从字节大小返回人类可读大小的函数:

>>> human_readable(2048)
'2 kilobytes'
>>>

如何做到这一点?


当前回答

这个解决方案可能也会吸引你,这取决于你的思维方式:

from pathlib import Path    

def get_size(path = Path('.')):
    """ Gets file size, or total directory size """
    if path.is_file():
        size = path.stat().st_size
    elif path.is_dir():
        size = sum(file.stat().st_size for file in path.glob('*.*'))
    return size

def format_size(path, unit="MB"):
    """ Converts integers to common size units used in computing """
    bit_shift = {"B": 0,
            "kb": 7,
            "KB": 10,
            "mb": 17,
            "MB": 20,
            "gb": 27,
            "GB": 30,
            "TB": 40,}
    return "{:,.0f}".format(get_size(path) / float(1 << bit_shift[unit])) + " " + unit

# Tests and test results
>>> get_size("d:\\media\\bags of fun.avi")
'38 MB'
>>> get_size("d:\\media\\bags of fun.avi","KB")
'38,763 KB'
>>> get_size("d:\\media\\bags of fun.avi","kb")
'310,104 kb'

其他回答

我喜欢senderle的十进制版本的固定精度,所以这里有一种与上面joctee的答案的混合(你知道你可以取非整数底数的对数吗?):

from math import log
def human_readable_bytes(x):
    # hybrid of https://stackoverflow.com/a/10171475/2595465
    #      with https://stackoverflow.com/a/5414105/2595465
    if x == 0: return '0'
    magnitude = int(log(abs(x),10.24))
    if magnitude > 16:
        format_str = '%iP'
        denominator_mag = 15
    else:
        float_fmt = '%2.1f' if magnitude % 3 == 1 else '%1.2f'
        illion = (magnitude + 1) // 3
        format_str = float_fmt + ['', 'K', 'M', 'G', 'T', 'P'][illion]
    return (format_str % (x * 1.0 / (1024 ** illion))).lstrip('0')

参考Sridhar Ratnakumar的回答,更新为:

def formatSize(sizeInBytes, decimalNum=1, isUnitWithI=False, sizeUnitSeperator=""):
  """format size to human readable string"""
  # https://en.wikipedia.org/wiki/Binary_prefix#Specific_units_of_IEC_60027-2_A.2_and_ISO.2FIEC_80000
  # K=kilo, M=mega, G=giga, T=tera, P=peta, E=exa, Z=zetta, Y=yotta
  sizeUnitList = ['','K','M','G','T','P','E','Z']
  largestUnit = 'Y'

  if isUnitWithI:
    sizeUnitListWithI = []
    for curIdx, eachUnit in enumerate(sizeUnitList):
      unitWithI = eachUnit
      if curIdx >= 1:
        unitWithI += 'i'
      sizeUnitListWithI.append(unitWithI)

    # sizeUnitListWithI = ['','Ki','Mi','Gi','Ti','Pi','Ei','Zi']
    sizeUnitList = sizeUnitListWithI

    largestUnit += 'i'

  suffix = "B"
  decimalFormat = "." + str(decimalNum) + "f" # ".1f"
  finalFormat = "%" + decimalFormat + sizeUnitSeperator + "%s%s" # "%.1f%s%s"
  sizeNum = sizeInBytes
  for sizeUnit in sizeUnitList:
      if abs(sizeNum) < 1024.0:
        return finalFormat % (sizeNum, sizeUnit, suffix)
      sizeNum /= 1024.0
  return finalFormat % (sizeNum, largestUnit, suffix)

示例输出如下:

def testKb():
  kbSize = 3746
  kbStr = formatSize(kbSize)
  print("%s -> %s" % (kbSize, kbStr))

def testI():
  iSize = 87533
  iStr = formatSize(iSize, isUnitWithI=True)
  print("%s -> %s" % (iSize, iStr))

def testSeparator():
  seperatorSize = 98654
  seperatorStr = formatSize(seperatorSize, sizeUnitSeperator=" ")
  print("%s -> %s" % (seperatorSize, seperatorStr))

def testBytes():
  bytesSize = 352
  bytesStr = formatSize(bytesSize)
  print("%s -> %s" % (bytesSize, bytesStr))

def testMb():
  mbSize = 76383285
  mbStr = formatSize(mbSize, decimalNum=2)
  print("%s -> %s" % (mbSize, mbStr))

def testTb():
  tbSize = 763832854988542
  tbStr = formatSize(tbSize, decimalNum=2)
  print("%s -> %s" % (tbSize, tbStr))

def testPb():
  pbSize = 763832854988542665
  pbStr = formatSize(pbSize, decimalNum=4)
  print("%s -> %s" % (pbSize, pbStr))


def demoFormatSize():
  testKb()
  testI()
  testSeparator()
  testBytes()
  testMb()
  testTb()
  testPb()

  # 3746 -> 3.7KB
  # 87533 -> 85.5KiB
  # 98654 -> 96.3 KB
  # 352 -> 352.0B
  # 76383285 -> 72.84MB
  # 763832854988542 -> 694.70TB
  # 763832854988542665 -> 678.4199PB

通过简单的实现(使用f-strings,所以Python 3.6+)解决上述“任务太小,不需要库”的问题:

def sizeof_fmt(num, suffix="B"):
    for unit in ["", "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi"]:
        if abs(num) < 1024.0:
            return f"{num:3.1f}{unit}{suffix}"
        num /= 1024.0
    return f"{num:.1f}Yi{suffix}"

支持:

所有当前已知的二进制前缀 负数和正数 大于1000约字节的数字 任意单位(也许你喜欢用吉比特来计数!)

例子:

>>> sizeof_fmt(168963795964)
'157.4GiB'

作者:Fred Cirera

重复作为匆匆.filesize()替代方案提供的代码段,下面的代码段根据所使用的前缀给出不同的精度数字。它不像某些片段那样简洁,但我喜欢这样的结果。

def human_size(size_bytes):
    """
    format a size in bytes into a 'human' file size, e.g. bytes, KB, MB, GB, TB, PB
    Note that bytes/KB will be reported in whole numbers but MB and above will have greater precision
    e.g. 1 byte, 43 bytes, 443 KB, 4.3 MB, 4.43 GB, etc
    """
    if size_bytes == 1:
        # because I really hate unnecessary plurals
        return "1 byte"

    suffixes_table = [('bytes',0),('KB',0),('MB',1),('GB',2),('TB',2), ('PB',2)]

    num = float(size_bytes)
    for suffix, precision in suffixes_table:
        if num < 1024.0:
            break
        num /= 1024.0

    if precision == 0:
        formatted_size = "%d" % num
    else:
        formatted_size = str(round(num, ndigits=precision))

    return "%s %s" % (formatted_size, suffix)

如果你安装了Django,你也可以试试filesizeformat:

from django.template.defaultfilters import filesizeformat
filesizeformat(1073741824)

=>

"1.0 GB"