Last active
February 9, 2017 18:10
-
-
Save hartez/2559086873b3e75875e3 to your computer and use it in GitHub Desktop.
PowerShell script to pull email body text out of GMVault
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
$emails = @() | |
$gmvaultdb = "[path to your gmvault data]" | |
$total = (Get-ChildItem $gmvaultdb -Recurse -Filter *.eml | measure).Count | |
Add-Type -Path "MimeKit.1.2.10.0\lib\net45\MimeKit.dll" | |
$formats = @{ | |
[MimeKit.Text.TextFormat]::Text = 0; | |
[MimeKit.Text.TextFormat]::Flowed = 0; | |
[MimeKit.Text.TextFormat]::Html = 0; | |
[MimeKit.Text.TextFormat]::Enriched = 0; | |
[MimeKit.Text.TextFormat]::RichText = 0; | |
[MimeKit.Text.TextFormat]::CompressedRichText = 0 | |
} | |
$unknownFormat = 0 | |
Get-ChildItem $gmvaultdb -Recurse -Filter *.eml | ForEach-Object {$i=0} { | |
Write-Host "Processing $_ ($i of $total)" | |
$mimeMessage = [MimeKit.MimeMessage]::Load($_.FullName) | |
$mimeMessage.From.ToString() -match '"\s<(.*)>$' | Out-Null; | |
$fromEmail = $Matches[1] | |
$bodyText = $null | |
$actualFormat = $null | |
# Run through all the enumeration values | |
# The pipe through sort ensures that we check them in the enum order, | |
# which is great because we prefer text over flowed over HTML, etc. | |
$formats.Keys | sort | % { | |
# try each Format until we find one that works | |
if($actualFormat -eq $null) { | |
# Try to get the body in the current format | |
$bodyText = $mimeMessage.GetTextBody($_) | |
if($bodyText) { | |
$actualFormat = $_ | |
} | |
} | |
} | |
if($actualFormat -eq $null) { | |
$unknownFormat += 1; | |
$actualFormat = "Unknown" | |
} else { | |
$formats[$actualFormat] += 1; | |
} | |
$props = @{ | |
Id = $mimeMessage.MessageId | |
To = $mimeMessage.To.ToString() | |
From = $mimeMessage.From.ToString() | |
FromEmail = $fromEmail | |
Subject = $mimeMessage.Subject | |
Body = $bodyText | |
Format = $actualFormat | |
} | |
$emails += (New-Object PSObject -Property $props) | |
$i++ | |
} | |
$emails | Select Id, To, From, FromEmail, Subject, Body, Format | Export-Csv bodytext.csv -NoTypeInformation | |
$formats.Keys | sort | % { Write-Host "There were"($formats[$_])"emails in $_ format" } | |
Write-Host "There were $unknownFormat emails with an indeterminate format" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment