backend/app.py

@@ -72,41 +72,77 @@ def _school_url(urn: int, school_name: str) -> str:
     return f"/school/{urn}-{slug}"
 
 
+# Routes worth submitting that are not a school page. /admissions was missing
+# from the sitemap entirely despite being a static, indexable guide.
+STATIC_SITEMAP_PATHS = ("/", "/rankings", "/compare", "/admissions")
+
+
+def _has_publishable_data(row) -> bool:
+    """True when a school page has something a search result could state.
+
+    A school with no results in any year and no Ofsted grade renders an empty
+    page. Submitting it spends crawl budget and drags the corpus-wide quality
+    signal down, so it stays out of the sitemap. The page itself still resolves
+    for anyone who has the URL.
+    """
+    for field in ("rwm_expected_pct", "attainment_8_score", "ofsted_grade"):
+        value = row.get(field)
+        if value is not None and not pd.isna(value):
+            return True
+    return False
+
+
+def _url_element(loc: str, lastmod: str | None = None) -> str:
+    """One <url> entry. No priority or changefreq — Google ignores both."""
+    body = f"<loc>{loc}</loc>"
+    if lastmod:
+        body += f"<lastmod>{lastmod}</lastmod>"
+    return f"  <url>{body}</url>"
+
+
+def _school_sitemap_rows(df) -> list[str]:
+    """A <url> element per school that has something to show.
+
+    lastmod comes from the school's Ofsted date where there is one and is
+    omitted otherwise. An always-now lastmod is a claim Google learns to
+    distrust; an absent one honestly means "unknown".
+    """
+    if df.empty or "urn" not in df.columns or "school_name" not in df.columns:
+        return []
+
+    rows: list[str] = []
+    seen: set[int] = set()
+
+    # Latest row per URN first, so a school's most recent Ofsted date wins.
+    ordered = df.sort_values("year", ascending=False) if "year" in df.columns else df
+
+    for _, row in ordered.iterrows():
+        urn = int(row["urn"])
+        if urn in seen:
+            continue
+        seen.add(urn)
+        if not _has_publishable_data(row):
+            continue
+
+        lastmod = None
+        ofsted_date = row.get("ofsted_date")
+        if ofsted_date is not None and not pd.isna(ofsted_date):
+            lastmod = pd.Timestamp(ofsted_date).date().isoformat()
+
+        rows.append(_url_element(
+            BASE_URL + _school_url(urn, str(row["school_name"])), lastmod))
+
+    return rows
+
+
 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.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)
 

backend/tests/test_sitemap.py

@@ -42,3 +42,53 @@ def test_every_loc_uses_the_www_host(sitemap):
     # The apex 301s to www. A <loc> that redirects burns a crawl per URL.
     assert "https://www.schoolcompare.co.uk" in sitemap
     assert "https://schoolcompare.co.uk" not in sitemap
+
+
+def test_school_with_results_is_listed(sitemap):
+    assert "/school/100001-alpha-primary" in sitemap
+
+
+def test_school_with_no_results_and_no_ofsted_is_omitted(sitemap):
+    # Nothing for a search result to say about it. Submitting it spends crawl
+    # budget and drags the corpus-wide quality signal down.
+    assert "/school/100002" not in sitemap
+
+
+def test_no_invented_priority_or_changefreq(sitemap):
+    # Google ignores both. They were noise dressed as signal.
+    assert "<priority>" not in sitemap
+    assert "<changefreq>" not in sitemap
+
+
+def test_ofsted_date_becomes_lastmod(monkeypatch):
+    from backend import app as app_module
+    import datetime
+
+    def _df():
+        base = _schools_df()
+        base.loc[base["urn"] == 100001, "ofsted_date"] = datetime.date(2024, 3, 14)
+        return base
+
+    monkeypatch.setattr(app_module, "load_school_data", _df)
+    xml = app_module.build_sitemap()
+    assert "<lastmod>2024-03-14</lastmod>" in xml
+
+
+def test_no_lastmod_invented_when_date_unknown(monkeypatch):
+    # An always-now lastmod is a claim Google learns to distrust. Absent
+    # honestly means unknown.
+    from backend import app as app_module
+
+    def _df():
+        df = _schools_df()
+        df["ofsted_date"] = None
+        return df
+
+    monkeypatch.setattr(app_module, "load_school_data", _df)
+    xml = app_module.build_sitemap()
+    assert "<lastmod>" not in xml
+
+
+def test_static_routes_are_listed(sitemap):
+    for path in ("/", "/rankings", "/compare", "/admissions"):
+        assert f"<loc>https://www.schoolcompare.co.uk{path}</loc>" in sitemap