我正在寻找一种方法来包含/排除文件模式并从os.walk()调用中排除目录。
这就是我现在正在做的事情：
import fnmatch
import os
includes = ['*.doc', '*.odt']
excludes = ['/home/paulo-freitas/Documents']
def _filter(paths):
matches = []
for path in paths:
append = None
for include in includes:
if os.path.isdir(path):
append = True
break
if fnmatch.fnmatch(path, include):
append = True
break
for exclude in excludes:
if os.path.isdir(path) and path == exclude:
append = False
break
if fnmatch.fnmatch(path, exclude):
append = False
break
if append:
matches.append(path)
return matches
for root, dirs, files in os.walk('/home/paulo-freitas'):
dirs[:] = _filter(map(lambda d: os.path.join(root, d), dirs))
files[:] = _filter(map(lambda f: os.path.join(root, f), files))
for filename in files:
filename = os.path.join(root, filename)
print filename
问题是：有更好的方法吗？怎么样？
答案 0 :(得分：46)
此解决方案使用fnmatch.translate将glob模式转换为正则表达式（假设仅包含用于文件）：
import fnmatch
import os
import os.path
import re
includes = ['*.doc', '*.odt'] # for files only
excludes = ['/home/paulo-freitas/Documents'] # for dirs and files
# transform glob patterns to regular expressions
includes = r'|'.join([fnmatch.translate(x) for x in includes])
excludes = r'|'.join([fnmatch.translate(x) for x in excludes]) or r'$.'
for root, dirs, files in os.walk('/home/paulo-freitas'):
# exclude dirs
dirs[:] = [os.path.join(root, d) for d in dirs]
dirs[:] = [d for d in dirs if not re.match(excludes, d)]
# exclude/include files
files = [os.path.join(root, f) for f in files]
files = [f for f in files if not re.match(excludes, f)]
files = [f for f in files if re.match(includes, f)]
for fname in files:
print fname
答案 1 :(得分：22)
os.walk（top [，topdown = True [，onerror = None [，followlinks = False]]]）
当topdown为True时，调用者可以就地修改dirnames列表...这可以用来修剪搜索...
for root, dirs, files in os.walk('/home/paulo-freitas', topdown=True):
# excludes can be done with fnmatch.filter and complementary set,
# but it's more annoying to read.
dirs[:] = [d for d in dirs if d not in excludes]
for pat in includes:
for f in fnmatch.filter(files, pat):
print os.path.join(root, f)
我应该指出，上面的代码假设excludes是一种模式，而不是完整路径。您需要调整列表推导以过滤os.path.join(root, d) not in excludes以匹配OP案例。
答案 2 :(得分：7)
为什么fnmatch？
import os
excludes=....
for ROOT,DIR,FILES in os.walk("/path"):
for file in FILES:
if file.endswith(('doc','odt')):
print file
for directory in DIR:
if not directory in excludes :
print directory
没有经过详尽的测试
答案 3 :(得分：1)
dirtools非常适合您的用例：
from dirtools import Dir
print(Dir('.', exclude_file='.gitignore').files())
答案 4 :(得分：0)
这是一种方法
import fnmatch
import os
excludes = ['/home/paulo-freitas/Documents']
matches = []
for path, dirs, files in os.walk(os.getcwd()):
for eachpath in excludes:
if eachpath in path:
continue
else:
for result in [os.path.abspath(os.path.join(path, filename)) for
filename in files if fnmatch.fnmatch(filename,'*.doc') or fnmatch.fnmatch(filename,'*.odt')]:
matches.append(result)
print matches
答案 5 :(得分：0)
import os
includes = ['*.doc', '*.odt']
excludes = ['/home/paulo-freitas/Documents']
def file_search(path, exe):
for x,y,z in os.walk(path):
for a in z:
if a[-4:] == exe:
print os.path.join(x,a)
for x in includes:
file_search(excludes[0],x)
答案 6 :(得分：0)
这是使用os.walk()排除目录和文件的示例：
ignoreDirPatterns=[".git"]
ignoreFilePatterns=[".php"]
def copyTree(src, dest, onerror=None):
src = os.path.abspath(src)
src_prefix = len(src) + len(os.path.sep)
for root, dirs, files in os.walk(src, onerror=onerror):
for pattern in ignoreDirPatterns:
if pattern in root:
break
else:
#If the above break didn't work, this part will be executed
for file in files:
for pattern in ignoreFilePatterns:
if pattern in file:
break
else:
#If the above break didn't work, this part will be executed
dirpath = os.path.join(dest, root[src_prefix:])
try:
os.makedirs(dirpath,exist_ok=True)
except OSError as e:
if onerror is not None:
onerror(e)
filepath=os.path.join(root,file)
shutil.copy(filepath,dirpath)
continue;#If the above else didn't executed, this will be reached
continue;#If the above else didn't executed, this will be reached
exist_ok中的makedirs ，python＆gt; = 3.2
答案 7 :(得分：0)
以上方法对我无效。
所以，这就是我对another question的原始答案的扩展。
对我有用的是：
if (not (str(root) + '/').startswith(tuple(exclude_foldr)))
它会编译路径并排除列出的文件夹中的元组。
这给了我我想要的确切结果。
我的目标是使Mac井井有条。
我可以通过folder，path特定的locate & move，file.types 搜索任何ignore subfolders，而我可以抢先{{1} }，如果他们prompt the user个文件。
注意：
want to move每次运行仅一次，而不是每个文件一次
默认情况下，当您按Enter键时，提示符默认为Prompt而不是[y / N]，并且只会列出要移动的NO个文件。
这仅仅是snippet of my GitHub，请访问以获取全部脚本。
提示：阅读下面的脚本，因为我在每行中添加了有关执行操作的信息。
Potential从终端运行脚本的示例：
#!/usr/bin/env python3
# =============================================================================
# Created On : MAC OSX High Sierra 10.13.6 (17G65)
# Created On : Python 3.7.0
# Created By : Jeromie Kirchoff
# =============================================================================
"""THE MODULE HAS BEEN BUILD FOR KEEPING YOUR FILES ORGANIZED."""
# =============================================================================
from os import walk
from os import path
from shutil import move
import getpass
import click
mac_username = getpass.getuser()
includes_file_extensn = ([".jpg", ".gif", ".png", ".jpeg", ])
search_dir = path.dirname('/Users/' + mac_username + '/Documents/')
target_foldr = path.dirname('/Users/' + mac_username + '/Pictures/Archive/')
exclude_foldr = set([target_foldr,
path.dirname('/Users/' + mac_username +
'/Documents/GitHub/'),
path.dirname('/Users/' + mac_username +
'/Documents/Random/'),
path.dirname('/Users/' + mac_username +
'/Documents/Stupid_Folder/'),
])
if click.confirm("Would you like to move files?",
default=False):
question_moving = True
else:
question_moving = False
def organize_files():
"""THE MODULE HAS BEEN BUILD FOR KEEPING YOUR FILES ORGANIZED."""
# topdown=True required for filtering.
# "Root" had all info i needed to filter folders not dir...
for root, dir, files in walk(search_dir, topdown=True):
for file in files:
# creating a directory to str and excluding folders that start with
if (not (str(root) + '/').startswith(tuple(exclude_foldr))):
# showcase only the file types looking for
if (file.endswith(tuple(includes_file_extensn))):
# using path.normpath as i found an issue with double //
# in file paths.
filetomove = path.normpath(str(root) + '/' +
str(file))
# forward slash required for both to split
movingfileto = path.normpath(str(target_foldr) + '/' +
str(file))
# Answering "NO" this only prints the files "TO BE Moved"
print('Files To Move: ' + str(filetomove))
# This is using the prompt you answered at the beginning
if question_moving is True:
print('Moving File: ' + str(filetomove) +
"\n To:" + str(movingfileto))
# This is the command that moves the file
move(filetomove, movingfileto)
pass
# The rest is ignoring explicitly and continuing
else:
pass
pass
else:
pass
else:
pass
if __name__ == '__main__':
organize_files()
列出文件的示例：
$ python3 organize_files.py
Exclude list: {'/Users/jkirchoff/Pictures/Archive', '/Users/jkirchoff/Documents/Stupid_Folder', '/Users/jkirchoff/Documents/Random', '/Users/jkirchoff/Documents/GitHub'}
Files found will be moved to this folder:/Users/jkirchoff/Pictures/Archive
Would you like to move files?
No? This will just list the files.
Yes? This will Move your files to the target folder.
[y/N]:
移动文件示例：
Files To Move: /Users/jkirchoff/Documents/Archive/JayWork/1.custom-award-768x512.jpg
Files To Move: /Users/jkirchoff/Documents/Archive/JayWork/10351458_318162838331056_9023492155204267542_n.jpg
...etc