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

import os

def get_size(path):
    total_size = 0
    for dirpath, dirnames, filenames in os.walk(path):
        for f in filenames:
            if os.path.exists(fp):
                fp = os.path.join(dirpath, f)
                total_size += os.path.getsize(fp)

    return total_size   # in megabytes

谢谢monkut & troex!

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

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。

import os
def get_size(path = os.getcwd()):
    print("Calculating Size: ",path)
    total_size = 0
    #if path is directory--
    if os.path.isdir(path):
      print("Path type : Directory/Folder")
      for dirpath, dirnames, filenames in os.walk(path):
          for f in filenames:
              fp = os.path.join(dirpath, f)
              # skip if it is symbolic link
              if not os.path.islink(fp):
                  total_size += os.path.getsize(fp)
    #if path is a file---
    elif os.path.isfile(path):
      print("Path type : File")
      total_size=os.path.getsize(path)
    else:
      print("Path Type : Special File (Socket, FIFO, Device File)" )
      total_size=0
    bytesize=total_size
    print(bytesize, 'bytes')
    print(bytesize/(1024), 'kilobytes')
    print(bytesize/(1024*1024), 'megabytes')
    print(bytesize/(1024*1024*1024), 'gegabytes')
    return total_size


x=get_size("/content/examples")

我相信这很有帮助!文件夹和文件!

问题的第二部分

def human(size):

    B = "B"
    KB = "KB" 
    MB = "MB"
    GB = "GB"
    TB = "TB"
    UNITS = [B, KB, MB, GB, TB]
    HUMANFMT = "%f %s"
    HUMANRADIX = 1024.

    for u in UNITS[:-1]:
        if size < HUMANRADIX : return HUMANFMT % (size, u)
        size /= HUMANRADIX

    return HUMANFMT % (size,  UNITS[-1])