使用分页进行网页抓取不会返回所有结果

Question

我正在尝试抓取 Indeed.com，但遇到了分页问题。 这是我的代码：

import scrapy
class JobsNySpider(scrapy.Spider):
    name = 'jobs_ny'
    allowed_domains = ['www.indeed.com']
    start_urls = ['https://www.indeed.com/jobs?q=analytics&l=New%20York%2C%20NY&vjk=7b2f6385304ffc78']

    def parse(self, response):
        jobs = response.xpath("//td[@id='resultsCol']")
        for job in jobs:
            yield {
                'Job_title': job.xpath(".//td[@class='resultContent']/div/h2/span/text()").get(),
                'Company_name': job.xpath(".//span[@class='companyName']/a/text()").get(),
                'Company_rating': job.xpath(".//span[@class='ratingNumber']/span/text()").get(),
                'Company_location': job.xpath(".//div[@class='companyLocation']/text()").get(),
                'Estimated_salary': job.xpath(".//span[@class='estimated-salary']/span/text()").get()
        }

        next_page = response.urljoin(response.xpath("//a[@aria-label='Next']/@href").get())

        if next_page:
           yield scrapy.Request(url=next_page, callback=self.parse)

问题是，根据 Indeed 的数据，有 28,789 个职位符合我的查询。 但是，当我将抓取的内容保存到 csv 文件时，只有 76 行。 我也试过： next_page = response.urljoin(response.xpath("//ul[@class='pagination-list']/li[position() = last()]/a/@href").get()) 但结果是相似的。 所以我的问题是我在处理分页时做错了什么。

Answer 1

1. 问题不在于分页，而在于您只能从每一页获得一份工作。
2. 最好在 if 语句后加上urljoin，以免出错。

import scrapy


class JobsNySpider(scrapy.Spider):
    name = 'jobs_ny'
    allowed_domains = ['www.indeed.com']
    start_urls = ['https://www.indeed.com/jobs?q=analytics&l=New%20York%2C%20NY&vjk=7b2f6385304ffc78']

    def parse(self, response):
        jobs = response.xpath('//div[@id="mosaic-provider-jobcards"]/a')
        for job in jobs:
            yield {
                'Job_title': job.xpath(".//td[@class='resultContent']/div/h2/span/text()").get(),
                'Company_name': job.xpath(".//span[@class='companyName']/a/text()").get(),
                'Company_rating': job.xpath(".//span[@class='ratingNumber']/span/text()").get(),
                'Company_location': job.xpath(".//div[@class='companyLocation']/text()").get(),
                'Estimated_salary': job.xpath(".//span[@class='estimated-salary']/span/text()").get()
            }

        next_page = response.xpath("//a[@aria-label='Next']/@href").get()

        if next_page:
            next_page = response.urljoin(next_page)
            yield scrapy.Request(url=next_page, callback=self.parse)