feat(seo): split the sitemap into a per-family index

Search Console reports coverage per submitted sitemap, so one file per page
family is what will make W2's location pages measurable when they land. The
index's lastmod is generation time, which is the correct semantic there —
unlike on a <url>, where it would be a claim we cannot support.

Children sit under /sitemaps/ because Next only treats a whole bracketed path
segment as dynamic; a route folder named sitemap-[...parts] would be read as a
literal static segment and never match. Confirmed by the build output, which
lists /sitemaps/[...parts] as a dynamic route.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015mWQnpye9F299NVRCCSRvj

backend/app.py

@@ -7,6 +7,7 @@ Uses real data from UK Government Compare School Performance downloads.
 import hashlib
 import re
 from contextlib import asynccontextmanager
+from datetime import datetime, timezone
 from typing import Optional
 
 import numpy as np
@@ -53,8 +54,9 @@ PHASE_GROUPS: dict[str, set[str]] = {
 BASE_URL = "https://www.schoolcompare.co.uk"
 MAX_SLUG_LENGTH = 60
 
-# In-memory sitemap cache
-_sitemap_xml: str | None = None
+# In-memory sitemap cache: name -> XML. Populated on startup and by the admin
+# regenerate endpoint after a pipeline run.
+_sitemaps: dict[str, str] | None = None
 
 
 def _slugify(text: str) -> str:
@@ -135,16 +137,65 @@ def _school_sitemap_rows(df) -> list[str]:
     return rows
 
 
-def build_sitemap() -> str:
-    """Generate sitemap XML from in-memory school data. Returns the XML string."""
+# Sitemaps cap at 50,000 URLs per file. 10,000 keeps a child small enough to
+# scan by eye in Search Console, which is the point of splitting at all:
+# coverage is reported per submitted sitemap, so one file per page family is
+# what makes an indexation problem attributable to a family.
+SITEMAP_CHUNK_SIZE = 10_000
+
+# Children are served under /sitemaps/ because Next.js only treats a whole
+# bracketed path segment as dynamic — a route folder named "sitemap-[...parts]"
+# is read as a literal static segment and never matches.
+SITEMAP_CHILD_PREFIX = "/sitemaps"
+
+
+def _urlset(rows: list[str]) -> str:
+    return "\n".join([
+        '<?xml version="1.0" encoding="UTF-8"?>',
+        '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">',
+        *rows,
+        "</urlset>",
+    ])
+
+
+def build_sitemaps() -> dict[str, str]:
+    """Build the sitemap index and every child, keyed by name."""
     df = load_school_data()
 
-    lines = ['<?xml version="1.0" encoding="UTF-8"?>',
-             '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">']
-    lines.extend(_url_element(BASE_URL + path) for path in STATIC_SITEMAP_PATHS)
-    lines.extend(_school_sitemap_rows(df))
-    lines.append("</urlset>")
-    return "\n".join(lines)
+    children: dict[str, str] = {
+        "static.xml": _urlset(
+            [_url_element(BASE_URL + path) for path in STATIC_SITEMAP_PATHS]),
+    }
+
+    school_rows = _school_sitemap_rows(df)
+    # Always emit at least one school child, so the index shape is stable even
+    # on an empty database.
+    chunks = [school_rows[i:i + SITEMAP_CHUNK_SIZE]
+              for i in range(0, len(school_rows), SITEMAP_CHUNK_SIZE)] or [[]]
+    for n, chunk in enumerate(chunks, start=1):
+        children[f"schools-{n}.xml"] = _urlset(chunk)
+
+    # On a sitemap index, lastmod means "when this sitemap file last changed",
+    # so generation time is the correct value here — unlike on a <url>, where
+    # it would be a claim about content we cannot support.
+    generated = datetime.now(timezone.utc).date().isoformat()
+    index_rows = [
+        f"  <sitemap><loc>{BASE_URL}{SITEMAP_CHILD_PREFIX}/{name}</loc>"
+        f"<lastmod>{generated}</lastmod></sitemap>"
+        for name in children
+    ]
+    index = "\n".join([
+        '<?xml version="1.0" encoding="UTF-8"?>',
+        '<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">',
+        *index_rows,
+        "</sitemapindex>",
+    ])
+    return {**children, "sitemap.xml": index}
+
+
+def build_sitemap() -> str:
+    """The sitemap index. Kept for `lifespan` and the admin endpoint."""
+    return build_sitemaps()["sitemap.xml"]
 
 
 def clean_filter_values(series: pd.Series) -> list[str]:
@@ -322,7 +373,7 @@ def validate_postcode(postcode: Optional[str]) -> Optional[str]:
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     """Application lifespan - startup and shutdown events."""
-    global _sitemap_xml
+    global _sitemaps
     print("Loading school data from marts...")
     df = load_school_data()
     if df.empty:
@@ -332,9 +383,9 @@ async def lifespan(app: FastAPI):
         # Pre-compute the latest-year snapshot so the first search request is fast
         await asyncio.to_thread(load_latest_school_data)
     try:
-        _sitemap_xml = build_sitemap()
-        n = _sitemap_xml.count("<url>")
-        print(f"Sitemap built: {n} URLs.")
+        _sitemaps = build_sitemaps()
+        n = sum(x.count("<url>") for x in _sitemaps.values())
+        print(f"Sitemaps built: {len(_sitemaps)} files, {n} URLs.")
     except Exception as e:
         print(f"Warning: sitemap build failed on startup: {e}")
 
@@ -1125,16 +1176,28 @@ async def robots_txt():
     return FileResponse(settings.frontend_dir / "robots.txt", media_type="text/plain")
 
 
-@app.get("/sitemap.xml")
-async def sitemap_xml():
-    """Serve sitemap.xml for search engine indexing."""
-    global _sitemap_xml
-    if _sitemap_xml is None:
+def _serve_sitemap(name: str) -> Response:
+    global _sitemaps
+    if _sitemaps is None:
         try:
-            _sitemap_xml = build_sitemap()
+            _sitemaps = build_sitemaps()
         except Exception as e:
             raise HTTPException(status_code=503, detail=f"Sitemap unavailable: {e}")
-    return Response(content=_sitemap_xml, media_type="application/xml")
+    if name not in _sitemaps:
+        raise HTTPException(status_code=404, detail="No such sitemap")
+    return Response(content=_sitemaps[name], media_type="application/xml")
+
+
+@app.get("/sitemap.xml")
+async def sitemap_xml():
+    """Serve the sitemap index."""
+    return _serve_sitemap("sitemap.xml")
+
+
+@app.get("/sitemaps/{name}")
+async def sitemap_child(name: str):
+    """Serve a child sitemap (static.xml, or schools-N.xml)."""
+    return _serve_sitemap(name)
 
 
 @app.post("/api/admin/regenerate-sitemap")
@@ -1144,10 +1207,10 @@ async def regenerate_sitemap(
     _: bool = Depends(verify_admin_api_key),
 ):
     """Rebuild and cache the sitemap from current school data. Called by Airflow after data updates."""
-    global _sitemap_xml
-    _sitemap_xml = build_sitemap()
-    n = _sitemap_xml.count("<url>")
-    return {"status": "ok", "urls": n}
+    global _sitemaps
+    _sitemaps = build_sitemaps()
+    n = sum(x.count("<url>") for x in _sitemaps.values())
+    return {"status": "ok", "urls": n, "sitemaps": len(_sitemaps)}
 
 
 # Mount static files directly (must be after all routes to avoid catching API calls)