python urllib urlretrieve学习使用

import urllib
import os

def reporthook(blocks_read, block_size, total_size):
    if not blocks_read:
        print "Connection opened"
        return
    if total_size < 0:
        print "Read %d blocks (%d bytes)" % (blocks_read, blocks_read * block_size)
        
    else:
        amount_read = blocks_read * block_size
        print "Read %d blocks,  %d/%d, %.0f%%" % (blocks_read, amount_read, total_size, amount_read*100.0/(total_size))
    
    return
try:
    filename, msg = urllib.urlretrieve("http://www.xiaomi.com", reporthook=reporthook)
    print
    print "File:", filename
    print "Headers:"
    print msg
    print "File exists before cleanup:", os.path.exists(filename)
    
finally:
    urllib.urlcleanup()
    
    print "File still exists:", os.path.exists(filename)
    

输出如下：

Connection opened
Read 1 blocks,  8192/55662, 15%
Read 2 blocks,  16384/55662, 29%
Read 3 blocks,  24576/55662, 44%
Read 4 blocks,  32768/55662, 59%
Read 5 blocks,  40960/55662, 74%
Read 6 blocks,  49152/55662, 88%
Read 7 blocks,  57344/55662, 103%

File: /tmp/tmp4lhkGA
Headers:
Date: Wed, 19 Feb 2014 08:55:20 GMT
Content-Type: text/html; charset=utf-8
Cache-Control: max-age=1800
X-Cacheable: MI-WWW-Cacheable
Server: MIFE/3.0
Expires: Wed, 19 Feb 2014 09:25:20 GMT
Powered-By-ChinaCache: MISS from 010519h3SP.4
Age: 990
Content-Length: 55662
Powered-By-ChinaCache: HIT from 01005143SG
Connection: close

File exists before cleanup: True
File still exists: False

可以看到最后竟然读取了103%， 这是由于每次读取都是按照block 8192bytes来读取的，就算最后不满8192bytes, 也返回一个block的size