在 Scrapy 中更改 request.url 以抓取 json 文件然后 return 到原始请求

Question

我正在从 url（产品名称、价格等）中抓取数据，但后端有一个 json 文件，我也想抓取该文件，因为它包含相关信息。简而言之，我想将我的请求 url 更改为 json，然后将 return 更改为原始的 url，以便继续抓取。

产品url:https://www2.hm.com/hu_hu/productpage.0906822002.html
相关 json url（可以在“网络”选项卡中找到，我将其存储在名为 availability_url 的变量中）： https://www2.hm.com/hmwebservices/service/product/hu/availability/0906822.json

在实际产量之前将可用性数据保存在变量中非常重要，因为在检查代码末尾的颜色之前，我必须 return 到原始 url：

import scrapy
import re

class HMSpider(scrapy.Spider):
    name = 'hm'
    
    start_urls= ['https://www2.hm.com/hu_hu/learazas/noi/dresses.html']
    custom_settings = {'FEED_EXPORT_ENCODING': 'utf-8'}

    def parse(self, response):
        
        items = response.css('h3.item-heading  a::attr(href)').getall()
        for item in items:
            link = 'https://www2.hm.com' + item
            yield scrapy.Request(link, self.parse_item)


    def parse_item(self, response, request):
        page_source_data = response.xpath('//div[@class= "tealiumProductviewtag productview parbase"]//text()')[0].get()
        data = response.css('div.product.parbase script::text').get()
        base_product_code = re.findall("ancestorProductCode = '(.*)';",data)[0]
        detailed_product_code = re.findall("articleCode':'(.*)', 'baseProductCode",data)[0]
        current_price = int(re.findall(r'\d+',re.findall('product_list_price :  \["(.*?)\],', page_source_data)[0])[0])
        original_price = int(re.findall(r'\d+',re.findall('product_original_price : \[(.*?)\],', page_source_data)[0])[0])
        availability_url = 'https://www2.hm.com/hmwebservices/service/product/hu/availability/' + base_product_code +".json"
        info_url = "https://tags.tiqcdn.com/dle/hm/hdl/" + detailed_product_code +".json"

        if current_price != original_price:
            yield{
            'product_name': re.findall('(?<=  ).*$',response.css('section.name-price h1.primary.product-item-headline::text').get())[0],
            'vendor': 'H&M',
            'current_price': int(current_price),
            'original_price': int(original_price),
            'discount_percent': 100-round((current_price / original_price)*100),
            'colors': response.css('li.list-item a::attr(title)').getall(),
            'link': response.request.url,
            #rating
            #reviews
            }
            color_count = len(response.css('div.mini-slider li.list-item a::attr(href)').getall()) 
            if color_count > 1:
                additonal_colors = response.css('div.mini-slider li.list-item a::attr(href)').getall()
                color_index = 1
                for color in additonal_colors:
                    if color_index <= color_count:
                        link = 'https://www2.hm.com' + color
                        yield scrapy.Request(link, self.parse_item)
                        color_index += 1

所以总结一下：我想把刮掉的 url 从 https://www2.hm.com/hu_hu/productpage.0906822002.html 至 https://www2.hm.com/hmwebservices/service/product/hu/availability/0906822.json 然后 return 回到 https://www2.hm.com/hu_hu/productpage.0906822002.html 这样我的抓取工具就可以继续工作了。

Answer 1

您可以这样做，如果您在提取所有项目数据后执行 json 请求，则不必 return 到函数。（仍然会创建颜色变化请求，因为我们正在生成请求并且什么都没有 returning）试试这是否适合你：

import json
import scrapy
import re

class HMSpider(scrapy.Spider):
    name = 'hm'
    
    start_urls= ['https://www2.hm.com/hu_hu/learazas/noi/dresses.html']
    custom_settings = {'FEED_EXPORT_ENCODING': 'utf-8'}

    def parse(self, response):
        
        items = response.css('h3.item-heading  a::attr(href)').getall()
        for item in items:
            link = 'https://www2.hm.com' + item
            yield scrapy.Request(link, self.parse_item)


    def parse_item(self, response, request):
        page_source_data = response.xpath('//div[@class= "tealiumProductviewtag productview parbase"]//text()')[0].get()
        data = response.css('div.product.parbase script::text').get()
        base_product_code = re.findall("ancestorProductCode = '(.*)';",data)[0]
        detailed_product_code = re.findall("articleCode':'(.*)', 'baseProductCode",data)[0]
        current_price = int(re.findall(r'\d+',re.findall('product_list_price :  \["(.*?)\],', page_source_data)[0])[0])
        original_price = int(re.findall(r'\d+',re.findall('product_original_price : \[(.*?)\],', page_source_data)[0])[0])
        availability_url = 'https://www2.hm.com/hmwebservices/service/product/hu/availability/' + base_product_code +".json"
        info_url = "https://tags.tiqcdn.com/dle/hm/hdl/" + detailed_product_code +".json"

        if current_price != original_price:
            item = {
                'product_name': re.findall('(?<=  ).*$',response.css('section.name-price h1.primary.product-item-headline::text').get())[0],
                'vendor': 'H&M',
                'current_price': int(current_price),
                'original_price': int(original_price),
                'discount_percent': 100-round((current_price / original_price)*100),
                'colors': response.css('li.list-item a::attr(title)').getall(),
                'link': response.request.url,
                #rating
                #reviews
            }

            if availability_url:
                yield scrapy.Request(
                    url=availability_url,
                    callback=self.parse_availability,
                    meta={
                        'item': item
                    }
                )

            color_count = len(response.css('div.mini-slider li.list-item a::attr(href)').getall()) 
            if color_count > 1:
                additonal_colors = response.css('div.mini-slider li.list-item a::attr(href)').getall()
                color_index = 1
                for color in additonal_colors:
                    if color_index <= color_count:
                        link = 'https://www2.hm.com' + color
                        yield scrapy.Request(link, self.parse_item)
                        color_index += 1
        
    def parse_availability(self, response):
        item = response.meta.get('item')
        json_data = json.loads(response.body)
        #do something with json data here and add it to item
        yield item

在 Scrapy 中更改 request.url 以抓取 json 文件然后 return 到原始请求

Change request.url in Scrapy to crawl a json file then return to the original request

python

json

scrapy