scrapy 中间件

就是发送请求的时候，会经过，中间件。中间件会处理，你的请求

下面是代码：

# Define here the models for your spider middleware
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter
class MidSpiderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.
    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s
    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.
        # Should return None or raise an exception.
        return None
    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.
        # Must return an iterable of Request, or item objects.
        for i in result:
            yield i
    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.
        # Should return either None or an iterable of Request or item objects.
        pass
    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.
        # Must return only requests (not items).
        for r in start_requests:
            yield r
    def spider_opened(self, spider):
        spider.logger.info("Spider opened: %s" % spider.name)
class MidDownloaderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.
    @classmethod
    def from_crawler(cls, crawler):
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        crawler.signals.connect(s.spider_over, signal=signals.spider_closed)
        return s
    def process_request(self, request, spider):
        print("我发发送请求了")
        return None
    def process_response(self, request, response, spider):
        print("我回来了")
        return response
    def process_exception(self, request, exception, spider):
        pass
    def spider_opened(self, spider):
        print("我开始了")
    def spider_over(self, spider):
        print("我结束了")