问Scrapy Spider

EN

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


class MercadoSpider(CrawlSpider):
    name = 'mercado'
    item_count = 0
    allowed_domain = ['www.amazon.es']
    start_urls = ['https://www.amazon.es/s/ref=sr_st_price-asc-rank?keywords=febi+bilstein&rh=i%3Aaps%2Ck%3Afebi+bilstein&__mk_es_ES=%C3%85M%C3%85Z%C3%95%C3%91&qid=1521977786&sort=price-asc-rank']

    rules = {

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


    def parse_item(self, response):
        ml_item = MercadoItem()

        #info de producto
        ml_item['articulo'] = response.xpath('//*[@id="result_0"]/div/div/div/div[2]/div[1]/div[1]/a/h2').extract()
        ml_item['precio'] = response.xpath('//*[@id="result_0"]/div/div/div/div[2]/div[2]/div[1]/div[1]/a/span[2]').extract()
        self.item_count += 1
        if self.item_count > 10:
            raise CloseSpider('item_exceeded')
        yield ml_item