如何准确地搜索包含文本文件中元素的目录？

Question

对 python 来说相当新。 我正在尝试使用由文本文件组成的列表来搜索文件和文件夹的目录。 它在一定程度上起作用，但前提是搜索元素位于文件/文件夹名称的开头，因为我正在使用 .startswith()。

我正在使用的代码如下。

我认为正则表达式可能是要走的路，但似乎无法弄清楚。

任何帮助表示赞赏。

谢谢。

import os

def data_cleansing(path):

    dirscount = 0
    filescount = 0


    with open("Y:\Admin\Data Cleansing\DCList.txt","r") as f:
        x = f.readlines()
        x = [x.replace("\n","") for x in x]

    #print(x)


    for root, dirs, files in os.walk(path):
        for dirs in dirs:
            if dirs.startswith(tuple(x)):
                dirscount = dirscount + 1
                #print(dirscount)
                print(os.path.join(dirs))



    for root, dirs, files in os.walk(path):
        for files in files:
            if files.startswith(tuple(x)):
                filescount = filescount + 1
                #print(filescount)
                print(os.path.join(files))



    total = (dirscount + filescount)
    print(total,"files and folders found in",path,"that need cleansing.")

data_cleansing(r"G:\Processed\failed")
print("*"*70)
data_cleansing(r"G:\Processed\done")
print("*"*70)
data_cleansing(r"S:\Prosort")
print("*"*70)
data_cleansing(r"S:\Prosort_Archive")

Answer 1

这是否符合您的需求？

from os import scandir
find_list = ['Uni', '.doc', 'XML']
path = r"c:\\Autoit\\ForumTests\\"

def scantree(path):
    """Recursively yield DirEntry objects for given directory."""
    for entry in scandir(path):
        if entry.is_dir(follow_symlinks=False):
            yield from scantree(entry.path)
        else:
            yield entry

if __name__ == '__main__':
    for entry in scantree(path):
        for pattern in find_list:
            if pattern in entry.path:
                print(pattern, '-->', entry.path)