Python で Beanstalkd を使用して非同期タスク処理を行う方法

from xxxxx.job_queue import JobQueue

queue = JobQueue()

@queue.task('task_tube_one')
def task_one(arg1, arg2, arg3):
 # do task

task_one.put(arg1="a", arg2="b", arg3="c")

class Subscriber(object):
 FUN_MAP = defaultdict(dict)

 def __init__(self, func, tube):
  logger.info('register func:{} to tube:{}.'.format(func.__name__, tube))
  Subscriber.FUN_MAP[tube][func.__name__] = func

class JobQueue(object):
 @classmethod
 def task(cls, tube):
  def wrapper(func):
   Subscriber(func, tube)
   return Putter(func, tube)

  return wrapper

class Putter(object):
 def __init__(self, func, tube):
  self.func = func
  self.tube = tube

 # 直接调用返回
 def __call__(self, *args, **kwargs):
  return self.func(*args, **kwargs)

 # 推给离线队列
 def put(self, **kwargs):
  args = {
   'func_name': self.func.__name__,
   'tube': self.tube,
   'kwargs': kwargs
  }
  logger.info('put job:{} to queue'.format(args))
  beanstalk = beanstalkc.Connection(host=BEANSTALK_CONFIG['host'], port=BEANSTALK_CONFIG['port'])
  try:
   beanstalk.use(self.tube)
   job_id = beanstalk.put(json.dumps(args))
   return job_id
  finally:
   beanstalk.close()

class Worker(object):
 worker_id = 0

 def __init__(self, tubes):
  self.beanstalk = beanstalkc.Connection(host=BEANSTALK_CONFIG['host'], port=BEANSTALK_CONFIG['port'])
  self.tubes = tubes
  self.reserve_timeout = 20
  self.timeout_limit = 1000
  self.kick_period = 600
  self.signal_shutdown = False
  self.release_delay = 0
  self.age = 0
  self.signal_shutdown = False
  signal.signal(signal.SIGTERM, lambda signum, frame: self.graceful_shutdown())
  Worker.worker_id += 1
  import_module_by_str('pear.web.controllers.controller_crawler')

 def subscribe(self):
  if isinstance(self.tubes, list):
   for tube in self.tubes:
    if tube not in Subscriber.FUN_MAP.keys():
     logger.error('tube:{} not register!'.format(tube))
     continue
    self.beanstalk.watch(tube)
  else:
   if self.tubes not in Subscriber.FUN_MAP.keys():
    logger.error('tube:{} not register!'.format(self.tubes))
    return
   self.beanstalk.watch(self.tubes)

 def run(self):
  self.subscribe()
  while True:
   if self.signal_shutdown:
    break
   if self.signal_shutdown:
    logger.info("graceful shutdown")
    break
   job = self.beanstalk.reserve(timeout=self.reserve_timeout) # 阻塞获取任务，最长等待 timeout
   if not job:
    continue
   try:
    self.on_job(job)
    self.delete_job(job)
   except beanstalkc.CommandFailed as e:
    logger.warning(e, exc_info=1)
   except Exception as e:
    logger.error(e)
    kicks = job.stats()['kicks']
    if kicks < 3:
     self.bury_job(job)
    else:
     message = json.loads(job.body)
     logger.error("Kicks reach max. Delete the job", extra={&#39;body&#39;: message})
     self.delete_job(job)

 @classmethod
 def on_job(cls, job):
  start = time.time()
  msg = json.loads(job.body)
  logger.info(msg)
  tube = msg.get(&#39;tube&#39;)
  func_name = msg.get(&#39;func_name&#39;)
  try:
   func = Subscriber.FUN_MAP[tube][func_name]
   kwargs = msg.get(&#39;kwargs&#39;)
   func(**kwargs)
   logger.info(u&#39;{}-{}&#39;.format(func, kwargs))
  except Exception as e:
   logger.error(e.message, exc_info=True)
  cost = time.time() - start
  logger.info(&#39;{} cost {}s&#39;.format(func_name, cost))

 @classmethod
 def delete_job(cls, job):
  try:
   job.delete()
  except beanstalkc.CommandFailed as e:
   logger.warning(e, exc_info=1)

 @classmethod
 def bury_job(cls, job):
  try:
   job.bury()
  except beanstalkc.CommandFailed as e:
   logger.warning(e, exc_info=1)

 def graceful_shutdown(self):
  self.signal_shutdown = True

import_module_by_str('pear.web.controllers.controller_crawler')

# import_module_by_str 的实现
def import_module_by_str(module_name):
 if isinstance(module_name, unicode):
  module_name = str(module_name)
 __import__(module_name)