PDF to text API in VB.NET using PDF.co Web API

How To: tutorial on PDF to text API in VB.NET

Source code documentation samples provide quick and easy way to add a required functionality into your application. PDF.co Web API was made to help with PDF to text API in VB.NET. PDF.co Web API is the Rest API that provides set of data extraction functions, tools for documents manipulation, splitting and merging of pdf files. Includes built-in OCR, images recognition, can generate and read barcodes from images, scans and pdf.

VB.NET, code samples for VB.NET, developers help to speed up the application development and writing a code when using PDF.co Web API. In order to implement this functionality, you should copy and paste code below into your app using code editor. Then compile and run your application. This basic programming language sample code for VB.NET will do the whole work for you in implementing PDF to text API in your app.

On our website you may get trial version of PDF.co Web API for free. Source code samples are included to help you with your VB.NET application.

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" />
  </ItemGroup>
  <ItemGroup>
    <None Include="packages.config" />
    <None Include="profile.json">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </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 = "***********************************"

    ' Direct URL of source PDF file.
    Const SourceFileUrl As String = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/sample.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 TXT file name
	const DestinationFile as string = ".\result.txt"

	' Some of advanced options available through profiles:
	' (JSON can be single/double-quoted and contain comments.)
	' {
	'     "profiles": [
	'         {
	'             "profile1": {                
	'                 "ExtractInvisibleText": true, // Invisible text extraction. Values: true / false
	'                 "ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false
	'                 "ExtractAnnotations": true, // Whether to extract PDF annotations.
	'                 "CheckPermissions": true, // Ignore document permissions. Values: true / false
	'                 "DetectNewColumnBySpacesRatio": 1.2, // A ratio affecting number of spaces between words. 
	'             }
	'         }
	'     ]
	' }

    ' Sample profile that sets advanced conversion options
    ' Advanced options are properties of TextExtractor class from ByteScout Text Extractor SDK used in the back-end:
    ' https://cdn.bytescout.com/help/BytescoutPDFExtractorSDK/html/8a2bae5a-346f-8338-b5aa-6f3522dca0d4.htm
    ReadOnly Profiles = 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)

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

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

        ' 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", SourceFileUrl)
		parameters.Add("profiles", Profiles)

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

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

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

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

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

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

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

			Else
				Console.WriteLine(json("message").ToString())
			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": {
        "TrimSpaces": "False",
        "PreserveFormattingOnTextExtraction": "True",
        "Unwrap": "True"
      }
    }
  ]
}

VIDEO

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

See also:

ON-DEMAND REST WEB API

Get Your API Key

See also: