urllib 如何限速下载

 

#!/usr/bin/python
#coding:utf-8


"""
urllib 如何限速下载
file:ratelimit-urllib.py
Fetch a url rate limited

Syntax: rate URL local_file_name

python ratelimit-urllib.py 200 http://localhost/share/netbeans-7.0-ml-linux.sh  1.sh

"""

import os
import sys
import urllib
from time import time, sleep

class RateLimit(object):
    """Rate limit a url fetch"""
    def __init__(self, rate_limit):
        """rate limit in kBytes / second"""
        self.rate_limit = rate_limit
        self.start = time()
    def __call__(self, block_count, block_size, total_size):
        total_kb = total_size / 1024
        downloaded_kb = (block_count * block_size) / 1024
        elapsed_time = time() - self.start
        if elapsed_time != 0:
            #实际下载速度
            rate = downloaded_kb / elapsed_time
            print "%d kb of %d kb downloaded %f.1 kBytes/s\n" % (downloaded_kb ,total_kb, rate),
            expected_time = downloaded_kb / self.rate_limit
            sleep_time = expected_time - elapsed_time
            print "Sleep for", sleep_time
            #等待时间
            if sleep_time > 0:
                sleep(sleep_time)

def main():
    """Fetch the contents of urls"""
    if len(sys.argv) != 4:
        print 'Syntax: %s "rate in kBytes/s" URL "local output path"' % sys.argv[0]
        raise SystemExit(1)
    rate_limit, url, out_path = sys.argv[1:]
    rate_limit = float(rate_limit)
    print "Fetching %r to %r with rate limit %.1f" % (url, out_path, rate_limit)
    #这个扩展接口支持一个回调函数，每下载一段就调用一次回调函数
    urllib.urlretrieve(url, out_path, reporthook=RateLimit(rate_limit))

if __name__ == "__main__": main()

 

参考资料:

http://www.gossamer-threads.com/lists/python/python/613388?do=post_view_threaded#613388