用Python批量获取某目录下压缩包中指定文件集

时间：04-26来源：作者：点击数：15

一、提前准备工作

以下两种方式根据你的实际情况二选一

1、如果你使用python没有用到虚拟环境管理工具，就直接把UnRAR.exe文件放在python安装目录下的Scripts文件夹下

2、如果你有使用虚拟环境管理工具，则把UnRAR.exe放到当前你需要使用的虚拟环境下的Scripts文件夹下

二、上代码

# _*_ coding: utf-8 _*_
import rarfile, os, re, shutil, zipfile
from os import listdir
from OperateFile import *

# param(压缩包所在文件夹的dir，指定压缩包解压后存放文件的位置，要从压缩包中匹配出的文件的文件名数组)
# return null
# @AuThor wavezhou
# @date 20211020
class BatchDecompression(object):
    def __int__(self):
        super(BatchDecompression, self)

    def __init__(self, sourcedir, targetdir, sample):
        self.source = sourcedir # 存放压缩包的目录
        self.target = targetdir # 输出压缩包中想保留的文件的存放目录
        self.sample = sample # 匹配出压缩包想保留的文件的匹配模板
        self.flag = None
        self.valid_file_list = list()
        self.origin_files = list()
        self.save_origin_other_files(sourcedir)

    def save_origin_other_files(self, sourcedir):
        for file_or_rar in os.listdir(sourcedir):
            if os.path.isfile(os.path.join(sourcedir, file_or_rar)) and str(file_or_rar)[-3:] not in (
                    'rar', 'RAR', 'ZIP', 'zip'):
                self.origin_files.append(file_or_rar)
                self.valid_file_list.append(file_or_rar)

    @staticmethod
    def compress(file_list, target_path):
        with zipfile.ZipFile(target_path, 'w', compression=zipfile.ZIP_DEFLATED) as zipf:
            for file in file_list:
                zipf.write(file, os.path.basename(file))

    def batchExt(self, pwd=None):
        if len(self.sample) < 1:
            raise Exception('第三个参数数组不能为空')
        filenames = listdir(self.source)
        for file in filenames:
            if '某某**压缩包' in file:# 如果确定某压缩包里没你想要的文件，可将该压缩包文件名里含有的部分文字替换掉这里的“某某**压缩包”
                continue
            if str(file)[-3:] not in ('rar', 'RAR', 'ZIP', 'zip') and str(file)[-2:] not in ['7z']:
                continue
            path1 = os.path.join(self.source, file)
            if file.lower().endswith('rar'):
                try:
                    rf = rarfile.RarFile(path1)  # 待解压文件
                    rf.extractall(self.target)
                    rf.close()  # 解压指定文件路径
                except Exception as e:
                    if pwd is None:
                        zf = zipfile.ZipFile(path1)
                        zf.extractall(self.target)
                    else:
                        zf = zipfile.ZipFile(path1, 'r')
                        zf.extractall(self.target, pwd=pwd.encode('utf-8'))
                    zf.close()
            elif file.lower().endswith('zip'):
                if pwd is None:
                    zf = zipfile.ZipFile(path1)
                    zf.extractall(self.target)
                else:
                    zf = zipfile.ZipFile(path1, 'r')
                    zf.extractall(self.target, pwd=pwd.encode('utf-8'))
                zf.close()
            elif file.lower().endswith('7z'):
                import py7zr
                with py7zr.SevenZipFile(path1, mode='r') as z:
                    z.extractall(self.target)
                z.close()
        folders = listdir(self.target)
        if len(self.sample) == 1:
            pattern = r"" + self.sample[0]  # 指定匹配模板
            self.flag = True
            self.recursion_search(folders, pattern)
        else:
            for i in range(len(self.sample)):
                if i == len(self.sample) - 1:
                    self.flag = True  # 最后一次遍历清楚压缩包
                pattern = r"" + self.sample[i]
                self.recursion_search(folders, pattern)

        for fd in folders:  # 最后清除多余文件夹和文件
            if os.path.isdir(os.path.join(self.target, fd)):
                shutil.rmtree(os.path.join(self.target, fd))
            elif fd not in self.valid_file_list:
                os.remove(os.path.join(self.target, fd))

    def recursion_search(self, folders, pattern):
        foders_tmp = folders[:]  # 能避免数组中元素删除造成的指针错位
        for fd in foders_tmp:
            if fd.endswith('rar') or fd.endswith('zip') or fd.endswith('7z'):
                if self.flag:
                    os.remove(os.path.join(self.target, fd))
                    folders.remove(fd)
                continue
            elif os.path.isfile(os.path.join(self.target, fd)):
                if re.search(pattern, fd) and re.search(pattern, fd).group(0) == pattern:
                    self.valid_file_list.append(fd)
                continue
            path2 = os.path.join(self.target, fd)
            self.rec_find(path2, pattern)

    def rec_find(self, path2, pattern):  # 开始递归查找想保留的文件内容
        file_names = os.listdir(path2)
        for fs in file_names:
            if os.path.isdir(os.path.join(path2, fs)):
                self.rec_find(os.path.join(path2, fs), pattern)
            elif re.search(pattern, fs) and re.search(pattern, fs).group(0) == pattern:
                self.valid_file_list.append(fs)
                shutil.move(os.path.join(path2, fs), os.path.join(self.target, fs))

if __name__ == '__main__':
    # 使用示例
    bd = BatchDecompression(r"D:\temp_ha",r'D:\temp_ha',['某某账单','.txt','.xlsx','pdf'])
    bd.batchExt()