Created
March 12, 2023 15:34
-
-
Save ezefranca/793ab0d1ecf6d0aa06187a0ea47f9fd0 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'nokogiri' | |
require 'open-uri' | |
Encoding.default_external = 'UTF-8' | |
query = params['query'] || 'banana' | |
page = (params['page'] || 0).to_i | |
url = "https://www.auchan.pt/pt/pesquisa?q=#{query}&search-button=&lang=pt_PT&start=#{page * 24}&sz=24" | |
document = Nokogiri::HTML(open(url)) | |
search_items = document.css('div.auc-product').map do |tile| | |
title = tile.css('a.link').text().capitalize | |
product, brand = title.split(' - ') | |
price = tile.css('span.value').text().strip | |
priceKg = tile.css('span.auc-measures--price-per-unit').text().strip.gsub('€/Kg', '') | |
unit = 'xx' | |
img_url = tile.css('img.tile-image').attr('data-src').value | |
brand = brand&.strip == 'Própria' ? 'Auchan' : brand&.strip | |
quantity = tile.css('span.auc-measures--avg-weight').text().strip | |
destiny_url = tile.css('a.auc-product-tile__image-container__image').attr('href').value | |
supermarket = 'Auchan' | |
{ | |
title: title, | |
price: price, | |
price_kg: priceKg.empty? ? nil : priceKg, | |
unit: unit, | |
img_url: img_url, | |
brand: brand, | |
quantity: quantity, | |
destiny_url: "https://www.auchan.pt/pt#{destiny_url}", | |
supermarket: supermarket | |
} | |
end | |
{ | |
query: query, | |
url: url, | |
page: page, | |
total_items: search_items.size, | |
search_items: search_items | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment