art_paintings_extractor 0.1.0

data/lib/art_paintings.rb

@@ -0,0 +1,75 @@
+# frozen_string_literal: true
+
+require_relative 'art_paintings_extractor/version'
+require_relative 'art_paintings_extractor/html_document'
+
+require 'logger'
+require 'base64'
+
+# ArtPaintingsExtractor module
+module ArtPaintingsExtractor
+  # This class is responsible for extracting painting information from an HTML file.
+  class ArtPaintings
+    attr_reader :doc, :logger
+
+    def initialize(html_file)
+      @logger = Logger.new($stdout)
+      @doc = HtmlDocument.new(html_file).call
+    end
+
+    def paintings
+      @doc.css('.klitem')
+    end
+
+    def extract_paintings
+      paintings.map { |item| build_painting_info(item) }
+    end
+
+    def build_painting_info(item)
+      info = {
+        'name' => extract_name(item),
+        'link' => extract_link(item),
+        'image' => nil
+        # 'image' => extract_image(item)
+      }
+
+      extensions = extract_extensions(item)
+      info['extensions'] = [extensions] unless extensions.empty?
+
+      info
+    end
+
+    private
+
+    def extract_name(item)
+      item['aria-label'] || 'Unknown'
+    rescue NoMethodError
+      @logger.warn("Failed to extract name for item: #{item}")
+      'Unknown'
+    end
+
+    def extract_extensions(item)
+      item.css('.ellip.klmeta').text
+    rescue NoMethodError
+      @logger.warn("Failed to extract extensions for item: #{item}")
+      'No extension found for item'
+    end
+
+    def extract_link(item)
+      href = item['href']
+      href ? "https://www.google.com#{href}" : 'No link'
+    rescue NoMethodError
+      @logger.warn("Failed to extract link for item: #{item}")
+      'No link'
+    end
+
+    def extract_image(item)
+      image = item.at_css('g-img > img')
+      image_src = image ? image['src'] : 'No image'
+      image_src || 'No image'
+    rescue NoMethodError
+      @logger.warn("Failed to extract image for item: #{item}")
+      'No image'
+    end
+  end
+end

data/lib/art_paintings_extractor/html_document.rb

@@ -0,0 +1,43 @@
+# frozen_string_literal: true
+
+module ArtPaintingsExtractor
+  # Class responsible for reading the contents of an HTML file
+  class HtmlDocument
+    attr_reader :logger
+
+    def initialize(html)
+      @html = html
+      @logger = Logger.new($stdout)
+    end
+
+    def call
+      extract_from_html
+    end
+
+    private
+
+    def read_html_file
+      File.read(@html)
+    rescue Errno::ENOENT
+      @logger.error("File not found: #{@html}")
+      nil
+    rescue Errno::EACCES
+      @logger.error("Permission denied: #{@html}")
+      nil
+    rescue StandardError => e
+      @logger.error("Error reading file: #{e.message}")
+      nil
+    end
+
+    def extract_from_html
+      html_file = read_html_file
+
+      return nil unless html_file
+
+      Nokogiri::HTML(read_html_file)
+    rescue Nokogiri::XML::SyntaxError => e
+      @logger.error("Error parsing HTML: #{e.message}")
+      nil
+    end
+  end
+end

data/lib/art_paintings_extractor/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module ArtPaintingsExtractor
+  VERSION = "0.1.0"
+end

data/run_extractor.rb

@@ -0,0 +1,19 @@
+# run_extractor.rb
+
+require_relative "lib/art_paintings_extractor"
+
+# Path to the HTML file you want to parse
+html_file = "./files/van-gogh-paintings.html"
+
+# Output JSON file
+# output_file = 'files/extracted_paintings.json'
+
+# Create an instance of the extractor
+extractor = ArtPaintingsExtractor::ArtPaintings.new(html_file)
+
+# Extract paintings and print them
+paintings = extractor.extract_paintings
+puts paintings
+
+# Save paintings to a JSON file
+# extractor.save_to_file(output_file)

data/sig/van_gogh_paintings_extractor.rbs

@@ -0,0 +1,4 @@
+module VanGoghPaintingsExtractor
+  VERSION: String
+  # See the writing guide of rbs: https://github.com/ruby/rbs#guides
+end

metadata

@@ -0,0 +1,77 @@
+--- !ruby/object:Gem::Specification
+name: art_paintings_extractor
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Jovan
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2024-07-27 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+description: ArtPaintingsExtractor is a Ruby gem that parses an HTML file to extract
+  information about art paintings.
+email:
+- jovansr@pm.me
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rspec"
+- ".rubocop.yml"
+- CHANGELOG.md
+- CODE_OF_CONDUCT.md
+- LICENSE.txt
+- README.md
+- Rakefile
+- files/expected-array-without-images.json
+- files/expected-array.json
+- files/van-gogh-paintings.html
+- files/van-gogh-paintings.json
+- files/van-gogh-paintings.png
+- lib/art_paintings.rb
+- lib/art_paintings_extractor/html_document.rb
+- lib/art_paintings_extractor/version.rb
+- run_extractor.rb
+- sig/van_gogh_paintings_extractor.rbs
+homepage: https://github.com/jovan-sremacki/code-challenge
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/jovan-sremacki/code-challenge
+  source_code_uri: https://github.com/jovan-sremacki/code-challenge
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.0.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.15
+signing_key:
+specification_version: 4
+summary: A tool to extract Art paintings from HTML pages.
+test_files: []