Created
December 10, 2012 15:23
-
-
Save docete/4251227 to your computer and use it in GitHub Desktop.
synchronization primitive: semaphore example (resource limitation)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf8 -*- | |
import threading | |
import time | |
import random | |
sema = threading.Semaphore(2) | |
class Grab(threading.Thread): | |
def __init__(self, url): | |
threading.Thread.__init__(self) | |
self.url = url | |
def run(self): | |
try: | |
k = random.randint(10, 20) | |
print "fetch page: %s, waiting for: %ds" % (self.url, k) | |
time.sleep(k) | |
print "page %s done" % self.url | |
finally: | |
sema.release() | |
class Crawler(threading.Thread): | |
def __init__(self, hosts): | |
threading.Thread.__init__(self) | |
self.hosts = hosts | |
def run(self): | |
for url in self.hosts: | |
sema.acquire() | |
g = Grab(url) | |
g.start() | |
print "Starting Crawling ..." | |
hosts = ['www.google.com', 'www.baidu.com', 'www.163.com', 'www.sina.com.cn', 'www.sohu.com', 'www.tencent.com'] | |
c = Crawler(hosts) | |
c.start() | |
c.join() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment