def crawl(self, async_mode, url, timeout, request_header, robotstxt_enabled, meta):
success, result = Downloader.preprocess(url, robotstxt_enabled)
if not success:
if async_mode:
result = defer_fail(result)
else:
if async_mode:
result = self._crawl_async(url, timeout, request_header, meta)
else:
result = self._crawl_sync(url, timeout, request_header, meta)
return misc.postprocess(async_mode, result, Downloader.postprocess)
def call_spider(self, result: Union[Response, Failure], request: Request, spider: Spider) -> Deferred:
if isinstance(result, Response):
if getattr(result, "request", None) is None:
result.request = request
callback = result.request.callback or spider._parse
warn_on_generator_with_return_value(spider, callback)
dfd = defer_succeed(result)
dfd.addCallbacks(callback=callback, callbackKeywords=result.request.cb_kwargs)
else: # result is a Failure
result.request = request
warn_on_generator_with_return_value(spider, request.errback)
dfd = defer_fail(result)
dfd.addErrback(request.errback)
return dfd.addCallback(iterate_spider_output)
def call_spider(self, result, request, spider):
if isinstance(result, Response): #从spider中拿到的事Response对象
if getattr(result, "request", None) is None:
result.request = request
callback = result.request.callback or spider._parse # 从request对象里面拿到 对应的callback 否则传入spider的_parse函数作为callback
warn_on_generator_with_return_value(spider, callback)
dfd = defer_succeed(result)
dfd.addCallback(callback, **result.request.cb_kwargs
) # 将spider的callback 添加到 deferred的回调链路上
else: # result is a Failure
result.request = request
warn_on_generator_with_return_value(spider, request.errback)
dfd = defer_fail(result)
dfd.addErrback(request.errback)
return dfd.addCallback(iterate_spider_output)
