Scrapy中间件user-agent和ip代理使用

一、定义实现随机User-Agent的下载中间件

1.在middlewares.py中完善代码

 import random
 from Tencent.settings import USER_AGENTS_LIST # 注意导入路径,请忽视pycharm的错误提示

 class UserAgentMiddleware(object):
     def process_request(self, request, spider):
         user_agent = random.choice(USER_AGENTS_LIST)
         request.headers['User-Agent'] = user_agent
         # 不写return

 class CheckUA:
     def process_response(self,request,response,spider):
         print(request.headers['User-Agent'])
         return response # 不能少！

2.在settings中设置开启自定义的下载中间件，设置方法同管道

 DOWNLOADER_MIDDLEWARES = {
    'Tencent.middlewares.UserAgentMiddleware': 543, # 543是权重值
    'Tencent.middlewares.CheckUA': 600, # 先执行543权重的中间件，再执行600的中间件
 }

3.在settings中添加UA的列表

 USER_AGENTS_LIST = [
     "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
     "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
     "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
     "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
     "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5"
 ]

二、代理ip的使用

1.在middlewares.py中完善代码

 class RandomProxy(object):

     def process_request(self, request, spider):

         proxy = random.choice(PROXY_LIST)
         print(proxy)

         if 'user_passwd' in proxy:
             # 对账号密码进行编码，基础认证,python3中需要是bytes类型的数据才能编码
             b64_up = base64.b64encode(proxy['user_passwd'].encode())

             # 进行代理认证
             request.headers['Proxy-Authorization'] = 'Basic ' + b64_up.decode()

             # 设置代理
             request.meta['proxy'] = proxy['ip_port']
         else:
             #设置代理
             request.meta['proxy'] = proxy['ip_port']

2.检测代理ip是否可用

在使用了代理ip的情况下可以在下载中间件的process_response()方法中处理代理ip的使用情况，如果该代理ip不能使用可以替换其他代理ip

 class ProxyMiddleware(object):
     ......
     def process_response(self, request, response, spider):
         if response.status != '':
             request.dont_filter = True # 重新发送的请求对象能够再次进入队列
             return requst

3.在settings中添加代理ip的列表

 PROXY_LIST = [
     {"ip_port": "139.199.121.163:16818", "user_passwd": "user:password"},#收费代理
     # {"ip_port": "114.234.81.72:9000"} # 免费代理
 ]

三. 在中间件中使用selenium

以github登陆为例

1. 完成爬虫代码

 import scrapy

 class Login4Spider(scrapy.Spider):
     name = 'login4'
     allowed_domains = ['github.com']
     start_urls = ['https://github.com/returnes'] # 直接对验证的url发送请求

     def parse(self, response):
         with open('check.html', 'w') as f:
             f.write(response.body.decode())

2.在middlewares.py中使用selenium获取cookie信息

 import time
 from selenium import webdriver

 def getCookies():
     # 使用selenium模拟登陆，获取并返回cookie
     username = input('输入github账号:')
     password = input('输入github密码:')
     options = webdriver.ChromeOptions()
     options.add_argument('--headless')
     options.add_argument('--disable-gpu')
     driver = webdriver.Chrome('/home/worker/Desktop/driver/chromedriver',
                               chrome_options=options)
     driver.get('https://github.com/login')
     time.sleep(1)
     driver.find_element_by_xpath('//*[@id="login_field"]').send_keys(username)
     time.sleep(1)
     driver.find_element_by_xpath('//*[@id="password"]').send_keys(password)
     time.sleep(1)
     driver.find_element_by_xpath('//*[@id="login"]/form/div[3]/input[3]').click()
     time.sleep(2)
     cookies_dict = {cookie['name']: cookie['value'] for cookie in driver.get_cookies()}
     driver.quit()
     return cookies_dict

 class LoginDownloaderMiddleware(object):

     def process_request(self, request, spider):
         cookies_dict = getCookies()
         print(cookies_dict)
         request.cookies = cookies_dict # 对请求对象的cookies属性进行替换

3.在middlewares.py中使用selenium获取指定页面渲染后的html源码

 class SelMiddleWare(object):

     def process_request(self, request, spider):

         url = request.url
         # 过滤需要渲染的请求对象
         if 'daydata' in url:

             driver = webdriver.Chrome()

             driver.get(url)
             time.sleep(3)

             data = driver.page_source
             driver.close()

             res = HtmlResponse(
                 url=url,
                 body=data,
                 encoding='utf-8',
                 request=request
             )

             return res