【Python】哈姆雷特字数统计

def getText():  #赋予txt哈姆雷特小说-全英文小写-全符号变空格-返回txt
txt = open('C:/Users/eternal/Desktop/hamlet.txt','r').read()  #路径要选好
txt = txt.lower()
for ch in '!"#$%&()*+,-./:;<=>?@[\]^_`{|}~':
txt = txt.replace(ch," ")
return txt
hamletTxt = getText()
words = hamletTxt.split()  #以空字符做列表返回
counts = {}
for word in words:
counts[word] = counts.get(word,0) + 1    #get不到word就创建word为下标的值0+1,如果get到了就在word的值上加1,然后更新字典
items = list(counts.items())            #字典的键值对变成列表
items.sort(key=lambda x:x[1],reverse=True)    #以出现次数为标准排列,从大到小
print(items)
for i in range(10):
word,count = items[i]
print('{0:<10}{1:>5}'.format(word,count))
原文地址:https://www.cnblogs.com/naraka/p/8984950.html