如何在 Python 中复制不同的文件类型，同时保持它们的目录结构

Question

我刚开始使用 Spyder 2.3.0 和 Python 3.4.1

我有一个带有子目录的目录结构。

与网络上的其他示例不同，我想选择多种文件类型并复制目录结构。我在下面尝试过，它可以工作，但一次只需要一种文件类型和“copytree's”（它会很慢）。

有没有办法或不同的方式来简化它以使其更快？

我想我想做的是：

制作文件类型和位置的综合列表（遍历目录结构）

例如以

结尾

fileExt = [".txt", ".doc", ".docx", ".xls",".xlsx", ".ppt", ".pptx", ".m", ".xmcd", ".pdf " ]

然后使用该列表只需“shutil.copytree”

非常感谢任何建议。

  srcDir  = 'c:/a/src/dir/'
  dirName = 'c:/a/dest/dir/'


import os
import shutil

##################################################################################

dstDir = os.path.abspath(dirName)

def ignore_list(path, files):

    filesToIgnore = []

    for fileName in files:

        fullFileName = os.path.join(os.path.normpath(path), fileName)

        if not os.path.isdir(fullFileName) and not fileName.endswith('.txt') :

            filesToIgnore.append(fileName)

    return filesToIgnore

# start of script

shutil.copytree(srcDir, dstDir, ignore=ignore_list)
####################################################################################################################################################################

dstDir = os.path.abspath(dirName)

def ignore_list(path, files):

    filesToIgnore = []

    for fileName in files:

        fullFileName = os.path.join(os.path.normpath(path), fileName)

        if not os.path.isdir(fullFileName) and not fileName.endswith('.docx') :


            filesToIgnore.append(fileName)

    return filesToIgnore

# start of script

shutil.copytree(srcDir, dstDir, ignore=ignore_list)

####################################################

复制并粘贴更改的“endswith('.docx') :”

Answer 1

我们可以多执行一些“ignore_list”方法

valid_formats = ["txt", "doc", "docx", "xls","xlsx", "ppt", "pptx", "m", "xmcd", "pdf "]

import timeit
import os.path as op

def ignore_list(path, files):
    dag_path = [op.join(op.normpath(path), f) for f in files]
    return [ff for ff in dag_path if not op.isdir(ff) and ff.split(".")[-1] not in valid_formats]

start = timeit.default_timer()
ignore = ignore_list(path, files)
print ("Time: {0}".format(str(timeit.default_timer()-start)))

Answer 2

这行得通，我知道它不漂亮，但它行得通

srcDir  = 'c:/a/src/dir/
dstDir = 'c:/a/dest/dir/'


A01= '.doc'
A02= '.docx'
A03= '.xls'
A04= '.xlsx'
A05= '.ppt'
A06= '.pptx'
A07= '.m'
A08= '.xmcd'
A09= '.inp'
A10= '.pdf'
A11= '.DOC'
A12= '.DOCX'
A13= '.XLS'
A14= '.XLSX'
A15= '.PPT'
A16= '.PPTX'
A17= '.M'
A18= '.XMCD'
A19= '.INP'
A20= '.PDF'



import os
import shutil

#########################################################################################################


def ignore_list(path, files):

    filesToIgnore = []

    for fileName in files:

        fullFileName = os.path.join(os.path.normpath(path), fileName)

        if not os.path.isdir(fullFileName) and not fileName.endswith(A01) and not fileName.endswith(A02) and not fileName.endswith(A03) and not fileName.endswith(A04) and not fileName.endswith(A05) and not fileName.endswith(A06) and not fileName.endswith(A07) and not fileName.endswith(A08) and not fileName.endswith(A09) and not fileName.endswith(A10) and not fileName.endswith(A11) and not fileName.endswith(A12) and not fileName.endswith(A13) and not fileName.endswith(A14) and not fileName.endswith(A15) and not fileName.endswith(A16) and not fileName.endswith(A17) and not fileName.endswith(A18) and not fileName.endswith(A19) and not fileName.endswith(A20) :


            filesToIgnore.append(fileName)

    return filesToIgnore




shutil.copytree(srcDir, dstDir, ignore=ignore_list)

#########################################################################################################