SEO: verify live indexable HTML for 12 official GSC Toolify inspection URLs

.github/workflows/toolify-live-index.yml

@@ -0,0 +1,38 @@
+name: Toolify live indexability recovery (12 URLs)
+on:
+  pull_request:
+    paths:
+      - 'scripts/toolify-live-index-gate.mjs'
+      - 'scripts/tests/toolify-live-index-gate.test.mjs'
+      - '.github/workflows/toolify-live-index.yml'
+  push:
+    branches: [main]
+    paths:
+      - 'scripts/toolify-live-index-gate.mjs'
+      - '.github/workflows/toolify-live-index.yml'
+  workflow_dispatch:
+jobs:
+  source:
+    runs-on: ubuntu-latest
+    timeout-minutes: 4
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '22'
+      - run: node --test scripts/tests/toolify-live-index-gate.test.mjs
+  live:
+    needs: source
+    if: github.event_name != 'pull_request'
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '22'
+      - run: node scripts/toolify-live-index-gate.mjs

scripts/tests/toolify-live-index-gate.test.mjs

@@ -0,0 +1,38 @@
+import test from "node:test";
+import assert from "node:assert/strict";
+import {readFileSync} from "node:fs";
+import {fileURLToPath} from "node:url";
+import {targets,urlFor,inspectHTML} from "../toolify-live-index-gate.mjs";
+
+const source=readFileSync(fileURLToPath(new URL("../../site/src/lib/tools/registry.ts",import.meta.url)),"utf8");
+function sourceBlock(start,end) {
+  const a=source.indexOf(start),b=source.indexOf(end,a+start.length);
+  assert.ok(a>=0&&b>a,"registry source declarations absent");
+  return source.slice(a,b);
+}
+test("12 nonduplicated source-indexable official-inspection URLs",()=>{
+ assert.equal(targets.length,12);
+ assert.equal(new Set(targets.map(urlFor)).size,12);
+ const core=sourceBlock("export const CORE_TOOLS_BY_DEMAND =","] as const;");
+ const exceptions=sourceBlock("export const INDEX_EXCEPTIONS:", "\n};");
+ for(const [loc,slug,type] of targets) {
+   if(type==="core") assert.ok(core.includes('"'+slug+'"'),loc+"/"+slug+" missing core");
+   else assert.ok(new RegExp("\\b"+loc+":\\s*\\[[^\\]]*\\\""+slug+"\\\"").test(exceptions),
+     loc+"/"+slug+" missing locale exception");
+ }
+});
+test("existing old Google noindex status must not override valid current HTTP+canonical",()=>{
+ const url=urlFor(targets[6]);
+ const html='<html><head><title>Date Calculator</title><link rel="canonical" href="'+url+
+   '"><meta name="robots" content="index, follow"></head><body>Tool</body></html>';
+ assert.equal(inspectHTML(html,{get:()=>null},url,200,url).pass,true);
+});
+test("reject noindex, missing canonical, bad HTTP and redirect",()=>{
+ const url=urlFor(targets[0]);
+ const html='<html><head><title>Workdays</title><link href="'+url+'" rel="canonical"></head></html>';
+ assert.ok(inspectHTML(html,{get:()=>null},url,200,url).pass);
+ assert.ok(!inspectHTML(html.replace('</head>','<meta content="noindex, follow" name="googlebot"></head>'),{get:()=>null},url,200,url).pass);
+ assert.ok(!inspectHTML(html,{get:()=> "noindex"},url,200,url).pass);
+ assert.ok(!inspectHTML(html,{get:()=>null},url,404,url).pass);
+ assert.ok(!inspectHTML(html,{get:()=>null},url,200,url+"/").pass);
+});

scripts/toolify-live-index-gate.mjs

@@ -0,0 +1,74 @@
+#!/usr/bin/env node
+/**
+ * Read-only exact live indexability diagnosis for the fixed 12 URL cohort
+ * Google URL Inspection inspected on 2026-10-26.
+ * It NEVER submits URLs to Google, updates robots, or touches credentials.
+ * Google cached 4 noindex statuses from July; the source's October policy
+ * intends all 12 to be indexable. Verify what is really PUBLIC today.
+ */
+export const targets = [
+  ["en", "workdays-calculator", "core"],
+  ["en", "date-calculator", "core"],
+  ["en", "pressure-converter", "core"],
+  ["en", "unit-price-calculator", "core"],
+  ["ja", "workdays-calculator", "core"],
+  ["ja", "pressure-converter", "core"],
+  ["th", "date-calculator", "exception"],
+  ["ru", "pressure-converter", "exception"],
+  ["tr", "grade-calculator", "exception"],
+  ["ar", "length-converter", "exception"],
+  ["fr", "speed-converter", "exception"],
+  ["es", "due-date-calculator", "exception"],
+];
+export const base="https://toolify365.com";
+export const urlFor=([loc,slug])=>base+"/"+loc+"/tools/"+slug;
+export function attr(tag,name){
+  const m=tag.match(new RegExp("\\b"+name+"\\s*=\\s*([\"'])(.*?)\\1","i"));
+  if(m)return m[2];
+  const loose=tag.match(new RegExp("\\b"+name+"\\s*=\\s*([^\\s>]+)","i"));
+  return loose?.[1]??null;
+}
+export function inspectHTML(html,headers,url,status,finalUrl){
+  const head=html.split(/<\/head>/i)[0]??"";
+  const metaTags=[...head.matchAll(/<meta\b[^>]*>/gi)].map(x=>x[0]);
+  const robotsMeta=metaTags.filter(t=>["robots","googlebot"].includes((attr(t,"name")??"").toLowerCase()))
+    .map(t=>attr(t,"content")??"").join(",");
+  const xRobots=headers?.get?.("x-robots-tag")??null;
+  const tags=[...head.matchAll(/<link\b[^>]*>/gi)].map(x=>x[0]);
+  const canonicals=tags.filter(t=>(attr(t,"rel")??"").toLowerCase().split(/\s+/).includes("canonical"))
+    .map(t=>attr(t,"href"));
+  const noindex=/(^|[\s,;])noindex($|[\s,;])/i.test(robotsMeta+","+String(xRobots??""));
+  const canonical=canonicals[0]??null;
+  return {url,httpStatus:status,finalUrl,canonical,canonicalCount:canonicals.length,
+    robotsMeta,xRobots,noindex,pass:status===200&&finalUrl===url&&canonicals.length===1&&
+    canonical===url&&!noindex&&/<title\b[^>]*>[^<]+<\/title>/i.test(head)};
+}
+export async function main(){
+ const results=await Promise.all(targets.map(async t=>{
+   const url=urlFor(t);
+   try {
+     const r=await fetch(url,{redirect:"follow",
+       headers:{"Cache-Control":"no-cache","Pragma":"no-cache","User-Agent":"ToolifyIndexSmoke/1.0"},
+       signal:AbortSignal.timeout(20000)});
+     return {...inspectHTML(await r.text(),r.headers,url,r.status,r.url),locale:t[0],slug:t[1],indexIntent:t[2]};
+   }catch(e){return {url,locale:t[0],slug:t[1],indexIntent:t[2],pass:false,error:String(e.message??e)};}
+ }));
+ const bad=results.filter(r=>!r.pass);
+ const summary={checked:results.length,liveIndexable:results.length-bad.length,problems:bad.length,
+   note:"Source intended indexability and live HTML are distinct from Google's cached index verdict. All 12 URL Inspection rows are a selected test cohort, not the whole site.",
+   checkedAtUtc:new Date().toISOString(),results};
+ console.log(JSON.stringify(summary,null,2));
+ if (process.env.GITHUB_STEP_SUMMARY) {
+   const {appendFileSync}=await import("node:fs");
+   appendFileSync(process.env.GITHUB_STEP_SUMMARY,
+     "## Toolify 12URL live indexability\n\n"+
+     "- Pass: "+(results.length-bad.length)+"/12\n"+
+     "- Live failures: "+bad.length+"\n\n"+
+     "| URL | HTTP | canonical | noindex | Result |\n|---|---|---|---|---|\n"+
+     results.map(x=>"| "+x.url+" | "+(x.httpStatus??"ERROR")+" | "+(x.canonical??"missing")+
+       " | "+(x.noindex??"unknown")+" | "+(x.pass?"PASS":"FAIL")+" |").join("\n")+"\n");
+ }
+ if(bad.length)process.exitCode=1;
+}
+if(process.argv[1]?.endsWith("toolify-live-index-gate.mjs"))
+  main().catch(e=>{console.error(e);process.exitCode=2});