Merge pull request scrapy#1284 from scrapy/crawler-cleanup

CrawlerProcess cleanup

Author: dangra

scrapy/crawler.py

@@ -216,7 +216,7 @@ def _signal_shutdown(self, signum, _):
         signame = signal_names[signum]
         logger.info("Received %(signame)s, shutting down gracefully. Send again to force ",
                     {'signame': signame})
-        reactor.callFromThread(self.stop)
+        reactor.callFromThread(self._graceful_stop_reactor)
 
     def _signal_kill(self, signum, _):
         install_shutdown_handlers(signal.SIG_IGN)
@@ -242,16 +242,30 @@ def start(self, stop_after_crawl=True):
             # Don't start the reactor if the deferreds are already fired
             if d.called:
                 return
-            d.addBoth(lambda _: self._stop_reactor())
+            d.addBoth(self._stop_reactor)
 
-        cache_size = self.settings.getint('DNSCACHE_SIZE') if self.settings.getbool('DNSCACHE_ENABLED') else 0
-        reactor.installResolver(CachingThreadedResolver(reactor, cache_size,
-                                                            self.settings.getfloat('DNS_TIMEOUT')))
+        reactor.installResolver(self._get_dns_resolver())
         tp = reactor.getThreadPool()
         tp.adjustPoolsize(maxthreads=self.settings.getint('REACTOR_THREADPOOL_MAXSIZE'))
         reactor.addSystemEventTrigger('before', 'shutdown', self.stop)
         reactor.run(installSignalHandlers=False)  # blocking call
 
+    def _get_dns_resolver(self):
+        if self.settings.getbool('DNSCACHE_ENABLED'):
+            cache_size = self.settings.getint('DNSCACHE_SIZE')
+        else:
+            cache_size = 0
+        return CachingThreadedResolver(
+            reactor=reactor,
+            cache_size=cache_size,
+            timeout=self.settings.getfloat('DNS_TIMEOUT')
+        )
+
+    def _graceful_stop_reactor(self):
+        d = self.stop()
+        d.addBoth(self._stop_reactor)
+        return d
+
     def _stop_reactor(self, _=None):
         try:
             reactor.stop()