迫于 OneDrive 太卡，发现是自己文件数目太多了，写了一个 Python 程序显示当前目录下每个文件夹的个数

V2EX = way to explore

V2EX 是一个关于分享和探索的地方

现在注册

已注册用户请登录

这是一个创建于 1425 天前的主题，其中的信息可能已经有所发展或是发生改变。

#!/usr/bin/env python

import os
import argparse
from collections import OrderedDict
import json

listdironly = lambda d: [os.path.join(d, o) for o in os.listdir(d) if os.path.isdir(os.path.join(d, o))]
listfileonly = lambda d: [os.path.join(d, f) for f in os.listdir(d) if os.path.isfile(os.path.join(d, f))]


def get_file_list_recursively(d):
    # get all files and dirs
    subfiles = listfileonly(d)
    subdirs = listdironly(d)

    if len(subdirs) == 0:
        return subfiles
    else:
        for subd in subdirs:
            # print (subd)
            subfiles = subfiles + get_file_list_recursively(subd)
        return subfiles

"""
+-----------+---------+-------+------------+
|   Names   | Weights | Costs | Unit_Costs |
+===========+=========+=======+============+
| bar       | 0.050   | 2     | 40         |
+-----------+---------+-------+------------+
| chocolate | 0.100   | 5     | 50         |
+-----------+---------+-------+------------+
| chips     | 0.250   | 3     | 12         |
+-----------+---------+-------+------------+
OrderedDict{
    'header': ['Names', 'Weights' ...],
    'bar': [0.05, 2, 40 ...],
    ...
}
"""
def print_texttab(tab_kv):
    import texttable as tt
    tab = tt.Texttable()

    for i, (k, v) in enumerate(tab_kv.items()):
        if i == 0:
            headings = tab_kv['header']
            tab.header(headings)
            tab.set_cols_align(["c"] * len(headings))
        else:
            if isinstance(v, (tuple, list)):
                row_data = [k] + v
            else:
                row_data = [k, v]
            tab.add_row(row_data)
    tab_output = tab.draw()
    print (tab_output)


def main(args):
    curr_dirs = listdironly(args.dir)
    count_dict = {os.path.basename(k):0 for k in curr_dirs}
    
    for curr_d in curr_dirs:
        curr_d_file_list = get_file_list_recursively(curr_d)
        k_d = os.path.basename(curr_d)
        count_dict[k_d] = len(curr_d_file_list)    
    count_rank = sorted(count_dict.items(), key=lambda x: x[1], reverse=True)

    # create table
    table_rank = OrderedDict()
    table_rank['header'] = ['Directory', 'File Count']
    for count_item in count_rank:
        table_rank[count_item[0]] = count_item[1]

    print_texttab(table_rank)



if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Count files number.")
    parser.add_argument('--dir', type=str, default='.')
    args = parser.parse_args()
    main(args)

显示效果如下：

+----------------------+------------+
|      Directory       | File Count |
+======================+============+
|         Apps         |   44254    |
+----------------------+------------+
|       Pictures       |    2349    |
+----------------------+------------+

就几行，我也懒得贴 gist 了：）

5 条回复 • 2020-12-30 09:58:21 +08:00