DataFlex Requires Chilkat v11.7.0+

Get a PDF Field Value by its Label (Value to the Right)

See more PDF Text Extraction Examples

Demonstrates the "label" option, which captures the text that belongs to a caption such as "Invoice Number:" without needing coordinates. With labelValue "right", the value is the rest of the label's line. Label matching ignores case, extra spaces and a trailing colon. DataFlex

Use ChilkatAx-win32.pkg

Procedure Test
    Boolean iSuccess
    Handle hoPdf
    Variant vJson
    Handle hoJson
    Variant vJsonOut
    Handle hoJsonOut
    String sTemp1
    Integer iTemp1

    Move False To iSuccess

    //  This example requires the Chilkat API to have been previously unlocked.
    //  See Global Unlock Sample for sample code.

    //  The invoice used in this example is available at invoice_labels.pdf

    Get Create (RefClass(cComChilkatPdf)) To hoPdf
    If (Not(IsComObjectCreated(hoPdf))) Begin
        Send CreateComObject of hoPdf
    End
    Get ComLoadFile Of hoPdf "qa_data/pdf/invoice_labels.pdf" To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

    Get Create (RefClass(cComChilkatJsonObject)) To hoJson
    If (Not(IsComObjectCreated(hoJson))) Begin
        Send CreateComObject of hoJson
    End
    Get Create (RefClass(cComChilkatJsonObject)) To hoJsonOut
    If (Not(IsComObjectCreated(hoJsonOut))) Begin
        Send CreateComObject of hoJsonOut
    End

    //  The invoice has lines such as "Invoice Number:   INV-2026-0412".
    //  The label option restricts the "text" operation to the text belonging to the label.
    Get ComUpdateString Of hoJson "label" "Invoice Number" To iSuccess

    //  "right" means the value is the rest of the label's line.
    //  (The default, "auto", uses the rest of the line if there is text there, otherwise the block below.)
    Get ComUpdateString Of hoJson "labelValue" "right" To iSuccess

    Get pvComObject of hoJson to vJson
    Get pvComObject of hoJsonOut to vJsonOut
    Get ComExtractText Of hoPdf "text" vJson vJsonOut To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

    //  The value is returned as the text.
    Get ComStringOf Of hoJsonOut "text" To sTemp1
    Showln "Invoice Number: " sTemp1

    //  The labelMatches array tells where the label was found and how it appeared in the PDF.
    Get ComIntOf Of hoJsonOut "labelMatches[0].page" To iTemp1
    Get ComStringOf Of hoJsonOut "labelMatches[0].label" To sTemp1
    Showln "Found on page " iTemp1 ' as "' sTemp1 '"'

    //  Matching ignores case and the trailing colon, so these all work:
    Get ComUpdateString Of hoJson "label" "CUSTOMER:" To iSuccess
    Get pvComObject of hoJson to vJson
    Get pvComObject of hoJsonOut to vJsonOut
    Get ComExtractText Of hoPdf "text" vJson vJsonOut To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

    Get ComStringOf Of hoJsonOut "text" To sTemp1
    Showln "Customer: " sTemp1

    Get ComUpdateString Of hoJson "label" "due date" To iSuccess
    Get pvComObject of hoJson to vJson
    Get pvComObject of hoJsonOut to vJsonOut
    Get ComExtractText Of hoPdf "text" vJson vJsonOut To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

    Get ComStringOf Of hoJsonOut "text" To sTemp1
    Showln "Due Date: " sTemp1

    //  The totals at the foot of the invoice are right-aligned labels with the amount beside them.
    Get ComUpdateString Of hoJson "label" "Total Due" To iSuccess
    Get pvComObject of hoJson to vJson
    Get pvComObject of hoJsonOut to vJsonOut
    Get ComExtractText Of hoPdf "text" vJson vJsonOut To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

    Get ComStringOf Of hoJsonOut "text" To sTemp1
    Showln "Total Due: " sTemp1

    //  A label that is not found is not an error.  The text is empty, labelMatches is empty,
    //  and the quality report has an issue with the code "labelNotFound".
    Get ComUpdateString Of hoJson "label" "Tracking Number" To iSuccess
    Get pvComObject of hoJson to vJson
    Get pvComObject of hoJsonOut to vJsonOut
    Get ComExtractText Of hoPdf "text" vJson vJsonOut To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

    Get ComSizeOfArray Of hoJsonOut "labelMatches" To iTemp1
    If (iTemp1 = 0) Begin
        Get ComStringOf Of hoJsonOut "quality.pages[0].issues[0].code" To sTemp1
        Showln "Tracking Number: (not found) " sTemp1
    End

    //  Sample output:

    //  Invoice Number: INV-2026-0412
    //  Found on page 1 as "Invoice Number:"
    //  Customer: Northwind Traders
    //  Due Date: April 13, 2026
    //  Total Due: $1,234.53
    //  Tracking Number: (not found) labelNotFound


End_Procedure