Extract table data from PDF in C++
Contents
[
Hide
]
Read detected PDF tables, filter them by a marked region, or convert the document to Excel with Aspose.PDF for C++.
Read detected tables
Print text from tables detected on every page.
- Open the input PDF as a Document.
- Iterate through the pages.
- Create a TableAbsorber and visit each page.
- Traverse detected tables, rows, cells, fragments, and segments.
- Join cell and fragment text using separators and print each row.
#include <Aspose.PDF.Cpp/Document.h>
#include <Aspose.PDF.Cpp/PageCollection.h>
#include <Aspose.PDF.Cpp/Page.h>
#include <Aspose.PDF.Cpp/Resources.h>
#include <Aspose.PDF.Cpp/Text/TextFragment.h>
#include <Aspose.PDF.Cpp/Text/TextFragmentCollection.h>
#include <Aspose.PDF.Cpp/Text/TextSegment.h>
#include <Aspose.PDF.Cpp/Text/TextSegmentCollection.h>
#include <Aspose.PDF.Cpp/Text/TableAbsorber/TableAbsorber.h>
#include <Aspose.PDF.Cpp/Text/TableAbsorber/AbsorbedTable.h>
#include <Aspose.PDF.Cpp/Text/TableAbsorber/AbsorbedRow.h>
#include <Aspose.PDF.Cpp/Text/TableAbsorber/AbsorbedCell.h>
using namespace System;
using namespace Aspose::Pdf;
using namespace Aspose::Pdf::Text;
void ExtractTablesFromPdf(System::String inputFile) {
auto document = MakeObject<Document>(inputFile);
for (auto& page : document->get_Pages()) {
auto absorber = MakeObject<TableAbsorber>();
absorber->Visit(page);
for (auto& table : absorber->get_TableList()) {
System::Console::WriteLine(u"Table");
for (auto& row : table->get_RowList()) {
auto rowText = MakeObject<System::Text::StringBuilder>();
for (auto& cell : row->get_CellList()) {
if (rowText->get_Length() > 0) {
rowText->Append(u"|");
}
auto cellText = MakeObject<System::Text::StringBuilder>();
for (auto& fragment : cell->get_TextFragments()) {
auto fragmentText = MakeObject<System::Text::StringBuilder>();
for (auto& segment : fragment->get_Segments()) {
fragmentText->Append(segment->get_Text());
}
if (cellText->get_Length() > 0) {
cellText->Append(u"|");
}
cellText->Append(fragmentText);
}
rowText->Append(cellText);
}
System::Console::WriteLine(rowText);
}
}
}
}
Read tables inside a square annotation
Use the first square annotation on page 1 as a region filter.
The boundary checks use strict inequalities; tables touching the annotation boundary are excluded.
- Open the input PDF as a Document.
- Find the first Square annotation on page 1.
- Return if no square annotation is found.
- Visit the page with TableAbsorber.
- Compare each detected table rectangle with the annotation rectangle.
- Print rows only for tables strictly contained inside the annotation.
#include <Aspose.PDF.Cpp/Document.h>
#include <Aspose.PDF.Cpp/PageCollection.h>
#include <Aspose.PDF.Cpp/Page.h>
#include <Aspose.PDF.Cpp/InteractiveFeatures/Annotations/AnnotationCollection.h>
#include <Aspose.PDF.Cpp/InteractiveFeatures/Annotations/AnnotationType.h>
#include <Aspose.PDF.Cpp/InteractiveFeatures/Annotations/Annotation.h>
#include <Aspose.PDF.Cpp/Text/TextFragment.h>
#include <Aspose.PDF.Cpp/Text/TextFragmentCollection.h>
#include <Aspose.PDF.Cpp/Text/TextSegment.h>
#include <Aspose.PDF.Cpp/Text/TextSegmentCollection.h>
#include <Aspose.PDF.Cpp/Text/TableAbsorber/TableAbsorber.h>
#include <Aspose.PDF.Cpp/Text/TableAbsorber/AbsorbedTable.h>
#include <Aspose.PDF.Cpp/Text/TableAbsorber/AbsorbedRow.h>
#include <Aspose.PDF.Cpp/Text/TableAbsorber/AbsorbedCell.h>
using namespace System;
using namespace Aspose::Pdf;
using namespace Aspose::Pdf::Text;
using namespace Aspose::Pdf::Annotations;
void ExtractTableFromSpecificArea(System::String inputFile) {
auto document = MakeObject<Document>(inputFile);
auto page = document->get_Pages()->idx_get(1);
SharedPtr<Annotation> squareAnnotation = nullptr;
for (auto& annotation : page->get_Annotations()) {
if (annotation->get_AnnotationType() == AnnotationType::Square) {
squareAnnotation = annotation;
break;
}
}
if (squareAnnotation == nullptr) {
System::Console::WriteLine(u"No square annotation found.");
return;
}
auto absorber = MakeObject<TableAbsorber>();
absorber->Visit(page);
for (auto& table : absorber->get_TableList()) {
auto tableRect = table->get_Rectangle();
auto annotationRect = squareAnnotation->get_Rect();
bool isInRegion = annotationRect->get_LLX() < tableRect->get_LLX()
&& annotationRect->get_LLY() < tableRect->get_LLY()
&& annotationRect->get_URX() > tableRect->get_URX()
&& annotationRect->get_URY() > tableRect->get_URY();
if (isInRegion) {
for (auto& row : table->get_RowList()) {
auto rowText = MakeObject<System::Text::StringBuilder>();
for (auto& cell : row->get_CellList()) {
if (rowText->get_Length() > 0) {
rowText->Append(u"|");
}
auto cellText = MakeObject<System::Text::StringBuilder>();
for (auto& fragment : cell->get_TextFragments()) {
auto fragmentText = MakeObject<System::Text::StringBuilder>();
for (auto& segment : fragment->get_Segments()) {
fragmentText->Append(segment->get_Text());
}
if (cellText->get_Length() > 0) {
cellText->Append(u"|");
}
cellText->Append(fragmentText);
}
rowText->Append(cellText);
}
System::Console::WriteLine(rowText);
}
}
}
}
Export a PDF to Excel
Save document content as XLSX using Excel conversion options.
This converts the document to Excel; it does not export a selected TableAbsorber result.
- Open the input PDF as a Document.
- Create ExcelSaveOptions and set Format to XLSX.
- Pass the output path and save options to Save().
#include <Aspose.PDF.Cpp/Document.h>
#include <Aspose.PDF.Cpp/ExcelSaveOptions.h>
using namespace Aspose::Pdf;
void ExportTablesToExcel(System::String inputFile, System::String outputFile) {
auto document = MakeObject<Document>(inputFile);
auto excelSave = MakeObject<ExcelSaveOptions>();
excelSave->set_Format(ExcelSaveOptions::ExcelFormat::XLSX);
document->Save(outputFile, excelSave);
}