Last active
February 22, 2022 13:27
How to Read PDF Table in Java. For more information, please follow link: https://kb.aspose.com/pdf/java/how-to-read-pdf-table-in-java/
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import com.aspose.pdf.License; | |
import com.aspose.pdf.AbsorbedCell; | |
import com.aspose.pdf.AbsorbedRow; | |
import com.aspose.pdf.AbsorbedTable; | |
import com.aspose.pdf.Document; | |
import com.aspose.pdf.TableAbsorber; | |
import com.aspose.pdf.TextFragmentCollection; | |
public class ReadPDFTableInJava { | |
public static void main(String[] args) throws Exception { // main function for reading PDF table data in ReadPDFTableInJava | |
// For avoiding the trial version limitation, load the Aspose.PDF license prior to reading table data | |
License licenseForHtmlToPdf = new License(); | |
licenseForHtmlToPdf.setLicense("Aspose.Pdf.lic"); | |
// Load a source PDF document which contains a table in it | |
Document pdfDocument = new Document("PdfWithTable.pdf"); | |
// Instantiate the TableAbsorber object for PDF tables extraction | |
TableAbsorber tableAbsorber = new TableAbsorber(); | |
// visit the table collection in the input PDF | |
tableAbsorber.visit(pdfDocument.getPages().get_Item(1)); | |
// Access the desired table from the tables collection | |
AbsorbedTable absorbedTable = tableAbsorber.getTableList().get(0); | |
// Parse all the rows and get each row using the AbsorbedRow | |
for (AbsorbedRow pdfTableRow : absorbedTable.getRowList()) | |
{ | |
// Access each cell in the cells collection using AbsorbedCell | |
for (AbsorbedCell pdfTableCell : pdfTableRow.getCellList()) | |
{ | |
// Access each text fragment from the cell | |
TextFragmentCollection textFragmentCollection = pdfTableCell.getTextFragments(); | |
// Access each text fragment from the fragments collection | |
for (com.aspose.pdf.TextFragment textFragment : textFragmentCollection) | |
{ | |
// Display the table cell text | |
System.out.println(textFragment.getText()); | |
} | |
} | |
} | |
System.out.println("Done"); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment