Simplify Your PDF Searches with PowerShell

# Prompt the user for the main PDF path and the search text
$main_url = Read-Host "Please enter the main path where the PDF files are located"

# Check if the path ends with a backslash, and add it if it's missing
if (-Not $main_url.EndsWith("\")) {
    $main_url += "\"
}

$search_value = Read-Host "Please enter the text to search for"

# Check if C:\Temp\ folder exists, if not create it
$temp_folder = "C:\Temp\"
if (-Not (Test-Path -Path $temp_folder)) {
    Write-Host "C:\Temp\ folder not found. Creating the folder..."
    New-Item -ItemType Directory -Path $temp_folder
}

# Check if the itextsharp.dll exists, if not download it
$dll_path = "$temp_folder\itextsharp.dll"
$dll_url = "https://yh.do/files/itextsharp.dll"
if (-Not (Test-Path -Path $dll_path)) {
    Write-Host "itextsharp.dll not found. Downloading the DLL..."
    try {
        Invoke-WebRequest -Uri $dll_url -OutFile $dll_path
        Write-Host "DLL downloaded successfully."
    } catch {
        Write-Host "Failed to download the DLL. Please check the URL or network connection."
        exit
    }
}

# Function to convert PDF to text
function convert-PDFtoText {
    param(
        [Parameter(Mandatory=$true)][string]$file
    )
    try {
        Add-Type -Path $dll_path
    } catch {
        Write-Host "Failed to load the itextsharp.dll. Please ensure the DLL is correctly downloaded."
        exit
    }    
    $pdf = New-Object iTextSharp.text.pdf.pdfreader -ArgumentList $file
    for ($page = 1; $page -le $pdf.NumberOfPages; $page++) {
        $text=[iTextSharp.text.pdf.parser.PdfTextExtractor]::GetTextFromPage($pdf,$page)
        Write-Output $text
    }    
    $pdf.Close()
}

# Search for the text in the PDFs
$search_value = "*"+$search_value+"*"
$all = Get-ChildItem -Recurse -Path $main_url | Where-Object { $_.Extension -eq ".pdf" } | Select-Object -Property FullName
$all_pdfs = $all.FullName
foreach($pdf in $all_pdfs){
    $file = $pdf
    $current_pdf = convert-PDFtoText $file
    if($null -ne $current_pdf){
        if($current_pdf.length -gt 1){        
            $i = 0
            while($i -ne $current_pdf.Length-1){
                if($current_pdf[$i] -like $search_value ){
                    $page = $i + 1
                    Write-Host($file + "  > Page "+$page)
                }
                $i++
            }
        }else{
            if($current_pdf[0] -like $search_value){
                Write-Host($file + "  > Page 1")
            }        
        }
    }
}