def _download(self, slot, request, spider):
# The order is very important for the following deferreds. Do not change!
# 1. Create the download deferred
dfd = mustbe_deferred(self.handlers.download_request, request, spider)
# 2. Notify response_downloaded listeners about the recent download
# before querying queue for next request
def _downloaded(response):
self.signals.send_catch_log(signal=signals.response_downloaded,
response=response,
request=request,
spider=spider)
return response
dfd.addCallback(_downloaded)
# 3. After response arrives, remove the request from transferring
# state to free up the transferring slot so it can be used by the
# following requests (perhaps those which came from the downloader
# middleware itself)
slot.transferring.add(request)
def finish_transferring(_):
slot.transferring.remove(request)
self._process_queue(spider, slot)
return _
return dfd.addBoth(finish_transferring)
def download(self, download_func, request, spider):
def process_request(request):
for method in self.methods['process_request']:
response = method(request=request, spider=spider)
assert response is None or isinstance(response, (Response, Request)), \
'Middleware %s.process_request must return None, Response or Request, got %s' % \
(method.im_self.__class__.__name__, response.__class__.__name__)
if response:
return response
return download_func(request=request, spider=spider)
def process_response(response):
assert response is not None, 'Received None in process_response'
if isinstance(response, Request):
return response
for method in self.methods['process_response']:
response = method(request=request, response=response, spider=spider)
assert isinstance(response, (Response, Request)), \
'Middleware %s.process_response must return Response or Request, got %s' % \
(method.im_self.__class__.__name__, type(response))
if isinstance(response, Request):
return response
return response
def process_exception(_failure):
exception = _failure.value
for method in self.methods['process_exception']:
response = method(request=request, exception=exception, spider=spider)
assert response is None or isinstance(response, (Response, Request)), \
'Middleware %s.process_exception must return None, Response or Request, got %s' % \
(method.im_self.__class__.__name__, type(response))
if response:
return response
return _failure
deferred = mustbe_deferred(process_request, request)
deferred.addErrback(process_exception)
deferred.addCallback(process_response)
return deferred