python123词频统计之哈姆雷特_hamlet.txt英文哈姆雷特下载及实现文本词频统计

CalHamletV1.py：

#CalHamletV1.py

def getText():

txt = open("hamlet.txt", "r").read()

txt = txt.lower()

for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~':

txt = txt.replace(ch, " ")

return txt

hamletTxt = getText()

words = hamletTxt.split()

counts = {}

for word in words:

counts[word] = counts.get(word, 0) + 1

items = list(counts.items())

items.sort(key = lambda x:x[1], reverse = True)

for i in range(10):

word, count = items[i]

print("{0:<10}{1:>5}".format(word, count))

运行结果：

the 1138

and 965

to 754

of 669

you 550

i 542

a 542

my 514

hamlet 462

in 436