ByteScout PDF To HTML SDK – VB.NET – Download and Process file

Home
/
Articles
/
ByteScout PDF To HTML SDK – VB.NET – Download and Process file

printable version:
ByteScout-PDF-To-HTML-SDK-VB-NET-Download-and-Process-file.pdf

download and process file in VB.NET using ByteScout PDF To HTML SDK

What is ByteScout PDF To HTML SDK? It is the SDK for PDF to HTML conversin. Generates static HTML version of input PDF and reconstructs all visual layout, text positions, vector and raster drawings, images, and form elements. Generated HTML requires no special software and can be viewed in any Internet browser.

On-demand (REST Web API) version:
Web API (on-demand version)

On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)

ExtractHTMLFromPage.VS2005.vbproj

      <Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <PropertyGroup>
    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
    <ProductVersion>8.0.50727</ProductVersion>
    <SchemaVersion>2.0</SchemaVersion>
    <ProjectGuid>{34509168-5D95-4323-8808-2A10FDE4E9A9}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <RootNamespace>ExtractHTMLFromPage</RootNamespace>
    <AssemblyName>ExtractHTMLFromPage</AssemblyName>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <Optimize>false</Optimize>
    <OutputPath>bin\Debug\</OutputPath>
    <DefineConstants>DEBUG,TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <DebugType>pdbonly</DebugType>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DefineConstants>TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <Import Project="$(MSBuildBinPath)\Microsoft.VisualBasic.Targets" />
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <Reference Include="Bytescout.PDF2HTML, Version=1.0.0.12, Culture=neutral, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
    <Compile Include="Program.vb" />
    <Compile Include="Properties\AssemblyInfo.vb" />
  </ItemGroup>
  <ItemGroup>
  </ItemGroup>
</Project>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF To HTML SDK Home Page

Explore ByteScout PDF To HTML SDK Documentation

Explore Samples

Sign Up for ByteScout PDF To HTML SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

ExtractHTMLFromPage.VS2008.vbproj

      <Project ToolsVersion="3.5" DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <PropertyGroup>
    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
    <ProductVersion>8.0.50727</ProductVersion>
    <SchemaVersion>2.0</SchemaVersion>
    <ProjectGuid>{34509168-5D95-4323-8808-2A10FDE4E9A9}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <RootNamespace>ExtractHTMLFromPage</RootNamespace>
    <AssemblyName>ExtractHTMLFromPage</AssemblyName>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <Optimize>false</Optimize>
    <OutputPath>bin\Debug\</OutputPath>
    <DefineConstants>DEBUG,TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <DebugType>pdbonly</DebugType>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DefineConstants>TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <Import Project="$(MSBuildBinPath)\Microsoft.VisualBasic.Targets" />
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <Reference Include="Bytescout.PDF2HTML, Version=1.0.0.12, Culture=neutral, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
    <Compile Include="Program.vb" />
    <Compile Include="Properties\AssemblyInfo.vb" />
  </ItemGroup>
  <ItemGroup>
  </ItemGroup>
</Project>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF To HTML SDK Home Page

Explore ByteScout PDF To HTML SDK Documentation

Explore Samples

Sign Up for ByteScout PDF To HTML SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

ExtractHTMLFromPage.VS2010.vbproj

      <Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003" ToolsVersion="4.0">
  <PropertyGroup>
    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
    <ProductVersion>
    </ProductVersion>
    <SchemaVersion>2.0</SchemaVersion>
    <ProjectGuid>{34509168-5D95-4323-8808-2A10FDE4E9A9}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <RootNamespace>ExtractHTMLFromPage</RootNamespace>
    <AssemblyName>ExtractHTMLFromPage</AssemblyName>
    <OldToolsVersion>3.5</OldToolsVersion>
    <TargetFrameworkVersion>v4.0</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <Optimize>false</Optimize>
    <OutputPath>bin\Debug\</OutputPath>
    <DefineConstants>DEBUG,TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <DebugType>pdbonly</DebugType>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DefineConstants>TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.Targets" />
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <Reference Include="Bytescout.PDF2HTML, Version=1.0.0.12, Culture=neutral, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
    <Compile Include="Program.vb" />
    <Compile Include="Properties\AssemblyInfo.vb" />
  </ItemGroup>
  <ItemGroup>
  </ItemGroup>
</Project>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF To HTML SDK Home Page

Explore ByteScout PDF To HTML SDK Documentation

Explore Samples

Sign Up for ByteScout PDF To HTML SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

Program.vb

      Imports System.IO
Imports Bytescout.PDF2HTML

Class Program
    Friend Shared Sub Main(args As String())

        ' Create Bytescout.PDF2HTML.HTMLExtractor instance
        Dim extractor As New HTMLExtractor()
        extractor.RegistrationName = "demo"
        extractor.RegistrationKey = "demo"

        ' Set plain HTML extraction mode
        extractor.ExtractionMode = HTMLExtractionMode.PlainHTML

        ' Input file Url
        Dim inputUrl As String = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/sample.pdf"

        ' Get Input Stream
        Dim inpStream As Stream = GetStreamFromUrl(inputUrl)

        ' Load sample PDF document stream
        extractor.LoadDocumentFromStream(inpStream)

        ' Convert 1-st page to HTML and save it to file
        extractor.SaveHtmlPageToFile(0, "output.html")

        ' Cleanup
        extractor.Dispose()

        ' Open output file in default associated application
        System.Diagnostics.Process.Start("output.html")

    End Sub

    ''' <summary>
    ''' Get stream from Url
    ''' </summary>
    Private Shared Function GetStreamFromUrl(ByVal url As String) As Stream

        Dim oData As Byte() = Nothing

        Using wc As New System.Net.WebClient()
            oData = wc.DownloadData(url)
        End Using

        Return New MemoryStream(oData)

    End Function


End Class