2、用python實現統計一篇英文文章內每個單詞的出現頻率，並返回出現頻率最高的前10個單詞及其出現次數，並解答以下問題？(標點符號可忽略)

(1) 創建文件對象f后，解釋f的readlines和xreadlines方法的區別？

(2) 追加需求：引號內元素需要算作一個單詞，如何實現？

cat /root/text.txt

hello world 2018 xiaowei,good luck

hello kitty 2017 wangleai,ha he

hello kitty ,hasd he

hello kitty ,hasaad hedsfds

#我的腳本

#!/usr/bin/python

#get ['a','b','c']

import re

with open('/root/text.txt') as f:

openfile = f.read()

def get_list_dict():

word_list = re.split('[0-9\W]+',openfile)

list_no_repeat = set(word_list)

dict_word = {}

for each_word in list_no_repeat:

dict_word[each_word] = word_list.count(each_word)

del dict_word['']

return dict_word

#{'a':2,'c':5,'b':1} => {'c':5,'a':2,'b':1}

def sort_dict_get_ten(dict_word):

list_after_sorted = sorted(dict_word.items(),key=lambda x:x[1],reverse=True)

print list_after_sorted

for i in range(3):

print list_after_sorted[i][0],list_after_sorted[i][1]

def main():

dict_word = get_list_dict()

sort_dict_get_ten(dict_word)

if __name__ == '__main__':

main()

[('hello', 4), ('kitty', 3), ('he', 2), ('good', 1), ('hasd', 1), ('wangleai', 1), ('hasaad', 1), ('xiaowei', 1), ('hedsfds', 1), ('luck', 1), ('world', 1), ('ha', 1)]

hello 4

kitty 3

he 2