Extract Text and Images from OneNote Documents using C#

ExtractTextAndImagesFromOneNote_CSharp.md

Learn how to extract text and images from OneNote documents using C#.

The following topics are covered in this article:

1. OneNote Text and Image Extractor C# API
2. Extract All the Text from OneNote Documents
3. Get Text from Specific Pages of OneNote Documents
4. Extract Images from OneNote Documents

ExtractTextAndImagesFromOneNote_CSharp_ExtractAll.cs

// This code example demonstrates how to extract all the text from OneNote document.
// Load the document into Aspose.Note.
Document oneFile = new Document(@"C:\Files\Note\Aspose.one");

// Retrieve text
string text = string.Join(Environment.NewLine, oneFile.GetChildNodes<RichText>().Select(e => e.Text)) + Environment.NewLine;

// Print text
Console.WriteLine(text);

ExtractTextAndImagesFromOneNote_CSharp_ExtractFromPages.cs

// This code example demonstrates how to get text from a specific page.
// Get First page from list of page nodes
var page = oneFile.GetChildNodes<Page>().FirstOrDefault();

if (page != null)
{
    // Retrieve text
    IList<RichText> textNodes = page.GetChildNodes<RichText>();

    foreach (RichText t in textNodes)
    {
        // Print text
        Console.WriteLine(t.Text);
    }
}

ExtractTextAndImagesFromOneNote_CSharp_ExtractImages.cs

// This code example demonstrates how to extract all the images.
// Get all Image nodes
IList<Aspose.Note.Image> nodes = oneFile.GetChildNodes<Aspose.Note.Image>();

foreach (Aspose.Note.Image image in nodes)
{
    Console.WriteLine("Width: {0}", image.Width);
    Console.WriteLine("Height: {0}", image.Height);
    Console.WriteLine("OriginalWidth: {0}", image.OriginalWidth);
    Console.WriteLine("OriginalHeight: {0}", image.OriginalHeight);
    Console.WriteLine("FileName: {0}", image.FileName);
    Console.WriteLine("LastModifiedTime: {0}", image.LastModifiedTime);

    using (MemoryStream stream = new MemoryStream(image.Bytes))
    {
        using (Bitmap bitMap = new Bitmap(stream))
        {
            // Save image bytes to a file
            bitMap.Save(String.Format(@"C:\Files\Note\" + "{0}", Path.GetFileName(image.FileName)));
        }
    }

    Console.WriteLine("Image saved!");
    Console.WriteLine();
}