scrapy爬虫之中间件Middleware

设置随机请求头

spider

class MiddlewSpider(scrapy.Spider):
    name = 'middlew'
    allowed_domains = ['exercise.kingname.info']
    start_urls = ['http://exercise.kingname.info/exercise_middleware_ua']
    count = 1

    def parse(self, response):
        print("*"*40)
        print(response.xpath("//body").extract())

        print("*" * 40)
        time.sleep(1)
        self.count +=1
        yield scrapy.Request(url=self.start_urls[0]+"/"+str(self.count),callback=self.parse)

        item ={}
        yield item
        pass

middleware

import random
class UAMiddleware(object):
    def process_request(self,request,spider):
        USER = [
        "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36",
          "Dalvik/1.6.0 (Linux; U; Android 4.2.1; 2013022 MIUI/JHACNBL30.0)",
          "Mozilla/5.0 (Linux; U; Android 4.4.2; zh-cn; HUAWEI MT7-TL00 Build/HuaweiMT7-TL00) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
          "AndroidDownloadManager",
          "Apache-HttpClient/UNAVAILABLE (java 1.4)",
          "Dalvik/1.6.0 (Linux; U; Android 4.3; SM-N7508V Build/JLS36C)",
          "Android50-AndroidPhone-8000-76-0-Statistics-wifi",
          "Dalvik/1.6.0 (Linux; U; Android 4.4.4; MI 3 MIUI/V7.2.1.0.KXCCNDA)",
          "Dalvik/1.6.0 (Linux; U; Android 4.4.2; Lenovo A3800-d Build/LenovoA3800-d)",
          "Lite 1.0 ( http://litesuits.com )",
          "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727)",
          "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 Safari/537.36 SE 2.X MetaSr 1.0",
          "Mozilla/5.0 (Linux; U; Android 4.1.1; zh-cn; HTC T528t Build/JRO03H) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30; 360browser(securitypay,securityinstalled); 360(android,uppayplugin); 360 Aphone Browser (2.0.4)",
        ]
        ua = random.choice(USER)
        request.headers['User-Agent'] = ua

settings
在这里插入图片描述

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值