gumbobench.cs

using Gumbo.Wrappers;
using Sgml;
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.IO;
using System.Linq;
using System.Net;
using System.Xml.Linq;

namespace ConsoleApplication55
{
    class Program
    {
        static void Bench(string label, Action<string> action)
        {
            var html = new WebClient().DownloadString("https://github.com/google/gumbo-parser");

            var sw = Stopwatch.StartNew();
            for (int i = 0; i < 100; i++)
            {
                action(html);
            }
            sw.Stop();

            Console.WriteLine(label + ":" + sw.Elapsed);
        }

        static void Main(string[] args)
        {
            Bench("SgmlReader", html =>
            {
                XDocument xdoc;
                using (var tr = new StringReader(html))
                using (var sgml = new SgmlReader() { InputStream = tr })
                {
                    xdoc = XDocument.Load(sgml);
                }
                var hogehogehoge = xdoc.Descendants("li")
                    .Select(x => x.Value)
                    .ToArray();
            });

            Bench("HtmlAgilityPack", html =>
            {
                var doc = new HtmlAgilityPack.HtmlDocument();
                doc.LoadHtml(html);
                var hogehoge = doc.DocumentNode.Descendants("li")
                    .Select(x => x.InnerText)
                    .ToArray();
            });

            Bench("Gumbo", html =>
            {
                var gumboParse = new Gumbo.Wrappers.GumboWrapper(html);
                var hoge = gumboParse.Document.Children
                    .TraverseDepthFirst(x => x.Children) // (IxのExpandがBreadthFirstでツカエネーと思った)
                    .OfType<ElementWrapper>()
                    .Where(x => x.NormalizedTagName == "li")
                    .Select(x => x.Value)
                    .ToArray();
            });
        }
    }
    public static class Extensions
    {
        public static IEnumerable<T> TraverseDepthFirst<T>(this IEnumerable<T> source, Func<T, IEnumerable<T>> selector)
        {
            foreach (var item in source)
            {
                yield return item;
                foreach (var subitem in selector(item).TraverseDepthFirst(selector))
                {
                    yield return subitem;
                }
            }
        }
    }
}