SharePoint Online: Get All Documents Inventory in a Site using PowerShell

#Load SharePoint CSOM Assemblies
Add-Type -Path "C:\Program Files\Common Files\Microsoft Shared\Web Server Extensions\16\ISAPI\Microsoft.SharePoint.Client.dll"
Add-Type -Path "C:\Program Files\Common Files\Microsoft Shared\Web Server Extensions\16\ISAPI\Microsoft.SharePoint.Client.Runtime.dll"
   
#Function to Generate Report on all documents in a SharePoint Online Site Collection
Function Get-SPODocumentInventory($SiteURL)
{
    Try {
        #Setup the context
        $Ctx = New-Object Microsoft.SharePoint.Client.ClientContext($SiteURL)
        $Ctx.Credentials = $Credentials
   
        #Get the web from given URL and its subsites
        $Web = $Ctx.web
        $Ctx.Load($Web)
        $Ctx.Load($Web.Lists)
        $Ctx.Load($web.Webs)
        $Ctx.executeQuery()
 
        #Arry to Skip System Lists and Libraries
        $SystemLists =@("Converted Forms", "Master Page Gallery", "Customized Reports", "Form Templates", "List Template Gallery", "Theme Gallery",
               "Reporting Templates", "Solution Gallery", "Style Library", "Web Part Gallery","Site Assets", "wfpub", "Site Pages", "Images")
     
        Write-host -f Yellow "Processing Site: $SiteURL"
 
        #Filter Document Libraries to Scan 
        $Lists = $Web.Lists | Where {$_.BaseType -eq "DocumentLibrary" -and $_.Hidden -eq $false -and $SystemLists -notcontains $_.Title -and $_.ItemCount -gt 0}
        #Loop through each document library
        Foreach ($List in $Lists)
        {
            #Define CAML Query to Get List Items in batches
            $Query = New-Object Microsoft.SharePoint.Client.CamlQuery
            $Query.ViewXml ="
                <View Scope='RecursiveAll'>
                   <Query>
                      <OrderBy><FieldRef Name='ID' Ascending='TRUE'/></OrderBy>
                   </Query>
                   <RowLimit Paged='TRUE'>$BatchSize</RowLimit>
                </View>"
 
            Write-host -f Cyan "`t Processing Document Library: '$($List.Title)' with $($List.ItemCount) Item(s)"
 
            Do {
                #Get List items
                $ListItems = $List.GetItems($Query) 
                $Ctx.Load($ListItems)
                $Ctx.ExecuteQuery() 

                #Filter Files
                $Files = $ListItems | Where { $_.FileSystemObjectType -eq "File"}

                #Iterate through each file and get data
                $DocumentInventory = @()
                Foreach($Item in $Files)
                {
                    $File = $Item.File
                    $Ctx.Load($File)
                    $Ctx.ExecuteQuery()
 
                    $DocumentData = New-Object PSObject
                    $DocumentData | Add-Member NoteProperty SiteURL($SiteURL)
                    $DocumentData | Add-Member NoteProperty DocLibraryName($List.Title)
                    $DocumentData | Add-Member NoteProperty FileName($File.Name)
                    $DocumentData | Add-Member NoteProperty FileURL($File.ServerRelativeUrl)
                    $DocumentData | Add-Member NoteProperty CreatedBy($Item["Author"].Email)
                    $DocumentData | Add-Member NoteProperty CreatedOn($File.TimeCreated)
                    $DocumentData | Add-Member NoteProperty ModifiedBy($Item["Editor"].Email)
                    $DocumentData | Add-Member NoteProperty LastModifiedOn($File.TimeLastModified)
                    $DocumentData | Add-Member NoteProperty Size-KB([math]::Round($File.Length/1KB))
                       
                    #Add the result to an Array
                    $DocumentInventory += $DocumentData
                }
                #Export the result to CSV file
                $DocumentInventory | Export-CSV $ReportOutput -NoTypeInformation -Append
                $Query.ListItemCollectionPosition = $ListItems.ListItemCollectionPosition
            } While($Query.ListItemCollectionPosition -ne $null)
        }
          
        #Iterate through each subsite of the current web and call the function recursively
        ForEach ($Subweb in $Web.Webs)
        {
            #Call the function recursively to process all subsites underneaththe current web
            Get-SPODocumentInventory($Subweb.url)
        }
    }
    Catch {
        write-host -f Red "Error Generating Document Inventory!" $_.Exception.Message
    }
}
  
#Config Parameters
$SiteCollURL="https://crescent.sharepoint.com/sites/marketing"
$ReportOutput="C:\temp\DocInventory.csv"
$BatchSize = 500

#Setup Credentials to connect
$Cred= Get-Credential
$Credentials = New-Object Microsoft.SharePoint.Client.SharePointOnlineCredentials($Cred.Username, $Cred.Password)
  
#Delete the Output Report, if exists
if (Test-Path $ReportOutput) { Remove-Item $ReportOutput }
  
#Call the function 
Get-SPODocumentInventory $SiteCollURL

#Parameters
$SiteURL = "https://crescent.SharePoint.com/sites/Marketing"
$CSVPath = "C:\Temp\DocumentInventory.csv"
$global:DocumentInventory = @()
$Pagesize = 2000
 
#Function to scan and collect Document Inventory
Function Get-DocumentInventory
{
     [cmdletbinding()]
    param([parameter(Mandatory = $true, ValueFromPipeline = $true)] $Web)
   
    Write-host "Getting Documents Inventory from Site '$($Web.URL)'" -f Yellow
    Connect-PnPOnline -Url $Web.URL -Interactive

    #Calculate the URL of the tenant
    If($Web.ServerRelativeUrl -eq "/")
    {
        $TenantURL = $Web.Url
    }
    Else
    {
        $TenantURL = $Web.Url.Replace($Web.ServerRelativeUrl,'')
    }
 
    #Exclude certain libraries
    $ExcludedLists = @("Form Templates", "Preservation Hold Library","Site Assets", "Pages", "Site Pages", "Images",
                            "Site Collection Documents", "Site Collection Images","Style Library") 
                               
    #Get All Document Libraries from the Web
    Get-PnPList -PipelineVariable List | Where-Object {$_.BaseType -eq "DocumentLibrary" -and $_.Hidden -eq $false -and $_.Title -notin $ExcludedLists -and $_.ItemCount -gt 0} | ForEach-Object {
        #Get Items from List   
        $global:counter = 0;
        $ListItems = Get-PnPListItem -List $_ -PageSize $Pagesize -Fields Author, Created, File_x0020_Type,File_x0020_Size -ScriptBlock `
                 { Param($items) $global:counter += $items.Count; Write-Progress -PercentComplete ($global:Counter / ($_.ItemCount) * 100) -Activity "Getting Documents from '$($_.Title)'" -Status "Processing Items $global:Counter to $($_.ItemCount)";} | Where {$_.FileSystemObjectType -eq "File"}
        Write-Progress -Activity "Completed Retrieving Documents from Library $($List.Title)" -Completed
     
            #Get Root folder of the List
            $Folder = Get-PnPProperty -ClientObject $_ -Property RootFolder
 
            #Iterate through each document and collect data           
            ForEach($ListItem in $ListItems)
            {  
                #Collect document data
                $global:DocumentInventory += New-Object PSObject -Property ([ordered]@{
                    SiteName  = $Web.Title
                    SiteURL  = $Web.URL
                    LibraryName = $List.Title
                    ParentFolder = $Folder.ServerRelativeURL
                    FileName = $ListItem.FieldValues.FileLeafRef
                    FileType = $ListItem.FieldValues.File_x0020_Type
                    FileSize = [math]::Round($ListItem.FieldValues.File_x0020_Size/1KB)
                    AbsoluteURL = "$TenantURL$($ListItem.FieldValues.FileRef)"
                    CreatedBy = $ListItem.FieldValues.Author.Email
                    CreatedAt = $ListItem.FieldValues.Created
                    ModifiedBy = $ListItem.FieldValues.Editor.Email
                    ModifiedAt = $ListItem.FieldValues.Modified
                })
            }
        }
}
  
#Connect to Site collection
Connect-PnPOnline -Url $SiteURL -Interactive
    
#Call the Function for Webs
Get-PnPSubWeb -Recurse -IncludeRootWeb | ForEach-Object { Get-DocumentInventory $_ }
   
#Export Documents Inventory to CSV
$Global:DocumentInventory | Export-Csv $CSVPath -NoTypeInformation
Write-host "Documents Inventory Report has been Exported to '$CSVPath'" -f Green