How to parse multipage table for document parser API in C# and PDF.co Web API
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.
On-demand (REST Web API) version:
Web API (on-demand version)
On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)
ByteScoutWebApiExample.csproj
<?xml version="1.0" encoding="utf-8"?> <Project ToolsVersion="12.0" DefaultTargets="Build" 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>{1E1C2C34-017E-4605-AE2B-55EA3313BE51}</ProjectGuid> <OutputType>Exe</OutputType> <RootNamespace>ByteScoutWebApiExample</RootNamespace> <AssemblyName>ByteScoutWebApiExample</AssemblyName> <TargetFrameworkVersion>v4.0</TargetFrameworkVersion> <FileAlignment>512</FileAlignment> </PropertyGroup> <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' "> <PlatformTarget>AnyCPU</PlatformTarget> <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' "> <PlatformTarget>AnyCPU</PlatformTarget> <DebugType>pdbonly</DebugType> <Optimize>true</Optimize> <OutputPath>bin\Release\</OutputPath> <DefineConstants>TRACE</DefineConstants> <ErrorReport>prompt</ErrorReport> <WarningLevel>4</WarningLevel> </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> <Private>True</Private> </Reference> <Reference Include="System" /> <Reference Include="System.Core" /> <Reference Include="System.Xml.Linq" /> <Reference Include="System.Data" /> <Reference Include="System.Xml" /> </ItemGroup> <ItemGroup> <Compile Include="Program.cs" /> </ItemGroup> <ItemGroup> <None Include="MultiPageTable-template1.yml"> <CopyToOutputDirectory>Always</CopyToOutputDirectory> </None> <None Include="MultiPageTable-template2.yml"> <CopyToOutputDirectory>Always</CopyToOutputDirectory> </None> <None Include="MultiPageTable.pdf"> <CopyToOutputDirectory>Always</CopyToOutputDirectory> </None> <None Include="packages.config" /> </ItemGroup> <Import Project="$(MSBuildToolsPath)\Microsoft.CSharp.targets" /> <!-- To modify your build process, add your task inside one of the targets below and uncomment it. Other similar extension points exist, see Microsoft.Common.targets. <Target Name="BeforeBuild"> </Target> <Target Name="AfterBuild"> </Target> --> </Project>
ByteScoutWebApiExample.sln
Microsoft Visual Studio Solution File, Format Version 12.00 # Visual Studio 2013 VisualStudioVersion = 12.0.40629.0 MinimumVisualStudioVersion = 10.0.40219.1 Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "ByteScoutWebApiExample", "ByteScoutWebApiExample.csproj", "{1E1C2C34-017E-4605-AE2B-55EA3313BE51}" EndProject Global GlobalSection(SolutionConfigurationPlatforms) = preSolution Debug|Any CPU = Debug|Any CPU Release|Any CPU = Release|Any CPU EndGlobalSection GlobalSection(ProjectConfigurationPlatforms) = postSolution {1E1C2C34-017E-4605-AE2B-55EA3313BE51}.Debug|Any CPU.ActiveCfg = Debug|Any CPU {1E1C2C34-017E-4605-AE2B-55EA3313BE51}.Debug|Any CPU.Build.0 = Debug|Any CPU {1E1C2C34-017E-4605-AE2B-55EA3313BE51}.Release|Any CPU.ActiveCfg = Release|Any CPU {1E1C2C34-017E-4605-AE2B-55EA3313BE51}.Release|Any CPU.Build.0 = Release|Any CPU EndGlobalSection GlobalSection(SolutionProperties) = preSolution HideSolutionNode = FALSE EndGlobalSection EndGlobal
MultiPageTable-template1.yml
templateName: Multipage Table Test templateVersion: 4 templatePriority: 0 detectionRules: keywords: - Sample document with multi-page table objects: - name: total objectType: field fieldProperties: fieldType: macros expression: TOTAL{{Spaces}}({{Number}}) regex: true dataType: decimal - name: table1 objectType: table tableProperties: start: expression: Item{{Spaces}}Description{{Spaces}}Price regex: true end: expression: TOTAL{{Spaces}}{{Number}} regex: true row: expression: '{{LineStart}}{{Spaces}}(?<itemNo>{{Digits}}){{Spaces}}(?<description>{{SentenceWithSingleSpaces}}){{Spaces}}(?<price>{{Number}}){{Spaces}}(?<qty>{{Digits}}){{Spaces}}(?<extPrice>{{Number}})' regex: true columns: - name: itemNo dataType: integer - name: description dataType: string - name: price dataType: decimal - name: qty dataType: integer - name: extPrice dataType: decimal multipage: true
MultiPageTable-template2.yml
templateName: Multipage Table Test templateVersion: 4 templatePriority: 0 detectionRules: keywords: - Sample document with multi-page table objects: - name: total objectType: field fieldProperties: fieldType: regex expression: TOTAL{{Spaces}}({{Number}}) regex: true dataType: decimal - name: table1 objectType: table tableProperties: start: expression: Item{{Spaces}}Description{{Spaces}}Price regex: true end: expression: (Page {{Digits}} of {{Digits}})|(TOTAL{{Spaces}}{{Number}}) regex: true left: 51 right: 528 columns: - x: 51 name: itemNo dataType: integer - x: 102 name: description dataType: string - x: 324 name: price dataType: decimal - x: 396 name: qty dataType: integer - x: 441 name: extPrice dataType: decimal multipage: true
Program.cs
using Newtonsoft.Json; using Newtonsoft.Json.Linq; using System; using System.Collections.Generic; using System.IO; using System.Net; using System.Threading; // Cloud API asynchronous "Document Parser" job example. // Allows to avoid timeout errors when processing huge or scanned PDF documents. namespace ByteScoutWebApiExample { class Program { // The authentication key (API Key). // Get your own by registering at https://app.pdf.co/documentation/api const String API_KEY = "***********************************"; // Source PDF file const string SourceFile = @".\MultiPageTable.pdf"; // PDF document password. Leave empty for unprotected documents. const string Password = ""; // Destination TXT file name const string DestinationFile = @".\result.json"; // (!) Make asynchronous job const bool Async = true; static void Main(string[] args) { // Template text. Use Document Parser SDK (https://bytescout.com/products/developer/documentparsersdk/index.html) // to create templates. // Read template from file: String templateText = File.ReadAllText(@".\MultiPageTable-template1.yml"); //String templateText = File.ReadAllText(@".\MultiPageTable-template2.yml"); // Create standard .NET web client instance WebClient 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 string query = 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 string response = webClient.DownloadString(query); // Parse JSON response JObject json = JObject.Parse(response); if (json["error"].ToObject<bool>() == false) { // Get URL to use for the file upload string uploadUrl = json["presignedUrl"].ToString(); string uploadedFileUrl = 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[] or Stream webClient.Headers.Remove("content-type"); // 3. PARSE UPLOADED PDF DOCUMENT // URL of `Document Parser` API call string url = "https://api.pdf.co/v1/pdf/documentparser"; Dictionary<string, object> requestBody = new Dictionary<string, object>(); requestBody.Add("template", templateText); requestBody.Add("name", Path.GetFileName(DestinationFile)); requestBody.Add("url", uploadedFileUrl); requestBody.Add("async", Async); // Convert dictionary of params to JSON string jsonPayload = JsonConvert.SerializeObject(requestBody); // Execute request response = webClient.UploadString(url, "POST", jsonPayload); // Parse JSON response json = JObject.Parse(response); if (json["error"].ToObject<bool>() == false) { // Asynchronous job ID string jobId = json["jobId"].ToString(); // Get URL of generated JSON file string resultFileUrl = 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 { string status = CheckJobStatus(webClient, jobId); // Possible statuses: "working", "failed", "aborted", "success". // Display timestamp and status (for demo purposes) Console.WriteLine(DateTime.Now.ToLongTimeString() + ": " + status); if (status == "success") { // Download JSON file webClient.DownloadFile(resultFileUrl, DestinationFile); Console.WriteLine("Generated JSON file saved as \"{0}\" file.", DestinationFile); break; } else if (status == "working") { // Pause for a few seconds Thread.Sleep(3000); } else { Console.WriteLine(status); break; } } while (true); } else { Console.WriteLine(json["message"].ToString()); } } else { Console.WriteLine(json["message"].ToString()); } } catch (WebException e) { Console.WriteLine(e.ToString()); } webClient.Dispose(); Console.WriteLine(); Console.WriteLine("Press any key..."); Console.ReadKey(); } static string CheckJobStatus(WebClient webClient, string jobId) { string url = "https://api.pdf.co/v1/job/check?jobid=" + jobId; string response = webClient.DownloadString(url); JObject json = JObject.Parse(response); return Convert.ToString(json["status"]); } } }
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-C-sharp-Parse-Multipage-Table.pdf
PDF-co-Web-API-C-sharp-Parse-Multipage-Table.pdf