UA池代理IP池 scrapy的下载中间件

佚名 6年前 (2019-05-09) 随笔 697人围观抢沙发百度已收录

# 一些概念

简述什么时候使用selenium?及其scrapy应用selenium的编码流程:
    - 导包selenium
    - 实例化浏览器对象(一次)  __in__(self,) 属性  bro
    - 需要编写浏览器自动化的操作(中间件的process_response)
    - 关闭浏览器 spider.py里面  self.bro.quit()

# UA池代理IP池 scrapy的下载中间件

SRE实战互联网时代守护先锋，助力企业售后服务体系运筹帷幄！一键直达领取阿里云限量特价优惠。

# -*- coding: utf-8 -*-
from scrapy import signals
import random
class MiddleproDownloaderMiddleware(object):
    user_agent_list = [
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 "
        "(KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
        "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 "
        "(KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 "
        "(KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 "
        "(KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 "
        "(KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 "
        "(KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
        "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 "
        "(KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "
        "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 "
        "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 "
        "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "
        "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "
        "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "
        "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "
        "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 "
        "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "
        "(KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 "
        "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 "
        "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
    ]
    PROXY_http = [
        '153.180.102.104:80',
        '195.208.131.189:56055',
    ]
    PROXY_https = [
        '120.83.49.90:9000',
        '95.189.112.214:35508',
    ]
    @classmethod
    def from_crawler(cls, crawler):
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    #可以处理拦截到所有的非异常的请求
    #spider参数表示的就是爬虫类实例化的一个对象
    def process_request(self, request, spider):
        print('this is process_request()')
        #UA伪装
        request.headers['User-Agent'] = random.choice(self.user_agent_list)

        #测试：代理操作是否生效
        request.meta['proxy'] = 'https://218.60.8.83:3129'
        return None
    #拦截所有的响应
    def process_response(self, request, response, spider):

        return response
    #拦截发生异常的请求对象
    def process_exception(self, request, exception, spider):
        if request.url.split(':')[0] == 'https':
            request.meta['proxy'] = 'https://'+random.choice(self.PROXY_https)
        else:
            request.meta['proxy'] = 'http://' + random.choice(self.PROXY_http)
        return request
    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)