1 def getText():
2 txt = open('I:\Hamlet_-Prince-of-Denmark_哈姆雷特_.txt','r').read()
3 txt = txt.lower()
4 for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':
5 txt = txt.replace(ch, " ")
6 return txt
7
8 hamletTxt = getText()
9 words = hamletTxt.split()
10 counts = {}
11 for word in words:
12 counts[word] = counts.get(word,0) + 1
13 items = list(counts.items())
14 items.sort(key=lambda x:x[1], reverse=True)
15 for i in range(10):
16 word, count = items[i]
17 print("{0:<10} {1:>5}".format(word,count))
标签：word,items,Hamlet,词频,counts,txt,统计 From： https://www.cnblogs.com/T-2187803607/p/17137589.html