Setup 2025 files and started parsing the archive site but was rate limited. Will need to finish it in the future.

2026-02-24 15:25:39 -08:00
parent 17c8270742
commit ab9abdb53e
11 changed files with 1158 additions and 1006 deletions
--- a/fix-tavolata.ps1
+++ b/fix-tavolata.ps1
@@ -0,0 +1,123 @@
+# fix-tavolata.ps1
+# Run this after the Wayback Machine rate limit resets (wait ~30 minutes after last run)
+# Recovers tavolata's Third Course using the same-block parser strategy
+
+$projectDir = Split-Path -Parent $MyInvocation.MyCommand.Definition
+$jsonPath   = Join-Path $projectDir '2025-restaurants.json'
+$data = Get-Content $jsonPath -Raw -Encoding UTF8 | ConvertFrom-Json
+
+function Decode-Html($str) {
+    if (-not $str) { return $str }
+    ($str -replace '&amp;','&' -replace '&#039;',"'" -replace '&quot;','"' -replace '&lt;','<' -replace '&gt;','>' -replace '&nbsp;',' ' -replace '\s+',' ').Trim()
+}
+function Get-CleanText($rawHtml) { Decode-Html ($rawHtml -replace '<[^>]+>', ' ') }
+function Test-DietaryTag($str) { $str -match '^(GF|GFA|V\+?|DF|DFA|V:|2025|Drink|V\+A)$' }
+
+function Get-Dish($pContent) {
+    $opts = [System.Text.RegularExpressions.RegexOptions]::Singleline
+    $bWithBrM = [regex]::Match($pContent, '(?s)<b>(.*?)<br\s*/?>', $opts)
+    if ($bWithBrM.Success) {
+        $name = Get-CleanText $bWithBrM.Groups[1].Value
+        if ($name.Length -ge 3 -and $name.Length -le 80 -and -not (Test-DietaryTag $name) -and $name -notmatch '^[A-Z]{1,3}:') {
+            return [PSCustomObject]@{ name = $name; desc = Get-CleanText ($pContent.Substring($bWithBrM.Index + $bWithBrM.Length)) }
+        }
+    }
+    $bM = [regex]::Match($pContent, '(?s)<b>(.*?)</b>', $opts)
+    if ($bM.Success) {
+        $namePart = Get-CleanText $bM.Groups[1].Value
+        if ($namePart.Length -ge 3 -and -not (Test-DietaryTag $namePart)) {
+            $afterB = $pContent.Substring($bM.Index + $bM.Length)
+            $sM2 = [regex]::Match($afterB, '(?s)^[^<]*<strong>(.*?)</strong>(.*)', $opts)
+            if ($sM2.Success) {
+                $p2 = Get-CleanText $sM2.Groups[1].Value
+                if (-not (Test-DietaryTag $p2) -and $p2.Length -ge 2) {
+                    return [PSCustomObject]@{ name = "$namePart $p2".Trim(); desc = Get-CleanText $sM2.Groups[2].Value }
+                }
+            }
+            return [PSCustomObject]@{ name = $namePart; desc = Get-CleanText $afterB }
+        }
+    }
+    $sM = [regex]::Match($pContent, '(?s)<strong>(.*?)</strong>', $opts)
+    if ($sM.Success) {
+        $name = Get-CleanText $sM.Groups[1].Value
+        if ($name.Length -lt 3 -or $name.Length -gt 80 -or (Test-DietaryTag $name) -or $name -match '^[A-Z]{1,3}:') { return $null }
+        $afterBr = ''
+        if ($pContent -match '(?s)<br\s*/?>(.*?)$') { $afterBr = $matches[1] }
+        else { $am = [regex]::Match($pContent, '(?s)</strong>(.*?)$', $opts); if ($am.Success) { $afterBr = $am.Groups[1].Value } }
+        return [PSCustomObject]@{ name = $name; desc = Get-CleanText $afterBr }
+    }
+    return $null
+}
+
+function Get-Dishes($courseHtml) {
+    $dishes = [System.Collections.ArrayList]@()
+    $opts = [System.Text.RegularExpressions.RegexOptions]::Singleline
+    foreach ($pm in [regex]::Matches($courseHtml, '(?s)<p[^>]*>(.*?)</p>', $opts)) {
+        $pc = $pm.Groups[1].Value
+        if ($pc -notmatch '<b>|<strong>') { continue }
+        $d = Get-Dish $pc
+        if ($d -and $d.name) { $null = $dishes.Add($d) }
+    }
+    return ,$dishes
+}
+
+function Get-CourseBlock($html, $label, $nextLabel) {
+    $opts = [System.Text.RegularExpressions.RegexOptions]::Singleline
+    if ($nextLabel) {
+        $m = [regex]::Match($html, ([regex]::Escape($label) + '(.+?)(?=' + [regex]::Escape($nextLabel) + ')'), $opts)
+        if ($m.Success) { return $m.Groups[1].Value }
+    }
+    $idx = $html.IndexOf($label)
+    if ($idx -ge 0) {
+        $sub = $html.Substring($idx, [Math]::Min(8000, $html.Length - $idx))
+        $sameDivM = [regex]::Match($sub, '(?s)</h[123]>\s*(<p.+?)(?=</div>)', $opts)
+        if ($sameDivM.Success -and $sameDivM.Groups[1].Value -match '<p') { return $sameDivM.Groups[1].Value }
+        $im = [regex]::Match($sub, '(?s)et_pb_text_inner">(?!<h[123])(.+?)(?=et_pb_text_inner"><h|</div>\s*</div>\s*</div>\s*</div>\s*<div)', $opts)
+        if ($im.Success) { return $im.Groups[1].Value }
+    }
+    return ''
+}
+
+$r = $data | Where-Object { $_.slug -eq 'tavolata' }
+Write-Host "tavolata currently: $($r.menu.courses.'First Course'.Count)/$($r.menu.courses.'Second Course'.Count)/$($r.menu.courses.'Third Course'.Count)"
+
+$timestamps = @('20250306132630','20250401000000','20250415000000','20250501000000')
+$success = $false
+
+foreach ($ts in $timestamps) {
+    if ($success) { break }
+    Write-Host "Trying timestamp $ts..." -NoNewline
+    try {
+        $url = "https://web.archive.org/web/$ts/https://inlanderrestaurantweek.com/project/tavolata/"
+        $resp = Invoke-WebRequest -Uri $url -UseBasicParsing -TimeoutSec 60 -ErrorAction Stop
+        $html = $resp.Content
+        if ($html -match '429 Too Many') { throw "Rate limited" }
+
+        $first  = Get-Dishes (Get-CourseBlock $html 'First Course' 'Second Course')
+        $second = Get-Dishes (Get-CourseBlock $html 'Second Course' 'Third Course')
+        $third  = Get-Dishes (Get-CourseBlock $html 'Third Course' $null)
+
+        Write-Host " -> $($first.Count)/$($second.Count)/$($third.Count)"
+
+        if ($third.Count -gt 0) {
+            if ($first.Count -gt 0)  { $r.menu.courses.'First Course'  = @($first) }
+            if ($second.Count -gt 0) { $r.menu.courses.'Second Course' = @($second) }
+            $r.menu.courses.'Third Course' = @($third)
+            Write-Host "SUCCESS! tavolata Third Course recovered." -ForegroundColor Green
+            $success = $true
+        } else {
+            Write-Host "  Third Course still empty, trying next timestamp..."
+        }
+    } catch {
+        Write-Host " ERROR: $_" -ForegroundColor Red
+    }
+    Start-Sleep -Seconds 10
+}
+
+if (-not $success) {
+    Write-Host "Could not recover tavolata Third Course. Try again later." -ForegroundColor Yellow
+} else {
+    $json = $data | ConvertTo-Json -Depth 10
+    [System.IO.File]::WriteAllText($jsonPath, $json, [System.Text.Encoding]::UTF8)
+    Write-Host "Saved to $jsonPath"
+}