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

根据之前所有的答案,以下是我的看法。它是一个以字节为单位以整数形式存储文件大小的对象。但是当你尝试打印对象时,你会自动得到一个人类可读的版本。

class Filesize(object):
    """
    Container for a size in bytes with a human readable representation
    Use it like this::

        >>> size = Filesize(123123123)
        >>> print size
        '117.4 MB'
    """

    chunk = 1024
    units = ['bytes', 'KB', 'MB', 'GB', 'TB', 'PB']
    precisions = [0, 0, 1, 2, 2, 2]

    def __init__(self, size):
        self.size = size

    def __int__(self):
        return self.size

    def __str__(self):
        if self.size == 0: return '0 bytes'
        from math import log
        unit = self.units[min(int(log(self.size, self.chunk)), len(self.units) - 1)]
        return self.format(unit)

    def format(self, unit):
        if unit not in self.units: raise Exception("Not a valid file size unit: %s" % unit)
        if self.size == 1 and unit == 'bytes': return '1 byte'
        exponent = self.units.index(unit)
        quotient = float(self.size) / self.chunk**exponent
        precision = self.precisions[exponent]
        format_string = '{:.%sf} {}' % (precision)
        return format_string.format(quotient, unit)

其他回答

这是我的版本。它不使用for循环。它具有常数复杂度O(1),理论上比这里使用for循环的答案更有效。

from math import log
unit_list = zip(['bytes', 'kB', 'MB', 'GB', 'TB', 'PB'], [0, 0, 1, 2, 2, 2])
def sizeof_fmt(num):
    """Human friendly file size"""
    if num > 1:
        exponent = min(int(log(num, 1024)), len(unit_list) - 1)
        quotient = float(num) / 1024**exponent
        unit, num_decimals = unit_list[exponent]
        format_string = '{:.%sf} {}' % (num_decimals)
        return format_string.format(quotient, unit)
    if num == 0:
        return '0 bytes'
    if num == 1:
        return '1 byte'

为了更清楚地说明发生了什么,我们可以省略字符串格式化的代码。以下是真正起作用的台词:

exponent = int(log(num, 1024))
quotient = num / 1024**exponent
unit_list[exponent]

你应该用humanize。

>>> humanize.naturalsize(1000000)
'1.0 MB'
>>> humanize.naturalsize(1000000, binary=True)
'976.6 KiB'
>>> humanize.naturalsize(1000000, gnu=True)
'976.6K'

参考: https://pypi.org/project/humanize/

def human_readable_data_quantity(quantity, multiple=1024):
    if quantity == 0:
        quantity = +0
    SUFFIXES = ["B"] + [i + {1000: "B", 1024: "iB"}[multiple] for i in "KMGTPEZY"]
    for suffix in SUFFIXES:
        if quantity < multiple or suffix == SUFFIXES[-1]:
            if suffix == SUFFIXES[0]:
                return "%d%s" % (quantity, suffix)
            else:
                return "%.1f%s" % (quantity, suffix)
        else:
            quantity /= multiple

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

使用1000或kibibytes的幂将更符合标准:

def sizeof_fmt(num, use_kibibyte=True):
    base, suffix = [(1000.,'B'),(1024.,'iB')][use_kibibyte]
    for x in ['B'] + map(lambda x: x+suffix, list('kMGTP')):
        if -base < num < base:
            return "%3.1f %s" % (num, x)
        num /= base
    return "%3.1f %s" % (num, x)

附注:永远不要相信一个以K(大写)后缀打印数千的库。