1.爬虫文件

import scrapy
from ..items import NewsdataItem
from urllib import parse


class NewsSpider(scrapy.Spider):
    name = 'news'
    allowed_domains = ['www.lunwenchina.cn']
    start_urls = ['http://www.lunwenchina.cn/html/11/category-catid-11.html']

    def parse(self, response):
        print(response.text)
        print("#########################3")
        total = response.xpath('//ul[@class="global_tx_list4"]/li')
        # print(total)
        for b in total:
            item = NewsdataItem()
            title = b.xpath('./a/text()').extract()
            lianjie = b.xpath('./a/@href').extract()
            date=b.xpath('./span/text()').extract()
            print("*********************")
            # print(lianjie)
            title =str(title)
            lianjie=str(lianjie)
            date=str(date)
            item['title'] = title
            item['lianjie'] = lianjie
            item['date']=date
            print("+++++++++++++++++++++")

            yield item

            # next_page_url=response.xpath('//a[class="next"]/@href').extract()
            # print("::::::::::::::::::::")
            # print(next_page_url)
            # print("?????????????????")
            # if next_page_url:
            #     yield scrapy.Request(url=response.urljoin(next_page_url),callback=self.parse)
            #     print("%%%%%%%%%%%%%%%%%%%%%%%%55")
            for i in range(2, 8):  # 爬取第2，3页的数据
                url = "http://www.lunwenchina.cn/html/11/category-catid-11-page-" + str(i)+".html"
                print(url)
                yield scrapy.Request(url,meta={'item':item},callback=self.parse)
                print("????????///////////////////////////")

        多页爬取就是观察列表页url规则，写url，再yield，注意，这里meta={'item':item}一定要有，否则代码不报错，但存入数据库只有一页的数据。

        写爬虫文件时多输出如print("++++++")等符号，有助于观察你的代码在哪出问题，哪一步停止了。

2.管道文件

import pymongo
class NewsdataPipeline(object):
    def process_item(self, item, spider):
        coon=pymongo.MongoClient('localhost',27017)
        db=coon.xxxxx    #xxxx代表数据库名
        table=db.yyyy         #yyyy代表集合名，表名
        table.insert_one(dict(item))
        return item

3.setting.py

需要改动的代码

DEFAULT_REQUEST_HEADERS = {
  'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
  'Accept-Language': 'en',
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36',
}

ITEM_PIPELINES = {
   'Newsdata.pipelines.NewsdataPipeline': 300,
     'Newsdata.pipelines.MongodbPipeline':400,
}

ROBOTSTXT_OBEY =False