UA池和代理池

先设置settings

DOWNLOADER_MIDDLEWARES = {
   'ippro.middlewares.IpproDownloaderMiddleware': 543,
}

LOG_LEVEL="ERROR"

中间件代码.py

class IpproDownloaderMiddleware(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

    # 拦截请求:request参数就是拦截到的请求
    proxy_http = ['http://209.34.29.9:8181', 'http://209.34.29.9:8181', 'http://209.34.29.9:8181']
    proxy_https = ['https://119.59.84.58:8080', 'https://119.59.84.58:8080', 'https://119.59.84.58:8080']
    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"
    ]

    #重写请求方法
    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
        print('下载中间件', request)
        #判断是 https 还是http
        if request.url.split(':')[0]=='http':
            request.meta['proxy']=random.choice(self.proxy_http)
        else:
            request.meta['proxy']=random.choice(self.proxy_https)
        #处理响应头
        request.headers['User-Agent']=random.choice(self.user_agent_list)

        print(request.headers['User-Agent'])
        return None
    #拦截响应
    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

一.下载中间件

先祭出框架图：

下载中间件（Downloader Middlewares） 位于scrapy引擎和下载器之间的一层组件。

- 作用：

（1）引擎将请求传递给下载器过程中， 下载中间件可以对请求进行一系列处理。比如设置请求的 User-Agent，设置代理等

（2）在下载器完成将Response传递给引擎中，下载中间件可以对响应进行一系列处理。比如进行gzip解压等。

我们主要使用下载中间件处理请求，一般会对请求设置随机的User-Agent ，设置随机的代理。目的在于防止爬取网站的反爬虫策略。

二.UA池：User-Agent池

- 作用：尽可能多的将scrapy工程中的请求伪装成不同类型的浏览器身份。

- 操作流程：

    1.在下载中间件中拦截请求

    2.将拦截到的请求的请求头信息中的UA进行篡改伪装

    3.在配置文件中开启下载中间件

代码展示：

#导包
from scrapy.contrib.downloadermiddleware.useragent import UserAgentMiddleware
import random
#UA池代码的编写（单独给UA池封装一个下载中间件的一个类）
class RandomUserAgent(UserAgentMiddleware):

    def process_request(self, request, spider):
        #从列表中随机抽选出一个ua值
        ua = random.choice(user_agent_list)
        #ua值进行当前拦截到请求的ua的写入操作
        request.headers.setdefault('User-Agent',ua)


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"
]

三.代理池

- 作用：尽可能多的将scrapy工程中的请求的IP设置成不同的。

- 操作流程：

    1.在下载中间件中拦截请求

    2.将拦截到的请求的IP修改成某一代理IP

    3.在配置文件中开启下载中间件

代码展示：

#批量对拦截到的请求进行ip更换
#单独封装下载中间件类
class Proxy(object):
    def process_request(self, request, spider):
        #对拦截到请求的url进行判断（协议头到底是http还是https）
        #request.url返回值：http://www.xxx.com
        h = request.url.split(':')[0]  #请求的协议头
        if h == 'https':
            ip = random.choice(PROXY_https)
            request.meta['proxy'] = 'https://'+ip
        else:
            ip = random.choice(PROXY_http)
            request.meta['proxy'] = 'http://' + ip

#可被选用的代理IP
PROXY_http = [
    '153.180.102.104:80',
    '195.208.131.189:56055',
]
PROXY_https = [
    '120.83.49.90:9000',
    '95.189.112.214:35508',
]