Question

我正在检查我的客户国家，以便知道我可以提供哪些服务... 所以问题是线程块，例如它检查15-20并阻止，我想要一个解决方案来保持它继续代码是：

import requests
import re
from sys import argv
from Queue import Queue
from threading import Thread


e = argv[1]

emails = open(e, 'r').readlines()
emails = map(lambda s: s.strip(), emails)

valid=[]

def base(email):
    xo = requests.get("http://www.paypal.com/xclick/business="+email,     headers={"User-Agent":"Mozilla/5.0 (Windows NT 5.0; rv:21.0) Gecko/20100101 Firefox/21.0"}).text
    x = re.search("s.eVar36=\"(.*?)\";", xo)
    try:
        if x.group(1) != "":
            print "%s === %s" % (email,x.group(1))
            w=open(str(x.group(1))+".txt", 'a')
            w.write(email+"\n")
            valid.append(email)
    except:
        pass

def work():
    email=q.get()
    base(email)
    q.task_done()

THREADS = 25
q=Queue()

for i in range(THREADS):
    t=Thread(target=work())
    t.daemon=True
    t.start()

if (len(argv)>0):
    for email in emails:
        q.put(email)
    q.join()`enter code here

提前致谢

Answer 1

您的问题是您在创建线程时调用work()而不是传递work函数。不要在代码中进行更改，而是考虑移动python的ThreadPool，它会为您完成繁重的任务。这是一个实现你想要的例子。

map为您的worker调用迭代器中的每个电子邮件，并将worker的结果作为迭代器（python 3）或list（python 2）返回。您的工作人员会为其给出的每封电子邮件返回有效的电子邮件或“无”，因此您只需在最后过滤掉Nones。

import requests
import re
from sys import argv
import multiprocessing.pool

e = argv[1]

emails = [line.strip() for line in open(e)]


def base(email):
    print("getting email {}".format(email))
    try:
        xo = requests.get("http://www.paypal.com/xclick/business="+email,     headers={"User-Agent":"Mozilla/5.0 (Windows NT 5.0; rv:21.0) Gecko/20100101 Firefox/21.0"}).text
        x = re.search("s.eVar36=\"(.*?)\";", xo)
        try:
            if x.group(1) != "":
                print "%s === %s" % (email,x.group(1))
                with open(str(x.group(1))+".txt", 'a') as w:
                    w.write(email+"\n")
                return email
        except:
            pass
    except requests.exceptions.RequestException as e:
        print(e)

THREADS = 25
pool = multiprocessing.pool.ThreadPool(THREADS)
valid = [email for email in pool.map(base, emails, chunksize=1) if email]
print(valid)
pool.close()

Python线程：线程阻塞

1 个答案: