Contents

# frozen_string_literal: true

module Html2rss
  module ItemExtractors
    ##
    # Returns the HTML content of the specified element.
    #
    # Example HTML structure:
    #
    #     <p>Lorem <b>ipsum</b> dolor ...</p>
    #
    # YAML usage example:
    #
    #    selectors:
    #      description:
    #        selector: p
    #        extractor: html
    #
    # Would return:
    #    '<p>Lorem <b>ipsum</b> dolor ...</p>'
    #
    # Always ensure to sanitize the HTML during post-processing with
    # {AttributePostProcessors::SanitizeHtml}.
    class Html
      # The available options for the html extractor.
      Options = Struct.new('HtmlOptions', :selector, keyword_init: true)

      ##
      # Initializes the Html extractor.
      #
      # @param xml [Nokogiri::XML::Element]
      # @param options [Options]
      def initialize(xml, options)
        @element = ItemExtractors.element(xml, options.selector)
      end

      ##
      # Retrieves and returns the HTML content of the element.
      #
      # @return [String] The HTML content.
      def get
        @element.to_s
      end
    end
  end
end

Version data entries

6 entries across 6 versions & 1 rubygems

Version	Path
html2rss-0.15.0	lib/html2rss/item_extractors/html.rb
html2rss-0.14.0	lib/html2rss/item_extractors/html.rb
html2rss-0.13.0	lib/html2rss/item_extractors/html.rb
html2rss-0.12.0	lib/html2rss/item_extractors/html.rb
html2rss-0.11.0	lib/html2rss/item_extractors/html.rb
html2rss-0.10.0	lib/html2rss/item_extractors/html.rb