• 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#

    复制代码
    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");
            }
        }
    }
    复制代码

    vb.net

    复制代码
    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
    复制代码

    参考资料:

    [1]. https://247accessibledocuments.com/what-is-a-tagged-pdf/

    [2]. https://accessibility-i.org/what-is-a-tagged-pdf/

     

    —END—

     

  • 相关阅读:
    设计大师都在用!电商设计素材网站大公开
    吐血整理的几十款小程序登陆界面【附完整代码】
    Vue2源码学习笔记 - 13.响应式原理—Watcher 类详解
    dreamweaver作业静态HTML网页设计——家乡海南旅游网站
    shell脚本监控CPU、磁盘、内存、网络流量
    基于go版本的LoraWAN Server 的470MHz频段的设置
    requests库编写的爬虫程序没有那么难!
    android嵌入式开发及实训答案,android面试简历模板
    【网络服务&数据库教程】11 MySQL 集群
    Matlab--微积分问题的计算机求解
  • 原文地址:https://www.cnblogs.com/Yesi/p/16590919.html