ByteScout Cloud API Server – PDF Text Search API – VB.NET – PDF Text Search from URL

Home
/
Articles
/
ByteScout Cloud API Server – PDF Text Search API – VB.NET – PDF Text Search from URL

printable version:
ByteScout-Cloud-API-Server-VB-NET-PDF-Text-Search-from-URL.pdf

How to PDF text search API in VB.NET and ByteScout Cloud API Server

What is ByteScout Cloud API Server? It is API server that is ready to use and can be installed and deployed in less than 30 minutes on your own Windows server or server in a cloud. It can save data and files on your local server-based file storage or in Amazon AWS S3 storage. Data is processed solely on the API server and is powered by ByteScout engine, no cloud services or Internet connection is required for data processing..

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" />
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.targets" />
</Project>

Module1.vb

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

' Please NOTE: In this sample we're assuming Cloud Api Server is hosted at "https://localhost". 
' If it's not then please replace this with with your hosting url.
Module Module1

    ' 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 = ""

    ' Search string.
    Const SearchString As String = "\d{1,}\.\d\d" 'Regular expression To find numbers Like '100.00'
    ' Note: Do Not use `+` char in regex, but use `{1,}` instead.
    ' `+` char Is valid for URL And will Not be escaped, And it will become a space char on the server side.

    ' Enable regular expressions (Regex) 
    Const RegexSearch As Boolean = True

    Sub Main()

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

        ' Prepare URL for PDF text search API call.
        Dim query As String = Uri.EscapeUriString(
            String.Format("https://localhost/pdf/find?password={0}&pages={1}&url={2}&searchString={3}&regexSearch={4}",
                Password,
                Pages,
                SourceFileUrl,
                SearchString,
                RegexSearch))

        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

                For Each item As JToken In json("body")
                    Console.WriteLine({code}quot;Found text {item("text")} at coordinates {item("left")}, {item("top")}")
                Next

            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>

VIDEO

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

ON-DEMAND REST WEB API

Get Your API Key

See also:

printable version:
ByteScout-Cloud-API-Server-VB-NET-PDF-Text-Search-from-URL.pdf