C# 创建标签PDF文件

Q1:关于“标签PDF文件(Tagged PDF)”

标签PDF文件包含描述文档结构和各种文档元素顺序的元数据,是一种包含后端提供的可访问标记,管理阅读顺序和文档内容表示的逻辑结构的PDF文件[1]

Q2:关于“标签(Tag)”

PDF标签是通过屏幕阅读器等支持技术访问PDF文档内容的关键。PDF标记在层次结构或标记树(tag tree)中排列PDF内容[1]

这里的标签是一种不可见的标签,它提供关于PDF文档内容的重要信息。带标签的PDF包含许多不同类型的标签,但最常用的是文本、替代文本(图像的替代文本)、标题、链接和链接描述[2]

Q3:PDF标签的用处及意义

添加PDF标签不会改变文档的视觉外观,但它提供了一个不可见的层,用于格式化文档与屏幕阅读器协作工作,这就使得从PDF文件中提取文本和图形变得更容易,并帮助屏幕阅读器以正确的顺序显示文件内容。[2]

PDF标签还可以用于将内容传输到屏幕较小的设备,如智能手机和平板电脑。[2]

Q4:如何创建标签PDF文件

本文将要介绍的创建方法是以后端C#程序代码的方式来创建标签PDF文件。创建时,通过NuGet安装引用PDF API-Spire.PDF for .NET,调用其提供的类及相关方法来标记内容、结构元素等。

C#

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");
        }
    }
}

vb.net

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

参考资料:

  1. https://247accessibledocuments.com/what-is-a-tagged-pdf/
  2. https://accessibility-i.org/what-is-a-tagged-pdf/

—END—

  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
C#实现生成PDF文档(附源码) 收藏 //write by wenhui.org using System; using System.IO; using System.Text; using System.Collections; namespace PDFGenerator { public class PDFGenerator { static float pageWidth = 594.0f; static float pageDepth = 828.0f; static float pageMargin = 30.0f; static float fontSize = 20.0f; static float leadSize = 10.0f; static StreamWriter pPDF=new StreamWriter("E:\myPDF.pdf"); static MemoryStream mPDF= new MemoryStream(); static void ConvertToByteAndAddtoStream(string strMsg) { Byte[] buffer=null; buffer=ASCIIEncoding.ASCII.GetBytes(strMsg); mPDF.Write(buffer,0,buffer.Length); buffer=null; } static string xRefFormatting(long xValue) { string strMsg =xValue.ToString(); int iLen=strMsg.Length; if (iLen<10) { StringBuilder s=new StringBuilder(); int i=10-iLen; s.Append('0',i); strMsg=s.ToString() + strMsg; } return strMsg; } static void Main(string[] args) { ArrayList xRefs=new ArrayList(); //Byte[] buffer=null; float yPos =0f; long streamStart=0; long streamEnd=0; long streamLen =0; string strPDFMessage=null; //PDF文档头信息 strPDFMessage="%PDF-1.1 "; ConvertToByteAndAddtoStream(strPDFMessage); xRefs.Add(mPDF.Length); strPDFMessage="1 0 obj "; ConvertToByteAndAddtoStream(strPDFMessage); strPDFMessage="<> "; ConvertToByteAndAddtoStream(strPDFMessage); strPDFMessage="stream "; ConvertToByteAndAddtoStream(strPDFMessage); ////////PDF文档描述 streamStart=mPDF.Length; //字体 strPDFMessage="BT /F0 " + fontSize +" Tf "; ConvertToByteAndAddtoStream(strPDFMessage); //PDF文档实体高度 yPos = pageDepth - pageMargin; strPDFMessage=pageMargin + " " + yPos +" Td " ; ConvertToByteAndAddtoStream(strPDFMessage); strPDFMessage= leadSize+" TL " ; ConvertToByteAndAddtoStream(strPDFMessage); //实体内容 strPDFMessage= "(http://www.wenhui.org)Tj " ; ConvertToByteAndAddtoStream(strPDFMessage); strPDFMessage= "ET "; ConvertToByteAndAddtoStream(strPDFMessage); streamEnd=mPDF.Length; streamLen=streamEnd-streamStart; strPDFMessage= "endstream endobj "; ConvertToByteAndAddtoStream(strPDFMessage); //PDF文档的版本信息 xRefs.Add(mPDF.Length); strPDFMessage="2 0 obj "+ streamLen + " endobj "; ConvertToByteAndAddtoStream(strPDFMessage); xRefs.Add(mPDF.Length); strPDFMessage="3 0 obj <> endobj "; ConvertToByteAndAddtoStream(strPDFMessage); xRefs.Add(mPDF.Length); strPDFMessage="4 0 obj <</Type /Pages /Count 1 "; ConvertToByteAndAddtoStream(strPDFMessage); strPDFMessage="/Kids[ 3 0 R ] "; ConvertToByteAndAddtoStream(strPDFMessage); strPDFMessage="/Resources<</ProcSet[/PDF/Text]/Font<> >> "; ConvertToByteAndAddtoStream(strPDFMessage); strPDFMessage="/MediaBox [ 0 0 "+ pageWidth + " " + pageDepth + " ] >> endobj "; ConvertToByteAndAddtoStream(strPDFMessage); xRefs.Add(mPDF.Length); strPDFMessage="5 0 obj <> endobj "; ConvertToByteAndAddtoStream(strPDFMessage); xRefs.Add(mPDF.Length); strPDFMessage="6 0 obj <> endobj "; ConvertToByteAndAddtoStream(strPDFMessage); streamStart=mPDF.Length; strPDFMessage="xref 0 7 0000000000 65535 f "; for(int i=0;i<xRefs.Count;i++) { strPDFMessage+=xRefFormatting((long) xRefs[i])+" 00000 n "; } ConvertToByteAndAddtoStream(strPDFMessage); strPDFMessage="trailer <> "; ConvertToByteAndAddtoStream(strPDFMessage); strPDFMessage="startxref " + streamStart+" %%EOF "; ConvertToByteAndAddtoStream(strPDFMessage); mPDF.WriteTo(pPDF.BaseStream); mPDF.Close(); pPDF.Close(); } } }
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值