第0006題：你有一個目錄，放了你一個月的日記，都是txt，為了避免分詞的問題，假設(shè)內(nèi)容都是英文，請統(tǒng)計出你認(rèn)為每篇日記最重要的詞。

解題思路：可以用剛寫的另一篇文章collections庫里面的一些方法，比如Counter()和most_common()。
代碼如下：

#! /usr/bin/env python
#coding=utf-8
import os
import re
from collections import Counter

def get_filepaths(directory):
    file_paths = []
    for root, directories, files in os.walk(directory):
        for filename in files:
            filepath = os.path.join(root, filename)
            file_paths.append(filepath)
            
    return file_paths

def counter_more_words(li):
    word_dict = Counter(li)
    return [i[0] for i in word_dict.most_common()[:10]]

if __name__ == '__main__':
    for file in get_filepaths(r'C:\diaries'):
        with open(file, 'r') as f:
            word_li = re.findall("\w+", f.read())
            print " ".join(counter_more_words(word_li))