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

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

其他回答

它很方便:

import os
import stat

size = 0
path_ = ""
def calculate(path=os.environ["SYSTEMROOT"]):
    global size, path_
    size = 0
    path_ = path

    for x, y, z in os.walk(path):
        for i in z:
            size += os.path.getsize(x + os.sep + i)

def cevir(x):
    global path_
    print(path_, x, "Byte")
    print(path_, x/1024, "Kilobyte")
    print(path_, x/1048576, "Megabyte")
    print(path_, x/1073741824, "Gigabyte")

calculate("C:\Users\Jundullah\Desktop")
cevir(size)

Output:
C:\Users\Jundullah\Desktop 87874712211 Byte
C:\Users\Jundullah\Desktop 85815148.64355469 Kilobyte
C:\Users\Jundullah\Desktop 83803.85609722137 Megabyte
C:\Users\Jundullah\Desktop 81.83970321994275 Gigabyte

这个脚本告诉您CWD中哪个文件最大,还告诉您文件在哪个文件夹中。 这个脚本适用于win8和python 3.3.3 shell

import os

folder=os.cwd()

number=0
string=""

for root, dirs, files in os.walk(folder):
    for file in files:
        pathname=os.path.join(root,file)
##        print (pathname)
##        print (os.path.getsize(pathname)/1024/1024)
        if number < os.path.getsize(pathname):
            number = os.path.getsize(pathname)
            string=pathname


##        print ()


print (string)
print ()
print (number)
print ("Number in bytes")

我在这里有点晚(和新),但我选择使用subprocess模块和Linux中的'du'命令行来检索文件夹大小的准确值,单位为MB。我必须使用if和elif用于根文件夹,否则子进程会由于返回的非零值而引发错误。

import subprocess
import os

#
# get folder size
#
def get_size(self, path):
    if os.path.exists(path) and path != '/':
        cmd = str(subprocess.check_output(['sudo', 'du', '-s', path])).\
            replace('b\'', '').replace('\'', '').split('\\t')[0]
        return float(cmd) / 1000000
    elif os.path.exists(path) and path == '/':
        cmd = str(subprocess.getoutput(['sudo du -s /'])). \
            replace('b\'', '').replace('\'', '').split('\n')
        val = cmd[len(cmd) - 1].replace('/', '').replace(' ', '')
        return float(val) / 1000000
    else: raise ValueError

这有点晚了,但只要安装了glob2和humanize,就行了。注意,在Python 3中,默认的iglob具有递归模式。如何修改Python 3的代码是留给读者的简单练习。

>>> import os
>>> from humanize import naturalsize
>>> from glob2 import iglob
>>> naturalsize(sum(os.path.getsize(x) for x in iglob('/var/**'))))
'546.2 MB'

使用pathlib,我想出了这个一行程序来获取文件夹的大小:

sum(file.stat().st_size for file in Path(folder).rglob('*'))

这是我为一个漂亮的格式化输出:

from pathlib import Path


def get_folder_size(folder):
    return ByteSize(sum(file.stat().st_size for file in Path(folder).rglob('*')))


class ByteSize(int):

    _KB = 1024
    _suffixes = 'B', 'KB', 'MB', 'GB', 'PB'

    def __new__(cls, *args, **kwargs):
        return super().__new__(cls, *args, **kwargs)

    def __init__(self, *args, **kwargs):
        self.bytes = self.B = int(self)
        self.kilobytes = self.KB = self / self._KB**1
        self.megabytes = self.MB = self / self._KB**2
        self.gigabytes = self.GB = self / self._KB**3
        self.petabytes = self.PB = self / self._KB**4
        *suffixes, last = self._suffixes
        suffix = next((
            suffix
            for suffix in suffixes
            if 1 < getattr(self, suffix) < self._KB
        ), last)
        self.readable = suffix, getattr(self, suffix)

        super().__init__()

    def __str__(self):
        return self.__format__('.2f')

    def __repr__(self):
        return '{}({})'.format(self.__class__.__name__, super().__repr__())

    def __format__(self, format_spec):
        suffix, val = self.readable
        return '{val:{fmt}} {suf}'.format(val=val, fmt=format_spec, suf=suffix)

    def __sub__(self, other):
        return self.__class__(super().__sub__(other))

    def __add__(self, other):
        return self.__class__(super().__add__(other))
    
    def __mul__(self, other):
        return self.__class__(super().__mul__(other))

    def __rsub__(self, other):
        return self.__class__(super().__sub__(other))

    def __radd__(self, other):
        return self.__class__(super().__add__(other))
    
    def __rmul__(self, other):
        return self.__class__(super().__rmul__(other))   

用法:

>>> size = get_folder_size("c:/users/tdavis/downloads")
>>> print(size)
5.81 GB
>>> size.GB
5.810891855508089
>>> size.gigabytes
5.810891855508089
>>> size.PB
0.005674699077644618
>>> size.MB
5950.353260040283
>>> size
ByteSize(6239397620)

我还遇到了这个问题,它有一些更紧凑、可能更高效的打印文件大小的策略。