中间件

代码

# Define here the models for your spider middleware
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
import random

from scrapy import signals

# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter


class MiddleproSpiderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider 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

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, or item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Request or item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info("Spider opened: %s" % spider.name)


class MiddleproDownloaderMiddleware:
    #UA池
    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"
    ]
    # 代理池
    PROXY_http = [
        '153.180.102.104:80',
        '195.208.131.189:56055',
    ]
    PROXY_https = [
        '120.83.49.90:9000',
        '95.189.112.214:35508',
    ]
    # 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.
    # 拦截请求
    def process_request(self, request, spider):
        #UA伪装
        request.headers['User-Agent'] = random.choice(self.user_agent_list)

        #为了验证代理的操作是否生效
        request.meta['proxy'] = 'http://39.108.254.31:80'
        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
    def process_exception(self, request, exception, spider):
        if request.url.split(':')[0] == 'http':
            # 代理
            request.meta['proxy'] = 'http://'+random.choice(self.PROXY_http)
        else:
            request.meta['proxy'] = 'https://'+random.choice(self.PROXY_https)
        return request  #将修正之后的请求对象进行重新的请求发送

import scrapy


class MiddleSpider(scrapy.Spider):
    name = "middle"
    allowed_domains = ["www.xxx.com"]
    start_urls = ["https://www.baidu.com/s?ie=UTF-8&wd=%E7%AB%99%E9%95%BF%E7%B4%A0%E6%9D%90"]

    def parse(self, response):
        page_text = response.text
        with open('baidu.html', 'w', encoding='utf-8') as fp:
            fp.write(page_text)

笔记

中间件：
    - 下载中间件：处于引擎和下载器之间
        - 作用：批量拦截到整个工程中所有的请求和响应
        - 拦截请求：
            - UA伪装
            - 代理IP
        - 拦截响应：
            - 篡改响应数据，响应对象

    - 爬虫中间件：处于引擎和爬虫之间

在settings文件中开启下载中间件