Last active
July 30, 2018 16:38
-
-
Save PatrickLang/6f54171a0acb94a9d4aefe450eb6e039 to your computer and use it in GitHub Desktop.
PowerShell script to scrape Apple 2 "4am" collection
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
$feedUrl = "https://archive.org/services/collection-rss.php?collection=apple_ii_library_4am" | |
# Issue - this only seems to get latest 50 entries | |
$feedContents = ([xml](Invoke-WebRequest -UseBasicParsing -Uri $feedUrl).Content).rss.channel.item | |
Write-Host Found $feedContents.Count items | |
$r = [regex]"([^/]+)/?$" # Thanks https://stackoverflow.com/a/8798550 | |
$feedContents | ForEach-Object { | |
$identifier = $r.Match($_.link).Value | |
$fileList = [xml](Invoke-WebRequest -UseBasicParsing -Uri "https://archive.org/download/$($identifier)/$($identifier)_files.xml") | |
$zipFileNames = $fileList.files.file | Where-Object { $_.name -Match "zip$" } | |
$zipFileNames | ForEach-Object { | |
$zipFileUri = "https://archive.org/download/$($identifier)/$($_.name)" | |
Write-Host $zipFileUri | |
Start-BitsTransfer $zipFileUri | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment