跳转至

Python 文件下载并显示下载进度条

先上代码，后面有空再整理细节：

# -*- coding:utf-8 -*-
# vim:et:ts=4:sw=4:
#!/usr/bin/env python

######################################################################
__author__  = 'ishenweiyan@qq.com'
__create__  = '2019-09-19'
__file__    = 'download_demo.py'
__license__ = '2019 All rights reserved.'
__doc__     = 'The test script.'
#####################################################################

import os
from urllib.request import urlopen

import requests
from tqdm import tqdm
from contextlib import closing


class ProgressBar(object):

    def __init__(self, title,
                 count=0.0,
                 run_status=None,
                 fin_status=None,
                 total=100.0,
                 unit='', sep='/',
                 chunk_size=1.0):
        super(ProgressBar, self).__init__()
        self.info = "[%s] %s %.2f %s %s %.2f %s"
        self.title = title
        self.total = total
        self.count = count
        self.chunk_size = chunk_size
        self.status = run_status or ""
        self.fin_status = fin_status or " " * len(self.status)
        self.unit = unit
        self.seq = sep

    def __get_info(self):
        # [名称] 状态 进度 单位 分割线 总数 单位
        _info = self.info % (self.title, self.status,
                             self.count/self.chunk_size, self.unit, self.seq, self.total/self.chunk_size, self.unit)
        return _info

    def refresh(self, count=1, status=None):
        self.count += count
        # if status is not None:
        self.status = status or self.status
        end_str = "\r"
        if self.count >= self.total:
            end_str = '\n'
            self.status = status or self.fin_status
        print(self.__get_info(), end=end_str)


def download_from_url(url, dst):
    """
    @param: url to download file
    @param: dst place to put the file
    """
    file_size = int(urlopen(url).info().get('Content-Length', -1))

    if os.path.exists(dst):
        first_byte = os.path.getsize(dst)
    else:
        first_byte = 0
    if first_byte >= file_size:
        return file_size
    header = {"Range": "bytes=%s-%s" % (first_byte, file_size)}
    pbar = tqdm(
        total=file_size, initial=first_byte,
        unit='B', unit_scale=True, desc=url.split('/')[-1])
    req = requests.get(url, headers=header, stream=True)
    with(open(dst, 'ab')) as f:
        for chunk in req.iter_content(chunk_size=1024):
            if chunk:
                f.write(chunk)
                pbar.update(1024)
    pbar.close()
    return file_size

def __main__():

    url = 'http://ftp.ncbi.nlm.nih.gov/gene/DATA/gene2ensembl.gz'
    file_name = 'gene2ensembl.gz'

    '''
    with closing(requests.get(url, stream=True)) as response:
        chunk_size = 1024 # 单次请求最大值
        content_size = int(response.headers['content-length']) # 内容体总大小
        progress = ProgressBar(file_name, total=content_size,
                                     unit="KB", chunk_size=chunk_size, run_status="正在下载", fin_status="下载完成")
        with open(file_name, "wb") as file:
            for data in response.iter_content(chunk_size=chunk_size):
                file.write(data)
                progress.refresh(count=len(data))
    '''
    download_from_url(url, file_name)

if __name__ == "__main__":
    __main__()

参考资料