python使用urllib下载文件

import urllib.request
import os
import sys
import tarfile

def download_and_uncompress_tarball(tarball_url, dataset_dir):
  """Downloads the `tarball_url` and uncompresses it locally.
  Args:
    tarball_url: The URL of a tarball file.
    dataset_dir: The directory where the temporary files are stored.
  """
  filename = tarball_url.split('/')[-1]
  filepath = os.path.join(dataset_dir, filename)

  def _progress(count, block_size, total_size):
    sys.stdout.write('\r>> Downloading %s %.1f%%' % (
        filename, float(count * block_size) / float(total_size) * 100.0))
    sys.stdout.flush()
  filepath, _ = urllib.request.urlretrieve(tarball_url, filepath, _progress)
  print()
  statinfo = os.stat(filepath)
  print('Successfully downloaded', filename, statinfo.st_size, 'bytes.')
  tarfile.open(filepath, 'r:gz').extractall(dataset_dir)

DATA_URL = 'http://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
DATA_DIR = 'data'


download_and_uncompress_tarball(DATA_URL, DATA_DIR)

代码说明

• 使用 urllib.request.urlretrieve下载
• 内嵌入了一个 回调函数 _progress，显示其进度
• 使用 tar.file.open 进行解压