Extract Text By Columns from PDF | PowershellByteScout PDF Extractor SDK

Extract Text By Columns from PDF | Powershell

ExtractTextByColumns.bat:

@echo off

if "%~1"=="" (
	echo -----------------------------------------------------
	echo Invalid parameter!
	echo -----------------------------------------------------
	echo Usage: ExtractTextByColumns.bat file_name
	echo Example: ExtractTextByColumns.bat "columns.pdf"
	echo -----------------------------------------------------
	if not "%NOPAUSE%"=="1" pause
	exit /b 1
)

powershell -NoProfile -ExecutionPolicy Bypass -Command "& .\ExtractTextByColumns.ps1" "%1"
echo Script finished with errorlevel=%errorlevel%

pause
        

ExtractTextByColumns.ps1:

#*******************************************************************************************#
#                                                                                           #
# Download Free Evaluation Version From: https://bytescout.com/download/web-installer       #
#                                                                                           #
# Also available as Web API! Get Your Free API Key: https://app.pdf.co/signup               #
#                                                                                           #
# Copyright © 2017-2020 ByteScout, Inc. All rights reserved.                                #
# https://www.bytescout.com                                                                 #
# https://pdf.co                                                                            #
#                                                                                           #
#*******************************************************************************************#

Param (
    [Parameter(Mandatory = $true)]
    [string] $InputFileName = ""
)

#Add reference to Bytescout.PDFExtractor.dll assembly
Add-Type -Path "C:\Program Files\Bytescout PDF Extractor SDK\net4.00\Bytescout.PDFExtractor.dll"

# Check input file exists
if ((Test-Path $InputFileName) -eq $false) {

    Write-Host "Input file does not exist." -ForegroundColor Red
    Exit 0
}

# Create and activate Bytescout.PDFExtractor.TextExtractor instance
$Extractor = New-Object Bytescout.PDFExtractor.TextExtractor
$Extractor.RegistrationName = "demo"
$Extractor.RegistrationKey = "demo"

try {
    # Load sample PDF document
    $Extractor.LoadDocumentFromFile($InputFileName)

    # Extract text by columns (useful if PDF document is designed in column layout like a newspaper)
    $Extractor.ExtractColumnByColumn = $true

    # Construct output file name
    $OutputFileName = [System.IO.Path]::ChangeExtension($InputFileName, "txt")
    # Save extracted text to file
    $Extractor.SaveTextToFile($OutputFileName)
    Write-Host "Data has been extracted to $OutputFileName file."
} catch {

    Write-Host $_.Exception.Message
}

$Extractor.Dispose()