MVP Attribute Extractor with test file

Gemfile

@@ -0,0 +1,7 @@
+source 'https://rubygems.org'
+
+# Gems here
+gem 'nokogiri'
+gem 'uri'
+gem 'rspec'
+gem 'json'

Gemfile.lock

@@ -0,0 +1,55 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    diff-lcs (1.6.1)
+    json (2.10.2)
+    nokogiri (1.18.7-aarch64-linux-gnu)
+      racc (~> 1.4)
+    nokogiri (1.18.7-aarch64-linux-musl)
+      racc (~> 1.4)
+    nokogiri (1.18.7-arm-linux-gnu)
+      racc (~> 1.4)
+    nokogiri (1.18.7-arm-linux-musl)
+      racc (~> 1.4)
+    nokogiri (1.18.7-arm64-darwin)
+      racc (~> 1.4)
+    nokogiri (1.18.7-x86_64-darwin)
+      racc (~> 1.4)
+    nokogiri (1.18.7-x86_64-linux-gnu)
+      racc (~> 1.4)
+    nokogiri (1.18.7-x86_64-linux-musl)
+      racc (~> 1.4)
+    racc (1.8.1)
+    rspec (3.13.0)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.3)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.3)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.2)
+    uri (1.0.3)
+
+PLATFORMS
+  aarch64-linux-gnu
+  aarch64-linux-musl
+  arm-linux-gnu
+  arm-linux-musl
+  arm64-darwin
+  x86_64-darwin
+  x86_64-linux-gnu
+  x86_64-linux-musl
+
+DEPENDENCIES
+  json
+  nokogiri
+  rspec
+  uri
+
+BUNDLED WITH
+   2.5.11

app/attribute_extractor.rb

@@ -0,0 +1,37 @@
+require "nokogiri"
+
+class AttributeExtractor
+
+    def initialize(html_file:)
+      @doc = Nokogiri::HTML(html_file)
+      # find the g-loading tag, 
+      icon_tag = @doc.css('g-loading-icon').first
+      # then go up 1 element to the parent div
+      container_div = icon_tag.parent
+      # Inside that div, an a-href tag. 
+      a_tag = container_div.css('a').first
+      # Get the parent div's class
+      @class_to_search = a_tag.ancestors('div').first['class']  
+    end
+
+
+    def get_artworks_attributes_hash
+      @cards = @doc.css(".#{@class_to_search}")
+      @json_of_cards = []
+      @cards.each do |card|
+        link_tag = card.css('a').first
+        image_tag = card.css('img').first
+        name_tag = link_tag.css('div').first
+        extension_tag = name_tag.css('div').count > 1 ? link_tag.css('div') : nil
+
+        values = {
+          name: "#{name_tag.css('div').first.text.strip.gsub(/\s+/, ' ')}",
+          extentions: extension_tag ? ["#{name_tag.css('div').last.text.strip}"] : nil,
+          link: "#{link_tag['href']}",
+          image: "#{image_tag['src']}",
+        }
+        @json_of_cards << values
+      end
+      @json_of_cards
+    end
+end

spec/attribute_extractor_spec.rb

@@ -0,0 +1,28 @@
+require 'rspec'
+require 'json'
+require_relative '../app/attribute_extractor'
+
+RSpec.describe AttributeExtractor do
+    context "with Van Gogh HTML" do
+        let(:html_file) do
+            File.open(File.expand_path('../../files/van-gogh-paintings.html', __FILE__))
+        end
+        let(:expected_array) do
+            file_path = File.expand_path('../../files/expected-array.json', __FILE__)
+            JSON.parse(File.read(file_path), symbolize_names: true)
+        end
+
+        it "finds the files and intiates the extractor" do
+            expect(html_file).to be_truthy
+            expect(expected_array).to be_truthy
+
+            extractor = AttributeExtractor.new(html_file: html_file)
+            expect(extractor).to be_truthy
+        end
+        it "provides a serialized attributes_hash for cards" do
+            extractor = AttributeExtractor.new(html_file: html_file)
+            json_of_artworks = extractor.get_artworks_attributes_hash
+            expect(json_of_artworks.count).to eq((expected_array.first[1].count))
+        end
+    end
+end