PowerBuilder 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. PowerBuilder

integer li_rc
long li_Success
oleobject loo_Pdf
oleobject loo_Json
oleobject loo_JsonOut
oleobject loo_SbRow
long li_CurrentRow
long li_Row
long j
long li_Count_j
long i
long li_Count_i

li_Success = 0

//  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

loo_Pdf = create oleobject
li_rc = loo_Pdf.ConnectToNewObject("Chilkat.Pdf")
if li_rc < 0 then
    destroy loo_Pdf
    MessageBox("Error","Connecting to COM object failed")
    return
end if
li_Success = loo_Pdf.LoadFile("qa_data/pdf/price_list.pdf")
if li_Success = 0 then
    Write-Debug loo_Pdf.LastErrorText
    destroy loo_Pdf
    return
end if

loo_Json = create oleobject
li_rc = loo_Json.ConnectToNewObject("Chilkat.JsonObject")

loo_JsonOut = create oleobject
li_rc = loo_JsonOut.ConnectToNewObject("Chilkat.JsonObject")

//  The "tables" operation returns the tables found on the selected pages.
//  Tables are recognized by their drawn cell borders.
li_Success = loo_Pdf.ExtractText("tables",loo_Json,loo_JsonOut)
if li_Success = 0 then
    Write-Debug loo_Pdf.LastErrorText
    destroy loo_Pdf
    destroy loo_Json
    destroy loo_JsonOut
    return
end if

Write-Debug "Number of tables: " + string(loo_JsonOut.IntOf("count"))

//  Used to build each row of output.
loo_SbRow = create oleobject
li_rc = loo_SbRow.ConnectToNewObject("Chilkat.StringBuilder")

i = 0
li_Count_i = loo_JsonOut.SizeOfArray("tables")
do while i < li_Count_i
    loo_JsonOut.I = i
    Write-Debug "Table on page " + string(loo_JsonOut.IntOf("tables[i].page")) + ": " + string(loo_JsonOut.IntOf("tables[i].rows")) + " rows x " + string(loo_JsonOut.IntOf("tables[i].columns")) + " columns, detected by " + loo_JsonOut.StringOf("tables[i].detectedBy")

    //  The cells are listed row by row.  Print each row as its cells separated by " | ".
    li_CurrentRow = -1
    loo_SbRow.SetString("")
    j = 0
    li_Count_j = loo_JsonOut.SizeOfArray("tables[i].cells")
    do while j < li_Count_j
        loo_JsonOut.J = j
        li_Row = loo_JsonOut.IntOf("tables[i].cells[j].row")
        if li_Row <> li_CurrentRow then
            if li_CurrentRow >= 0 then
                Write-Debug loo_SbRow.GetAsString()
            end if

            li_CurrentRow = li_Row
            loo_SbRow.SetString("  ")
        else
            loo_SbRow.Append(" | ")
        end if

        loo_SbRow.Append(loo_JsonOut.StringOf("tables[i].cells[j].text"))
        j = j + 1
    loop
    Write-Debug loo_SbRow.GetAsString()
    i = i + 1
loop

//  The cells of the first table as JSON:
loo_JsonOut.EmitCompact = 0
Write-Debug loo_JsonOut.Emit()

//  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",
//      ...
//    }
//  }


destroy loo_Pdf
destroy loo_Json
destroy loo_JsonOut
destroy loo_SbRow