Question

启动约300个线程需要大约15分钟（打印出来：'使用代理启动'）;但是，每当我删除线程运行函数中while循环中的所有代码时，它会在10秒内启动所有线程（可能更少）。有关while循环中的内容是否使所有线程启动/启动非常缓慢的任何想法？

#!/usr/bin/env python
import requests
import sys
import string
import os.path
import urllib.request
import threading
import mimetypes
from time import gmtime, strftime, sleep
from random import choice

#list of our proxies
proxies = []
working = []

downloads = 1
initiated = 0

#the number of files we want to download
target = int(sys.argv[1])

#argument 2 - proxies
try:
    sys.argv[2]
except:
    pass
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
        global working
        global initiated

        initiated += 1

        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)
        else:
            print(self.name +' initiating without a proxy.')

        #start actual downloads
        while downloads <= target and self.running:
            #wait for all threads to be loaded before starting requests
            if (initiated-1) == len(proxies):
                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 ['+ rstr +']', gmtime()) +'.png'

                try:
                    if self.proxy != False:
                        #make our requests go through proxy
                        r = requests.get(url, None, {'http' : self.proxy})
                    else:
                        r = requests.get(url)
                except IOError:
                    if self.fails >= 10:
                        #print(self.name +': Proxy is not working. Stopping thread.')
                        self.running = False

                    self.fails += 1
                    pass
                except:
                    pass
                else:

                    if r.status_code == 200 and r.headers['Content-Type'] != 'text/html':
                        with open(filename, 'wb') as f:
                            for chunk in r.iter_content(1024):
                                f.write(chunk)

                        print(self.name +': '+ filename+' downloaded...' + str(downloads))

                        downloads += 1
                        self.downloads += 1

                        if not self.proxy in working and self.proxy != False:
                                working.append(self.proxy)

                        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, 'Thread-main', 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.')

Answer 1

首先，我完全同意Matteo Italia的评论。我还认为您对变量initiated的使用存在问题：

您的代码如下：

   while downloads <= target and self.running:
        #wait for all threads to be loaded before starting requests
        if (initiated-1) == len(proxies):
            ...
        # nothing in else

因此所有线程都在积极等待！这意味着他们只是在等待其他线程使用大量的CPU ......你应该阻止一个事件：

initiated = 0
all_ready = Event()

和run()：

if initiated-1 == len(proxies):
    all_ready.set()
else:
    all_ready.wait()
while downloads <= target and self.running:
    ...

Answer 2

这种情况正在发生，因为你按顺序运行每个线程 - 你创建每个线程，然后你启动它，然后它启动，它打印出消息，然后它去做所有的web东西，然后它睡觉，然后在如果没有安排另一个已经创建的线程，那么可以启动下一个线程的休眠。

当然，正如前面提到的，python在线程方面非常糟糕。尽量避免它。

为什么线程缓慢启动？

2 个答案: