Reputation: 10058
I'm trying to add a delay between requests in an asynchronous way. When I use Tornado gen.sleep(x) my function (launch) doesn't get executed. If I remove yield from yield gen.sleep(1.0), function is called, but no delay is added. How to add delay between requests in my for loop? I need to control Request per second to external API. If I use time.sleep the response is delayed after all requests are completed. Tried to add @gen.engine decorator to launch function and no results.
Code:
import collections
import tornado.httpclient
class BacklogClient(object):
MAX_CONCURRENT_REQUESTS = 20
def __init__(self, ioloop):
self.ioloop = ioloop
self.client = tornado.httpclient.AsyncHTTPClient(max_clients=self.MAX_CONCURRENT_REQUESTS)
self.client.configure(None, defaults=dict(connect_timeout=20, request_timeout=30))
self.backlog = collections.deque()
self.concurrent_requests = 0
def __get_callback(self, function):
def wrapped(*args, **kwargs):
self.concurrent_requests -= 1
self.try_run_request()
return function(*args, **kwargs)
return wrapped
def try_run_request(self):
while self.backlog and self.concurrent_requests < self.MAX_CONCURRENT_REQUESTS:
request, callback = self.backlog.popleft()
self.client.fetch(request, callback=callback)
self.concurrent_requests += 1
def fetch(self, request, callback=None):
wrapped = self.__get_callback(callback)
self.backlog.append((request, wrapped))
self.try_run_request()
import time
from tornado import ioloop, httpclient, gen
class TornadoBacklog:
def __init__(self):
self.queue = 0
self.debug = 1
self.toProcess = [
'http://google.com',
'http://yahoo.com',
'http://nytimes.com',
'http://msn.com',
'http://cnn.com',
'http://twitter.com',
'http://facebook.com',
]
def handle_request(self, response):
print response.code
if not self.backlog.backlog and self.backlog.concurrent_requests == 0:
ioloop.IOLoop.instance().stop()
def launch(self):
self.ioloop = ioloop.IOLoop.current()
self.backlog = BacklogClient(self.ioloop)
for item in self.toProcess:
yield gen.sleep(1.0)
print item
self.backlog.fetch(
httpclient.HTTPRequest(
item,
method='GET',
headers=None,
),
self.handle_request
)
self.ioloop.start()
def main():
start_time = time.time()
scraper = TornadoBacklog()
scraper.launch()
elapsed_time = time.time() - start_time
print('Process took %f seconds processed %d items.' % (elapsed_time, len(scraper.toProcess)))
if __name__ == "__main__":
main()
Reference: https://github.com/tornadoweb/tornado/issues/1400
Upvotes: 0
Views: 1864
Reputation: 24007
Tornado coroutines have two components:
Use the "coroutine" decorator on your "launch" function:
@gen.coroutine
def launch(self):
Run a Tornado coroutine from start to finish like this:
tornado.ioloop.IOLoop.current().run_sync(launch)
Remove the call to "ioloop.start" from your "launch" function: the loop runs the "launch" function, not vice-versa.
Upvotes: 1