python - 每页只抓取两个结果

Question

首先非常感谢您的帮助！

我不知道为什么我每页只获得两个结果。请你帮助我好吗？这是代码：

# -*- coding: utf-8 -*-
import scrapy
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from mercado.items import MercadoItem


class MercadoSpider(CrawlSpider):
    name = 'mercado'
    item_count = 0
    allowed_domain = ['https://www.amazon.es']
    start_urls = ['https://www.amazon.es/s/ref=sr_pg_2rh=n%3A1951051031%2Cn%3A2424922031%2Ck%3Afe bi&page=1&keywords=febi&ie=UTF8&qid=1 535314254']

rules = {

    Rule(LinkExtractor(allow =(), restrict_xpaths = ('//*[h2]')),
                    callback = 'parse_item', follow = False)
}

def start_requests(self):
    yield scrapy.Request("https://www.amazon.es/s/ref=sr_pg_2?rh=n%3A1951051031%2Cn%3A2424922031%2Ck%3Afebi&page=1&keywords=febi&ie=UTF8&qid=1535314254",self.parse_item)

    for i in range(2,400):
        yield scrapy.Request("https://www.amazon.es/s/ref=sr_pg_2?rh=n%3A1951051031%2Cn%3A2424922031%2Ck%3Afebi&page="+str(i)+"&keywords=febi&ie=UTF8&qid=1535314254",self.parse_item)


def parse_item(self, response):

    for mercado in response.xpath('//*[h2]'):
        ml_item = MercadoItem()

        ml_item['articulo'] = response.xpath("@title").extract()[0]
        ml_item['precio'] = response.xpath("@href").extract()[0]

        yield ml_item        

标签： pythonscrapyweb-crawlerscrapy-spider

Answer 1

您需要相对于您的mercado元素进行搜索：

def parse_item(self, response):

    for mercado in response.xpath('//*[h2]'):
        ml_item = MercadoItem()

        ml_item['articulo'] = mercado.xpath("@title").extract()[0]
        ml_item['precio'] = mercado.xpath("@href").extract()[0]

        yield ml_item