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.com", "http://google.com", "http://ibm.com"]
queue = Queue()
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)
url.read(4096)
self.queue.task_done()
class MyHTMLParser(HTMLParser):
def handle_starttag(self, tag, attrs):
print("Start tag:", tag)
for attr in attrs:
print(" attr:", attr)
def consumer():
for i in range(3):
t = ThreadUrl(queue)
t.setDaemon(True)
t.start()
for host in hosts:
parser = MyHTMLParser()
parser.feed(host)
queue.put(host)
queue.join()
consumer()
My goal is to extract content of the URLS,read the queue and finally parse it.When I execute the code it does not print anything.Where should I place the parser?