C#代码实现创建带结构标签的PDF文档

PM> Install-Package Spire.PDF

using Spire.Pdf;
using Spire.Pdf.Graphics;
using Spire.Pdf.Interchange.TaggedPdf;
using Spire.Pdf.Tables;
using System.Data;
using System.Drawing;

namespace CreatePDFUA
{
    class Program
    {
        static void Main(string[] args)
        {
            // 创建 PdfDocument 对象
            PdfDocument doc = new PdfDocument();

            // 添加一个页面
            PdfPageBase page = doc.Pages.Add(PdfPageSize.A4, new PdfMargins(20));          

            // 设置 Tab 顺序为结构顺序
            page.SetTabOrder(TabOrder.Structure);

            // 创建 PdfTaggedContent 类对象
            PdfTaggedContent taggedContent = new PdfTaggedContent(doc);

            // 设置文档语言和标题
            taggedContent.SetLanguage("en-US");
            taggedContent.SetTitle("test");

            // 设置 PDF/UA1 标识（符合无障碍标准）
            taggedContent.SetPdfUA1Identification();

            // 创建字体和画刷
            PdfTrueTypeFont font = new PdfTrueTypeFont(new Font("Times New Roman", 14), true);
            PdfSolidBrush brush = new PdfSolidBrush(Color.Black);

            // 添加“document”结构元素
            PdfStructureElement document = taggedContent.StructureTreeRoot.AppendChildElement(PdfStandardStructTypes.Document);

            // 添加“heading”（一级标题）元素
            PdfStructureElement heading1 = document.AppendChildElement(PdfStandardStructTypes.HeadingLevel1);
            heading1.BeginMarkedContent(page);      
            string headingText = "What Is a Tagged PDF?";
            page.Canvas.DrawString(headingText, font, brush, new PointF(0, 0));
            heading1.EndMarkedContent(page);

            // 添加“paragraph”（段落）元素
            PdfStructureElement paragraph = document.AppendChildElement(PdfStandardStructTypes.Paragraph);
            paragraph.BeginMarkedContent(page);
            string paragraphText = "“Tagged PDF” doesn't seem like a life-changing term. But for some, it is. For people who are " +
                "blind or have low vision and use assistive technology (such as screen readers and connected Braille displays) to " +
                "access information, an untagged PDF means they are missing out on information contained in the document because assistive " +
                "technology cannot “read” untagged PDFs. Digital accessibility has opened up so many avenues to information that were once " +
                "closed to people with visual disabilities, but PDFs often get left out of the equation.";
            RectangleF rect = new RectangleF(0, 30, page.Canvas.ClientSize.Width, page.Canvas.ClientSize.Height);
            page.Canvas.DrawString(paragraphText, font, brush, rect);
            paragraph.EndMarkedContent(page);

            // 添加“figure”（图像）元素
            PdfStructureElement figure = document.AppendChildElement(PdfStandardStructTypes.Figure);
            figure.BeginMarkedContent(page);
            PdfImage image = PdfImage.FromFile(@"C:\Users\Administrator\Desktop\pdfua.png");
            page.Canvas.DrawImage(image, new PointF(0, 150));
            figure.EndMarkedContent(page);

            // 添加“table”（表格）元素
            PdfStructureElement table = document.AppendChildElement(PdfStandardStructTypes.Table);
            table.BeginMarkedContent(page);
            PdfTable pdfTable = new PdfTable();
            pdfTable.Style.DefaultStyle.Font = font;

            DataTable dataTable = new DataTable();
            dataTable.Columns.Add("Name");
            dataTable.Columns.Add("Age");
            dataTable.Columns.Add("Sex");
            dataTable.Rows.Add(new string[] { "John", "22", "Male" });
            dataTable.Rows.Add(new string[] { "Katty", "25", "Female" });

            pdfTable.DataSource = dataTable;
            pdfTable.Style.ShowHeader = true;
            pdfTable.Draw(page.Canvas, new PointF(0, 280), 300f);
            table.EndMarkedContent(page);

            // 将文档保存为文件
            doc.SaveToFile("CreatePDFUA.pdf");
        }
    }
}

using Spire.Pdf;
using Spire.Pdf.Graphics;
using Spire.Pdf.Interchange.TaggedPdf;
using System.Drawing;
 
namespace CreateTaggedPDF
{
    class Program
    {
        static void Main(string[] args)
        {
            //创建PdfDocument类的对象
            PdfDocument pdf = new PdfDocument();
 
            //添加一页
            pdf.Pages.Add(PdfPageSize.A4);
 
            //设置tab order
            pdf.Pages[0].SetTabOrder(TabOrder.Structure);
 
            //创建PdfTaggedContent类的对象
            PdfTaggedContent taggedContent = new PdfTaggedContent(pdf);
            taggedContent.SetLanguage("en-US");
            taggedContent.SetTitle("test");
 
            //创建字体、画刷、字符串格式
            PdfTrueTypeFont font = new PdfTrueTypeFont(new Font("Times New Roman", 10), true);
            PdfSolidBrush brush = new PdfSolidBrush(Color.Black);
            PdfStringFormat format = new PdfStringFormat(PdfTextAlignment.Left);
 
            //添加elements
            PdfStructureElement article = taggedContent.StructureTreeRoot.AppendChildElement(PdfStandardStructTypes.Document);
            PdfStructureElement paragraph1 = article.AppendChildElement(PdfStandardStructTypes.Paragraph);
            PdfStructureElement span1 = paragraph1.AppendChildElement(PdfStandardStructTypes.Span);
            span1.BeginMarkedContent(pdf.Pages[0]);
            //绘制内容到页面
            pdf.Pages[0].Canvas.DrawString("A PDF tag is the key to accessing the contents of PDF documents with supporting technologies such as screen readers. ", font, brush, new Rectangle(40, 0, 480, 80), format);
            span1.EndMarkedContent(pdf.Pages[0]);
 
            PdfStructureElement paragraph2 = article.AppendChildElement(PdfStandardStructTypes.Paragraph);
            paragraph2.BeginMarkedContent(pdf.Pages[0]);
            pdf.Pages[0].Canvas.DrawString("A PDF tag arranges the PDF content in a hierarchical architecture or tag tree.", font, brush, new Rectangle(40, 80, 480, 80), format);
            paragraph2.EndMarkedContent(pdf.Pages[0]);
 
            PdfStructureElement figure1 = article.AppendChildElement(PdfStandardStructTypes.Figure);
            //Set Alternate text 
            figure1.Alt = "replacement text1";
            figure1.BeginMarkedContent(pdf.Pages[0], null);
            PdfImage image = PdfImage.FromFile(@"logo.png");
            pdf.Pages[0].Canvas.DrawImage(image, new PointF(40, 200), new SizeF(100, 100));//绘制图片到页面
            figure1.EndMarkedContent(pdf.Pages[0]);
 
            PdfStructureElement figure2 = article.AppendChildElement(PdfStandardStructTypes.Figure);
            //Set Alternate text
            figure2.Alt = "replacement text2";
            figure2.BeginMarkedContent(pdf.Pages[0], null);
            pdf.Pages[0].Canvas.DrawRectangle(PdfPens.Black, new Rectangle(300, 200, 100, 100));
            figure2.EndMarkedContent(pdf.Pages[0]);
 
            //保存文档          
            pdf.SaveToFile("CreateTaggedFile_result.pdf");
        }
    }
}

Imports Spire.Pdf
Imports Spire.Pdf.Graphics
Imports Spire.Pdf.Interchange.TaggedPdf
Imports System.Drawing
 
Namespace CreateTaggedPDF
	Class Program
		Private Shared Sub Main(args As String())
			'创建PdfDocument类的对象
			Dim pdf As New PdfDocument()
 
			'添加一页
			pdf.Pages.Add(PdfPageSize.A4)
 
			'设置tab order
			pdf.Pages(0).SetTabOrder(TabOrder.[Structure])
 
			'创建PdfTaggedContent类的对象
			Dim taggedContent As New PdfTaggedContent(pdf)
			taggedContent.SetLanguage("en-US")
			taggedContent.SetTitle("test")
 
			'创建字体、画刷、字符串格式
			Dim font As New PdfTrueTypeFont(New Font("Times New Roman", 10), True)
			Dim brush As New PdfSolidBrush(Color.Black)
			Dim format As New PdfStringFormat(PdfTextAlignment.Left)
 
			'添加elements
			Dim article As PdfStructureElement = taggedContent.StructureTreeRoot.AppendChildElement(PdfStandardStructTypes.Document)
			Dim paragraph1 As PdfStructureElement = article.AppendChildElement(PdfStandardStructTypes.Paragraph)
			Dim span1 As PdfStructureElement = paragraph1.AppendChildElement(PdfStandardStructTypes.Span)
			span1.BeginMarkedContent(pdf.Pages(0))
			'绘制内容到页面
			pdf.Pages(0).Canvas.DrawString("A PDF tag is the key to accessing the contents of PDF documents with supporting technologies such as screen readers. ", font, brush, New Rectangle(40, 0, 480, 80), format)
			span1.EndMarkedContent(pdf.Pages(0))
 
			Dim paragraph2 As PdfStructureElement = article.AppendChildElement(PdfStandardStructTypes.Paragraph)
			paragraph2.BeginMarkedContent(pdf.Pages(0))
			pdf.Pages(0).Canvas.DrawString("A PDF tag arranges the PDF content in a hierarchical architecture or tag tree.", font, brush, New Rectangle(40, 80, 480, 80), format)
			paragraph2.EndMarkedContent(pdf.Pages(0))
 
			Dim figure1 As PdfStructureElement = article.AppendChildElement(PdfStandardStructTypes.Figure)
			'Set Alternate text 
			figure1.Alt = "replacement text1"
			figure1.BeginMarkedContent(pdf.Pages(0), Nothing)
			Dim image As PdfImage = PdfImage.FromFile("logo.png")
			pdf.Pages(0).Canvas.DrawImage(image, New PointF(40, 200), New SizeF(100, 100))
			'绘制图片到页面
			figure1.EndMarkedContent(pdf.Pages(0))
 
			Dim figure2 As PdfStructureElement = article.AppendChildElement(PdfStandardStructTypes.Figure)
			'Set Alternate text
			figure2.Alt = "replacement text2"
			figure2.BeginMarkedContent(pdf.Pages(0), Nothing)
			pdf.Pages(0).Canvas.DrawRectangle(PdfPens.Black, New Rectangle(300, 200, 100, 100))
			figure2.EndMarkedContent(pdf.Pages(0))
 
			'保存文档          
			pdf.SaveToFile("CreateTaggedFile_result.pdf")
			System.Diagnostics.Process.Start("CreateTaggedFile_result.pdf")
		End Sub
	End Class
End Namespace