python-利用queue和threading实现多线程下载

主代码：

#----------------------------------------------------
#download worker
#----------------------------------------------------
queue_download = Queue.Queue(0)
DOWNLOAD_WORKERS = 20
for i in range(DOWNLOAD_WORKERS):
DownloadWorker(queue_download).start()  #start a download worker

for md5 in MD5S:
queue_download.put(md5)
for i in range(DOWNLOAD_WORKERS):
queue_download.put(None)

downloadworkers.py

类继承 threading.Thread,重载run方法..在__init__中调用threading.Thread.__init__(self),

在run方法中实现耗时的操作

import threading
import Queue
import md5query
import DOM
import os,sys
########################################################################
class DownloadWorker(threading.Thread):
""""""

#----------------------------------------------------------------------
def __init__(self, queue):
"""Constructor"""
self.__queue = queue
threading.Thread.__init__(self)

def run(self):
while 1:
md5 = self.__queue.get()
if md5 is None:
break #reached end of queue
#this is a time-cost produce
self._down(md5)

print "task:", md5, "finished"

def _down(self, md5):
config = {
'input':sys.stdin,
'output':'./samples',
'location':'xxx',
'has-fn':False,
'options':{'connect.timeout':60, 'timeout':3600},
'log':file('logs.txt', 'w'),
}
print 'download %s...' % (md5)
try:
data = downloadproc(config['location'], config['options'])  我的下载过程
if data:
dom, fileData = md5query.splited(data)
filename = md5
if config['has-fn']:
filename = '%s_%s' % (md5, dom.nodeValue2('xxxxxxx', '').encode('utf-8'))   这是我的下载的方法
f = file(os.path.join(config['output'], filename), 'w')
f.write(fileData)
f.close()

print '%s\tok' % (md5)
else:
print>>config['log'], '%s\t%s' % (md5, 'failed')
except Exception, e:
print>>config['log'], '%s\t%s' % (md5, str(e))