Get text coordinates Leave feedback

Use the ExtractText property of the ViewInfoOptions class to get the text contained in a source document and its coordinates. Then you can use this data to add a selectable text over the image or to implement a text search in image-based rendering.

The following code snippet shows how to retrieve and print out text (lines/words/characters) on each document page with coordinates:

using System;
using GroupDocs.Viewer;
using GroupDocs.Viewer.Options;
using GroupDocs.Viewer.Results;
// ...

using (Viewer viewer = new Viewer("sample.docx"))
{
    // Get the file information and extract it text.
    bool extractText = true;
    ViewInfoOptions viewInfoOptions = ViewInfoOptions.ForPngView(extractText);
    ViewInfo viewInfo = viewer.GetViewInfo(viewInfoOptions);

    // Display the file information and text.
    foreach (Page page in viewInfo.Pages)
    {
        Console.WriteLine($"Page: {page.Number}");
        Console.WriteLine("Text lines/words/characters:");

        foreach (Line line in page.Lines)
        {
            Console.WriteLine(line);
            foreach (Word word in line.Words)
            {
                Console.WriteLine($"\t{word}");
                foreach (Character character in word.Characters)
                {
                    Console.WriteLine($"\t\t{character}");
                }
            }
        }
    }
}

VB.NET

Imports System
Imports GroupDocs.Viewer
Imports GroupDocs.Viewer.Options
Imports GroupDocs.Viewer.Results
' ...

Module Program
    Sub Main(args As String())
        Using viewer As Viewer = New Viewer("sample.docx")
            ' Get the file information and extract it text.
            Dim extractText As Boolean = True
            Dim viewInfoOptions As ViewInfoOptions = ViewInfoOptions.ForPngView(extractText)
            Dim viewInfo As ViewInfo = viewer.GetViewInfo(viewInfoOptions)
        
            ' Display the file information and text.
            For Each page As Page In viewInfo.Pages
                Console.WriteLine($"Page: {page.Number}")
                Console.WriteLine("Text lines/words/characters:")
        
                For Each line As Line In page.Lines
                    Console.WriteLine(line)
                    For Each word As Word In line.Words
                        Console.WriteLine($"	{word}")
                        For Each character As Character In word.Characters
                            Console.WriteLine($"		{character}")
                        Next
                    Next
                Next
            Next
        End Using
    End Sub
End Module

The following image shows a sample console output:

We value your opinion. Your feedback will help us improve our documentation.

Get text coordinates Leave feedback

Was this page helpful?

Any additional feedback you'd like to share with us?

Please tell us how we can improve this page.

Thank you for your feedback!