/// <summary>
/// Extracts the text from HTML.
/// </summary>
/// <param name="htmlFileName">Name of the HTML file.</param>
public static void ExtractTextFromHtml(string htmlFileName)
{
    using (Vintasoft.Imaging.ImageCollection images = new Vintasoft.Imaging.ImageCollection())
    {
        // open HTML document
        images.Add(htmlFileName);

        try
        {
            // page number
            int pageNumber = 1;
            
            // for each page of HTML dcoument
            foreach (Vintasoft.Imaging.VintasoftImage image in images)
            {
                // write page number
                System.Console.WriteLine("\tPage Number: {0}", pageNumber++);
                System.Console.WriteLine();
                System.Console.WriteLine();

                // find text region metadata
                Vintasoft.Imaging.Metadata.TextRegionMetadata textRegionMetadata =
                    image.Metadata.MetadataTree.FindChildNode<Vintasoft.Imaging.Metadata.TextRegionMetadata>();

                // if current page has text content
                if (textRegionMetadata != null)
                {
                    // get text region
                    Vintasoft.Imaging.Text.TextRegion textRegion = textRegionMetadata.GetTextRegion();
                    // write page text content
                    System.Console.Write(textRegion.TextContent);
                }

                // if page separator must be added between pages
                if (pageNumber < images.Count)
                {
                    System.Console.WriteLine();
                    System.Console.WriteLine();
                    System.Console.WriteLine();
                }
            }
        }
        finally
        {
            // clear and dispose images
            images.ClearAndDisposeItems();
        }
    }
}

''' <summary>
''' Extracts the text from HTML.
''' </summary>
''' <param name="htmlFileName">Name of the HTML file.</param>
Public Shared Sub ExtractTextFromHtml(htmlFileName As String)
    Using images As New Vintasoft.Imaging.ImageCollection()
        ' open HTML document
        images.Add(htmlFileName)

        Try
            ' page number
            Dim pageNumber As Integer = 1

            ' for each page of HTML dcoument
            For Each image As Vintasoft.Imaging.VintasoftImage In images
                ' write page number
                System.Console.WriteLine(vbTab & "Page Number: {0}", System.Math.Max(System.Threading.Interlocked.Increment(pageNumber),pageNumber - 1))
                System.Console.WriteLine()
                System.Console.WriteLine()

                ' find text region metadata
                Dim textRegionMetadata As Vintasoft.Imaging.Metadata.TextRegionMetadata = image.Metadata.MetadataTree.FindChildNode(Of Vintasoft.Imaging.Metadata.TextRegionMetadata)()

                ' if current page has text content
                If textRegionMetadata IsNot Nothing Then
                    ' get text region
                    Dim textRegion As Vintasoft.Imaging.Text.TextRegion = textRegionMetadata.GetTextRegion()
                    ' write page text content
                    System.Console.Write(textRegion.TextContent)
                End If

                ' if page separator must be added between pages
                If pageNumber < images.Count Then
                    System.Console.WriteLine()
                    System.Console.WriteLine()
                    System.Console.WriteLine()
                End If
            Next
        Finally
            ' clear and dispose images
            images.ClearAndDisposeItems()
        End Try
    End Using
End Sub