:>5}".format(word, count))

  

标签:jieba,rword,word,items,elif,counts,txt,西游记,分词
来源: https://www.cnblogs.com/dt1005/p/13972868.html