extract_links

in lib/crawler/data/crawl_result/html.rb [58:79]

• 14 lines of code
• 5 McCabe index (conditional complexity)

        def extract_links(limit: nil, skip_invalid: false)
          links = Set.new
          limit_reached = false

          parsed_content.css('a[href]').each do |a|
            
            link = Link.new(base_url:, node: a)

            
            next if skip_invalid && !link.valid?

            links << link

            if limit && links.count >= limit
              limit_reached = true
              break
            end
          end

          { links:, limit_reached: }
        end