先上代码，后面有空再整理细节：

  1. # -*- coding:utf-8 -*-
  2. # vim:et:ts=4:sw=4:
  3. #!/usr/bin/env python
  5. ######################################################################
  6. __author__  = 'ishenweiyan@qq.com'
  7. __create__  = '2019-09-19'
  8. __file__    = 'download_demo.py'
  9. __license__ = '2019 All rights reserved.'
  10. __doc__     = 'The test script.'
  11. #####################################################################
  13. import os
  14. from urllib.request import urlopen
  16. import requests
  17. from tqdm import tqdm
  18. from contextlib import closing
  21. class ProgressBar(object):
  23.     def __init__(self, title,
  24.                  count=0.0,
  25.                  run_status=None,
  26.                  fin_status=None,
  27.                  total=100.0,
  28.                  unit='', sep='/',
  29.                  chunk_size=1.0):
  30.         super(ProgressBar, self).__init__()
  31.         self.info = "[%s] %s %.2f %s %s %.2f %s"
  32.         self.title = title
  33.         self.total = total
  34.         self.count = count
  35.         self.chunk_size = chunk_size
  36.         self.status = run_status or ""
  37.         self.fin_status = fin_status or " " * len(self.status)
  38.         self.unit = unit
  39.         self.seq = sep
  41.     def __get_info(self):
  42.         # [名称] 状态 进度 单位 分割线 总数 单位
  43.         _info = self.info % (self.title, self.status,
  44.                              self.count/self.chunk_size, self.unit, self.seq, self.total/self.chunk_size, self.unit)
  45.         return _info
  47.     def refresh(self, count=1, status=None):
  48.         self.count += count
  49.         # if status is not None:
  50.         self.status = status or self.status
  51.         end_str = "\r"
  52.         if self.count >= self.total:
  53.             end_str = '\n'
  54.             self.status = status or self.fin_status
  55.         print(self.__get_info(), end=end_str)
  58. def download_from_url(url, dst):
  59.     """
  60.     @param: url to download file
  61.     @param: dst place to put the file
  62.     """
  63.     file_size = int(urlopen(url).info().get('Content-Length', -1))
  65.     if os.path.exists(dst):
  66.         first_byte = os.path.getsize(dst)
  67.     else:
  68.         first_byte = 0
  69.     if first_byte >= file_size:
  70.         return file_size
  71.     header = {"Range": "bytes=%s-%s" % (first_byte, file_size)}
  72.     pbar = tqdm(
  73.         total=file_size, initial=first_byte,
  74.         unit='B', unit_scale=True, desc=url.split('/')[-1])
  75.     req = requests.get(url, headers=header, stream=True)
  76.     with(open(dst, 'ab')) as f:
  77.         for chunk in req.iter_content(chunk_size=1024):
  78.             if chunk:
  79.                 f.write(chunk)
  80.                 pbar.update(1024)
  81.     pbar.close()
  82.     return file_size
  84. def __main__():
  86.     url = 'http://ftp.ncbi.nlm.nih.gov/gene/DATA/gene2ensembl.gz'
  87.     file_name = 'gene2ensembl.gz'
  89.     '''
  90.     with closing(requests.get(url, stream=True)) as response:
  91.         chunk_size = 1024 # 单次请求最大值
  92.         content_size = int(response.headers['content-length']) # 内容体总大小
  93.         progress = ProgressBar(file_name, total=content_size,
  94.                                      unit="KB", chunk_size=chunk_size, run_status="正在下载", fin_status="下载完成")
  95.         with open(file_name, "wb") as file:
  96.             for data in response.iter_content(chunk_size=chunk_size):
  97.                 file.write(data)
  98.                 progress.refresh(count=len(data))
  99.     '''
  100.     download_from_url(url, file_name)
  102. if __name__ == "__main__":
  103.     __main__()

参考资料