This article example describes the python based queue and threading to achieve multi-threaded download method, shared for your reference. Specific methods are as follows:
The main code is as follows:
#download worker queue_download = (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)
included among these
Class inheritance, overloading the run method... Called in __init__. __init__(self), __init__(self), __init__(self), __init__(self)
Implementing time-consuming operations in the run method
import threading import Queue import md5query import DOM import os,sys class DownloadWorker(): """""" def __init__(self, queue): """Constructor""" self.__queue = queue .__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':, 'output':'./samples', 'location':'xxx', 'has-fn':False, 'options':{'':60, 'timeout':3600}, 'log':file('', 'w'), } print 'download %s...' % (md5) try: data = downloadproc(config['location'], config['options'])# My download process if data: dom, fileData = (data) filename = md5 if config['has-fn']: filename = '%s_%s' % (md5, dom.nodeValue2('xxxxxxx', '').encode('utf-8'))# This is how I downloaded it f = file((config['output'], filename), 'w') (fileData) () 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))
I hope that what I have described in this article will help you in your Python programming.