1 #三国演义人物出场次数统计
2 import jieba
3 excludes = {"将军","却说","荆州","二人","不可","不能","如此","商议","军士","如何","主公","军马","左右",}
4 with open("./三国演义.txt", "r", )as file:
5 txt=file.read()
6 words=jieba.lcut(txt)
7 counts = {}
8 for word in words:
9 if len(word) == 1:
10 continue
11 elif word == "诸葛亮" or word == "孔明曰":
12 rword = "孔明"
13 elif word == "关公" or word == "云长":
14 rword = "关羽"
15 elif word == "玄德" or word == "玄德曰":
16 rword = "刘备"
17 elif word == "孟德" or word == "丞相":
18 rword = "曹操"
19 else:
20 rword = word
21 counts[rword] = counts.get(rword,0) + 1
22 for word in excludes:
23 del(counts[word])
24 items = list(counts.items())
25 items.sort(key=lambda x:x[1], reverse=True)
26 for i in range(5):
27 word, count=items[i]
28 print("{0:<10}{1:>5}".format(word, count))