Como converter PDF para HTML em C# com IronPDF

using IronPdf;
using System;

PdfDocument pdf = PdfDocument.FromFile("sample.pdf");

// Convert PDF to HTML string
string html = pdf.ToHtmlString();
Console.WriteLine(html);

// Convert PDF to HTML file
pdf.SaveAsHtml("myHtml.html");

Imports IronPdf
Imports System

Dim pdf As PdfDocument = PdfDocument.FromFile("sample.pdf")

' Convert PDF to HTML string
Dim html As String = pdf.ToHtmlString()
Console.WriteLine(html)

' Convert PDF to HTML file
pdf.SaveAsHtml("myHtml.html")

using IronPdf;
using IronSoftware.Drawing;
using System;

PdfDocument pdf = PdfDocument.FromFile("sample.pdf");

// PDF to HTML configuration options
HtmlFormatOptions htmlformat = new HtmlFormatOptions();
htmlformat.BackgroundColor = Color.White;
htmlformat.PdfPageMargin = 10;
htmlformat.H1Color = Color.Blue;
htmlformat.H1FontSize = 25;
htmlformat.H1TextAlignment = TextAlignment.Center;

// Convert PDF to HTML string
string html = pdf.ToHtmlString();
Console.WriteLine(html);

// Convert PDF to HTML file
pdf.SaveAsHtml("myHtmlConfigured.html", true, "Hello World", htmlFormatOptions: htmlformat);

Imports IronPdf
Imports IronSoftware.Drawing
Imports System

Dim pdf As PdfDocument = PdfDocument.FromFile("sample.pdf")

' PDF to HTML configuration options
Dim htmlformat As New HtmlFormatOptions()
htmlformat.BackgroundColor = Color.White
htmlformat.PdfPageMargin = 10
htmlformat.H1Color = Color.Blue
htmlformat.H1FontSize = 25
htmlformat.H1TextAlignment = TextAlignment.Center

' Convert PDF to HTML string
Dim html As String = pdf.ToHtmlString()
Console.WriteLine(html)

' Convert PDF to HTML file
pdf.SaveAsHtml("myHtmlConfigured.html", True, "Hello World", htmlFormatOptions:=htmlformat)

using IronPdf;
using System.IO;

public class BatchPdfToHtmlConverter
{
    public static void ConvertPdfDirectory(string inputDirectory, string outputDirectory)
    {
        // Ensure output directory exists
        Directory.CreateDirectory(outputDirectory);

        // Configure HTML output settings once for consistency
        HtmlFormatOptions formatOptions = new HtmlFormatOptions
        {
            BackgroundColor = Color.WhiteSmoke,
            PdfPageMargin = 15,
            H1FontSize = 28,
            H1TextAlignment = TextAlignment.Left
        };

        // Process all PDF files in the directory
        string[] pdfFiles = Directory.GetFiles(inputDirectory, "*.pdf");

        foreach (string pdfPath in pdfFiles)
        {
            try
            {
                // Load PDF document
                PdfDocument pdf = PdfDocument.FromFile(pdfPath);

                // Generate output filename
                string fileName = Path.GetFileNameWithoutExtension(pdfPath);
                string htmlPath = Path.Combine(outputDirectory, $"{fileName}.html");

                // Convert and save as HTML with consistent formatting
                pdf.SaveAsHtml(htmlPath, true, fileName, htmlFormatOptions: formatOptions);

                Console.WriteLine($"Converted: {fileName}.pdf → {fileName}.html");
            }
            catch (Exception ex)
            {
                Console.WriteLine($"Error converting {pdfPath}: {ex.Message}");
            }
        }
    }
}

Imports IronPdf
Imports System.IO

Public Class BatchPdfToHtmlConverter
    Public Shared Sub ConvertPdfDirectory(inputDirectory As String, outputDirectory As String)
        ' Ensure output directory exists
        Directory.CreateDirectory(outputDirectory)

        ' Configure HTML output settings once for consistency
        Dim formatOptions As New HtmlFormatOptions With {
            .BackgroundColor = Color.WhiteSmoke,
            .PdfPageMargin = 15,
            .H1FontSize = 28,
            .H1TextAlignment = TextAlignment.Left
        }

        ' Process all PDF files in the directory
        Dim pdfFiles As String() = Directory.GetFiles(inputDirectory, "*.pdf")

        For Each pdfPath As String In pdfFiles
            Try
                ' Load PDF document
                Dim pdf As PdfDocument = PdfDocument.FromFile(pdfPath)

                ' Generate output filename
                Dim fileName As String = Path.GetFileNameWithoutExtension(pdfPath)
                Dim htmlPath As String = Path.Combine(outputDirectory, $"{fileName}.html")

                ' Convert and save as HTML with consistent formatting
                pdf.SaveAsHtml(htmlPath, True, fileName, htmlFormatOptions:=formatOptions)

                Console.WriteLine($"Converted: {fileName}.pdf → {fileName}.html")
            Catch ex As Exception
                Console.WriteLine($"Error converting {pdfPath}: {ex.Message}")
            End Try
        Next
    End Sub
End Class