Last active
March 12, 2023 15:21
-
-
Save ezefranca/a095f090fcf3874b90659ed86d537a31 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://lojaonline.intermarche.pt/26-famoes/produit/recherche?mot=#{query}" | |
document = Nokogiri::HTML(open(url)) | |
search_items = document.css('ul.vignettes_produit > li.vignette_produit_info').map do |tile| | |
title = tile.css('div.vignette_info > p').text().gsub(tile.css('p.js-marque').text(), '').strip() | |
price_str = tile.css('div.vignette_prix > p').text().strip() | |
price, priceKg = price_str.split('€').map { |s| s.strip unless s.nil? } | |
img_url = tile.css('div.vignette_img > img').attr('src')&.value || tile.css('div.vignette_img > img').attr('data-original')&.value | |
brand = tile.css('p.js-marque').text().strip unless tile.css('p.js-marque').nil? | |
next if img_url.nil? || brand.nil? | |
quantity = tile.css('div.vignette_produit_quantite').text().strip() | |
unit = quantity&.split("\n")&.first&.strip() | |
unit = nil if unit&.empty? | |
quantity = quantity&.gsub("\n","")&.gsub(" ","") | |
quantity = nil if quantity&.empty? | |
destiny_url = url | |
supermarket = 'Intermarché' | |
{ | |
title: title, | |
price: price, | |
price_kg: priceKg, | |
img_url: img_url, | |
brand: brand, | |
quantity: quantity, | |
unit: unit, | |
destiny_url: destiny_url, | |
supermarket: supermarket | |
} | |
end.compact | |
{ | |
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