Scrape-Files.ps1

<#
Sequential Web Scraper (for PowerShell) v1.0
Written by Aaron Loessberg-Zahl
Last modified 20 July 2013

Scrapes images/files/etc that are named sequentially.  Will properly skip files
that return a HTTP 404 error.

For comments/questions/bugs, please contact
<[email protected]> or <[email protected]>.

----------------------------------------------------------------------------
"THE BEER-WARE LICENSE" (Revision 2659):
<[email protected]> wrote this file. As long as you retain this
notice, you can do whatever you want with this stuff. If we meet some day,
and you think this stuff is worth it, you can buy me a beer in return.
----------------------------------------------------------------------------

Changelog:
v1.0    07-20-2013      amloessb        Created and debugged
#>

Param (
    [String] $BaseURL,
    [String] $Separators,
    [Int] $Padding,
    [Int] $EndNumber,
    [String] $SaveTo
)

Function butLast ([Array] $arr, [String] $sep) {
    $return = ""
    $num = 0
    If ($sep) {
        While ($num -le ($arr.Length - 2)) {
            $return += $arr[$num] + $sep
            $num ++
        }
        Return $return
    }
    Return $arr[0..($arr.Length - 2)]
}

$ErrorActionPreference = "Stop"

Add-Type -AssemblyName System.Web

If (!($SaveTo.EndsWith("\"))) {
    $SaveTo += "\"
}

$splitURL = $BaseURL.split("/")
$filename = $splitURL[-1]
$arrURL = $filename.split($Separators, [StringSplitOptions]'RemoveEmptyEntries')
$currentLink = [Int] $arrURL[-2]

$wc = New-Object system.Net.WebClient

$badLinks = 0

While ($currentLink -le $EndNumber) {
    If ($arrURL.Length -gt 2) {
        $url = (butLast $splitURL "/") + $arrURL[0] + $Separators[0] + "{0:D$padding}" -f $currentLink + $Separators[1] + $arrURL[-1]
    } Else {
        $url = (butLast $splitURL "/") + $Separators[0] + "{0:D$padding}" -f $currentLink + $Separators[1] + $arrURL[-1]
    }
    $nameOnDisk = $url.split("/")[-1]
    Write-Progress -Activity "Sequential Web Scraper" -Status "Scraping files..." -CurrentOperation $nameOnDisk
    Try {
        $wc.DownloadFile($url, $SaveTo + $nameOnDisk)
    } Catch {
        $badLinks ++
    }
    $currentLink ++
}

Write-Progress -Activity "Sequential Web Scraper" -Status "Completed" -Completed