Extract visible text from HTML in C#

<!DOCTYPE html>
<html lang="en">
<head>
  <title>Opening hours</title>
  <style>.promo { display: none }</style>
  <script>window.dataLayer = [];</script>
</head>
<body>
  <h1>Opening hours</h1>
  <p class="promo">Members save 10%</p>
  <p>Monday&ndash;Friday, 9 to 6.<br>The caf&eacute; closes at 5.</p>
  <p hidden>Draft: holiday hours</p>
  <ul><li>Wi-Fi</li><li>Printing</li></ul>
  <noscript>Turn on JavaScript to book a room.</noscript>
  <script>document.querySelector("h1").addEventListener("click", track);</script>
</body>
</html>

using AngleSharp.Html.Parser;
using HtmlAgilityPack;
using OneHtml = RecursiveAI.OneHtml;
 
string html = File.ReadAllText("hours.html");
 
var hap = new HtmlDocument();
hap.LoadHtml(html);
string hapText = hap.DocumentNode.SelectSingleNode("//body")!.InnerText;
 
var angle = new HtmlParser().ParseDocument(html);
string angleText = angle.Body!.TextContent;
 
OneHtml.Document one = OneHtml.Document.Parse(html);
string oneText = one.Root.QuerySelector("body").TextContent!;
 
Show("HtmlAgilityPack InnerText", hapText);
Show("AngleSharp TextContent", angleText);
Show("onehtml TextContent", oneText);
 
// Collapse runs of whitespace so the three are easy to compare
static void Show(string label, string text) =>
    Console.WriteLine($"{label}:\n  {string.Join(' ', text.Split((char[]?)null, StringSplitOptions.RemoveEmptyEntries))}\n");

HtmlAgilityPack InnerText:
  Opening hours Members save 10% Monday–Friday, 9 to 6.The café closes at 5. Draft: holiday hours Wi-FiPrinting Turn on JavaScript to book a room.
 
AngleSharp TextContent:
  Opening hours Members save 10% Monday–Friday, 9 to 6.The café closes at 5. Draft: holiday hours Wi-FiPrinting Turn on JavaScript to book a room. document.querySelector("h1").addEventListener("click", track);
 
onehtml TextContent:
  Opening hours Members save 10% Monday–Friday, 9 to 6.The café closes at 5. Draft: holiday hours Wi-FiPrinting Turn on JavaScript to book a room. document.querySelector("h1").addEventListener("click", track);

using System.Text;
using RecursiveAI.OneHtml;
using RecursiveAI.OneHtml.Css;
 
Document doc = Document.Parse(File.ReadAllBytes("hours.html"));
Node body = doc.Root.QuerySelector("body");
 
Console.WriteLine("--- markup only");
Console.WriteLine(VisibleText(body));
 
Console.WriteLine("--- with the cascade");
Console.WriteLine(VisibleText(body, DocumentStyles.Create(doc)));
 
// The text a reader sees, one line per block, without script, style, template or noscript content.
// With styles, text hidden by CSS (display: none, the hidden attribute, visibility: hidden) is left out too.
static string VisibleText(Node root, DocumentStyles? styles = null)
{
    const string Skip = "script, style, template, noscript";
    const string Blocks = "address, article, aside, blockquote, dd, details, div, dl, dt, figcaption, figure, footer, form, "
        + "h1, h2, h3, h4, h5, h6, header, li, main, nav, ol, p, pre, section, summary, table, td, th, tr, ul";
 
    var text = new StringBuilder();
    Node block = default;
    foreach (Node node in root.Descendants)
    {
        if (node.IsElement && node.LocalName == "br")
        {
            text.Append('\n');
        }
        else if (node.Kind == NodeKind.Text && node.ParentElement.Closest(Skip).IsNull
                 && (styles is null || !IsHidden(node.ParentElement, styles)))
        {
            // Start a new line whenever the text belongs to a different block than the last text did
            Node current = node.ParentElement.Closest(Blocks);
            if (current != block)
            {
                text.Append('\n');
                block = current;
            }
            text.Append(node.Data);
        }
    }
 
    // Collapse whitespace inside each line, as a browser does, and drop empty lines
    return string.Join('\n', text.ToString().Split('\n')
        .Select(line => string.Join(' ', line.Split((char[]?)null, StringSplitOptions.RemoveEmptyEntries)))
        .Where(line => line.Length > 0));
}
 
// display isn't inherited, so check every ancestor; visibility is, so the element's own value is enough
static bool IsHidden(Node element, DocumentStyles styles)
{
    for (Node e = element; !e.IsNull; e = e.ParentElement)
    {
        if (styles.GetStyle(e).GetPropertyValue("display") == "none")
        {
            return true;
        }
    }
    return styles.GetStyle(element).GetPropertyValue("visibility") is "hidden" or "collapse";
}

--- markup only
Opening hours
Members save 10%
Monday–Friday, 9 to 6.
The café closes at 5.
Draft: holiday hours
Wi-Fi
Printing
--- with the cascade
Opening hours
Monday–Friday, 9 to 6.
The café closes at 5.
Wi-Fi
Printing

using RecursiveAI.OneHtml;
using RecursiveAI.OneHtml.Accessibility;
using RecursiveAI.OneHtml.Css;
 
Document doc = Document.Parse(File.ReadAllBytes("hours.html"));
 
// The accessibility tree is built with the cascade: CSS-hidden, hidden and aria-hidden content is left out
AccessibilityTree tree = AccessibilityTree.Build(doc, DocumentStyles.Create(doc));
Console.WriteLine(tree.CreateReadingView().ToText());

heading level 1: Opening hours
Monday–Friday, 9 to 6.The café closes at 5.
list with 2 items
  item 1 of 2
  Wi-Fi
  item 2 of 2
  Printing
end of list

using HtmlAgilityPack;
 
var doc = new HtmlDocument();
doc.Load("hours.html");
 
// Remove the elements whose text is never shown, then decode the entities InnerText leaves in
foreach (HtmlNode node in doc.DocumentNode.SelectNodes("//script|//style|//noscript|//template") ?? Enumerable.Empty<HtmlNode>())
{
    node.Remove();
}
 
string text = HtmlEntity.DeEntitize(doc.DocumentNode.SelectSingleNode("//body")!.InnerText);
Console.WriteLine(string.Join(' ', text.Split((char[]?)null, StringSplitOptions.RemoveEmptyEntries)));

Opening hours Members save 10% Monday–Friday, 9 to 6.The café closes at 5. Draft: holiday hours Wi-FiPrinting

using AngleSharp.Dom;
using AngleSharp.Html.Parser;
 
var doc = new HtmlParser().ParseDocument(File.ReadAllText("hours.html"));
 
// Remove the elements whose text is never shown, then read TextContent
foreach (IElement element in doc.QuerySelectorAll("script, style, noscript, template"))
{
    element.Remove();
}
 
string text = doc.Body!.TextContent;
Console.WriteLine(string.Join(' ', text.Split((char[]?)null, StringSplitOptions.RemoveEmptyEntries)));

Opening hours Members save 10% Monday–Friday, 9 to 6.The café closes at 5. Draft: holiday hours Wi-FiPrinting