HTML에서 이미지 추출

Install-Package Aspose.HTML

using Aspose.Html;
using Aspose.Html.Net;
using System.Linq;
using System.IO;
...

    // Prepare a path to a source HTML file
    string documentPath = Path.Combine(DataDir, "images-from-html.html");

    // Create an instance of an HTML document
    using (var document = new HTMLDocument(documentPath))
    {
        // Collect all <img> elements
        var images = document.GetElementsByTagName("img");

        // Create a distinct collection of relative image URLs
        var urls = images.Select(element => element.GetAttribute("src")).Distinct();

        // Create absolute image URLs
        var absUrls = urls.Select(src => new Url(src, document.BaseURI));

        foreach (var url in absUrls)
        {
            // Create an image request message
            using var request = new RequestMessage(url);

            // Download image
            using var response = document.Context.Network.Send(request);

            var imgName = url.Pathname.Split('/').Last();

            //Check the image in base64 encoding
            if (url.Protocol == "data:" && response.Headers.ContentType.MediaType.Type == "image")
            {
                // Get the image type and set to extension
                imgName = "img1." + response.Headers.ContentType.MediaType.SubType;
            }

            // Check whether a response is successful
            if (response.IsSuccess)
            {
                // Save image to a local file system
                File.WriteAllBytes(Path.Combine(OutputDir, imgName), response.Content.ReadAsByteArray());
            }
        }
    }