PDF.co Web API – PDF To XML API – VB.NET – Advanced Conversion Options With Rotated Input

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

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

ByteScoutWebApiExample.sln

      

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 15
VisualStudioVersion = 15.0.26730.10
MinimumVisualStudioVersion = 10.0.40219.1
Project("{F184B08F-C81C-45F6-A57F-5ABD9991F28F}") = "ByteScoutWebApiExample", "ByteScoutWebApiExample.vbproj", "{9B91124C-66C3-4BD9-B29E-168C1ABB15AC}"
EndProject
Global
	GlobalSection(SolutionConfigurationPlatforms) = preSolution
		Debug|Any CPU = Debug|Any CPU
		Release|Any CPU = Release|Any CPU
	EndGlobalSection
	GlobalSection(ProjectConfigurationPlatforms) = postSolution
		{9B91124C-66C3-4BD9-B29E-168C1ABB15AC}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
		{9B91124C-66C3-4BD9-B29E-168C1ABB15AC}.Debug|Any CPU.Build.0 = Debug|Any CPU
		{9B91124C-66C3-4BD9-B29E-168C1ABB15AC}.Release|Any CPU.ActiveCfg = Release|Any CPU
		{9B91124C-66C3-4BD9-B29E-168C1ABB15AC}.Release|Any CPU.Build.0 = Release|Any CPU
	EndGlobalSection
	GlobalSection(SolutionProperties) = preSolution
		HideSolutionNode = FALSE
	EndGlobalSection
	GlobalSection(ExtensibilityGlobals) = postSolution
		SolutionGuid = {4576C9BB-A42D-46A8-9198-7E2982E122FA}
	EndGlobalSection
EndGlobal

    

ByteScoutWebApiExample.vbproj

      
<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="15.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <Import Project="$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props" Condition="Exists('$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props')" />
  <PropertyGroup>
    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
    <ProjectGuid>{9B91124C-66C3-4BD9-B29E-168C1ABB15AC}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <StartupObject>ByteScoutWebApiExample.Module1</StartupObject>
    <RootNamespace>ByteScoutWebApiExample</RootNamespace>
    <AssemblyName>ByteScoutWebApiExample</AssemblyName>
    <FileAlignment>512</FileAlignment>
    <MyType>Console</MyType>
    <TargetFrameworkVersion>v4.0</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <DefineDebug>true</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\Debug\</OutputPath>
    <DocumentationFile>ByteScoutWebApiExample.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugType>pdbonly</DebugType>
    <DefineDebug>false</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DocumentationFile>ByteScoutWebApiExample.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup>
    <OptionExplicit>On</OptionExplicit>
  </PropertyGroup>
  <PropertyGroup>
    <OptionCompare>Binary</OptionCompare>
  </PropertyGroup>
  <PropertyGroup>
    <OptionStrict>Off</OptionStrict>
  </PropertyGroup>
  <PropertyGroup>
    <OptionInfer>On</OptionInfer>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Newtonsoft.Json, Version=10.0.0.0, Culture=neutral, PublicKeyToken=30ad4fe6b2a6aeed, processorArchitecture=MSIL">
      <HintPath>packages\Newtonsoft.Json.10.0.3\lib\net40\Newtonsoft.Json.dll</HintPath>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Deployment" />
    <Reference Include="System.Xml" />
    <Reference Include="System.Core" />
    <Reference Include="System.Xml.Linq" />
    <Reference Include="System.Data.DataSetExtensions" />
  </ItemGroup>
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <Import Include="System.Collections" />
    <Import Include="System.Collections.Generic" />
    <Import Include="System.Data" />
    <Import Include="System.Diagnostics" />
    <Import Include="System.Linq" />
    <Import Include="System.Xml.Linq" />
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Module1.vb" />
    <Compile Include="My Project\AssemblyInfo.vb" />
    <Compile Include="My Project\Application.Designer.vb">
      <AutoGen>True</AutoGen>
      <DependentUpon>Application.myapp</DependentUpon>
    </Compile>
    <Compile Include="My Project\Resources.Designer.vb">
      <AutoGen>True</AutoGen>
      <DesignTime>True</DesignTime>
      <DependentUpon>Resources.resx</DependentUpon>
    </Compile>
    <Compile Include="My Project\Settings.Designer.vb">
      <AutoGen>True</AutoGen>
      <DependentUpon>Settings.settings</DependentUpon>
      <DesignTimeSharedInput>True</DesignTimeSharedInput>
    </Compile>
  </ItemGroup>
  <ItemGroup>
    <EmbeddedResource Include="My Project\Resources.resx">
      <Generator>VbMyResourcesResXFileCodeGenerator</Generator>
      <LastGenOutput>Resources.Designer.vb</LastGenOutput>
      <CustomToolNamespace>My.Resources</CustomToolNamespace>
      <SubType>Designer</SubType>
    </EmbeddedResource>
  </ItemGroup>
  <ItemGroup>
    <None Include="My Project\Application.myapp">
      <Generator>MyApplicationCodeGenerator</Generator>
      <LastGenOutput>Application.Designer.vb</LastGenOutput>
    </None>
    <None Include="My Project\Settings.settings">
      <Generator>SettingsSingleFileGenerator</Generator>
      <CustomToolNamespace>My</CustomToolNamespace>
      <LastGenOutput>Settings.Designer.vb</LastGenOutput>
    </None>
    <None Include="packages.config" />
    <Content Include="sample-rotated.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
    <Content Include="profile.json">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.targets" />
</Project>
    

Module1.vb

      
Imports System.IO
Imports System.Net
Imports Newtonsoft.Json
Imports Newtonsoft.Json.Linq

Module Module1

    ' The authentication key (API Key).
    ' Get your own by registering at https://app.pdf.co/documentation/api
    Const API_KEY As String = "******************************"

    ' Source PDF file
    Const SourceFile As String = ".\sample-rotated.pdf"
    ' Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
    Const Pages As String = ""
    ' PDF document password. Leave empty for unprotected documents.
    Const Password As String = ""
    ' Destination XML file name
    Const DestinationFile As String = ".\result.xml"

    ' Some of advanced options available through profiles:
    ' (it can be single/double-quoted and contain comments.)
    ' {
    ' 	"profiles": [
    ' 		{
    ' 			"profile1": {
    ' 				"SaveImages": "None", // Whether to extract images. Values: "None", "Embed".
    ' 				"ImageFormat": "PNG", // Image format for extracted images. Values: "PNG", "JPEG", "GIF", "BMP".
    ' 				"SaveVectors": false, // Whether to extract vector objects (vertical and horizontal lines). Values: true / false
    ' 				"ExtractInvisibleText": true, // Invisible text extraction. Values: true / false
    ' 				"ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false
    ' 				"LineGroupingMode": "None", // Values: "None", "GroupByRows", "GroupByColumns", "JoinOrphanedRows"
    ' 				"ColumnDetectionMode": "ContentGroupsAndBorders", // Values: "ContentGroupsAndBorders", "ContentGroups", "Borders", "BorderedTables"
    ' 				"Unwrap": false, // Unwrap grouped text in table cells. Values: true / false
    ' 				"ShrinkMultipleSpaces": false, // Shrink multiple spaces in table cells that affect column detection. Values: true / false
    ' 				"DetectNewColumnBySpacesRatio": 1, // Spacing ratio that affects column detection.
    ' 				"CustomExtractionColumns": [ 0, 50, 150, 200, 250, 300 ], // Explicitly specify columns coordinates for table extraction.
    ' 				"CheckPermissions": true, // Ignore document permissions. Values: true / false
    ' 			}
    ' 		}
    ' 	]
    ' }

    ' Sample profile that sets advanced conversion options.
    ' Advanced options are properties of XMLExtractor class from ByteScout PDF Extractor SDK used in the back-end:
    ' https://cdn.bytescout.com/help/BytescoutPDFExtractorSDK/html/87ce5fa6-3143-167d-abbd-bc7b5e160fe5.htm

    'Valid RotationAngle values
    '0 - no rotation
    '1 - 90 degrees
    '2 - 180 degrees
    '3 - 270 degrees
    ReadOnly Profiles As String = File.ReadAllText("profile.json")

    Sub Main()

        ' Create standard .NET web client instance
        Dim webClient As WebClient = New WebClient()

        ' Set API Key
        webClient.Headers.Add("x-api-key", API_KEY)

        ' 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
        ' * If you already have a direct file URL, skip to the step 3.

        ' Prepare URL for `Get Presigned URL` API call
        Dim query As String = Uri.EscapeUriString(String.Format(
            "https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name={0}",
            Path.GetFileName(SourceFile)))

        Try
            ' Execute request
            Dim response As String = webClient.DownloadString(query)

            ' Parse JSON response
            Dim json As JObject = JObject.Parse(response)

            If json("error").ToObject(Of Boolean) = False Then
                ' Get URL to use for the file upload
                Dim uploadUrl As String = json("presignedUrl").ToString()
                ' Get URL of uploaded file to use with later API calls
                Dim uploadedFileUrl As String = json("url").ToString()

                ' 2. UPLOAD THE FILE TO CLOUD.

                webClient.Headers.Add("content-type", "application/octet-stream")
                webClient.UploadFile(uploadUrl, "PUT", SourceFile) ' You can use UploadData() instead if your file is byte array or Stream

                ' Set JSON content type
                webClient.Headers.Add("Content-Type", "application/json")

                ' 3. CONVERT UPLOADED PDF FILE TO XML

                ' Prepare URL for `PDF To XML` API call
                Dim url As String = "https://api.pdf.co/v1/pdf/convert/to/xml"

                ' Prepare requests params as JSON
                ' See documentation: https : //apidocs.pdf.co
                Dim parameters As New Dictionary(Of String, Object)
                parameters.Add("name", Path.GetFileName(DestinationFile))
                parameters.Add("password", Password)
                parameters.Add("pages", Pages)
                parameters.Add("url", uploadedFileUrl)
                parameters.Add("profiles", Profiles)

                ' Convert dictionary of params to JSON
                Dim jsonPayload As String = JsonConvert.SerializeObject(parameters)

                ' Execute POST request with JSON payload
                response = webClient.UploadString(url, jsonPayload)

                ' Parse JSON response
                json = JObject.Parse(response)

                If json("error").ToObject(Of Boolean) = False Then

                    ' Get URL of generated XML file
                    Dim resultFileUrl As String = json("url").ToString()

                    ' Download XML file
                    webClient.DownloadFile(resultFileUrl, DestinationFile)

                    Console.WriteLine("Generated XML file saved as ""{0}"" file.", DestinationFile)

                Else
                    Console.WriteLine(json("message").ToString())
                End If

            End If

        Catch ex As WebException
            Console.WriteLine(ex.ToString())
        End Try

        webClient.Dispose()


        Console.WriteLine()
        Console.WriteLine("Press any key...")
        Console.ReadKey()

    End Sub

End Module

    

packages.config

      
<?xml version="1.0" encoding="utf-8"?>
<packages>
  <package id="Newtonsoft.Json" version="10.0.3" targetFramework="net40" />
</packages>
    

profile.json

      
{
  "profiles": [
    {
      "profile1": {
        "RotationAngle": 1
      }
    }
  ]
}
    

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

See also:

• Explore Documentation
• Explore Source Code Samples
• Watch Video Course

ON-DEMAND REST WEB API

Get Your API Key

See also:

• Web API Docs
• Learn About Security
• Explore Source Code Samples