How to create custom template for document parser API in VB.NET with PDF.co Web API
What is PDF.co Web API? It is the Web API with a set of tools for documents manipulation, data conversion, data extraction, splitting and merging of documents. Includes image recognition, built-in OCR, barcode generation and barcode decoders to decode bar codes from scans, pictures and pdf.
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="SampleInvoice.pdf">
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</None>
<None Include="SampleTemplate.yml">
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</None>
</ItemGroup>
<Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.targets" />
</Project>
Module1.vb
Imports System.Collections.Specialized
Imports System.IO
Imports System.Net
Imports System.Text
Imports System.Threading
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 = ".\SampleInvoice.pdf"
' PDF document password. Leave empty for unprotected documents.
Const Password As String = ""
' Destination TXT file name
Const DestinationFile As String = ".\result.json"
' (!) Make asynchronous job
Const Async As Boolean = True
Sub Main()
' Template text. Use Document Parser SDK (https//bytescout.com/products/developer/documentparsersdk/index.html)
' to create templates.
' Read template from file
Dim templateText As String = File.ReadAllText("SampleTemplate.yml")
' 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
' 3. PARSE UPLOADED PDF DOCUMENT
' URL for `Document Parser` API call
query = Uri.EscapeUriString(
String.Format("https://api.pdf.co/v1/pdf/documentparser?url={0}&async={1}", uploadedFileUrl, Async)
)
Dim requestBody As New NameValueCollection()
requestBody.Add("template", templateText)
' Execute request
Dim responseBytes As Byte() = webClient.UploadValues(query, "POST", requestBody)
response = Encoding.UTF8.GetString(responseBytes)
' Parse JSON response
json = JObject.Parse(response)
If json("error").ToObject(Of Boolean) = False Then
' Asynchronous job ID
Dim jobId As String = json("jobId").ToString()
' URL of generated PDF file that will available after the job completion
Dim resultFileUrl As String = json("url").ToString()
' Check the job status in a loop.
' If you don't want to pause the main thread you can rework the code
' to use a separate thread for the status checking and completion.
Do
Dim status As String = CheckJobStatus(jobId) ' Possible statuses: "working", "failed", "aborted", "success".
' Display timestamp and status (for demo purposes)
Console.WriteLine(DateTime.Now.ToLongTimeString() + ": " + status)
If status = "success" Then
' Download PDF file
webClient.DownloadFile(resultFileUrl, DestinationFile)
Console.WriteLine("Generated JSON file saved as ""{0}"" file.", DestinationFile)
Exit Do
ElseIf status = "working" Then
' Pause for a few seconds
Thread.Sleep(3000)
Else
Console.WriteLine(status)
Exit Do
End If
Loop
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
Function CheckJobStatus(jobId As String) As String
Using webClient As WebClient = New WebClient()
' Set API Key
webClient.Headers.Add("x-api-key", API_KEY)
Dim url As String = "https://api.pdf.co/v1/job/check?jobid=" + jobId
Dim response As String = webClient.DownloadString(url)
Dim json As JObject = JObject.Parse(response)
Return Convert.ToString(json("status"))
End Using
End Function
End Module
SampleTemplate.yml
templateName: My Custom Template
templateVersion: 4
templatePriority: 0
detectionRules:
keywords:
- Your Company Name
- Invoice No\.
- TOTAL
objects:
- name: total
objectType: field
fieldProperties:
fieldType: macros
expression: TOTAL{{Spaces}}{{Number}}
dataType: decimal
pageIndex: 0
- name: dateIssued
objectType: field
fieldProperties:
fieldType: macros
expression: Invoice Date {{SmartDate}}
dataType: date
dateFormat: auto-mdy
pageIndex: 0
- name: invoiceId
objectType: field
fieldProperties:
fieldType: macros
expression: Invoice No. {{Digits}}
pageIndex: 0
- name: companyName
objectType: field
fieldProperties:
fieldType: static
expression: Vendor Company
pageIndex: 0
- name: billTo
objectType: field
fieldProperties:
fieldType: rectangle
rectangle:
- 32.25
- 150
- 348
- 70.5
pageIndex: 0
- name: notes
objectType: field
fieldProperties:
fieldType: rectangle
rectangle:
- 32.25
- 227.25
- 531
- 47.25
pageIndex: 0
- name: table1
objectType: table
tableProperties:
start:
expression: Item\s+Quantity\s+Price\s+Total
regex: true
end:
expression: TOTAL
regex: true
row:
expression: ^\s*(?<description>\w+.*)(?<quantity>\d+)\s+(?<unitPrice>\d+\.\d{2})\s+(?<itemTotal>\d+\.\d{2})\s*$
regex: true
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
See also:
ON-DEMAND REST WEB API
Get Your API Key
See also:
printable version:
PDF-co-Web-API-VB-NET-Create-Custom-Template.pdf
PDF-co-Web-API-VB-NET-Create-Custom-Template.pdf
