词频统计-Python

 #Hamlet词频统计
 import requests

def getText():
    #txt = open("hamlet",'r').read()
    #读取网页的词频
    url = "https://python123.io/resources/pye/hamlet.txt"
    response = requests.get(url)
    txt = response.text

    txt = txt.lower() #大写字母转换小写
    for word in '~!@#$%^&*()_+-={}[],./:";<>?':
        txt = txt.replace(word," ")#把多余符号转换为空格
    return txt
hamletTxt = getText()
words = hamletTxt.split() #以空格拆分为列表
counts = {} # 相当于java的 hashmap （k,v）
for word in words:
    counts[word] = counts.get(word,0) + 1  #以每个词为键，值默认0，,每出现一次累加1
items = list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)  #[1]按照第二维排序，reverse=True表示降序
for i in range(10):
    word,count = items[i]
    # 输出按照第二维度排序后的前十
    print("{0:<10}{1:5}".format(word,count))