This code is giving the items for the first page but is not going to the next page. First function calls the second function runs through the products of the first page but after finishing the loop in the first function it should call itself for next page the but its not. A help will be appreciated

    from gc import callbacks
    from subprocess import call
    import scrapy
    from scrapy.spiders import CrawlSpider, Rule
    from scrapy.linkextractors import LinkExtractor
    from lxml import html

    class EbaySpider(scrapy.Spider):
    name = 'ebay'
    allowed_domains = ['ebay.co.uk']
    start_urls = ['https://www.ebay.co.uk/sch/i.html?_dmd=2&_dkr=1&iconV2Request=true&_ssn=jessicasmith2022&store_name=jesssuperstoreenterprise&_sop=10&_oac=1&_ipg=240&_fcid=3&_pgn=1' 
    ]

    for url in start_urls:
        def parse(self, response):
            for link in (response.css('.s-item__info.clearfix > a::attr(href)').getall()):
                yield response.follow(link , callback = self.productlinks)
            next_page = response.xpath('//*[contains(concat( " ", @class, " " ), concat( " ", "icon-link", " " ))]/@href').extract_first()
            if next_page:
                next_page_link = response.urljoin(next_page)
                yield scrapy.Request(url=next_page_link , callback=self.parse)

        def productlinks(self , response):
            yield {
                    'ITEM_Name' : response.xpath('//*[@id="LeftSummaryPanel"]/div[1]/div[1]/div/h1/span/text()').extract_first(),
                    'TIMES_Sold' : response.xpath('//*[@id="mainContent"]/form/div[1]/div[3]/div[2]/div/div[1]/span[2]/span[3]/a/text()').extract_first(), 
                    'ITEM_Price £': response.xpath('//*[(@id = "prcIsum")]/text()').extract_first().replace('£','')
                    }

CodePudding user response：

You get two results for the pagination: the first is the previous page, and the second is the next page. Since you use extract_first() you get the previous page, and it doesn't exists (because you're already in the first page).

Also your code can be improved in a lot of ways. Please read the documentation again, and maybe use an xpath cheat sheet or something.

import scrapy


class EbaySpider(scrapy.Spider):
    name = 'ebay'
    allowed_domains = ['ebay.co.uk']
    start_urls = ['https://www.ebay.co.uk/sch/i.html?_dmd=2&_dkr=1&iconV2Request=true&_ssn=jessicasmith2022&store_name=jesssuperstoreenterprise&_sop=10&_oac=1&_ipg=240&_fcid=3&_pgn=1']

    custom_settings = {'DOWNLOAD_DELAY': 0.5}

    def parse(self, response):
        for link in (response.css('.s-item__info.clearfix > a::attr(href)').getall()):
            yield response.follow(link, callback=self.productlinks)

        next_page = response.xpath('//a[contains(@class, "pagination__next")]/@href').get()
        if next_page:
            next_page_link = response.urljoin(next_page)
            yield scrapy.Request(url=next_page_link, callback=self.parse)

    def productlinks(self, response):
        yield {
            'ITEM_Name': response.xpath('//h1//span//text()').get(),
            'TIMES_Sold': response.xpath('//div[contains(@class, "quantity")]//a/text()').get(default='Unknown'),
            'ITEM_Price £': response.xpath('//span[@id="prcIsum"]/text()').get(default='').replace('£', '')
        }