Python-使用模式匹配目录（正则表达式）

Question

我写了一个循环，忽略了其中包含.txt文件的所有子目录。

src = raw_input("Enter source disk location: ")
src = os.path.abspath(src)
dst = raw_input("Enter first destination to copy: ")
dst = os.path.abspath(dst)
dest = raw_input("Enter second destination to move : ")
dest = os.path.abspath(dest) 

path_patter = '(\S+)_(\d+)_(\d+)_(\d+)__(\d+)_(\d+)_(\d+)'

for dir, dirs, files in os.walk(src):
if any(f.endswith('.txt') for f in files):
    dirs[:] = []  # do not recurse into subdirectories
    continue  
files = [os.path.join(dir, f) for f in files ]

for f in files:

    part1 = os.path.dirname(f)
    part2 = os.path.dirname(os.path.dirname(part1))
    part3 = os.path.split(part1)[1]
    path_miss1 = os.path.join(dst, "missing_txt")
    path_miss = os.path.join(path_miss1, part3)
    path_missing = os.path.join(dest, "missing_txt")
    searchFileName = re.search(path_patter, part3)#### update

    if searchFileName:#####update
    try:
        if not os.path.exists(path_miss):
            os.makedirs(path_miss)
        else:
            pass

        if os.path.exists(path_miss):
            distutils.dir_util.copy_tree(part1, path_miss)
        else:
            debug_status += "missing_file\n"
            pass

        if (get_size(path_miss)) == 0:
            os.rmdir(path_miss)
        else:
            pass

        if not os.path.exists(path_missing):
            os.makedirs(path_missing)
        else:
            pass

        if os.path.exists(path_missing):
            shutil.move(part1, path_missing)
        else:
            pass

        if (get_size(path_missing)) == 0:
            os.rmdir(path_missing)
        else:
            pass
    except Exception:
        pass
    else:
    continue

在这种情况下，如何修改此代码以将目录名与正则表达式进行比较。 （它必须忽略带有.txt文件的目录）

Answer 1

import os
import re

def createEscapedPattern(path,pattern):
    newPath = os.path.normpath(path)
    newPath = newPath.replace("\\","\\\\\\\\")
    return newPath + "\\\\\\\\" +  pattern

def createEscapedPath(path):
    newPath =  os.path.normpath(path)
    return newPath.replace("\\","\\\\")

src = 'C:\\Home\\test'
path_patter = '(\S+)_(\d+)_(\d+)_(\d+)__(\d+)_(\d+)_(\d+)$'
p = re.compile(createEscapedPattern(src,path_patter))
for dir, dirs, files in os.walk(src):
    if any(f.endswith('.txt') for f in files):
        dirs[:] = []
        continue
    if any(p.match(createEscapedPath(dir)) for f in files):
        for f in files:
            print createEscapedPath(dir + "/" + f)
    p = re.compile(createEscapedPattern(dir,path_patter))

我在这里做了几件事，希望这个例子对您有所帮助

• 我为Windows fs编写了此代码，因此使用了两个路径转换功能。
• 该脚本会像您实现它一样忽略带有.txt文件的目录
• 该脚本将从您启动脚本的目录开始，并且仅在模式匹配时才打印文件名。 对于先前规则未忽略的所有子目录，将完成此操作。
• 在python中使用了正则表达式，并使其针对每个目录再次进行编译，因此您得到：'directory /（\\ S +） （\\ d +） （\\ d +）_（\\ d +）__（\\ d +） （\\ d +） （\\ d +）$ '