Mikhail Sinegubov Mifody

Вытаскивание продавца

запрос на https://api.ozon.ru/composer-api.bx/page/json/v1?url=/products/[тут ID продукта]/?layout_container=appPdpPage3&layout_page_index=3
в узле "layout" найти узел с параметром component=seller
из найденного узла взять stateId (например seller-814807-appPdpPage3-3)
в узле pdp найти узел с следующим полным xpath /pdb/seller/seller-814807-appPdpPage3-3 последняя ветка это параметр из предыдущего пункта
найденный узел и будет информацией о продавце

Описание и характеристики товара

curl --location --request POST 'https://kiev.prom.ua/graphql'
--header 'Content-Type: application/json'
--data-raw '[{"variables":{"categoryId":0,"target":"company-listing-page","path":"/c197461-internet-magazin-grand.html"},"extensions":{},"operationName":"PromoPanelQuery","query":"query PromoPanelQuery($categoryId: Intu0021, $target: Stringu0021, $path: Stringu0021) {\n promoPanel(category_id: $categoryId, target: $target, path: $path) {\n isAvailable\n url\n data {\n id\n image\n text\n textColor\n gradientStart\n gradientStop\n url\n urlTarget\n __typename\n }\n __typename\n }\n}\n"},{"variables":{"pageName":"company-listing-page","path":"/c197461-internet-magazin-grand.html"},"extensions":{},"operationName":"ListingBannerQuery","query":"query ListingBannerQuery($currentCategoryId: Int, $pageName: Stringu0021, $path: Stringu0021) {\n listingBanner(category_id: $currentCategoryId, target: $pageName, path: $path) {\n isAvailable\n url\

	(scrapy) developer@ip-172-31-36-21:~/cosmetics_catalogs$ python test.py
	Traceback (most recent call last):
	File "test.py", line 13, in <module>
	asyncio.run(main())
	File "/usr/lib/python3.8/asyncio/runners.py", line 44, in run
	return loop.run_until_complete(main)
	File "/usr/lib/python3.8/asyncio/base_events.py", line 616, in run_until_complete
	return future.result()
	File "test.py", line 7, in main
	browser = await browser_type.launch()

	def process_request(self, request, spider):
	cookiejarkey = request.meta.get('proxy') or request.meta.get("cookiejar")
	proxy = request.meta.get('proxy')
	token = self.tokens.get(cookiejarkey)
	# req = request.copy()
	if token:
	s = ''
	session = requests.Session()
	headers = self.headers
	headers['User-Agent'] = self.ua

	import os
	import logging
	from scrapy.utils.project import get_project_settings
	from scrapy.utils.log import configure_logging
	from notifiers.logging import NotificationHandler
	from os import getenv
	from dotenv import load_dotenv
	from datetime import datetime

	load_dotenv()

	from itemadapter import ItemAdapter
	from shutterstock.db_utils import db_handle, CatalogModel
	from scrapy.pipelines.images import ImagesPipeline
	from scrapy import Request
	import json


	class ShutterstockImagePipeline(ImagesPipeline):
	def get_media_requests(self, item, info):
	url = ItemAdapter(item).get('thumb_url')

	# -- coding: utf-8 --

	# Define your item pipelines here
	#
	# Don't forget to add your pipeline to the ITEM_PIPELINES setting
	# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html

	from rssparser.db_utils import *
	from rssparser.items import *
	import logging