无法使用 iText7 将使用 OpenXML 的带有图像的 HTML 转换为 PDF

如何解决无法使用 iText7 将使用 OpenXML 的带有图像的 HTML 转换为 PDF

我正在使用 Open XML SDK 2.12.1 version 将 docx word 转换为 html 文件

d1 = {'Alanine,aspartate and glutamate Metabolism': 4,'Ascorbate and aldarate Metabolism': 4,'Benzoate degradation': 6,'Biosynthesis of antibiotics': 16}

d2 = {'Amino sugar and nucleotide sugar Metabolism': 5,'Arginine and proline Metabolism': 4,'Biosynthesis of antibiotics': 11,'Biosynthesis of secondary Metabolites': 21}

print(merge(d1,d2))

并使用 iText (Version 7.1.14) 使用 {'Biosynthesis of antibiotics': [16,11],'Amino sugar and nucleotide sugar Metabolism': [0,5],'Arginine and proline Metabolism': [0,4],'Alanine,aspartate and glutamate Metabolism': [4,0],'Ascorbate and aldarate Metabolism': [4,'Benzoate degradation': [6,'Biosynthesis of secondary Metabolites': [0,21]}

将 html 转换为 pdf

protected void btndisplay_Click(object sender,EventArgs e)
{
    byte[] byteArray = (byte[])(Session["ByteArray"]);

    if (byteArray != null)
    {
        try
        {
            DirectoryInfo convertedDocsDirectory =
                new DirectoryInfo(Server.MapPath(DocxConvertedToHtmlDirectory));

            if (!convertedDocsDirectory.Exists)
                convertedDocsDirectory.Create();

            Guid g = Guid.NewGuid();

            var htmlFileName = g.ToString() + ".html";

            ConvertToHtml(byteArray,convertedDocsDirectory,htmlFileName);

            Response.Redirect(DocxConvertedToHtmlDirectory + htmlFileName);
        }
        catch (Exception ex)
        {
            lblMessage.Text = "ERROR: " + ex.Message.ToString();
        }
    }
    else
    {
        lblMessage.Text = "You have not specified a file.";
    }
}


public static void ConvertToHtml(byte[] byteArray,DirectoryInfo destDirectory,string htmlFileName)
{
    FileInfo fiHtml = new FileInfo(Path.Combine(destDirectory.FullName,htmlFileName));

    using (MemoryStream memoryStream = new MemoryStream())
    {
        memoryStream.Write(byteArray,byteArray.Length);

        using (WordprocessingDocument wDoc = WordprocessingDocument.Open(memoryStream,true))
        {
            var imageDirectoryFullName =
                fiHtml.FullName.Substring(0,fiHtml.FullName.Length - fiHtml.Extension.Length) + "_files";

            var imageDirectoryRelativeName =
                fiHtml.Name.Substring(0,fiHtml.Name.Length - fiHtml.Extension.Length) + "_files";

            int imageCounter = 0;

            var pageTitle = (string)wDoc
                .CoreFilePropertiesPart
                .GetXDocument()
                .Descendants(DC.title)
                .FirstOrDefault();

            HtmlConverterSettings settings = new HtmlConverterSettings()
            {
                PageTitle = pageTitle,FabricateCssClasses = true,CssClassprefix = "pt-",RestrictToSupportedLanguages = false,RestrictToSupportednumberingFormats = false,ImageHandler = imageInfo =>
                {
                    DirectoryInfo localDirInfo = new DirectoryInfo(imageDirectoryFullName);
                    if (!localDirInfo.Exists)
                        localDirInfo.Create();
                    ++imageCounter;

                    string extension = imageInfo.ContentType.Split('/')[1].ToLower();

                    ImageFormat imageFormat = null;
                    if (extension == "png")
                    {
                        // Convert png to jpeg.
                        extension = "gif";
                        imageFormat = ImageFormat.Gif;
                    }
                    else if (extension == "gif")
                        imageFormat = ImageFormat.Gif;
                    else if (extension == "bmp")
                        imageFormat = ImageFormat.Bmp;
                    else if (extension == "jpeg")
                        imageFormat = ImageFormat.Jpeg;
                    else if (extension == "tiff")
                    {
                        // Convert tiff to gif.
                        extension = "gif";
                        imageFormat = ImageFormat.Gif;
                    }
                    else if (extension == "x-wmf")
                    {
                        extension = "wmf";
                        imageFormat = ImageFormat.Wmf;
                    }

                    // If the image format isn't one that we expect,ignore it,// and don't return markup for the link.
                    if (imageFormat == null)
                        return null;

                    FileInfo imageFileName = new FileInfo(imageDirectoryFullName + "/image" +
                        imageCounter.ToString() + "." + extension);
                    try
                    {
                        imageInfo.Bitmap.Save(imageFileName.FullName,imageFormat);
                    }

                    catch (System.Runtime.InteropServices.ExternalException)
                    {
                        return null;
                    }

                    XElement img = new XElement(Xhtml.img,new XAttribute(NoNamespace.src,imageDirectoryRelativeName + "/" + imageFileName.Name),imageInfo.ImgStyleAttribute,imageInfo.AltText != null ?
                            new XAttribute(NoNamespace.alt,imageInfo.AltText) : null);
                    return img;
                }
            };

            XElement html = HtmlConverter.ConvertToHtml(wDoc,settings);

            var body = html.Descendants(Xhtml.body).First();

            body.AddFirst(
                new XElement(Xhtml.p,new XElement(Xhtml.a,new XAttribute("href","/Default2.aspx"),"Go back to Upload Page")));

            var htmlString = html.ToString(SaveOptions.disableFormatting);

            File.WriteallText(fiHtml.FullName,htmlString,Encoding.UTF8);
        }
    }
}

结果中的 PDF 根本没有图像！

PDF 文件应该是这样的

但结果是没有图像，因为itext7支持base64图像。

我试过没有成功

HtmlConverter (html2pdf version 2.0.1)

如何使用支持 base64 图像编辑我的代码以将 docx word 转换为 html 文件？

HMTL

这是 HTML 代码。

要查看 pdf 文件中的图像，我需要这部分

protected void Page_Load(object sender,EventArgs e)
{
    PdfWriter writer = new PdfWriter(Response.OutputStream);
    PdfDocument pdf = new PdfDocument(writer);
    Document document = new Document(pdf);

    using (MysqLConnection con =
        new MysqLConnection(ConfigurationManager.ConnectionStrings["con"].ConnectionString))
    {
        using (MysqLCommand cmd =
            new MysqLCommand("SELECT `HEAD` FROM `xmltable`;",myConnectionString))
        {
            cmd.Connection.open();
            cmd.CommandType = CommandType.Text;

            MysqLDataReader reader = cmd.ExecuteReader();

            if (reader.HasRows)
            {
                while (reader.Read())
                {
                    Paragraph contents = new Paragraph(reader.GetString("HEAD"))
                    .SetTextAlignment(TextAlignment.JUSTIFIED)
                    .SetFontSize(12);                        

                    nomefile = @"C:\\Desktop\Management_" + Guid.NewGuid() + ".pdf";
                    html = reader.GetString("HEAD").ToString();
                    dest = nomefile.ToString();

                    document.Add(contents);

                    HtmlConverter.ConvertToPdf(html,new FileStream(dest,FileMode.Create));
                }
            }

            reader.Close();
            cmd.Connection.Close();
        }
    }

    document.Close();

    Response.Clear();
    Response.ContentType = "application/pdf";
    Response.AppendHeader("Content-disposition","attachment; filename=" + dest);
    Response.TransmitFile(dest);
    Response.End();
}

改为

try
{
    imageInfo.Bitmap.Save(imageFileName.FullName,imageFormat);
    byte[] imageBytes = memoryStream.ToArray();
    string base64String = Convert.ToBase64String(imageBytes);
}

（请注意，base64 编码的图像被截断以适合此页面）

带有 base64 编码图像的文件的浏览器视图和结果 PDF

Reference

<img src="01a5094b-2d44-4399-93b2-2cc2db7ebfc2_files/image1.gif" style="width: 2.875in; height: 0.4583333in" alt="Immagine 9" />