需求

爬取网易新闻中的新闻数据（标题和内容）

1.通过网易新闻的首页解析出五大板块对应的详情页的url（没有动态加载）

2.每一个板块对应的新闻标题都是动态加载出来的（动态加载）

3.通过解析出每一条新闻详情页的url获取详情页的页面源码，解析出新闻内容

代码实现

数据解析

需要获取国内、国际，两大板块的详情页地址。它们均存在ul下的li标签

xpath定位：//*[@id="index2016_wrap"]/div[2]/div[2]/div[2]/div[2]/div/ul/li

分别位于第3 和 4 标签列

import scrapy
from wangyiPro.items import WangyiproItem
from selenium import webdriver

class WangyiSpider(scrapy.Spider):
    name = 'wangyi'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://news.163.com/']
    url_list = [] #存储板块对应详情页的url


    #实例化一个浏览器对象
    def __init__(self):
        self.bro = webdriver.Chrome()

    ##解析大板块对应详情页的url
    def parse(self, response):
        list = response.xpath('//*[@id="index2016_wrap"]/div[2]/div[2]/div[2]/div[2]/div/ul/li')
        index_list = [2,3]
        for index in index_list:
            url = list[index].xpath('./a/@href').extract_first()
            self.url_list.append(url)

        for url in self.url_list:
            yield scrapy.Request(url,callback=self.parse_model)

    # 每一个板块对应的新闻标题相关的内容都是动态加载
    def parse_model(self, response):#解析每一个板块页面中对应新闻的标题和新闻详情页的url
        div_list = response.xpath('/html/body/div/div[3]/div[4]/div[1]/div[1]/div/ul/li/div/div')
        for div in div_list:
            title = div.xpath('./div/div/h3/a/text()').extract_first()
            detail_url = div.xpath('./div/div/h3/a/@href').extract_first()

            item = WangyiproItem()
            item['title'] = title
            # 对新闻详情页的url发起请求
            yield scrapy.Request(url=detail_url,callback=self.parse_detail,meta={'item':item})

    # 解析新闻内容
    def parse_detail(self, response):
        content = response.xpath('//div[@id="content"]/div[2]//text()').extract()
        content = ''.join(content)
        item = response.meta['item']
        item['content'] = content

        yield item


    #关闭浏览器
    def closed(self,spider):
        self.bro.quit()

中间件处理

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

from scrapy import signals
from time import sleep

from scrapy.http import HtmlResponse

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


class WangyiproSpiderMiddleware:
    # 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 WangyiproDownloaderMiddleware:
    # 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.

    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
        return None
        
    # 该方法拦截板块对应的响应对象，进行篡改
    def process_response(self, request, response, spider):#spider爬虫对象
        bro = spider.bro  # 获取了在爬虫类中定义的浏览器对象
        # 挑选出指定的响应对象进行篡改
        # 通过url指定request
        # 通过request指定response
        if request.url in spider.url_list:
            bro.get(request.url)  # 五个板块对应的url进行请求
            sleep(3)
            page_text = bro.page_source  # 包含了动态加载的新闻数据

            # response #五大板块对应的响应对象
            # 针对定位到的这些response进行篡改
            # 实例化一个新的响应对象（符合需求：包含动态加载出的新闻数据），替代原来旧的响应对象
            # 如何获取动态加载出的新闻数据？
            # 基于selenium便捷的获取动态加载数据
            new_response = HtmlResponse(url=request.url, body=page_text, encoding='utf-8', request=request)

            return new_response
        else:
            # response #其他请求对应的响应对象
            return response #其他请求对应的响应对象

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

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

配置文件

持久化存储