Created
June 4, 2018 03:15
-
-
Save stephenfuqua/ca25feb0afe97606f31df870f7fc8b0d to your computer and use it in GitHub Desktop.
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
# After a botched Windows file history process a few years ago, many of my | |
# photos files ended up being duplicated (sometimes several times). This | |
# script hunts down duplicates by name and size and deletes the one | |
# with the longer name. Examples: | |
# IMG_2825.JPG and IMG_2825 (2015_03_26 01_58_35 UTC).JPG | |
# IMG_2199.JPG, IMG_2199-1.JPG, IMG_2199 (2014_10_13 02_31_59 UTC).JPG, IMG_2199-1 (2014_10_13 02_31_59 UTC).JPG | |
$startDir = "c:\temp\Photos" | |
(Get-ChildItem -Path $startDir -Recurse) | ForEach-Object { | |
$dir = $_.FullName | |
(Get-ChildItem -Path $dir -Filter "*.JPG") | Sort-Object -Descending | Where-Object {$_.Name.Length -eq 12} | ForEach-Object { | |
$duplicated = $_.Name | |
$duplicatedLength = $_.Length | |
Write-Host "Evaluating $duplicated..." | |
(Get-ChildItem -Path $dir -Filter "$($duplicated.Substring(0,8))*.JPG") | ForEach-Object { | |
# `-Exclude $duplicated` in the Get-ChildItem command isn't working - | |
# for some reason it excludes all files :-( | |
if ($_.Name -ne $duplicated -and $_.Length -eq $duplicatedLength) { | |
Write-Host "Delete $($_.Name)" | |
Remove-Item -Path $_.FullName -Force | |
} | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment