python linux中打包指定文件

问题场景：

有一个很大csv文件存储了不同类别的编号，然后对应编号的图片数据都在linux上，然后我需要每个类别取一小部分，将指定部分的数据从linux上打包下来

---

解决方案：

具体解决方案：

import os
import datetime
import tarfile
import pandas as pd
from tqdm import tqdm
import cv2

filename = '../resource/data_train_100.csv'
df = pd.read_csv(filename)
img_ls = df.iloc[:, 0].tolist()

def re_Iamge_reader(name):
    path = ['/e/images/shortImage/', '/e/images/1758/', '/e/images/1762/', '/e/images/Image/', '/e/images/picture/']
    img_name = name + '.jpg'
    i = 0
    while True:
        img_path = path[i] + img_name
        img = cv2.imread(img_path)
        if img is None:
            i += 1
            if i > 4:
                print('所有路径都没这个{}图片，拉倒吧你'.format(img_name))
                return None
        else:
            return img_path

def Is_img(url, name):
    img = cv2.imread(url)
    if img is None:
        url = re_Iamge_reader(name)
        return url
    else:
        return url

def find_file(root, patterns=['*']):
    path = "/d/images_Lib/image/"
    for i in tqdm(root):
        img_path = path + i + '.jpg'
        img_path = Is_img(img_path, i)
        yield os.path.join(img_path)

def cre_tarfile():
    args = ["*.jpg", "*.jepg"]
    now = datetime.datetime.now().strftime("%Y_%m_%d_%H_%M_%S")
    filename = "all{0}.tar.gz".format(now)
    with tarfile.open(filename, mode='w:gz') as f:
        for item in find_file(img_ls, args):
            f.add(item)

if __name__ == "__main__":
    cre_tarfile()