jieba分词 | 西游记相关分词,出现次数最高的20个。

代码

 1 import jieba
 2 
 3 txt = open("《西游记》.txt", "r", encoding='utf-8').read()
 4 
 5 words = jieba.lcut(txt)  # 使用精确模式对文本进行分词
 6 
 7 counts = {}  # 通过键值对的形式存储词语及其出现的次数
 8 
 9 for word in words:
10     if len(word) == 1:
11         continue
12     elif word == "大圣" or word == "老孙" or word == "行者" or word == "孙大圣" or word == "孙行者"\
13         or word == "猴王" or word == "悟空" or word == "齐天大圣" or word == "猴子":
14         rword = "孙悟空"
15     elif word == "师父" or word == "三藏" or word == "圣僧":
16         rword = "唐僧"
17     elif word == "呆子" or word == "八戒" or word == "老猪":
18         rword = "猪八戒"
19     elif word == "沙和尚":
20         rword = "沙僧"
21     elif word == "妖精" or word == "妖魔" or word == "妖道":
22         rword = "妖怪"
23     elif word == "佛祖":
24         rword = "如来"
25     elif word == "三太子":
26         rword = "白马"
27     else:
28         rword = word
29 
30     counts[rword] = counts.get(rword, 0) + 1
31 
32 items = list(counts.items())  # 将键值对转换成列表
33 
34 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
35 
36 for i in range(20):
37     word, count = items[i]
38     print("{0:<10}{1:>5}".format(word, count))