spiders.py 文件源码

def start_requests(self):
        if not self.page_clf and self.settings.get(
                'QUEUE_MAX_RELEVANT_DOMAINS'):
            raise NotConfigured('Pass page_clf to spider')
        for request in super().start_requests():
            request.priority = self.initial_priority
            if self.queue is not None:
                self.queue.push(request)
            else:
                yield request