PowerShell script to convert VTT files to SRT

ConvertTo-SRT.ps1

# Reads VTT and writes SRT
param (
    [Parameter(Mandatory = $true)][string]$localPath
    )

# Function to convert VTT to SRT
function Convert-VttToSrt {
    param (
        [string]$filePath
    )

    # Read the file into an array of lines
    $file_data = Get-Content $filePath

    # Verify that we are reading a WebVTT file
    $IsVTT = $file_data[0] -like 'WEBVTT*'

    if ($IsVTT -eq $True)
    {
        # Generate the destination filename
        $srtFilename = [io.path]::ChangeExtension($filePath, 'srt')

        # Create a new list to hold the converted data
        $new_data = New-Object System.Collections.Generic.List[System.Object]

        # Loop through the lines of the file and process them
        $fdl = $file_data.Length

        $CurentLine = 2
        $Counter = 1

        while ($CurentLine -lt $fdl)
        {
            # Read the current line and split it into parts
            $ThisLine = $file_data[$CurentLine]

            $ThisTime = $ThisLine.Split(" ")

            # Check if the line contains a timestamp
            if ($ThisTime.Length -eq 3)
            {
                if ($ThisTime[1] -eq "-->")
                {
                    # Change the time format from VTT to SRT
                    $ThisLine = $ThisLine.Replace('.', ',')

                    $new_data.Add($Counter++)
                    $new_data.Add($ThisLine)

                    $CurentLine++

                    # Read the next set of lines for the caption
                    # Treat as caption until the next blank line

                    $caption = Update-NameFormat -inputString $file_data[$CurentLine]

                    while ($caption -ne '' -and $CurentLine -lt $fdl)
                    {
                        $new_data.Add($caption)

                        $caption = Update-NameFormat -inputString $file_data[++$CurentLine]
                    }

                    $new_data.Add($caption)
                }
            }

            $CurentLine++
        }

        # Write out the updated data to the SRT file
        Out-File -FilePath $srtFilename -InputObject $new_data
    }
}

function Convert-HtmlEntities {
    param (
        [string]$inputString
    )
    
    $decodedString = $inputString
    
    # Define common HTML escape sequences and their replacements
    $htmlEntities = @{
        "&"  = "&"
        "&lt;"   = "<"
        "&gt;"   = ">"
        "&quot;"  = '"'
        "&apos;" = "'"
        "&nbsp;" = " "
    }
    
    # Replace each entity with its corresponding character
    foreach ($entity in $htmlEntities.Keys) {
        $decodedString = $decodedString -replace [regex]::Escape($entity), $htmlEntities[$entity]
    }
    
    return $decodedString
}

function Update-NameFormat{
    param (
        [string]$inputString
    )
    $vpattern = "^<v "
    $trailingPattern = "</v>$"

    # Does the string start with <v ?
    if ($inputString -match $vpattern) {
        # Remove the <v> tag
        $outputString = $inputString -replace $vpattern, ''

        # look for the closing part of <v> tag
        $index = $outputString.IndexOf('>')
        if ($index -ge 0) {
            $outputString = $outputString.Substring(0, $index) + ": " + $outputString.Substring($index + 1)
        }        

    } else {
        $outputString = $inputString
    }

    # Remove any trailing </v>
    $outputString = $outputString -replace $trailingPattern, ''

    # Decode HTML entities
    $outputString = Convert-HtmlEntities -inputString $outputString

    return $outputString.Trim()
}

# Get all matching .vtt files
$vttFiles = Get-ChildItem -Path $localPath -Filter "*.vtt" -File

# Get the count of files to process sowe can display a progress bar
$FileCount = $vttFiles.Count
$CurrentFile = 0

# walk through the list of files
try
{
    foreach ($file in $vttFiles) {
        $percent = [int]($CurrentFile++ * 100 / $FileCount)
        Write-Progress -Activity "VTT to SRT" -PercentComplete $percent -Status "$($file.Name)" 

        Convert-VttToSrt -filePath $file.FullName
    }
} catch {
    Write-Host "Error: $_"
    exit 1
}