我目前的代码面临以下问题,以使其正常运行。我只是连接了URL,但无法正常工作:
当前相对路径(这是我通过常规response.xpath爬取得到的):
/imagename.jpg
这是我当前的代码:
class MercadoSpider(CrawlSpider):
name = 'extractor'
item_count = 0
rules = {
# Para cada item
Rule(LinkExtractor(allow = (), restrict_xpaths = ('//*[@id="main-container"]/div/div[2]/div[1]/ul/li[7]/a'))),
Rule(LinkExtractor(allow =(), restrict_xpaths = ('//*[@id="main-container"]/div/div[2]/div[2]/div/div/div/h4/a')),
callback = 'parse_item', follow = False)
}
def parse_item(self, response):
ml_item = MercadoItem()
ml_item['titulo'] = response.xpath('normalize-space(//*[@id="main-container"]/div/div[2]/div[1]/div[2]/h2)').extract_first()
ml_item['sku'] = response.xpath('normalize-space(//*[@id="main-container"]/div/div[2]/div[1]/div[2]/ul/li[2]/a)').extract()
ml_item['marca'] = response.xpath('normalize-space(//*[@id="main-container"]/div/div[2]/div[1]/div[2]/ul/li[1]/a)').extract()
ml_item['tecnologia'] = response.xpath('normalize-space(//*[@id="DetailedSpecs"]/table/tbody/tr[4]/td)').extract_first()
ml_item['tipo'] = response.xpath('normalize-space(//*[@id="DetailedSpecs"]/table/tbody/tr[3]/td)').extract()
ml_item['precio'] = response.xpath('normalize-space(//*[@id="main-container"]/div/div[2]/div[1]/div[2]/div[1]/span[2])').extract()
ml_item['color'] = response.xpath('normalize-space(//*[@id="mainC"]/div/div/div/div/ul/li/b)').extract()
ml_item['potencia'] = response.xpath('normalize-space(//*[@id="ProductReview"]/div/div/div/dl/dd/strong)').extract()
ml_item['condicion'] = response.xpath('normalize-space(//*[@class="stock in-stock"])').extract_first()
ml_item['desc_corta'] = response.xpath('normalize-space(//*[@id="tab-additional_information"])').extract()
ml_item['descripcion'] = response.xpath('normalize-space(//*[@id="main-container"]/div/div[2]/div[2]/div)').extract()
ml_item['id_publicacion'] = response.xpath('normalize-space(//*[@id="mainC"]/div/div/div[11]/div[1]/ul/li[1]/b)').extract()
#imagenes del producto
xpath1 = 'http://www.website.com.ar'
xpath2 = response.xpath('//*[@id="main-container"]/div/div[2]/div[1]/div[1]/p/img/@src').extract_first()
ml_item['image_urls'] = xpath1 + xpath2
ml_item['image_name'] = response.xpath('//*[@id="main-container"]/div/div[2]/div[1]/div[1]/p/img/@src').extract()
#info de la tienda o vendedor
ml_item['categoria'] = response.xpath('normalize-space(//*[@class="woocommerce-breadcrumb breadcrumbs"])').extract_first()
self.item_count += 1
if self.item_count > 10000:
raise CloseSpider('item_exceeded')
yield ml_item