Files
Python/python代码/Python讲例/哈姆莱特统计/6-3哈姆雷特统计.py
T

21 lines
638 B
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#e10.2CalHamlet.py
excludes = {"the","and","of","you","a","i","my","in"}
def gettext():
txt = open("hamlet.txt", "r").read()
txt = txt.lower()
for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_{|}~':
txt = txt.replace(ch, " ") #将文本中特殊字符替换为空格
return txt
hamletTxt = gettext()
words = hamletTxt.split()
counts = {}
for word in words:
counts[word] = counts.get(word,0) + 1
for word in excludes:
del(counts[word])
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))