Important Update
Learn how to find table and extract as CSV from PDF in C++ with this source code sample. What is ByteScout PDF Extractor SDK? It is the SDK that helps developers to extract data from unstructured documents, pdf, images, scanned and electronic forms. Includes AI functions like automatic table detection, automatic table extraction and restructuring, text recognition and text restoration from pdf and scanned documents. Includes PDF to CSV, PDF to XML, PDF to JSON, PDF to searchable PDF functions as well as methods for low level data extraction. It can help you to find table and extract as CSV from PDF in your C++ application.
This code snippet below for ByteScout PDF Extractor SDK works best when you need to quickly find table and extract as CSV from PDF in your C++ application. In order to implement the functionality, you should copy and paste this code for C++ below into your code editor with your app, compile and run your application. Test C++ sample code examples whether they respond your needs and requirements for the project.
Free trial version of ByteScout PDF Extractor SDK is available for download from our website. Get it to try other source code samples for C++.
On-demand (REST Web API) version:
Web API (on-demand version)
On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)
#include "stdafx.h"
#include "comip.h"
#import "c:\\Program Files\\Bytescout PDF Extractor SDK\\net4.00\\Bytescout.PDFExtractor.tlb" raw_interfaces_only
using namespace Bytescout_PDFExtractor;
int _tmain(int argc, _TCHAR* argv[])
{
// Initialize COM.
HRESULT hr = CoInitializeEx(NULL, COINIT_APARTMENTTHREADED);
// Create CSVExtractor instance
_CSVExtractorPtr pICSVExtractor(__uuidof(CSVExtractor));
pICSVExtractor->put_RegistrationName(_bstr_t(L"DEMO"));
pICSVExtractor->put_RegistrationKey(_bstr_t(L"DEMO"));
// Create TableDetector instance
_TableDetectorPtr pITableDetector(__uuidof(TableDetector));
pITableDetector->put_RegistrationName(_bstr_t(L"DEMO"));
pITableDetector->put_RegistrationKey(_bstr_t(L"DEMO"));
// Set table detection mode to "bordered tables" - best for tables with closed solid borders.
pITableDetector->put_ColumnDetectionMode(ColumnDetectionMode_BorderedTables);
// We should define what kind of tables we should detect.
// So we set min required number of columns to 2 ...
pITableDetector->put_DetectionMinNumberOfColumns(2);
// ... and we set min required number of rows to 2
pITableDetector->put_DetectionMinNumberOfRows(2);
// Load sample PDF document
_bstr_t inputFile(L"..\\..\\sample3.pdf");
pICSVExtractor->LoadDocumentFromFile(inputFile);
pITableDetector->LoadDocumentFromFile(inputFile);
// Get page count
long pageCount;
pITableDetector->GetPageCount(&pageCount);
for (int pageIndex = 0; pageIndex < pageCount; pageIndex++)
{
int t = 1;
VARIANT_BOOL vbResult;
// Find first table and continue if found
pITableDetector->FindTable(pageIndex, &vbResult);
if (vbResult == VARIANT_TRUE)
{
do
{
float left, top, width, height;
pITableDetector->GetFoundTableRectangle_Left(&left);
pITableDetector->GetFoundTableRectangle_Top(&top);
pITableDetector->GetFoundTableRectangle_Width(&width);
pITableDetector->GetFoundTableRectangle_Height(&height);
// Set extraction area for CSV extractor to rectangle received from the table detector
pICSVExtractor->SetExtractionArea(left, top, width, height);
// Export the table to CSV file
CString fileName;
fileName.Format(L"page-%d-table-%d.csv", pageIndex, t);
pICSVExtractor->SavePageCSVToFile(pageIndex, _bstr_t(fileName));
t++;
pITableDetector->FindNextTable(&vbResult);
} while (vbResult == VARIANT_TRUE);
}
}
pICSVExtractor->Release();
pITableDetector->Release();
CoUninitialize();
return 0;
}
60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page
Explore ByteScout PDF Extractor SDK Documentation
Explore Samples
Sign Up for ByteScout PDF Extractor SDK Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples
// stdafx.cpp : source file that includes just the standard includes
// CPPExample.pch will be the pre-compiled header
// stdafx.obj will contain the pre-compiled type information
#include "stdafx.h"
// TODO: reference any additional headers you need in STDAFX.H
// and not in this file
60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page
Explore ByteScout PDF Extractor SDK Documentation
Explore Samples
Sign Up for ByteScout PDF Extractor SDK Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples
// stdafx.h : include file for standard system include files,
// or project specific include files that are used frequently, but
// are changed infrequently
//
#pragma once
#include "targetver.h"
#include <stdio.h>
#include <tchar.h>
// TODO: reference additional headers your program requires here
#include <atlstr.h>
60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page
Explore ByteScout PDF Extractor SDK Documentation
Explore Samples
Sign Up for ByteScout PDF Extractor SDK Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples
#pragma once
// Including SDKDDKVer.h defines the highest available Windows platform.
// If you wish to build your application for a previous Windows platform, include WinSDKVer.h and
// set the _WIN32_WINNT macro to the platform you wish to support before including SDKDDKVer.h.
#include <SDKDDKVer.h>
60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page
Explore ByteScout PDF Extractor SDK Documentation
Explore Samples
Sign Up for ByteScout PDF Extractor SDK Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples
60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page
Explore ByteScout PDF Extractor SDK Documentation
Explore Samples
Sign Up for ByteScout PDF Extractor SDK Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples
also available as: