DataFlex Requires Chilkat v11.7.0+

Extract Tables from a PDF

See more PDF Text Extraction Examples

Demonstrates the "tables" operation, which returns the tables detected on the pages as rows and cells. Each cell has its row and column (counted from 0), its row and column span, and its text. DataFlex

Use ChilkatAx-win32.pkg

Procedure Test
    Boolean iSuccess
    Handle hoPdf
    Variant vJson
    Handle hoJson
    Variant vJsonOut
    Handle hoJsonOut
    Handle hoSbRow
    Integer iCurrentRow
    Integer iRow
    Integer j
    Integer iCount_j
    Integer i
    Integer iCount_i
    String sTemp1
    Integer iTemp1
    Integer iTemp2
    Integer iTemp3

    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 is available at price_list.pdf

    Get Create (RefClass(cComChilkatPdf)) To hoPdf
    If (Not(IsComObjectCreated(hoPdf))) Begin
        Send CreateComObject of hoPdf
    End
    Get ComLoadFile Of hoPdf "qa_data/pdf/price_list.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 "tables" operation returns the tables found on the selected pages.
    //  Tables are recognized by their drawn cell borders.
    Get pvComObject of hoJson to vJson
    Get pvComObject of hoJsonOut to vJsonOut
    Get ComExtractText Of hoPdf "tables" vJson vJsonOut To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

    Get ComIntOf Of hoJsonOut "count" To iTemp1
    Showln "Number of tables: " iTemp1

    //  Used to build each row of output.
    Get Create (RefClass(cComChilkatStringBuilder)) To hoSbRow
    If (Not(IsComObjectCreated(hoSbRow))) Begin
        Send CreateComObject of hoSbRow
    End

    Move 0 To i
    Get ComSizeOfArray Of hoJsonOut "tables" To iCount_i
    While (i < iCount_i)
        Set ComI Of hoJsonOut To i
        Get ComIntOf Of hoJsonOut "tables[i].page" To iTemp1
        Get ComIntOf Of hoJsonOut "tables[i].rows" To iTemp2
        Get ComIntOf Of hoJsonOut "tables[i].columns" To iTemp3
        Get ComStringOf Of hoJsonOut "tables[i].detectedBy" To sTemp1
        Showln "Table on page " iTemp1 ": " iTemp2 " rows x " iTemp3 " columns, detected by " sTemp1

        //  The cells are listed row by row.  Print each row as its cells separated by " | ".
        Move -1 To iCurrentRow
        Get ComSetString Of hoSbRow "" To iSuccess
        Move 0 To j
        Get ComSizeOfArray Of hoJsonOut "tables[i].cells" To iCount_j
        While (j < iCount_j)
            Set ComJ Of hoJsonOut To j
            Get ComIntOf Of hoJsonOut "tables[i].cells[j].row" To iRow
            If (iRow <> iCurrentRow) Begin
                If (iCurrentRow >= 0) Begin
                    Get ComGetAsString Of hoSbRow To sTemp1
                    Showln sTemp1
                End

                Move iRow To iCurrentRow
                Get ComSetString Of hoSbRow "  " To iSuccess
            End
            Else Begin
                Get ComAppend Of hoSbRow " | " To iSuccess
            End

            Get ComStringOf Of hoJsonOut "tables[i].cells[j].text" To sTemp1
            Get ComAppend Of hoSbRow sTemp1 To iSuccess
            Move (j + 1) To j
        Loop

        Get ComGetAsString Of hoSbRow To sTemp1
        Showln sTemp1
        Move (i + 1) To i
    Loop

    //  The cells of the first table as JSON:
    Set ComEmitCompact Of hoJsonOut To False
    Get ComEmit Of hoJsonOut To sTemp1
    Showln sTemp1

    //  Sample output:

    //  Number of tables: 1
    //  Table on page 1: 8 rows x 5 columns, detected by ruled
    //    Code | Product | Unit | Price | In Stock
    //    HT-101 | Claw hammer, 16 oz | each | $18.00 | 24
    //    HT-102 | Adjustable wrench, 10 in | each | $14.50 | 31
    //    HT-103 | Screwdriver set, 6 piece | set | $22.00 | 12
    //    HT-104 | Tape measure, 25 ft | each | $9.75 | 40
    //    HT-105 | Utility knife | each | $6.20 | 58
    //    HT-106 | Pliers, needle nose | each | $11.00 | 19
    //    HT-107 | Hand saw, 20 in | each | $21.40 | 8
    //  {
    //    "count": 1,
    //    "tables": [
    //      {
    //        "page": 1,
    //        "detectedBy": "ruled",
    //        "rows": 8,
    //        "columns": 5,
    //        "cells": [
    //          {
    //            "row": 0,
    //            "col": 0,
    //            "rowSpan": 1,
    //            "colSpan": 1,
    //            "text": "Code"
    //          },
    //          {
    //            "row": 0,
    //            "col": 1,
    //            "rowSpan": 1,
    //            "colSpan": 1,
    //            "text": "Product"
    //          },
    //          ...
    //        ]
    //      }
    //    ],
    //    "quality": {
    //      "rating": "good",
    //      ...
    //    }
    //  }


End_Procedure