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'

Chris的回答很好，但可以通过使用set来检查已看到的目录来使其更加惯用，这也避免了对控制流使用异常:

def directory_size(path):
    total_size = 0
    seen = set()

    for dirpath, dirnames, filenames in os.walk(path):
        for f in filenames:
            fp = os.path.join(dirpath, f)

            try:
                stat = os.stat(fp)
            except OSError:
                continue

            if stat.st_ino in seen:
                continue

            seen.add(stat.st_ino)

            total_size += stat.st_size

    return total_size  # size in bytes

Du默认情况下不遵循符号链接。这里没有答案，使用follow_symlinks=False。

下面是一个遵循du默认行为的实现:

def du(path) -> int:
    total = 0
    for entry in os.scandir(path):
        if entry.is_file(follow_symlinks=False):
            total += entry.stat().st_size
        elif entry.is_dir(follow_symlinks=False):
            total += du(entry.path)
    return total

测试:

class Test(unittest.TestCase):
    def test_du(self):
        root = '/tmp/du_test'
        subprocess.run(['rm', '-rf', root])
        test_utils.mkdir(root)
        test_utils.create_file(root, 'A', '1M')
        test_utils.create_file(root, 'B', '1M')
        sub = '/'.join([root, 'sub'])
        test_utils.mkdir(sub)
        test_utils.create_file(sub, 'C', '1M')
        test_utils.create_file(sub, 'D', '1M')
        subprocess.run(['ln', '-s', '/tmp', '/'.join([root, 'link']), ])
        self.assertEqual(4 << 20, util.du(root))

def recursive_dir_size(path):
    size = 0

    for x in os.listdir(path):
        if not os.path.isdir(os.path.join(path,x)):
            size += os.stat(os.path.join(path,x)).st_size
        else:
            size += recursive_dir_size(os.path.join(path,x))

    return size

我写了这个函数，它给了我一个目录的准确总体大小，我尝试了其他for循环解决方案与os。行走，但我不知道为什么最终结果总是小于实际大小(在ubuntu 18 env)。我一定是做错了什么，但谁在乎写这个工作完美无缺。

不管怎样……树命令免费完成所有这些工作:

tree -h --du /path/to/dir  # files and dirs
tree -h -d --du /path/to/dir  # dirs only

我喜欢Python，但到目前为止，这个问题最简单的解决方案不需要新的代码。

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。