Download and extract a zip from Dropbox

dropbox_download_and_extract.py

import os
import urllib.request
import zipfile

from tqdm import tqdm

from util import create_dir_if_not_exist

ZIP_URL = "https://www.dropbox.com/s/<drop_box_id>/<file_name>?dl=1"
ZIP_PATH = "<path_to_download_dest>"
PROCESSED_DIR = "<path_to_extract_dest>"


def download():
    if not os.path.exists(ZIP_PATH):
        print('Downloading from Dropbox')
        response = urllib.request.urlopen(ZIP_URL)
        total_length = int(response.info()['Content-Length'])/1000000
        size = 16 * 1024
        with open(ZIP_PATH, 'wb') as f:
            with tqdm(total=total_length, unit='MB',
                      bar_format='{l_bar}{bar}| {n:.1f}/{total:.1f}MB [{elapsed}<{remaining}, ' '{rate_fmt}{postfix}]') \
                    as pbar:
                while True:
                    chunk = response.read(size)
                    if not chunk:
                        break
                    f.write(chunk)
                    pbar.update(len(chunk)/1000000)
        response.close()
    else:
        print('Zip file already found')


def extract():
    print('Extracting from zip')
    create_dir_if_not_exist(PROCESSED_DIR)
    with zipfile.ZipFile(ZIP_PATH, 'r') as zip_ref:
        for member in tqdm(zip_ref.infolist(), desc='Extracting'):
            zip_ref.extract(member, PROCESSED_DIR)


if __name__ == "__main__":
    download()
    extract()