在我重新发明这个特殊的轮子之前,有没有人有一个很好的用Python计算目录大小的例程?如果该例程能以Mb/Gb等格式格式化大小,那就太好了。
当前回答
你说一句俏皮话… 这里有一句话:
sum([sum(map(lambda fname: os.path.getsize(os.path.join(directory, fname)), files)) for directory, folders, files in os.walk(path)])
尽管我可能会把它分开,它不执行检查。
要转换为kb,请参阅可重用库以获得人类可读版本的文件大小?然后算进去
其他回答
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))
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'
它很方便:
import os
import stat
size = 0
path_ = ""
def calculate(path=os.environ["SYSTEMROOT"]):
global size, path_
size = 0
path_ = path
for x, y, z in os.walk(path):
for i in z:
size += os.path.getsize(x + os.sep + i)
def cevir(x):
global path_
print(path_, x, "Byte")
print(path_, x/1024, "Kilobyte")
print(path_, x/1048576, "Megabyte")
print(path_, x/1073741824, "Gigabyte")
calculate("C:\Users\Jundullah\Desktop")
cevir(size)
Output:
C:\Users\Jundullah\Desktop 87874712211 Byte
C:\Users\Jundullah\Desktop 85815148.64355469 Kilobyte
C:\Users\Jundullah\Desktop 83803.85609722137 Megabyte
C:\Users\Jundullah\Desktop 81.83970321994275 Gigabyte
你说一句俏皮话… 这里有一句话:
sum([sum(map(lambda fname: os.path.getsize(os.path.join(directory, fname)), files)) for directory, folders, files in os.walk(path)])
尽管我可能会把它分开,它不执行检查。
要转换为kb,请参阅可重用库以获得人类可读版本的文件大小?然后算进去
下面的脚本打印指定目录的所有子目录的目录大小。它还试图(如果可能的话)从缓存递归函数的调用中获益。如果省略一个参数,脚本将在当前目录中工作。输出按目录大小从大到小排序。所以你可以根据自己的需要进行调整。
PS我已经使用配方578019以人性化的格式显示目录大小(http://code.activestate.com/recipes/578019/)
from __future__ import print_function
import os
import sys
import operator
def null_decorator(ob):
return ob
if sys.version_info >= (3,2,0):
import functools
my_cache_decorator = functools.lru_cache(maxsize=4096)
else:
my_cache_decorator = null_decorator
start_dir = os.path.normpath(os.path.abspath(sys.argv[1])) if len(sys.argv) > 1 else '.'
@my_cache_decorator
def get_dir_size(start_path = '.'):
total_size = 0
if 'scandir' in dir(os):
# using fast 'os.scandir' method (new in version 3.5)
for entry in os.scandir(start_path):
if entry.is_dir(follow_symlinks = False):
total_size += get_dir_size(entry.path)
elif entry.is_file(follow_symlinks = False):
total_size += entry.stat().st_size
else:
# using slow, but compatible 'os.listdir' method
for entry in os.listdir(start_path):
full_path = os.path.abspath(os.path.join(start_path, entry))
if os.path.isdir(full_path):
total_size += get_dir_size(full_path)
elif os.path.isfile(full_path):
total_size += os.path.getsize(full_path)
return total_size
def get_dir_size_walk(start_path = '.'):
total_size = 0
for dirpath, dirnames, filenames in os.walk(start_path):
for f in filenames:
fp = os.path.join(dirpath, f)
total_size += os.path.getsize(fp)
return total_size
def bytes2human(n, format='%(value).0f%(symbol)s', symbols='customary'):
"""
(c) http://code.activestate.com/recipes/578019/
Convert n bytes into a human readable string based on format.
symbols can be either "customary", "customary_ext", "iec" or "iec_ext",
see: http://goo.gl/kTQMs
>>> bytes2human(0)
'0.0 B'
>>> bytes2human(0.9)
'0.0 B'
>>> bytes2human(1)
'1.0 B'
>>> bytes2human(1.9)
'1.0 B'
>>> bytes2human(1024)
'1.0 K'
>>> bytes2human(1048576)
'1.0 M'
>>> bytes2human(1099511627776127398123789121)
'909.5 Y'
>>> bytes2human(9856, symbols="customary")
'9.6 K'
>>> bytes2human(9856, symbols="customary_ext")
'9.6 kilo'
>>> bytes2human(9856, symbols="iec")
'9.6 Ki'
>>> bytes2human(9856, symbols="iec_ext")
'9.6 kibi'
>>> bytes2human(10000, "%(value).1f %(symbol)s/sec")
'9.8 K/sec'
>>> # precision can be adjusted by playing with %f operator
>>> bytes2human(10000, format="%(value).5f %(symbol)s")
'9.76562 K'
"""
SYMBOLS = {
'customary' : ('B', 'K', 'M', 'G', 'T', 'P', 'E', 'Z', 'Y'),
'customary_ext' : ('byte', 'kilo', 'mega', 'giga', 'tera', 'peta', 'exa',
'zetta', 'iotta'),
'iec' : ('Bi', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi', 'Yi'),
'iec_ext' : ('byte', 'kibi', 'mebi', 'gibi', 'tebi', 'pebi', 'exbi',
'zebi', 'yobi'),
}
n = int(n)
if n < 0:
raise ValueError("n < 0")
symbols = SYMBOLS[symbols]
prefix = {}
for i, s in enumerate(symbols[1:]):
prefix[s] = 1 << (i+1)*10
for symbol in reversed(symbols[1:]):
if n >= prefix[symbol]:
value = float(n) / prefix[symbol]
return format % locals()
return format % dict(symbol=symbols[0], value=n)
############################################################
###
### main ()
###
############################################################
if __name__ == '__main__':
dir_tree = {}
### version, that uses 'slow' [os.walk method]
#get_size = get_dir_size_walk
### this recursive version can benefit from caching the function calls (functools.lru_cache)
get_size = get_dir_size
for root, dirs, files in os.walk(start_dir):
for d in dirs:
dir_path = os.path.join(root, d)
if os.path.isdir(dir_path):
dir_tree[dir_path] = get_size(dir_path)
for d, size in sorted(dir_tree.items(), key=operator.itemgetter(1), reverse=True):
print('%s\t%s' %(bytes2human(size, format='%(value).2f%(symbol)s'), d))
print('-' * 80)
if sys.version_info >= (3,2,0):
print(get_dir_size.cache_info())
样例输出:
37.61M .\subdir_b
2.18M .\subdir_a
2.17M .\subdir_a\subdir_a_2
4.41K .\subdir_a\subdir_a_1
----------------------------------------------------------
CacheInfo(hits=2, misses=4, maxsize=4096, currsize=4)
编辑:根据user2233949的建议,将null_decorator移到上面
推荐文章
- Numpy Max vs amax vs maximum
- 我应该在.gitignore文件中添加Django迁移文件吗?
- 每n行有熊猫
- 实例属性attribute_name定义在__init__之外
- 如何获取在Python中捕获的异常的名称?
- 第一次出现的值大于现有值的Numpy
- 如何从Python函数中返回两个值?
- 前一个月的Python日期
- Python中方括号括起来的列表和圆括号括起来的列表有什么区别?
- Python日志记录不输出任何东西
- 每n秒运行特定代码
- SQLAlchemy是否有与Django的get_or_create等价的函数?
- 如何将python datetime转换为字符串,具有可读格式的日期?
- 美丽的汤和提取div及其内容的ID
- 在Python中重置生成器对象