Python implements multi threaded download instances based on queue and threading
- 2020-04-02 14:15:49
- OfStack
This article illustrates python's approach to multi-threading download based on queue and threading and shares it with you for your reference. Specific methods are as follows:
The main code is as follows:
#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)
The downloadworkers. Py
Class inherits threading.Thread, reloads the run method.. Calling threading.Thread. Arbitration (self)
Implement time-consuming operations in the run method
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'])# My download process
if data:
dom, fileData = md5query.splited(data)
filename = md5
if config['has-fn']:
filename = '%s_%s' % (md5, dom.nodeValue2('xxxxxxx', '').encode('utf-8'))# This is my download method
f = file(os.path.join(config['output'], filename), 'w')
f.write(fileData)
f.close()
print '%stok' % (md5)
else:
print>>config['log'], '%st%s' % (md5, 'failed')
except Exception, e:
print>>config['log'], '%st%s' % (md5, str(e))
I hope this article has helped you with your Python programming.