如果我问这个问题时看起来像个菜鸟,那是因为这是我第一次尝试多线程。对不起。
看到多线程是为了使过程更快,我试图找出我在哪里出错了。我注意到的第一件事是“主线程”线程比它应该的要慢得多(它是唯一不使用代理的线程)。
在进程是多线程之前,它会在单个进程/线程中在一分钟内下载大约 10-15 个图像。但是现在,“多线程”(它是唯一不通过代理发送 HTTP 请求的)真的从未显示(如您所见: http: //puu.sh/3KfwY.png)。它应该是最快的线程!
我希望我清楚地解释了我的问题。:S
PS:程序启动时,15秒内下载约20张图片;但是,在初始启动后,程序会急剧变慢。关于为什么会这样的任何想法?
#!/usr/bin/env python
import sys
import string
import os.path
import urllib.request
import threading
from time import gmtime, strftime, sleep
from random import choice
#list of our proxies
proxies = []
downloads = 1
#the number of files we want to download
target = int(sys.argv[1])
#argument 2 - proxies
try:
sys.argv[2]
except:
print('')
else:
param = sys.argv[2]
if param.find('.txt') != -1:
print('Loading specified proxy list ('+ param +').')
f = open(param, 'r+')
print('Opening '+ f.name)
proxylist = f.read()
f.close()
#split retrieved list by new line
proxies = proxylist.split('\n')
else:
print('Single proxy specified.')
proxies.append(param)
class thread(threading.Thread):
def __init__(self, ID, name, proxy):
threading.Thread.__init__(self)
self.id = ID
self.name = name
self.downloads = 0
self.proxy = proxy
self.running = True
self.fails = 0
def run(self):
global downloads
if self.proxy != False:
#id is always above one, so make the ID -1
self.proxy = proxies[(self.id-1)]
print(self.name +' initiating with proxy: '+self.proxy)
#make our requests go through proxy
self.p_handler = urllib.request.ProxyHandler({'http' : self.proxy})
self.opener = urllib.request.build_opener(self.p_handler)
urllib.request.install_opener(self.opener)
else:
print(self.name +' initiating without a proxy.')
while downloads <= target and self.running:
rstr = ''.join(choice(string.ascii_letters + string.digits) for x in range(5))
url = 'http://puu.sh/'+rstr
filename = 'downloaded/'+ strftime('%Y %m %d %H-%M-%S', gmtime()) +'.png';
try:
urllib.request.urlretrieve(url, filename)
except urllib.request.HTTPError:
pass
except IOError:
if self.fails > 10:
print(self.name +': Proxy is not working. Stopping thread.')
self.running = False
self.fails += 1
except:
pass
else:
print(self.name +': downloading '+ filename+'...' + str(downloads))
#if self.downloads % 10 == 0:
# print(self.name +': Sleeping a bit.')
# sleep(60)
downloads += 1
self.downloads += 1
sleep(5)
#lets create the "downloaded" folder if it does not exist
if not os.path.isdir('downloaded'):
try:
os.mkdir('downloaded')
except:
pass
#thread count
thread_count = 1
#create threads, and initiate them
try:
thread(0, 'main-thread', False).start()
for x in proxies:
thread(thread_count, 'Thread-'+str(thread_count), proxies[(thread_count-1)]).start()
thread_count += 1
except:
print('Couldn\'t start threads.')