python爬虫框架scrapy下载中间件的编写方法_python

def process_request(self, request, spider):
return None

def process_response(self, request, response, spider):
return response

def process_exception(self, request, exception, spider):
pass

def process_request(self, request, spider):
        # UA伪装,从UA池随机一个
        request.headers['User-Agent'] = random.choice(self.user_agent_list)
        return None

 def process_response(self, request, response, spider):
        # 浏览器对象
        bro = spider.bro
        # 参数spider是爬虫对象
        # 挑选出指定响应对象进行篡改url->request->response
        bro.get(request.url)
        page_text = bro.page_source  # 包含了动态加载的数据
        # 针对定位到的response篡改
        # 实例化新的响应对象（包含动态加载的数据）
        response = HtmlResponse(url=bro.current_url, body=page_text, encoding='utf-8', request=request)
        return response

import scrapy
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver import ChromeOptions

class XxxSpider(scrapy.Spider):
    name = 'xxx'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['……']
    def __init__(self):
        service = Service('/Users/soutsukyou/PyCharm_Workspace/网络爬虫/study_selenium/chromedriver')
        chrome_options = ChromeOptions()
        # 规避检测
        chrome_options.add_experimental_option('excludeSwitches', ['enable-automation'])
        # 实例化浏览器
        self.bro = webdriver.Chrome(service=service, options=chrome_options)

 def process_exception(self, request, exception, spider):
        # 可以设置代理ip
        if request.url.split(':')[0] == 'http':
            request.meta['proxy'] = 'http://'+random.choice(self.PROXY_http)
        if request.url.split(':')[0] == 'https':
            request.meta['proxy'] = 'https://'+random.choice(self.PROXY_https)
        # 重新请求发送
        return request

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   'xxx.middlewares.XxxDownloaderMiddleware': 543,
}