problem withscrapy.response.follow () in python-CodePudding

I´m new in scrapy and I have a little problem. Here is my code:

import scrapy


class SubcategoriasSpider(scrapy.Spider):
    name = 'subCategorias'
    start_urls = ['https://donvino.com.ar/categoria-producto/bodegas']

    def parse(self, response):
        bodegas = response.css('ul.menu#menu-bodegas li')
        for bodega in bodegas:
            url = bodega.css("a::attr(href)").get()
            #name_bodega = bodega.css('a::text').get() 
            yield response.follow(url,callback=self.parse_items)

    def parse_items(self,response):
        vinos = response.css('a.woocommerce-LoopProduct-link.woocommerce-loop-product__link')#no se puede dejar espacio vacío entre palabras, hay que poner un punto
        
        for vino in vinos:      

            yield {
              
                'nombre' : vino.css('h2::text').get(),
                'precio' : str(vino.css('span.woocommerce-Price-amount.amount::text').get()).replace(",", "")

            }

I need to add name_bodega = bodega.css('a::text').get() in def parse_items()...something like this:

yield {
                'name_bodega' :  ............
                'nombre' : vino.css('h2::text').get(),
                'precio' : str(vino.css('span.woocommerce-Price-amount.amount::text').get()).replace(",", "")

            }

the problem is that name_bodega is not in vino...so...I don´t know how to solve it...is there any way to add the name bodega ??. Thanks in advance!!!.

CodePudding user response：

You can use meta to pass item between callback function

class SubcategoriasSpider(scrapy.Spider):
    name = 'subCategorias'
    start_urls = ['https://donvino.com.ar/categoria-producto/bodegas']

    def parse(self, response):
        bodegas = response.css('ul.menu#menu-bodegas li')
        for bodega in bodegas:
            url = bodega.css("a::attr(href)").get()
            name_bodega = bodega.css('a::text').get() 
            yield response.follow(url,callback=self.parse_items,meta={'item':{"name_bodegae": name_bodega}})

    def parse_items(self,response):
        vinos = response.css('a.woocommerce-LoopProduct-link.woocommerce-loop-product__link')#no se puede dejar espacio vacío entre palabras, hay que poner un punto
        
        for vino in vinos:      

            yield {
                'name_bodega':response.meta.get("item")['name_bodegae'], # or -> response.meta.get("item")["name_bodegae"]
                'nombre' : vino.css('h2::text').get(),
                'precio' : str(vino.css('span.woocommerce-Price-amount.amount::text').get()).replace(",", "")

            }

see detaisls here scrapy: understanding how do items and requests work between callbacks