DataFlex Requires Chilkat v11.7.0+

Get Every Occurrence of a Label in a PDF

See more PDF Text Extraction Examples

Demonstrates the "labelOccurrence" option. When the same label appears more than once (for example "Total:" on each of several receipts), "first" (the default) uses the first occurrence, "all" returns every occurrence with its page, and a number selects one occurrence. DataFlex

Use ChilkatAx-win32.pkg

Procedure Test
    Boolean iSuccess
    Handle hoPdf
    Variant vJson
    Handle hoJson
    Variant vJsonOut
    Handle hoJsonOut
    Integer i
    Integer iCount_i
    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 PDF used in this example (three receipts, one per page) is available at three_receipts.pdf

    Get Create (RefClass(cComChilkatPdf)) To hoPdf
    If (Not(IsComObjectCreated(hoPdf))) Begin
        Send CreateComObject of hoPdf
    End
    Get ComLoadFile Of hoPdf "qa_data/pdf/three_receipts.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

    //  Each of the three pages is a receipt with a "Total:" line.
    Get ComUpdateString Of hoJson "label" "Total" To iSuccess
    Get ComUpdateString Of hoJson "labelValue" "right" To iSuccess

    //  By default only the first occurrence (in reading order) is used.
    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 "First total: " sTemp1

    //  labelOccurrence "all" returns every occurrence.  The "text" member holds the values joined
    //  by line breaks, and labelMatches has one entry per occurrence with its page.
    Get ComUpdateString Of hoJson "labelOccurrence" "all" 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

    Move 0 To i
    Get ComSizeOfArray Of hoJsonOut "labelMatches" To iCount_i
    While (i < iCount_i)
        Set ComI Of hoJsonOut To i
        Get ComIntOf Of hoJsonOut "labelMatches[i].page" To iTemp1
        Get ComStringOf Of hoJsonOut "labelMatches[i].text" To sTemp1
        Showln "Page " iTemp1 " total: " sTemp1
        Move (i + 1) To i
    Loop

    //  A number selects one occurrence: 2 is the second.
    Get ComUpdateInt Of hoJson "labelOccurrence" 2 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 "Second total: " sTemp1

    //  The occurrences are counted over the selected pages, so combining "pages" with the label
    //  is another way to pick one receipt:
    Get ComUpdateString Of hoJson "labelOccurrence" "first" To iSuccess
    Get ComUpdateString Of hoJson "pages" "3" To iSuccess
    Get ComUpdateString Of hoJson "label" "Receipt No." 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 "Receipt number on page 3: " sTemp1

    //  Sample output:

    //  First total: $19.86
    //  Page 1 total: $19.86
    //  Page 2 total: $17.34
    //  Page 3 total: $23.62
    //  Second total: $17.34
    //  Receipt number on page 3: 1003


End_Procedure