Python urllib2 进度挂钩

Question

我正在尝试使用 urllib2 http 客户端在 python 中创建下载进度条。我查看了 API（以及谷歌），似乎 urllib2 不允许您注册进度挂钩。然而，较旧的已弃用的 urllib 确实具有此功能。

有谁知道如何使用 urllib2 创建进度条或报告挂钩？或者还有其他一些技巧可以获得类似的功能吗？

Answer 1

这是一个完全有效的示例，它建立在 Anurag 响应分块方法的基础上。我的版本允许您设置块大小，并附加任意报告功能：

import urllib2, sys

def chunk_report(bytes_so_far, chunk_size, total_size):
   percent = float(bytes_so_far) / total_size
   percent = round(percent*100, 2)
   sys.stdout.write("Downloaded %d of %d bytes (%0.2f%%)\r" % 
       (bytes_so_far, total_size, percent))

   if bytes_so_far >= total_size:
      sys.stdout.write('\n')

def chunk_read(response, chunk_size=8192, report_hook=None):
   total_size = response.info().getheader('Content-Length').strip()
   total_size = int(total_size)
   bytes_so_far = 0

   while 1:
      chunk = response.read(chunk_size)
      bytes_so_far += len(chunk)

      if not chunk:
         break

      if report_hook:
         report_hook(bytes_so_far, chunk_size, total_size)

   return bytes_so_far

if __name__ == '__main__':
   response = urllib2.urlopen('http://www.ebay.com');
   chunk_read(response, report_hook=chunk_report)

Answer 2

为什么不直接以块的形式读取数据并在其间做任何您想做的事情，例如在线程中运行、挂钩到 UI 等

import urllib2

urlfile = urllib2.urlopen("http://www.google.com")

data_list = []
chunk = 4096
while 1:
    data = urlfile.read(chunk)
    if not data:
        print "done."
        break
    data_list.append(data)
    print "Read %s bytes"%len(data)

输出：

Read 4096 bytes
Read 3113 bytes
done.

Answer 3

urlgrabber 内置了对进度通知的支持。

Answer 4

简化版：

temp_filename = "/tmp/" + file_url.split('/')[-1]
f = open(temp_filename, 'wb')
remote_file = urllib2.urlopen(file_url)

try:
    total_size = remote_file.info().getheader('Content-Length').strip()
    header = True
except AttributeError:
    header = False # a response doesn't always include the "Content-Length" header

if header:
    total_size = int(total_size)

bytes_so_far = 0

while True:
    buffer = remote_file.read(8192)
    if not buffer:
        sys.stdout.write('\n')
        break

    bytes_so_far += len(buffer)
    f.write(buffer)
    if not header:
        total_size = bytes_so_far # unknown size

    percent = float(bytes_so_far) / total_size
    percent = round(percent*100, 2)
    sys.stdout.write("Downloaded %d of %d bytes (%0.2f%%)\r" % (bytes_so_far, total_size, percent))

Answer 5

对 Triptych 的响应进行小修改，以允许实际写出文件（python3）：

from urllib.request import urlopen

def chunk_report(bytes_so_far, chunk_size, total_size):
    percent = float(bytes_so_far) / total_size
    percent = round(percent*100, 2)
    sys.stdout.write("Downloaded %d of %d bytes (%0.2f%%)\r" %
                     (bytes_so_far, total_size, percent))

    if bytes_so_far >= total_size:
        sys.stdout.write('\n')


def chunk_read(response, chunk_size=8192, report_hook=None):
    total_size = response.info().get("Content-Length").strip()
    total_size = int(total_size)
    bytes_so_far = 0
    data = b""

    while 1:
        chunk = response.read(chunk_size)
        bytes_so_far += len(chunk)

        if not chunk:
            break

        if report_hook:
            report_hook(bytes_so_far, chunk_size, total_size)

        data += chunk

    return data

用法：

with open(out_path, "wb") as f:
    response = urlopen(filepath)
    data_read = chunk_read(response, report_hook=chunk_report)

    f.write(data_read)