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))

接受的答案不考虑硬链接或软链接，并将这些文件计算两次。您可能希望跟踪已看到的inode，而不是为这些文件添加大小。

import os
def get_size(start_path='.'):
    total_size = 0
    seen = {}
    for dirpath, dirnames, filenames in os.walk(start_path):
        for f in filenames:
            fp = os.path.join(dirpath, f)
            try:
                stat = os.stat(fp)
            except OSError:
                continue

            try:
                seen[stat.st_ino]
            except KeyError:
                seen[stat.st_ino] = True
            else:
                continue

            total_size += stat.st_size

    return total_size

print get_size()

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])

使用库sh: du模块执行:

pip install sh

import sh
print( sh.du("-s", ".") )
91154728        .

如果您想传递asterix，请使用此处描述的glob。

要转换human readable中的值，请使用humanize:

pip install humanize

import humanize
print( humanize.naturalsize( 91157384 ) )
91.2 MB

使用pathlib在Python 3.6上工作的解决方案。

from pathlib import Path

sum([f.stat().st_size for f in Path("path").glob("**/*")])

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")