在我重新发明这个特殊的轮子之前,有没有人有一个很好的用Python计算目录大小的例程?如果该例程能以Mb/Gb等格式格式化大小,那就太好了。


当前回答

获取目录大小

解决方案的性质:

返回两者:表观大小(文件中的字节数)和文件使用的实际磁盘空间。 硬链接文件只计算一次 计数符号链接的方式与du相同 不使用递归 使用st.st_blocks表示所使用的磁盘空间,因此只适用于类unix系统

代码:

import os


def du(path):
    if os.path.islink(path):
        return (os.lstat(path).st_size, 0)
    if os.path.isfile(path):
        st = os.lstat(path)
        return (st.st_size, st.st_blocks * 512)
    apparent_total_bytes = 0
    total_bytes = 0
    have = []
    for dirpath, dirnames, filenames in os.walk(path):
        apparent_total_bytes += os.lstat(dirpath).st_size
        total_bytes += os.lstat(dirpath).st_blocks * 512
        for f in filenames:
            fp = os.path.join(dirpath, f)
            if os.path.islink(fp):
                apparent_total_bytes += os.lstat(fp).st_size
                continue
            st = os.lstat(fp)
            if st.st_ino in have:
                continue  # skip hardlinks which were already counted
            have.append(st.st_ino)
            apparent_total_bytes += st.st_size
            total_bytes += st.st_blocks * 512
        for d in dirnames:
            dp = os.path.join(dirpath, d)
            if os.path.islink(dp):
                apparent_total_bytes += os.lstat(dp).st_size
    return (apparent_total_bytes, total_bytes)

使用示例:

>>> du('/lib')
(236425839, 244363264)

$ du -sb /lib
236425839   /lib
$ du -sB1 /lib
244363264   /lib

人类可读的文件大小

解决方案的性质:

最高支持Yottabytes 支持SI单位或IEC单位 支持自定义后缀

代码:

def humanized_size(num, suffix='B', si=False):
    if si:
        units = ['','K','M','G','T','P','E','Z']
        last_unit = 'Y'
        div = 1000.0
    else:
        units = ['','Ki','Mi','Gi','Ti','Pi','Ei','Zi']
        last_unit = 'Yi'
        div = 1024.0
    for unit in units:
        if abs(num) < div:
            return "%3.1f%s%s" % (num, unit, suffix)
        num /= div
    return "%.1f%s%s" % (num, last_unit, suffix)

使用示例:

>>> humanized_size(236425839)
'225.5MiB'
>>> humanized_size(236425839, si=True)
'236.4MB'
>>> humanized_size(236425839, si=True, suffix='')
'236.4M'

其他回答

这是一个递归地完成它的一行代码(从Python 3.5开始提供递归选项):

import os
import glob
print(sum(os.path.getsize(f) for f in glob.glob('**', recursive=True) if os.path.isfile(f))/(1024*1024))

下面的脚本打印指定目录的所有子目录的目录大小。它还试图(如果可能的话)从缓存递归函数的调用中获益。如果省略一个参数,脚本将在当前目录中工作。输出按目录大小从大到小排序。所以你可以根据自己的需要进行调整。

PS我已经使用配方578019以人性化的格式显示目录大小(http://code.activestate.com/recipes/578019/)

from __future__ import print_function
import os
import sys
import operator

def null_decorator(ob):
    return ob

if sys.version_info >= (3,2,0):
    import functools
    my_cache_decorator = functools.lru_cache(maxsize=4096)
else:
    my_cache_decorator = null_decorator

start_dir = os.path.normpath(os.path.abspath(sys.argv[1])) if len(sys.argv) > 1 else '.'

@my_cache_decorator
def get_dir_size(start_path = '.'):
    total_size = 0
    if 'scandir' in dir(os):
        # using fast 'os.scandir' method (new in version 3.5)
        for entry in os.scandir(start_path):
            if entry.is_dir(follow_symlinks = False):
                total_size += get_dir_size(entry.path)
            elif entry.is_file(follow_symlinks = False):
                total_size += entry.stat().st_size
    else:
        # using slow, but compatible 'os.listdir' method
        for entry in os.listdir(start_path):
            full_path = os.path.abspath(os.path.join(start_path, entry))
            if os.path.isdir(full_path):
                total_size += get_dir_size(full_path)
            elif os.path.isfile(full_path):
                total_size += os.path.getsize(full_path)
    return total_size

def get_dir_size_walk(start_path = '.'):
    total_size = 0
    for dirpath, dirnames, filenames in os.walk(start_path):
        for f in filenames:
            fp = os.path.join(dirpath, f)
            total_size += os.path.getsize(fp)
    return total_size

def bytes2human(n, format='%(value).0f%(symbol)s', symbols='customary'):
    """
    (c) http://code.activestate.com/recipes/578019/

    Convert n bytes into a human readable string based on format.
    symbols can be either "customary", "customary_ext", "iec" or "iec_ext",
    see: http://goo.gl/kTQMs

      >>> bytes2human(0)
      '0.0 B'
      >>> bytes2human(0.9)
      '0.0 B'
      >>> bytes2human(1)
      '1.0 B'
      >>> bytes2human(1.9)
      '1.0 B'
      >>> bytes2human(1024)
      '1.0 K'
      >>> bytes2human(1048576)
      '1.0 M'
      >>> bytes2human(1099511627776127398123789121)
      '909.5 Y'

      >>> bytes2human(9856, symbols="customary")
      '9.6 K'
      >>> bytes2human(9856, symbols="customary_ext")
      '9.6 kilo'
      >>> bytes2human(9856, symbols="iec")
      '9.6 Ki'
      >>> bytes2human(9856, symbols="iec_ext")
      '9.6 kibi'

      >>> bytes2human(10000, "%(value).1f %(symbol)s/sec")
      '9.8 K/sec'

      >>> # precision can be adjusted by playing with %f operator
      >>> bytes2human(10000, format="%(value).5f %(symbol)s")
      '9.76562 K'
    """
    SYMBOLS = {
        'customary'     : ('B', 'K', 'M', 'G', 'T', 'P', 'E', 'Z', 'Y'),
        'customary_ext' : ('byte', 'kilo', 'mega', 'giga', 'tera', 'peta', 'exa',
                           'zetta', 'iotta'),
        'iec'           : ('Bi', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi', 'Yi'),
        'iec_ext'       : ('byte', 'kibi', 'mebi', 'gibi', 'tebi', 'pebi', 'exbi',
                           'zebi', 'yobi'),
    }
    n = int(n)
    if n < 0:
        raise ValueError("n < 0")
    symbols = SYMBOLS[symbols]
    prefix = {}
    for i, s in enumerate(symbols[1:]):
        prefix[s] = 1 << (i+1)*10
    for symbol in reversed(symbols[1:]):
        if n >= prefix[symbol]:
            value = float(n) / prefix[symbol]
            return format % locals()
    return format % dict(symbol=symbols[0], value=n)

############################################################
###
###  main ()
###
############################################################
if __name__ == '__main__':
    dir_tree = {}
    ### version, that uses 'slow' [os.walk method]
    #get_size = get_dir_size_walk
    ### this recursive version can benefit from caching the function calls (functools.lru_cache)
    get_size = get_dir_size

    for root, dirs, files in os.walk(start_dir):
        for d in dirs:
            dir_path = os.path.join(root, d)
            if os.path.isdir(dir_path):
                dir_tree[dir_path] = get_size(dir_path)

    for d, size in sorted(dir_tree.items(), key=operator.itemgetter(1), reverse=True):
        print('%s\t%s' %(bytes2human(size, format='%(value).2f%(symbol)s'), d))

    print('-' * 80)
    if sys.version_info >= (3,2,0):
        print(get_dir_size.cache_info())

样例输出:

37.61M  .\subdir_b
2.18M   .\subdir_a
2.17M   .\subdir_a\subdir_a_2
4.41K   .\subdir_a\subdir_a_1
----------------------------------------------------------
CacheInfo(hits=2, misses=4, maxsize=4096, currsize=4)

编辑:根据user2233949的建议,将null_decorator移到上面

递归的一行代码:

def getFolderSize(p):
   from functools import partial
   prepend = partial(os.path.join, p)
   return sum([(os.path.getsize(f) if os.path.isfile(f) else getFolderSize(f)) for f in map(prepend, os.listdir(p))])

到目前为止,建议的一些方法实现了递归,其他方法使用shell或不会生成格式整齐的结果。当您的代码对于Linux平台是一次性的,您可以像往常一样获得格式化,包括递归,作为一行程序。除了最后一行的输出,它将适用于当前版本的python2和python3:

du.py
-----
#!/usr/bin/python3
import subprocess

def du(path):
    """disk usage in human readable format (e.g. '2,1GB')"""
    return subprocess.check_output(['du','-sh', path]).split()[0].decode('utf-8')

if __name__ == "__main__":
    print(du('.'))

简单,高效,将工作于文件和多级目录:

$ chmod 750 du.py
$ ./du.py
2,9M

当计算子目录的大小时,它应该更新其父目录的文件夹大小,这将一直进行下去,直到它到达根父目录。

下面的函数计算文件夹及其所有子文件夹的大小。

import os

def folder_size(path):
    parent = {}  # path to parent path mapper
    folder_size = {}  # storing the size of directories
    folder = os.path.realpath(path)

    for root, _, filenames in os.walk(folder):
        if root == folder:
            parent[root] = -1  # the root folder will not have any parent
            folder_size[root] = 0.0  # intializing the size to 0

        elif root not in parent:
            immediate_parent_path = os.path.dirname(root)  # extract the immediate parent of the subdirectory
            parent[root] = immediate_parent_path  # store the parent of the subdirectory
            folder_size[root] = 0.0  # initialize the size to 0

        total_size = 0
        for filename in filenames:
            filepath = os.path.join(root, filename)
            total_size += os.stat(filepath).st_size  # computing the size of the files under the directory
        folder_size[root] = total_size  # store the updated size

        temp_path = root  # for subdirectories, we need to update the size of the parent till the root parent
        while parent[temp_path] != -1:
            folder_size[parent[temp_path]] += total_size
            temp_path = parent[temp_path]

    return folder_size[folder]/1000000.0