feat(seo): static sitemap generation job via Airflow

- Backend builds sitemap.xml from school data at startup (in-memory)
- POST /api/admin/regenerate-sitemap refreshes it after data updates
- New Airflow DAG (sitemap_generate) runs Sundays 05:00 and calls the endpoint
- Next.js proxies /sitemap.xml to the backend; removes the slow dynamic sitemap.ts
- docker-compose passes BACKEND_URL + ADMIN_API_KEY to Airflow env

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

backend/app.py

@@ -35,6 +35,66 @@ from .utils import clean_for_json
 # Values to exclude from filter dropdowns (empty strings, non-applicable labels)
 EXCLUDED_FILTER_VALUES = {"", "Not applicable", "Does not apply"}
 
+BASE_URL = "https://schoolcompare.co.uk"
+MAX_SLUG_LENGTH = 60
+
+# In-memory sitemap cache
+_sitemap_xml: str | None = None
+
+
+def _slugify(text: str) -> str:
+    text = text.lower()
+    text = re.sub(r"[^\w\s-]", "", text)
+    text = re.sub(r"\s+", "-", text)
+    text = re.sub(r"-+", "-", text)
+    return text.strip("-")
+
+
+def _school_url(urn: int, school_name: str) -> str:
+    slug = _slugify(school_name)
+    if len(slug) > MAX_SLUG_LENGTH:
+        slug = slug[:MAX_SLUG_LENGTH].rstrip("-")
+    return f"/school/{urn}-{slug}"
+
+
+def build_sitemap() -> str:
+    """Generate sitemap XML from in-memory school data. Returns the XML string."""
+    df = load_school_data()
+
+    static_urls = [
+        (BASE_URL + "/",          "daily",   "1.0"),
+        (BASE_URL + "/rankings",  "weekly",  "0.8"),
+        (BASE_URL + "/compare",   "weekly",  "0.8"),
+    ]
+
+    lines = ['<?xml version="1.0" encoding="UTF-8"?>',
+             '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">']
+
+    for url, freq, priority in static_urls:
+        lines.append(
+            f"  <url><loc>{url}</loc>"
+            f"<changefreq>{freq}</changefreq>"
+            f"<priority>{priority}</priority></url>"
+        )
+
+    if not df.empty and "urn" in df.columns and "school_name" in df.columns:
+        seen = set()
+        for _, row in df[["urn", "school_name"]].drop_duplicates(subset="urn").iterrows():
+            urn = int(row["urn"])
+            name = str(row["school_name"])
+            if urn in seen:
+                continue
+            seen.add(urn)
+            path = _school_url(urn, name)
+            lines.append(
+                f"  <url><loc>{BASE_URL}{path}</loc>"
+                f"<changefreq>monthly</changefreq>"
+                f"<priority>0.6</priority></url>"
+            )
+
+    lines.append("</urlset>")
+    return "\n".join(lines)
+
 
 def clean_filter_values(series: pd.Series) -> list[str]:
     """Return sorted unique values from a Series, excluding NaN and junk labels."""
@@ -148,12 +208,19 @@ def validate_postcode(postcode: Optional[str]) -> Optional[str]:
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     """Application lifespan - startup and shutdown events."""
+    global _sitemap_xml
     print("Loading school data from marts...")
     df = load_school_data()
     if df.empty:
         print("Warning: No data in marts. Run the annual EES pipeline to populate KS2 data.")
     else:
         print(f"Data loaded successfully: {len(df)} records.")
+    try:
+        _sitemap_xml = build_sitemap()
+        n = _sitemap_xml.count("<url>")
+        print(f"Sitemap built: {n} URLs.")
+    except Exception as e:
+        print(f"Warning: sitemap build failed on startup: {e}")
 
     yield
 
@@ -805,7 +872,26 @@ async def robots_txt():
 @app.get("/sitemap.xml")
 async def sitemap_xml():
     """Serve sitemap.xml for search engine indexing."""
-    return FileResponse(settings.frontend_dir / "sitemap.xml", media_type="application/xml")
+    global _sitemap_xml
+    if _sitemap_xml is None:
+        try:
+            _sitemap_xml = build_sitemap()
+        except Exception as e:
+            raise HTTPException(status_code=503, detail=f"Sitemap unavailable: {e}")
+    return Response(content=_sitemap_xml, media_type="application/xml")
+
+
+@app.post("/api/admin/regenerate-sitemap")
+@limiter.limit("10/minute")
+async def regenerate_sitemap(
+    request: Request,
+    _: 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}
 
 
 # Mount static files directly (must be after all routes to avoid catching API calls)