__init__.py 文件源码

def process_response(self, request, response, spider):
        meta = request.meta

        # parse CDX requests and schedule future snapshot requests
        if meta.get('wayback_machine_cdx_request'):
            snapshot_requests = self.build_snapshot_requests(response, meta)

            # treat empty listings as 404s
            if len(snapshot_requests) < 1:
                return Response(meta['wayback_machine_original_request'].url, status=404)

            # schedule all of the snapshots
            for snapshot_request in snapshot_requests:
                self.crawler.engine.schedule(snapshot_request, spider)

            # abort this request
            raise UnhandledIgnoreRequest

        # clean up snapshot responses
        if meta.get('wayback_machine_url'):
            return response.replace(url=meta['wayback_machine_original_request'].url)

        return response