Extract Tagged Content from PDF

In this article you will learn how to to extract tagged content PDF document using C#.

The following code snippet also work with Aspose.PDF.Drawing library.

Getting Tagged PDF Content

In order to get content of PDF Document with Tagged Text, Aspose.PDF offers TaggedContent property of Document class.

Following code snippet shows how to get content of a PDF document with Tagged Text:

.NET Core 3.1

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void GetTaggedContent()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_WorkingDocuments();

    // Create PDF Document
    using (var document = new Aspose.Pdf.Document())
    {
        // Get Content for work with Tagged PDF
        Aspose.Pdf.Tagged.ITaggedContent taggedContent = document.TaggedContent;

        // Work with Tagged PDF content
        // Set Title and Language for Document
        taggedContent.SetTitle("Simple Tagged Pdf Document");
        taggedContent.SetLanguage("en-US");

        // Save Tagged PDF Document
        document.Save(dataDir + "TaggedPDFContent_out.pdf");
    }
}

.NET 8

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void GetTaggedContent()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_WorkingDocuments();

    // Create PDF Document
    using var document = new Aspose.Pdf.Document();

    // Get Content for work with TaggedPdf
    Aspose.Pdf.Tagged.ITaggedContent taggedContent = document.TaggedContent;

    // Work with Tagged PDF content
    // Set Title and Language for Document
    taggedContent.SetTitle("Simple Tagged Pdf Document");
    taggedContent.SetLanguage("en-US");

    // Save Tagged PDF Document
    document.Save(dataDir + "TaggedPDFContent_out.pdf");
}

Getting Root Structure

In order to get the root structure of Tagged PDF Document, Aspose.PDF offers StructTreeRootElement property of ITaggedContent interface and StructureElement. Following code snippet shows how to get the root structure of Tagged PDF Document:

.NET Core 3.1

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void GetRootStructure()
{
    // Create PDF Document
    using (var document = new Aspose.Pdf.Document())
    {
        // Get Content for work with Tagged PDF
        Aspose.Pdf.Tagged.ITaggedContent taggedContent = document.TaggedContent;

        // Set Title and Language for Document
        taggedContent.SetTitle("Tagged Pdf Document");
        taggedContent.SetLanguage("en-US");

        // Properties StructTreeRootElement and RootElement are used for access to
        // StructTreeRoot object of pdf document and to root structure element (Document structure element).
        Aspose.Pdf.LogicalStructure.StructTreeRootElement structTreeRootElement = taggedContent.StructTreeRootElement;
        Aspose.Pdf.LogicalStructure.StructureElement rootElement = taggedContent.RootElement;
    }
}

.NET 8

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void GetRootStructure()
{
    // Create PDF Document
    using var document = new Aspose.Pdf.Document();

    // Get Content for work with Tagged PDF
    Aspose.Pdf.Tagged.ITaggedContent taggedContent = document.TaggedContent;

    // Set Title and Language for Document
    taggedContent.SetTitle("Tagged Pdf Document");
    taggedContent.SetLanguage("en-US");

    // Properties StructTreeRootElement and RootElement are used for access to
    // StructTreeRoot object of pdf document and to root structure element (Document structure element).
    Aspose.Pdf.LogicalStructure.StructTreeRootElement structTreeRootElement = taggedContent.StructTreeRootElement;
    Aspose.Pdf.LogicalStructure.StructureElement rootElement = taggedContent.RootElement;
}

Accessing Child Elements

In order to access child elements of a Tagged PDF Document, Aspose.PDF offers ElementList class. Following code snippet shows how to access child elements of a Tagged PDF Document:

.NET Core 3.1

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void AccessChildElements()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_WorkingDocuments();

    // Open PDF Document
    using (var document = new Aspose.Pdf.Document(dataDir + "StructureElementsTree.pdf"))
    {
        // Get Content for work with Tagged PDF
        Aspose.Pdf.Tagged.ITaggedContent taggedContent = document.TaggedContent;

        // Access to root element(s)
        Aspose.Pdf.LogicalStructure.ElementList elementList = taggedContent.StructTreeRootElement.ChildElements;

        foreach (Aspose.Pdf.LogicalStructure.Element element in elementList)
        {
            if (element is Aspose.Pdf.LogicalStructure.StructureElement)
            {
                var structureElement = element as Aspose.Pdf.LogicalStructure.StructureElement;

                // Get properties
                string title = structureElement.Title;
                string language = structureElement.Language;
                string actualText = structureElement.ActualText;
                string expansionText = structureElement.ExpansionText;
                string alternativeText = structureElement.AlternativeText;
            }
        }

        // Access to child elements of first element in root element
        elementList = taggedContent.RootElement.ChildElements[1].ChildElements;

        foreach (Aspose.Pdf.LogicalStructure.Element element in elementList)
        {
            if (element is Aspose.Pdf.LogicalStructure.StructureElement)
            {
                var structureElement = element as Aspose.Pdf.LogicalStructure.StructureElement;

                // Set properties
                structureElement.Title = "title";
                structureElement.Language = "fr-FR";
                structureElement.ActualText = "actual text";
                structureElement.ExpansionText = "exp";
                structureElement.AlternativeText = "alt";
            }
        }

        // Save Tagged PDF Document
        document.Save(dataDir + "AccessChildElements_out.pdf");
    }
}

.NET 8

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void AccessChildElements()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_WorkingDocuments();

    // Open PDF Document
    using var document = new Aspose.Pdf.Document(dataDir + "StructureElementsTree.pdf");

    // Get Content for work with Tagged PDF
    Aspose.Pdf.Tagged.ITaggedContent taggedContent = document.TaggedContent;

    // Access to root element(s)
    Aspose.Pdf.LogicalStructure.ElementList elementList = taggedContent.StructTreeRootElement.ChildElements;

    foreach (Aspose.Pdf.LogicalStructure.Element element in elementList)
    {
        if (element is Aspose.Pdf.LogicalStructure.StructureElement)
        {
            var structureElement = element as Aspose.Pdf.LogicalStructure.StructureElement;

            // Get properties
            string title = structureElement.Title;
            string language = structureElement.Language;
            string actualText = structureElement.ActualText;
            string expansionText = structureElement.ExpansionText;
            string alternativeText = structureElement.AlternativeText;
        }
    }

    // Access to child elements of first element in root element
    elementList = taggedContent.RootElement.ChildElements[1].ChildElements;

    foreach (Aspose.Pdf.LogicalStructure.Element element in elementList)
    {
        if (element is Aspose.Pdf.LogicalStructure.StructureElement)
        {
            var structureElement = element as Aspose.Pdf.LogicalStructure.StructureElement;

            // Set properties
            structureElement.Title = "title";
            structureElement.Language = "fr-FR";
            structureElement.ActualText = "actual text";
            structureElement.ExpansionText = "exp";
            structureElement.AlternativeText = "alt";
        }
    }

    // Save Tagged PDF Document
    document.Save(dataDir + "AccessChildElements_out.pdf");
}

Tagging Images in Existing PDF

In order to tag images in existing PDF document, Aspose.PDF offers FindElements method of StructureElement class. You can add alternative text for figures using AlternativeText property of FigureElement class.

Following code snippet shows how to tag images in existing PDF document:

.NET Core 3.1

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void TagImages()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_WorkingDocuments();

    // Open PDF document
    using (var document1 = new Aspose.Pdf.Document(dataDir + "TH.pdf"))
    {
        // Gets tagged content and root structure element
        Aspose.Pdf.Tagged.ITaggedContent taggedContent = document1.TaggedContent;
        Aspose.Pdf.LogicalStructure.StructureElement rootElement = taggedContent.RootElement;

        // Set title for tagged PDF document
        taggedContent.SetTitle("Document with images");

        foreach (Aspose.Pdf.LogicalStructure.FigureElement figureElement in rootElement.FindElements<Aspose.Pdf.LogicalStructure.FigureElement>(true))
        {
            // Set AlternativeText for Figure
            figureElement.AlternativeText = "Figure alternative text (technique 2)";

            // Create and Set BBox Attribute
            var bboxAttribute = new Aspose.Pdf.LogicalStructure.StructureAttribute(Aspose.Pdf.LogicalStructure.AttributeKey.BBox);
            bboxAttribute.SetRectangleValue(new Aspose.Pdf.Rectangle(0.0, 0.0, 100.0, 100.0));

            Aspose.Pdf.LogicalStructure.StructureAttributes figureLayoutAttributes = figureElement.Attributes.GetAttributes(Aspose.Pdf.LogicalStructure.AttributeOwnerStandard.Layout);
            figureLayoutAttributes.SetAttribute(bboxAttribute);
        }

        // Move Span Element into Paragraph (find wrong span and paragraph in first TD)
        Aspose.Pdf.LogicalStructure.TableElement tableElement = rootElement.FindElements<Aspose.Pdf.LogicalStructure.TableElement>(true)[0];
        Aspose.Pdf.LogicalStructure.SpanElement spanElement = tableElement.FindElements<Aspose.Pdf.LogicalStructure.SpanElement>(true)[0];
        Aspose.Pdf.LogicalStructure.TableTDElement firstTdElement = tableElement.FindElements<Aspose.Pdf.LogicalStructure.TableTDElement>(true)[0];
        Aspose.Pdf.LogicalStructure.ParagraphElement paragraph = firstTdElement.FindElements<Aspose.Pdf.LogicalStructure.ParagraphElement>(true)[0];

        // Move Span Element into Paragraph
        spanElement.ChangeParentElement(paragraph);

        // Save PDF document
        document1.Save(dataDir + "TH_out.pdf");
    }

    // Check PDF/UA Compliance for out document
    using (var document2 = new Aspose.Pdf.Document(dataDir + "TH_out.pdf"))
    {
        bool isPdfUaCompliance = document2.Validate(dataDir + "TH_out.xml", Aspose.Pdf.PdfFormat.PDF_UA_1);
        Console.WriteLine(String.Format("PDF/UA compliance: {0}", isPdfUaCompliance));
    }
}

.NET 8

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void TagImages()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_WorkingDocuments();

    // Open PDF document
    using var document1 = new Aspose.Pdf.Document(dataDir + "TH.pdf");

    // Gets tagged content and root structure element
    Aspose.Pdf.Tagged.ITaggedContent taggedContent = document1.TaggedContent;
    Aspose.Pdf.LogicalStructure.StructureElement rootElement = taggedContent.RootElement;

    // Set title for tagged PDF document
    taggedContent.SetTitle("Document with images");

    foreach (Aspose.Pdf.LogicalStructure.FigureElement figureElement in rootElement.FindElements<Aspose.Pdf.LogicalStructure.FigureElement>(true))
    {
        // Set AlternativeText for Figure
        figureElement.AlternativeText = "Figure alternative text (technique 2)";

        // Create and Set BBox Attribute
        var bboxAttribute = new Aspose.Pdf.LogicalStructure.StructureAttribute(Aspose.Pdf.LogicalStructure.AttributeKey.BBox);
        bboxAttribute.SetRectangleValue(new Aspose.Pdf.Rectangle(0.0, 0.0, 100.0, 100.0));

        Aspose.Pdf.LogicalStructure.StructureAttributes figureLayoutAttributes = figureElement.Attributes.GetAttributes(Aspose.Pdf.LogicalStructure.AttributeOwnerStandard.Layout);
        figureLayoutAttributes.SetAttribute(bboxAttribute);
    }

    // Move Span Element into Paragraph (find wrong span and paragraph in first TD)
    Aspose.Pdf.LogicalStructure.TableElement tableElement = rootElement.FindElements<Aspose.Pdf.LogicalStructure.TableElement>(true)[0];
    Aspose.Pdf.LogicalStructure.SpanElement spanElement = tableElement.FindElements<Aspose.Pdf.LogicalStructure.SpanElement>(true)[0];
    Aspose.Pdf.LogicalStructure.TableTDElement firstTdElement = tableElement.FindElements<Aspose.Pdf.LogicalStructure.TableTDElement>(true)[0];
    Aspose.Pdf.LogicalStructure.ParagraphElement paragraph = firstTdElement.FindElements<Aspose.Pdf.LogicalStructure.ParagraphElement>(true)[0];

    // Move Span Element into Paragraph
    spanElement.ChangeParentElement(paragraph);

    // Save PDF document
    document1.Save(dataDir + "TH_out.pdf");

    // Check PDF/UA Compliance for out document
    using var document2 = new Aspose.Pdf.Document(dataDir + "TH_out.pdf");

    bool isPdfUaCompliance = document2.Validate(dataDir + "TH_out.pdf", Aspose.Pdf.PdfFormat.PDF_UA_1);
    Console.WriteLine(String.Format("PDF/UA compliance: {0}", isPdfUaCompliance));
}