用Python将一个文件夹下多个子文件夹中相同文件拷贝到同一个文件夹中并重新命名

问题描述提取多个嵌套文件夹下面同名文件

目录

代码 a

代码A

代码B

代码C

---

在这个文件夹下有三个文件夹

每一个文件夹下又有多个文件夹，要找的图片在这个文件夹里

 

代码 a

import shutil
from os.path import join
from os import listdir
# 打开文件
path = "E:\图片\Images\mao"


dirs = listdir(path)
new_dirs = "E:\图片\OCRS"

count = 0

for files in dirs:
    if files == ".DS_Store":
        continue

    file_path = join(path, files)

    for files_second in listdir(file_path):
        if files_second == ".DS_Store":
            continue
        # file_path_second = join(path + files, files_second)
        file_path_second = join(path, files)
        file_path_second = join(file_path_second, files_second)


        for file in listdir(file_path_second):
            if file.startswith("ocr"):
                count += 1
                new_name = str(count) + ".jpg"
                shutil.copy(file_path_second + '/' + file, new_dirs + new_name)

# 如何放到指定的文件夹呢？？

如果所有图在一个文件夹下面则

import shutil
from os.path import join
from os import listdir

path = ""E:\图片\Images\mao""
dirs = listdir(path)
new_dirs = "E:\图片\OCRS"
for files in dirs:
    if files == ".DS_Store":
        continue
    file_path = join(path, files)
    for file in listdir(file_path):
        if file.startswith("1v"):
            new_name = files + ".jpg"
            shutil.copy(file_path + '/' + file, new_dirs + new_name)

以上代码问题

1 路径前加r，避免特殊字符转义

2 新图片不能放到指定的文件夹

修改如下

代码A

import shutil
from os.path import join
from os import listdir


# 打开文件
path = r"E:\SourceOCR"
dirs = listdir(path)
new_dirs = r"E:\OCR"

count = 0

for files in dirs:
    if files == ".DS_Store":
        continue

    file_path = join(path, files)

    for files_second in listdir(file_path):
        if files_second == ".DS_Store":
            continue
        # file_path_second = join(path + files, files_second)
        file_path_second = join(path, files)
        files_path = join(file_path_second, files_second)

        for file in listdir(files_path):
            if file.startswith("ocr"):
                count += 1
                new_name = str(count) + ".jpg"
                det_dir = join(new_dirs, new_name)
                source_file_dir = files_path + '/' + file
                shutil.copy(source_file_dir, det_dir)
                # shutil.copyfile(source_file_dir, det_dir)

代码B

import os
import shutil
# 将文件夹中所有的文件名存入一个list
from os.path import join


def find_copy_files(files):
    for file in files:
        if file == "ocr.jpg":
            global count
            count += 1
            source = secDir + '\\' + str(file)
            newFileName = "ocr" + str(count) + ".jpg"
            det = join(determination, newFileName)
            shutil.copyfile(source, det)

#目标文件夹，此处为相对路径，也可以改为绝对路径
determination = r'E:\OCR'
if not os.path.exists(determination):
    os.makedirs(determination)

#源文件夹路径
path = r'E:\SourceOCR'
folders= os.listdir(path)
count = 0

for folder in folders:
    dir = path + '\\' +  str(folder)
    folder_second = os.listdir(dir)

    for secfolder in folder_second:
        secDir = dir + '\\' + str(secfolder)
        files = os.listdir(secDir)

        find_copy_files(files)

        # for file in files:
        #     if file == "ocr.jpg":
        #         count += 1
        #         source = secDir + '\\' + str(file)
        #         # deter = determination + str(file)
        #         newFileName = "ocr" + str(count) +".jpg"
        #         det = join(determination, newFileName)
        #         shutil.copyfile(source, det)

假如文件目录为a/b,c,d

图片在bcd文件夹中可以实现

但如果b文件夹里面有b1, b2, b3文件夹则其不能提取

对其修改后可以直接提取所有文件并重新命名，不用考虑文件夹里嵌套了多少

代码C

import os
import shutil
from os.path import join

file_dir = r'E:\SourceOCR'
determination = r'E:\OCR'
count = 0

for roots, dirs, files in os.walk(file_dir):  # 注意这里一定要加 roots，否则报错

    for dir_name in files:
        # 返回所有路径
        dir = os.path.join(roots, dir_name)
        # 分割路径，返回路径名和文件扩展名的元组
        # https://www.runoob.com/python/python-os-path.html
        dir_fileName = os.path.splitext(dir)
        # print(dir_fileName[0])
        # print(dir_fileName)
        # 找到需要的文件名
        aim = dir_fileName[0].split("\\")[-1]
        # print(dir)

        if aim == "ocr":
            count += 1
            NewFileName = str(count) + ".jpg"
            det = join(determination, str(count) + ".jpg")
            # det = join(determination, NewFileName)
            shutil.copyfile(dir, det)

还可以提升用try catch考虑如果文件夹为空或不存在要找的文件名时会出错，以后有空再修改。