feat(seo): list public author profiles in the pages sitemap

scripts/seo/public-crawl-smoke.mjs

@@ -64,6 +64,14 @@ async function main() {
     'News sitemap URLs point to the canonical host',
   )
 
+  const { text: pagesXML } = await request('/pages-sitemap.xml')
+  assert(pagesXML.includes('<urlset'), 'pages sitemap returns a URL set')
+  const pageURLs = sitemapLocs(pagesXML)
+  assert(
+    pageURLs.every((url) => new URL(url).host === canonicalHost),
+    'pages sitemap URLs point to the canonical host',
+  )
+
   for (const locale of ['fr', 'en']) {
     const { text: homeHTML } = await request(`/${locale}`)
     const visibleHome = documentWithoutScripts(homeHTML)
@@ -83,6 +91,15 @@ async function main() {
     assert(/<h1\b/i.test(visibleArticle), `${locale} article heading is in the HTML response`)
     assert(!/class="site-skeleton(?:\s|")/i.test(visibleArticle), `${locale} crawler does not receive global placeholder markup`)
     assert(/rel="canonical"/.test(articleHTML) && articleHTML.includes(article), `${locale} article carries its canonical URL`)
+
+    const author = pageURLs.find((url) => new URL(url).pathname.startsWith(`/${locale}/authors/`))
+    assert(Boolean(author), `${locale} pages sitemap lists at least one author profile`)
+    if (!author) continue
+
+    const { text: authorHTML } = await request(new URL(author).pathname)
+    const visibleAuthor = documentWithoutScripts(authorHTML)
+    assert(/<h1\b/i.test(visibleAuthor), `${locale} author profile heading is in the HTML response`)
+    assert(/rel="canonical"/.test(authorHTML) && authorHTML.includes(author), `${locale} author profile carries its canonical URL`)
   }
 }
 

src/app/(frontend)/(sitemaps)/pages-sitemap.xml/route.ts

@@ -5,6 +5,7 @@ import { unstable_cache } from 'next/cache'
 
 import { SITE_IDENTITY } from '@/seo/structuredData'
 import { editorialRubrics, localizedRubricPath } from '@/editorial/rubrics'
+import { buildLocalizedAuthorSitemapEntries } from '@/seo/authorsSitemap'
 
 const localizedEditorialPaths = [
   '',
@@ -43,6 +44,37 @@ const getPagesSitemap = unstable_cache(
     const dateFallback = new Date().toISOString()
     const locales = ['fr', 'en'] as const
 
+    // Author profiles exist only through the posts they sign, per locale.
+    const authorPages = []
+    for (const locale of locales) {
+      const posts = await payload.find({
+        collection: 'posts',
+        overrideAccess: false,
+        draft: false,
+        depth: 0,
+        fallbackLocale: false,
+        locale,
+        limit: 1000,
+        pagination: false,
+        where: {
+          _status: {
+            equals: 'published',
+          },
+        },
+        select: {
+          title: true,
+          slug: true,
+          excerpt: true,
+          content: true,
+          updatedAt: true,
+          authors: true,
+          populatedAuthors: true,
+        },
+      })
+
+      authorPages.push(...buildLocalizedAuthorSitemapEntries(locale, posts.docs, dateFallback))
+    }
+
     const localizedEditorialPages = locales.flatMap((locale) => [
       ...localizedEditorialPaths.map((path) => ({
         loc: `${SITE_URL}/${locale}${path}`,
@@ -64,9 +96,9 @@ const getPagesSitemap = unstable_cache(
           }))
       : []
 
-    return [...localizedEditorialPages, ...cmsPages]
+    return [...localizedEditorialPages, ...authorPages, ...cmsPages]
   },
-  ['pages-sitemap-v4'],
+  ['pages-sitemap-v5'],
   {
     tags: ['pages-sitemap'],
     revalidate: 86400,

src/collections/Posts/hooks/revalidatePost.ts

@@ -14,6 +14,8 @@ import { LLMS_CACHE_TAG } from '@/seo/llms'
 function revalidateEditorialSitemaps() {
   revalidateTag('posts-sitemap', 'max')
   revalidateTag('news-sitemap', 'max')
+  // Author profile URLs in the pages sitemap are derived from published posts.
+  revalidateTag('pages-sitemap', 'max')
   revalidateTag(LLMS_CACHE_TAG, 'max')
 }
 

src/seo/authorsSitemap.ts

@@ -0,0 +1,41 @@
+import { absoluteCanonicalURL } from '@/seo/structuredData'
+import { isPublicLocalizedPost, type PublicSitemapPost } from '@/seo/postsSitemap'
+import type { SiteLocale } from '@/i18n/config'
+import { authorSlug } from '@/utilities/authorSlug'
+
+export type PublicSitemapAuthorPost = PublicSitemapPost & {
+  populatedAuthors?: Array<{ name?: string | null } | null> | null
+}
+
+/**
+ * One canonical entry per public author profile. An author is listed only when
+ * they sign at least one article the localized route can render, which is also
+ * the condition for the profile page itself to return 200.
+ */
+export function buildLocalizedAuthorSitemapEntries(
+  locale: SiteLocale,
+  posts: PublicSitemapAuthorPost[],
+  fallbackDate = new Date().toISOString(),
+) {
+  const lastmodBySlug = new Map<string, string>()
+
+  for (const post of posts) {
+    if (!isPublicLocalizedPost(post)) continue
+    const updatedAt = post.updatedAt || fallbackDate
+
+    for (const author of post.populatedAuthors || []) {
+      const slug = author?.name ? authorSlug(author.name) : ''
+      if (!slug) continue
+
+      const current = lastmodBySlug.get(slug)
+      if (!current || updatedAt > current) lastmodBySlug.set(slug, updatedAt)
+    }
+  }
+
+  return [...lastmodBySlug.entries()]
+    .sort(([a], [b]) => a.localeCompare(b))
+    .map(([slug, lastmod]) => ({
+      loc: absoluteCanonicalURL(`/${locale}/authors/${slug}`),
+      lastmod,
+    }))
+}

tests/unit/authorsSitemap.spec.ts

@@ -0,0 +1,61 @@
+import { describe, expect, it } from 'vitest'
+
+import { buildLocalizedAuthorSitemapEntries } from '@/seo/authorsSitemap'
+
+const content = { root: { children: [] } }
+
+describe('localized author profile sitemap', () => {
+  it('lists each author once with the canonical URL and latest article date', () => {
+    expect(
+      buildLocalizedAuthorSitemapEntries('fr', [
+        {
+          slug: 'older',
+          title: 'Older',
+          excerpt: 'Summary',
+          content,
+          updatedAt: '2026-10-01T10:00:00.000Z',
+          populatedAuthors: [{ name: 'Éloïse Ngono' }, { name: 'Team Trigenys' }],
+        },
+        {
+          slug: 'newer',
+          title: 'Newer',
+          excerpt: 'Summary',
+          content,
+          updatedAt: '2026-10-11T10:00:00.000Z',
+          populatedAuthors: [{ name: 'Eloise Ngono' }],
+        },
+      ]),
+    ).toEqual([
+      {
+        loc: 'https://insight.trigenys.com/fr/authors/eloise-ngono',
+        lastmod: '2026-10-11T10:00:00.000Z',
+      },
+      {
+        loc: 'https://insight.trigenys.com/fr/authors/team-trigenys',
+        lastmod: '2026-10-01T10:00:00.000Z',
+      },
+    ])
+  })
+
+  it('skips authors whose only articles cannot render in that locale', () => {
+    expect(
+      buildLocalizedAuthorSitemapEntries('en', [
+        {
+          slug: 'untranslated',
+          title: '',
+          excerpt: null,
+          content: null,
+          updatedAt: '2026-10-11T10:00:00.000Z',
+          populatedAuthors: [{ name: 'French Only' }],
+        },
+        {
+          slug: 'anonymous',
+          title: 'Anonymous',
+          excerpt: 'Summary',
+          content,
+          populatedAuthors: [null, { name: '  ' }],
+        },
+      ]),
+    ).toEqual([])
+  })
+})

tests/unit/seoPublicCrawl.spec.ts

@@ -31,6 +31,8 @@ describe('P0: public crawl entry points', () => {
     expect(script).toContain('posts-sitemap.xml')
     expect(script).toContain('article-reading-main')
     expect(script).toContain('rel="canonical"')
+    expect(script).toContain('pages-sitemap.xml')
+    expect(script).toContain('/authors/')
   })
 })