python线程小学习
以前我写多线程程序时候,经常把一个线程类单独封装,然后使用全局锁来控制竞争资源的处理。今天看了这样一段代码
class Fetcher:
def __init__(self,threads):
self.opener = urllib2.build_opener(urllib2.HTTPHandler)
self.lock = Lock() #线程锁
self.q_req = Queue() #任务队列
self.q_ans = Queue() #完成队列
self.threads = threads
for i in range(threads):
t = Thread(target=self.threadget)
t.setDaemon(True)
t.start()
self.running = 0
def __del__(self): #解构时需等待两个队列完成
time.sleep(0.5)
self.q_req.join()
self.q_ans.join()
def taskleft(self):
return self.q_req.qsize()+self.q_ans.qsize()+self.running
def push(self,req):
self.q_req.put(req)
def pop(self):
return self.q_ans.get()
def threadget(self):
while True:
req = self.q_req.get()
with self.lock: #要保证该操作的原子性,进入critical area
self.running += 1
try:
ans = self.opener.open(req).read()
except Exception, what:
ans = ''
print what
self.q_ans.put((req,ans))
with self.lock:
self.running -= 1
self.q_req.task_done()
time.sleep(0.1) # don't spam
原文链接: http://www.pythonclub.org/python-network-application/observer-spider
从上面文章收获了不少。
把一个类作为一个线程池,进而从内部控制加锁或者释放锁,这样代码更加清晰。