python网络爬虫（第十一章：Scrapy框架实战：爬取网页新闻标题和内容）

综合练习：爬取网易新闻标题和内容

1.spider.py【完成数据的爬取解析】

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

class WangyiSpider(scrapy.Spider):
    name = 'wangyi'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://news.163.com/']
    all_url = []  # 存储2个模块对应的详细页的URL

    #selenium模块
    def __init__(self):

        # options = webdriver.ChromeOptions()
        #
        # # 忽略无用的日志
        # options.add_experimental_option("excludeSwitches", ['enable-automation', 'enable-logging'])
        # self.driver = webdriver.Chrome(chrome_options=options)
        # # self.driver.get(r'https://192.168.1.1')
        # #
        self.driver = webdriver.Chrome(executable_path='./chromedriver.exe')

    #1.首页数据解析
    def parse(self, response):
        li_list = response.xpath('//*[@id="index2016_wrap"]/div[1]/div[2]/div[2]/div[2]/div[2]/div/ul/li')

        num = [3,4]

        for index in num:

            title_url = li_list[index].xpath('./a/@href').extract_first()
            self.all_url.append(title_url)

        #对每一个板块对应的页面进行请求
        for url in self.all_url:
            yield scrapy.Request(url=url,callback=self.parse_url)

    #2.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_url(self,response):


        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('./a/img/@alt').extract_first()

            item = WangyiproItem()
            item['title'] = title
            print('title:',title)
            detail_url = div.xpath('./a/@href').extract_first() or div.xpath('./div/div[1]/h3/a/@href').extract_first()

                # div.xpath('./a/@href' | './div/div[1]/h3/a/@href').extract_first()
            yield scrapy.Request(url=detail_url,callback=self.parse_detail,meta={'item':item})

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

        yield item

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

2.middlewares.py

# 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

# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter
from time import sleep
from scrapy.http import HtmlResponse
class WangyiproDownloaderMiddleware:

    # 该方法拦截2大板块对应的响应对象，进行篡改
    def process_response(self, request, response, spider):  # spider指爬虫文件

        # 获取了在爬虫类中定义的浏览器对象
        driver = spider.driver

        # 挑选出指定的响应对象进行篡改
        if request.url in spider.all_url:

            driver.get(request.url)  # 2个板块对应的url进行请求
            sleep(3)
            page_text = driver.page_source  # 包含了动态加载数据

            # 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
            # new_response = HtmlResponse(url,body,encoding,request)
            # 如何获取动态加载出来的新闻数据
            # 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


    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

3.items.py【明确爬取目标：新闻标题title和内容news】

import scrapy


class WangyiproItem(scrapy.Item):
    # define the fields for your item here like:
    title = scrapy.Field()
    news = scrapy.Field()

4.pipelines.py【存储数据】

class WangyiproPipeline:
    def process_item(self, item, spider):
        # print(item)
        return item

5.settings.py

1:
ITEM_PIPELINES = {
   'wangyiPro.pipelines.WangyiproPipeline': 300,
}
2:
DOWNLOADER_MIDDLEWARES = {
   'wangyiPro.middlewares.WangyiproDownloaderMiddleware': 543,
}
3:
USER_AGENT = 'XXX'  #自己服务器的user_agent

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

LOG_LEVEL = 'ERROR'