使用 StreamProvider 加载 HTML 到 Excel

在加载包含外部资源的html文件时，我们经常会遇到以下两个问题:

1. 当加载 HTML 流时，无法通过相对路径获取 HTML 文件引用的图像和外部资源。
2. html文件中引用的外部资源路径需要映射

本文介绍了如何实现IStreamProvider接口来设置HtmlLoadOptions.StreamProvider属性。通过实现此接口，您将能够在加载Html流期间加载外部资源，或者这些外部资源是相对的。

下面是显示使用HtmlLoadOptions.StreamProvider属性的主要代码

internal class HtmlAttachedStreamProvider : Aspose.Cells.IStreamProvider
{
    internal static bool IsHRef(string picPath)
    {
        //This handles http://,https:// file:// and probably ftp://.
        if (picPath.StartsWith("http://")
            || picPath.StartsWith("https://")
            || picPath.StartsWith("file://")
            || picPath.StartsWith("ftp://"))
        {
            return true;
        }
        return false;
    }
    internal static Stream GetStreamFromHref(string href)
    {
        try
        {
            WebRequest request = WebRequest.Create(href);
            WebResponse response = request.GetResponse();

            // FIX: Do not specify capacity since the length of the response is sometimes not known.
            MemoryStream dstStream = new MemoryStream();
            using (Stream responseStream = response.GetResponseStream())
            {
                byte[] buf = new byte[4096];
                while (true)
                {
                    int bytesRead = responseStream.Read(buf, 0, buf.Length);
                    // Read returns 0 when reached end of stream. Checking for negative too to make it conceptually close to Java.
                    if (bytesRead <= 0)
                        break;
                    else
                        dstStream.Write(buf, 0, bytesRead);
                }
            }


            dstStream.Position = 0;
            return dstStream;
        }
        catch
        {
            //ignored
        }
        return null;

    }
    public void InitStream(StreamProviderOptions options)
    {
        string absolutePath = null;
        switch (options.DefaultPath)
        {
            case "/Files/Image1.png":
                absolutePath = @"D:/filetemp/G1.png";
                break;
             case "/Files/Image2.png":
                absolutePath = @"D:/filetemp/E1.png";
                break;
            case "https://www.aspose.com/templates/aspose/img/products/cells/aspose_cells-for-net.svg":
                absolutePath = @"D:/filetemp/F1.png";
                break;
            default:
                break;

        }
        if(absolutePath == null)
        {
            if(IsHRef(options.DefaultPath))
            {
                options.Stream = GetStreamFromHref(options.DefaultPath);
            }
            else if(File.Exists(options.DefaultPath))
            {
                options.Stream = File.OpenRead(options.DefaultPath);
            }
            return;
        }
        options.Stream = File.OpenRead(absolutePath);

    }

    public void CloseStream(StreamProviderOptions options)
    {
        if(options.Stream != null)
        {

            options.Stream.Close();
        }

    }
}

static void Main(string[] args)
{
		HtmlAttachedStreamProvider attachedStreamProvider = new HtmlAttachedStreamProvider();
		HtmlLoadOptions options = new HtmlLoadOptions();
		options.StreamProvider = attachedStreamProvider;
		var workbook = new Workbook(@"html1.html", options);
		workbook.Save("dest.xlsx");
}