Extract Data from Tables in PDF using Java

readme.md

Learn how to extract data from tables in PDF using Java: https://blog.aspose.com/2021/10/11/extract-data-from-tables-in-pdf-using-java/

extract-text-from-pdf-table-specific-area.java

// Load source PDF document
com.aspose.pdf.Document pdfDocument = new com.aspose.pdf.Document("sample.pdf");

// Get reference of the desired page
com.aspose.pdf.Page page = pdfDocument.getPages().get_Item(1);

// Create an annotation selector
com.aspose.pdf.AnnotationSelector annotationSelector = new com.aspose.pdf.AnnotationSelector(
        new com.aspose.pdf.SquareAnnotation(page, com.aspose.pdf.Rectangle.getTrivial()));

// Get list of annotations
java.util.List<com.aspose.pdf.Annotation> list = annotationSelector.getSelected();
if (list.size() == 0) {
    System.out.println("Marked tables not found..");
    return;
}

// Create a square annotation
com.aspose.pdf.SquareAnnotation squareAnnotation = (com.aspose.pdf.SquareAnnotation) list.get(0);

// Create table absorber and visit page
com.aspose.pdf.TableAbsorber absorber = new com.aspose.pdf.TableAbsorber();
absorber.visit(page);

// Iterate through tables
for (com.aspose.pdf.AbsorbedTable table : absorber.getTableList()) {
    {
        // Check is table exists
        boolean isInRegion = (squareAnnotation.getRect().getLLX() < table.getRectangle().getLLX())
                && (squareAnnotation.getRect().getLLY() < table.getRectangle().getLLY())
                && (squareAnnotation.getRect().getURX() > table.getRectangle().getURX())
                && (squareAnnotation.getRect().getURY() > table.getRectangle().getURY());

        if (isInRegion) {
            for (com.aspose.pdf.AbsorbedRow row : table.getRowList()) {
                {
                    for (com.aspose.pdf.AbsorbedCell cell : row.getCellList()) {
                        for (com.aspose.pdf.TextFragment fragment : cell.getTextFragments()) {
                            StringBuilder sb = new StringBuilder();
                            for (com.aspose.pdf.TextSegment seg : fragment.getSegments())
                                sb.append(seg.getText());
                            System.out.print(sb.toString() + "|");
                        }
                    }
                    System.out.println();
                }
            }
        }
    }
}

extract-text-from-pdf-table.java

// Load source PDF document
com.aspose.pdf.Document pdfDocument = new com.aspose.pdf.Document("sample.pdf");

// Create a table absrober
com.aspose.pdf.TableAbsorber absorber = new com.aspose.pdf.TableAbsorber();

// Scan pages
for (com.aspose.pdf.Page page : pdfDocument.getPages()) {
    
    // Vist page
    absorber.visit(page);
  
    // Iterate through tables
    for (com.aspose.pdf.AbsorbedTable table : absorber.getTableList()) {
        System.out.println("Table");
        
        // Iterate throught list of rows
        for (com.aspose.pdf.AbsorbedRow row : table.getRowList()) {
            
            // Iterate throught list of cell
            for (com.aspose.pdf.AbsorbedCell cell : row.getCellList()) {
                
                // Iterate through text fragments
                for (com.aspose.pdf.TextFragment fragment : cell.getTextFragments()) {
                    StringBuilder sb = new StringBuilder();
                    for (com.aspose.pdf.TextSegment seg : fragment.getSegments())
                        sb.append(seg.getText());
                    System.out.print(sb.toString() + "|");
                }
            }
            System.out.println();
        }
    }
}