From 62f8283587d5d86284bd8f97d20daa71e5ebcd4d Mon Sep 17 00:00:00 2001 From: Pete Matsyburka Date: Tue, 2 Jun 2026 13:44:52 +0300 Subject: [PATCH] adjust html to text --- lib/html_to_plain_text.rb | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/lib/html_to_plain_text.rb b/lib/html_to_plain_text.rb index 1001f40c..f0040d06 100644 --- a/lib/html_to_plain_text.rb +++ b/lib/html_to_plain_text.rb @@ -10,7 +10,7 @@ module HtmlToPlainText doc = Nokogiri::HTML.fragment(cleaned) - doc.css('script').each(&:remove) + doc.xpath('.//script').each(&:remove) result = process_nodes(doc, line_length) @@ -33,12 +33,9 @@ module HtmlToPlainText result = +'' node.children.each do |child| - case child - when Nokogiri::XML::Text + if child.text? || child.cdata? result << child.text - when Nokogiri::XML::Comment - next - when Nokogiri::XML::Element + elsif child.element? result << process_element(child, line_length) end end