Parsing Python Queue Object

I am thinking where the problem is in my code from queue import Queue from threading import Thread from html.parser import HTMLParser import urllib.request hosts = ['http://yahoo.

Solution 1:

Here is an example:

from queue import Queue
from threading import Thread
from html.parser import HTMLParser
import urllib.request


NUMBER_OF_THREADS = 3


HOSTS = ["http://yahoo.com", "http://google.com", "http://ibm.com"]


class MyHTMLParser(HTMLParser):
    def handle_starttag(self, tag, attrs):
        print("Start tag:", tag)
        for attr in attrs:
            print("\tattr:", attr)


class ThreadUrl(Thread):
   def __init__(self, queue):
       Thread.__init__(self)
       self.queue = queue

   def run(self):
       while True:
           host = self.queue.get()
           url = urllib.request.urlopen(host)
           content = str(url.read(4096))
           parser = MyHTMLParser()
           parser.feed( content )
           self.queue.task_done()


def consumer():
    queue = Queue()
    for i in range(NUMBER_OF_THREADS):
        thread = ThreadUrl(queue)
        thread.setDaemon(True)
        thread.start()
    for host in HOSTS:
        queue.put(host) 
    queue.join()


if __name__ == '__main__':
    consumer()