asg/scripts/Download-All-SharePoint-Files.ps1

<#
.SYNOPSIS
    Recursively downloads all SharePoint document libraries and files from a site using Microsoft Graph.

.DESCRIPTION
    Connects to the Microsoft Graph API, resolves a SharePoint site URL, enumerates all document libraries (drives),
    and recursively downloads folders and files to a designated local target directory.
    
    Includes automatic filename sanitization for Windows file systems, pagination support, skipping existing files,
    and a final download statistics report.

.PARAMETER SiteUrl
    The full URL of the target SharePoint site (e.g., "https://zefiromethane.sharepoint.com/sites/contentTypeHub").

.PARAMETER Destination
    The local root folder path where document libraries and files will be saved.

.PARAMETER SkipAuthentication
    Switch parameter to skip 'Connect-MgGraph' if an active Graph session is already established.

.EXAMPLE
    .\Export-SharePointSiteFiles.ps1 -SiteUrl "https://zefiromethane.sharepoint.com/sites/contentTypeHub" -Destination "F:\TeamSite"

.EXAMPLE
    .\Export-SharePointSiteFiles.ps1 -SiteUrl "https://contoso.sharepoint.com/sites/hr" -Destination "C:\Backup\HR" -Verbose

.NOTES
    Created:     2025-03-05
    Modified:    2026-10-04
#>

[CmdletBinding()]
param (
    [Parameter(Mandatory = $true, Position = 0, ValueFromPipeline = $true)]
    [ValidateNotNullOrEmpty()]
    [string]$SiteUrl,

    [Parameter(Mandatory = $true, Position = 1)]
    [ValidateNotNullOrEmpty()]
    [string]$Destination,

    [switch]$SkipAuthentication
)

# 1. Prerequisite Module Check
if (-not (Get-Module -ListAvailable -Name Microsoft.Graph.Authentication)) {
    Write-Error "The 'Microsoft.Graph.Authentication' module is required. Install it using: Install-Module Microsoft.Graph"
    return
}

# 2. State & Metric Counters
$script:downloadCount = 0
$script:skippedCount  = 0
$script:folderCount   = 0
$script:errorCount    = 0
$script:totalBytes    = 0

# 3. Helper Functions

function Sanitize-PathSegment {
    param([string]$Name)
    # Replaces Windows reserved filename characters: \ / : * ? " < > |
    $invalidChars = [System.IO.Path]::GetInvalidFileNameChars()
    $sanitized = $Name
    foreach ($char in $invalidChars) {
        $sanitized = $sanitized.Replace([string]$char, '_')
    }
    return $sanitized.TrimEnd('.')
}

function Get-GraphCollection {
    param([string]$Uri)

    do {
        $response = Invoke-MgGraphRequest -Method GET -Uri $Uri -ErrorAction Stop

        foreach ($item in @($response.value)) {
            Write-Output $item
        }

        $Uri = $response.'@odata.nextLink'
    }
    while ($Uri)
}

function Copy-GraphFolder {
    param(
        [string]$DriveId,
        [string]$ChildrenUri,
        [string]$LocalFolder
    )

    if (-not (Test-Path -LiteralPath $LocalFolder)) {
        New-Item -ItemType Directory -Path $LocalFolder -Force | Out-Null
    }

    try {
        $items = Get-GraphCollection -Uri $ChildrenUri
    }
    catch {
        Write-Error "Failed to retrieve folder contents from URI: $ChildrenUri. Error: $_"
        $script:errorCount++
        return
    }

    foreach ($item in $items) {
        # Sanitize item name to prevent Windows file path errors
        $safeName       = Sanitize-PathSegment -Name $item.name
        $localPath      = Join-Path -Path $LocalFolder -ChildPath $safeName
        $escapedDriveId = [Uri]::EscapeDataString($DriveId)
        $escapedItemId  = [Uri]::EscapeDataString([string]$item.id)

        # Handle Folders / Packages
        if ($null -ne $item.folder -or $null -ne $item.package) {
            $script:folderCount++
            New-Item -ItemType Directory -Path $localPath -Force | Out-Null

            $childUri = "https://graph.microsoft.com/v1.0/drives/$escapedDriveId/items/$escapedItemId/children"
            
            Copy-GraphFolder -DriveId $DriveId -ChildrenUri $childUri -LocalFolder $localPath
        }
        # Handle Files
        elseif ($null -ne $item.file) {
            if (Test-Path -LiteralPath $localPath) {
                Write-Verbose "Skipping existing file: $localPath"
                $script:skippedCount++
                continue
            }

            Write-Host "Downloading: $safeName" -ForegroundColor Cyan
            $contentUri = "https://graph.microsoft.com/v1.0/drives/$escapedDriveId/items/$escapedItemId/content"

            try {
                Invoke-MgGraphRequest -Method GET -Uri $contentUri -OutputFilePath $localPath -ErrorAction Stop
                $script:downloadCount++
                if ($item.size) { $script:totalBytes += $item.size }
            }
            catch {
                Write-Error "Failed to download '$($item.name)' to '$localPath'. Error: $_"
                $script:errorCount++
            }
        }
        else {
            Write-Warning "Unsupported item skipped: $($item.name)"
            $script:skippedCount++
        }
    }
}

# 4. Main Execution Flow

try {
    # Establish Graph Connection
    if (-not $SkipAuthentication) {
        Write-Host "Connecting to Microsoft Graph..." -ForegroundColor Yellow
        Connect-MgGraph -Scopes "Sites.Read.All" -NoWelcome
    }

    # Resolve SharePoint Site ID
    $parsedSiteUrl = [Uri]$SiteUrl
    $sitePath      = $parsedSiteUrl.AbsolutePath.TrimEnd("/")

    if ([string]::IsNullOrWhiteSpace($sitePath)) {
        $siteLookupUri = "https://graph.microsoft.com/v1.0/sites/$($parsedSiteUrl.Host)"
    }
    else {
        $siteLookupUri = "https://graph.microsoft.com/v1.0/sites/$($parsedSiteUrl.Host):$sitePath"
    }

    Write-Host "Resolving SharePoint site..." -ForegroundColor Yellow
    $site = Invoke-MgGraphRequest -Method GET -Uri $siteLookupUri -ErrorAction Stop

    # Ensure root destination folder exists
    if (-not (Test-Path -LiteralPath $Destination)) {
        New-Item -ItemType Directory -Path $Destination -Force | Out-Null
    }

    # Enumerate Site Drives (Document Libraries)
    $drivesUri = "https://graph.microsoft.com/v1.0/sites/$($site.id)/drives"
    $drives    = Get-GraphCollection -Uri $drivesUri

    foreach ($drive in $drives) {
        $safeDriveName  = Sanitize-PathSegment -Name $drive.name
        $localLibrary   = Join-Path -Path $Destination -ChildPath $safeDriveName
        $escapedDriveId = [Uri]::EscapeDataString([string]$drive.id)

        Write-Host "`n========================================" -ForegroundColor Green
        Write-Host "Downloading Library: $($drive.name)" -ForegroundColor Green
        Write-Host "Local Target       : $localLibrary" -ForegroundColor Green
        Write-Host "========================================" -ForegroundColor Green

        $rootChildrenUri = "https://graph.microsoft.com/v1.0/drives/$escapedDriveId/root/children"

        Copy-GraphFolder -DriveId $drive.id -ChildrenUri $rootChildrenUri -LocalFolder$localLibrary
    }

    # Display Execution Summary
    $MBTransferred = [math]::Round($script:totalBytes / 1MB, 2)
    Write-Host "`nSharePoint Download Summary:" -ForegroundColor Green
    Write-Host "  Files Downloaded : $script:downloadCount ($MBTransferred MB)"
    Write-Host "  Files Skipped    : $script:skippedCount"
    Write-Host "  Folders Created  : $script:folderCount"
    Write-Host "  Errors Encountered: $script:errorCount"
}
finally {
    if (-not $SkipAuthentication) {
        Write-Host "`nDisconnecting Microsoft Graph session..." -ForegroundColor Yellow
        Disconnect-MgGraph
    }
}