6-2 middlewares.py

# -*- coding: utf-8 -*-

# Define here the models for your spider middleware
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals
from selenium import webdriver
from time import sleep

from scrapy.http import HtmlResponse

class ToutiaoDownloaderMiddleware(object):
    # 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):
        # 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_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called

        # 创建一个webdriver对象
        opt = webdriver.ChromeOptions()
        opt.add_argument("--headless")
        driver = webdriver.Chrome(options=opt)
        driver.get(request.url)
        sleep(3)
        # 让页面滚动
        js = "var q = document.documentElement.scrollTop=%d"
        distance = 100
        for i in range(100):
            driver.execute_script(js%distance)
            distance += 100
            sleep(0.5)
        body = driver.page_source
        print("正在使用中间件下载...")
        print("当前浏览器正在访问的网址是：",driver.current_url)
        # 响应体需要重新定义
        res = HtmlResponse(url=driver.current_url,body=body,encoding='utf-8',request=request)

        return res

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)