Html Agility Pack の使用方法

導入

Html Agility Pack を NuGet からインストールする。

実装方法

void Main()
{
    WebScrapingRunner.RunAsync().Wait();
}

public static class WebScrapingRunner
{
    public static async Task RunAsync()
    {
        // 時間計測用のタイマー
        var timer = new System.Diagnostics.Stopwatch();
        timer.Start();

        using (var client = new HttpClient() { Timeout = TimeSpan.FromMilliseconds(30000) })
        {
            var targetUri = new Uri("https://www.gotokyo.org/eventlist/ja/list");
            var pageHtml = await client.GetHtmlAsync(targetUri);
            Console.WriteLine(pageHtml.DocumentNode.WriteTo());
        }

        Console.WriteLine("HTML取得完了: {0:0.000}秒", timer.Elapsed.TotalSeconds);
    }
}

public static class HttpClientExtensions
{
    public static async Task<HtmlDocument> GetHtmlAsync(this HttpClient httpClient, Uri requestUri)
    {
        var response = await httpClient.GetAsync(requestUri);
        return await response.Content.ReadAsHtmlAsync();
    }

    public static async Task<HtmlDocument> ReadAsHtmlAsync(this HttpContent httpContent)
    {
        var html = await httpContent.ReadAsStringAsync();
        var doc = new HtmlDocument();
        doc.LoadHtml(html);
        return doc;
    }
}