Link Search Menu Expand Document
ByteScout Docs

Return to previous pageExplore PDF To HTML SDK

Getting Started in ASP.NET

The following sample demonstrates how to convert PDF document to HTML in ASP.NET using Bytescout PDF To HTML SDK

C#
Copy
<legacyBold xmlns="http://ddue.schemas.microsoft.com/authoring/2003/5">Default.aspx:</legacyBold>
<%@ Page Language="C#" AutoEventWireup="true" CodeBehind="Default.aspx.cs" Inherits="ExtractHTML._Default" %>

<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">

<html xmlns="http://www.w3.org/1999/xhtml" >
<head runat="server">
    <title>Untitled Page</title>
</head>
<body>
    <form id="form1" runat="server">
    <div>

    </div>
    </form>
</body>
</html>

        <legacyBold xmlns="http://ddue.schemas.microsoft.com/authoring/2003/5">Default.aspx.cs:</legacyBold>
using System;
using Bytescout.PDF2HTML;

namespace ExtractHTML
{
    public partial class _Default : System.Web.UI.Page
    {
        protected void Page_Load(object sender, EventArgs e)
        {
            // This test file will be copied to the project directory on the pre-build event (see the project properties).
            String inputFile = Server.MapPath("sample2.pdf");

            // Create Bytescout.PDF2HTML.HTMLExtractor instance
            HTMLExtractor extractor = new HTMLExtractor();
            extractor.RegistrationName = "demo";
            extractor.RegistrationKey = "demo";

            // Set HTML with CSS extraction mode
            extractor.ExtractionMode = HTMLExtractionMode.HTMLWithCSS;

            // Load sample PDF document
            extractor.LoadDocumentFromFile(inputFile);

            Response.Clear();
            Response.ContentType = "text/html";

            // Save extracted text to output stream
            extractor.SaveHtmlToStream(Response.OutputStream);

            Response.End();

            extractor.Dispose();
        }
    }
}