我如何在Python中获得给定目录中的所有文件(和目录)的列表?


当前回答

#import modules
import os

_CURRENT_DIR = '.'


def rec_tree_traverse(curr_dir, indent):
    "recurcive function to traverse the directory"
    #print "[traverse_tree]"

    try :
        dfList = [os.path.join(curr_dir, f_or_d) for f_or_d in os.listdir(curr_dir)]
    except:
        print "wrong path name/directory name"
        return

    for file_or_dir in dfList:

        if os.path.isdir(file_or_dir):
            #print "dir  : ",
            print indent, file_or_dir,"\\"
            rec_tree_traverse(file_or_dir, indent*2)

        if os.path.isfile(file_or_dir):
            #print "file : ",
            print indent, file_or_dir

    #end if for loop
#end of traverse_tree()

def main():

    base_dir = _CURRENT_DIR

    rec_tree_traverse(base_dir," ")

    raw_input("enter any key to exit....")
#end of main()


if __name__ == '__main__':
    main()

其他回答

下面是我经常使用的一个辅助函数:

import os

def listdir_fullpath(d):
    return [os.path.join(d, f) for f in os.listdir(d)]

如果你需要通配符,也有一个模块。例如:

import glob
glob.glob('./[0-9].*')

将返回如下内容:

['./1.gif', './2.txt']

请在这里查看文档。

这是一种遍历目录树中每个文件和目录的方法:

import os

for dirname, dirnames, filenames in os.walk('.'):
    # print path to all subdirectories first.
    for subdirname in dirnames:
        print(os.path.join(dirname, subdirname))

    # print path to all filenames.
    for filename in filenames:
        print(os.path.join(dirname, filename))

    # Advanced usage:
    # editing the 'dirnames' list will stop os.walk() from recursing into there.
    if '.git' in dirnames:
        # don't go into any .git directories.
        dirnames.remove('.git')

虽然os.listdir()用于生成文件和目录名称的列表很好,但一旦有了这些名称,通常您还想做更多的事情——在Python3中,pathlib使这些其他杂事变得简单。让我们看一看,看看你是否和我一样喜欢它。

要列出目录内容,构造一个Path对象并获取迭代器:

In [16]: Path('/etc').iterdir()
Out[16]: <generator object Path.iterdir at 0x110853fc0>

如果我们只想要一个事物名称的列表

In [17]: [x.name for x in Path('/etc').iterdir()]
Out[17]:
['emond.d',
 'ntp-restrict.conf',
 'periodic',

如果你只想要dirs:

In [18]: [x.name for x in Path('/etc').iterdir() if x.is_dir()]
Out[18]:
['emond.d',
 'periodic',
 'mach_init.d',

如果你想要该树中所有conf文件的名称:

In [20]: [x.name for x in Path('/etc').glob('**/*.conf')]
Out[20]:
['ntp-restrict.conf',
 'dnsextd.conf',
 'syslog.conf',

如果你想在树>= 1K中列出conf文件:

In [23]: [x.name for x in Path('/etc').glob('**/*.conf') if x.stat().st_size > 1024]
Out[23]:
['dnsextd.conf',
 'pf.conf',
 'autofs.conf',

解析相对路径变得简单:

In [32]: Path('../Operational Metrics.md').resolve()
Out[32]: PosixPath('/Users/starver/code/xxxx/Operational Metrics.md')

使用路径导航非常清楚(尽管出乎意料):

In [10]: p = Path('.')

In [11]: core = p / 'web' / 'core'

In [13]: [x for x in core.iterdir() if x.is_file()]
Out[13]:
[PosixPath('web/core/metrics.py'),
 PosixPath('web/core/services.py'),
 PosixPath('web/core/querysets.py'),

我写了一个很长的版本,包含了我可能需要的所有选项:http://sam.nipl.net/code/python/find.py

我想它也适合这里:

#!/usr/bin/env python

import os
import sys

def ls(dir, hidden=False, relative=True):
    nodes = []
    for nm in os.listdir(dir):
        if not hidden and nm.startswith('.'):
            continue
        if not relative:
            nm = os.path.join(dir, nm)
        nodes.append(nm)
    nodes.sort()
    return nodes

def find(root, files=True, dirs=False, hidden=False, relative=True, topdown=True):
    root = os.path.join(root, '')  # add slash if not there
    for parent, ldirs, lfiles in os.walk(root, topdown=topdown):
        if relative:
            parent = parent[len(root):]
        if dirs and parent:
            yield os.path.join(parent, '')
        if not hidden:
            lfiles   = [nm for nm in lfiles if not nm.startswith('.')]
            ldirs[:] = [nm for nm in ldirs  if not nm.startswith('.')]  # in place
        if files:
            lfiles.sort()
            for nm in lfiles:
                nm = os.path.join(parent, nm)
                yield nm

def test(root):
    print "* directory listing, with hidden files:"
    print ls(root, hidden=True)
    print
    print "* recursive listing, with dirs, but no hidden files:"
    for f in find(root, dirs=True):
        print f
    print

if __name__ == "__main__":
    test(*sys.argv[1:])