Muhammad Owais solution # 2 in Ruby

.gitignore

@@ -49,3 +49,13 @@ build-iPhoneSimulator/
 # unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
 .rvmrc
 .DS_Store
+
+
+
+# python virtual lib
+*venv/
+*.venv/
+
+# python cache
+*__pycache__/
+*.pytest_cache

moya_ruby_solution/.rspec

@@ -0,0 +1 @@
+--require spec_helper

moya_ruby_solution/.ruby-version

@@ -0,0 +1 @@
+3.4.1

moya_ruby_solution/Gemfile

@@ -0,0 +1,9 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+# gem "rails"
+gem 'rspec', '~> 3.0'
+gem 'nokogiri'

moya_ruby_solution/Gemfile.lock

@@ -0,0 +1,51 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    diff-lcs (1.6.1)
+    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)
+
+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
+  nokogiri
+  rspec (~> 3.0)
+
+BUNDLED WITH
+   2.6.7

moya_ruby_solution/bin/rspec

@@ -0,0 +1,27 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+#
+# This file was generated by Bundler.
+#
+# The application 'rspec' is installed as part of a gem, and
+# this file is here to facilitate running it.
+#
+
+ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../Gemfile", __dir__)
+
+bundle_binstub = File.expand_path("bundle", __dir__)
+
+if File.file?(bundle_binstub)
+  if File.read(bundle_binstub, 300).include?("This file was generated by Bundler")
+    load(bundle_binstub)
+  else
+    abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
+Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
+  end
+end
+
+require "rubygems"
+require "bundler/setup"
+
+load Gem.bin_path("rspec-core", "rspec")

moya_ruby_solution/lib/parser.rb

@@ -0,0 +1,77 @@
+# Google Artwork parser solution for serp api code challenge
+# Author: Muhammad Owais
+# Date: 10-April-2025
+
+
+require 'nokogiri'
+
+class GoogleArtworksParser
+
+  def initialize(html_content=nil)
+    @google_host = "https://www.google.com"
+    @doc = Nokogiri::HTML(html_content)
+  end
+
+  def parse
+    { artworks: extract_all_artworks}
+  end
+
+  def extract_all_artworks
+    # iterate over all artworks div containers and extract title, link, extensions and image
+    @doc.css('div.iELo6').map do |artwork_div|
+      {
+        name: extract_artwork_name(artwork_div),
+        link: extract_artwork_link(artwork_div),
+        extensions: extract_artwork_extensions(artwork_div),
+        image: extract_artwork_image(artwork_div)
+      }
+    end
+  end
+
+  def extract_artwork_name(artwork_div)
+    name_div = artwork_div.at_css('div.pgNMRc')
+    name_div.text
+  end
+
+  def extract_artwork_link(artwork_div)
+    link = artwork_div.at_css('a')&.[]('href')
+    return nil unless link
+    link.start_with?(@google_host) ? link : "#{@google_host}#{link}"
+  end
+
+  def extract_artwork_extensions(artwork_div)
+    extensions_div = artwork_div.at_css('div.cxzHyb')
+    [extensions_div.text]
+  end
+
+  def extract_artwork_image(artwork_div)
+    attr_data_src_value = artwork_div.at_css('img.taFZJe')&.[]('data-src')
+    attr_id_value = artwork_div.at_css('img.taFZJe')&.[]('id')
+    return attr_data_src_value unless attr_id_value
+    extract_img_base64_str(attr_id_value)
+  end
+
+  def extract_img_base64_str(attr_id_value)
+    @doc.css('script').each do |script|
+      content = script.text
+      next unless content.include?(attr_id_value)
+      if match = content.match(/var\s+s\s*=\s*'([^']+)'/)
+        return unescape_hex_chars(match[1])
+      end
+    end
+    nil
+  end
+
+  def unescape_hex_chars(encoded_string)
+    encoded_string.gsub(/\\x([0-9a-fA-F]{2})/) { [$1].pack('H*') }
+  end
+end
+
+
+# Example usage
+if __FILE__ == $PROGRAM_NAME
+  html = File.read("sample_html_files/van-gogh-paintings.html", encoding: "utf-8")
+  parser = GoogleArtworksParser.new(html)
+  result = parser.parse
+  puts result
+end