feat(seo): static sitemap generation job via Airflow
All checks were successful
Build and Push Docker Images / Build Backend (FastAPI) (push) Successful in 45s
Build and Push Docker Images / Build Frontend (Next.js) (push) Successful in 1m5s
Build and Push Docker Images / Build Pipeline (Meltano + dbt + Airflow) (push) Successful in 1m29s
Build and Push Docker Images / Trigger Portainer Update (push) Successful in 0s

- 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>
This commit is contained in:
2026-03-29 15:15:41 +01:00
parent 748891ab31
commit b7bff7bf6b
5 changed files with 156 additions and 56 deletions

View File

@@ -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)

View File

@@ -119,6 +119,8 @@ services:
PG_DATABASE: schoolcompare
TYPESENSE_URL: http://typesense:8108
TYPESENSE_API_KEY: ${TYPESENSE_API_KEY:-changeme}
BACKEND_URL: http://backend:80
ADMIN_API_KEY: ${ADMIN_API_KEY:-changeme}
volumes:
depends_on:

View File

@@ -1,55 +0,0 @@
/**
* Dynamic Sitemap Generation
* Generates sitemap with all school pages and main routes
*/
import { MetadataRoute } from 'next';
import { fetchSchools } from '@/lib/api';
import { schoolUrl } from '@/lib/utils';
const BASE_URL = 'https://schoolcompare.co.uk';
export default async function sitemap(): Promise<MetadataRoute.Sitemap> {
// Static pages
const staticPages: MetadataRoute.Sitemap = [
{
url: BASE_URL,
lastModified: new Date(),
changeFrequency: 'daily',
priority: 1.0,
},
{
url: `${BASE_URL}/compare`,
lastModified: new Date(),
changeFrequency: 'weekly',
priority: 0.8,
},
{
url: `${BASE_URL}/rankings`,
lastModified: new Date(),
changeFrequency: 'weekly',
priority: 0.8,
},
];
// Fetch all schools (in batches if necessary)
try {
const schoolsData = await fetchSchools({
page: 1,
page_size: 10000, // Fetch all schools
});
const schoolPages: MetadataRoute.Sitemap = schoolsData.schools.map((school) => ({
url: `${BASE_URL}${schoolUrl(school.urn, school.school_name)}`,
lastModified: new Date(),
changeFrequency: 'monthly',
priority: 0.6,
}));
return [...staticPages, ...schoolPages];
} catch (error) {
console.error('Failed to generate sitemap:', error);
// Return just static pages if school fetch fails
return staticPages;
}
}

View File

@@ -6,11 +6,16 @@ const nextConfig = {
// API Proxy to FastAPI backend
async rewrites() {
const apiUrl = process.env.FASTAPI_URL || 'http://localhost:8000/api';
const backendUrl = apiUrl.replace(/\/api$/, '');
return [
{
source: '/api/:path*',
destination: `${apiUrl}/:path*`,
},
{
source: '/sitemap.xml',
destination: `${backendUrl}/sitemap.xml`,
},
];
},

View File

@@ -0,0 +1,62 @@
"""
Sitemap Generation DAG
Rebuilds the sitemap.xml on the backend after data updates so search engines
get fresh school URLs. Runs weekly (Sunday 05:00) and can be triggered manually.
"""
from __future__ import annotations
from datetime import datetime, timedelta
from airflow import DAG
try:
from airflow.providers.standard.operators.bash import BashOperator
except ImportError:
from airflow.operators.bash import BashOperator
default_args = {
"owner": "school-compare",
"depends_on_past": False,
"email_on_failure": False,
"retries": 2,
"retry_delay": timedelta(minutes=5),
}
with DAG(
dag_id="sitemap_generate",
default_args=default_args,
description="Rebuild sitemap.xml on the backend after school data updates",
schedule="0 5 * * 0", # Sundays 05:00 — after the weekly data window
start_date=datetime(2025, 1, 1),
catchup=False,
tags=["school-compare", "seo"],
) as dag:
regenerate_sitemap = BashOperator(
task_id="call_regenerate_sitemap",
bash_command="""
set -e
BACKEND_URL="${BACKEND_URL:-http://backend:80}"
ADMIN_KEY="${ADMIN_API_KEY:-changeme}"
echo "Calling $BACKEND_URL/api/admin/regenerate-sitemap ..."
response=$(curl -s -o /tmp/sitemap_response.json -w "%{http_code}" \\
-X POST "$BACKEND_URL/api/admin/regenerate-sitemap" \\
-H "X-API-Key: $ADMIN_KEY" \\
-H "Content-Type: application/json")
echo "HTTP status: $response"
cat /tmp/sitemap_response.json
if [ "$response" != "200" ]; then
echo "ERROR: sitemap regeneration failed (HTTP $response)"
exit 1
fi
urls=$(python3 -c "import json,sys; d=json.load(open('/tmp/sitemap_response.json')); print(d.get('urls', '?'))")
echo "Sitemap regenerated: $urls URLs."
""",
)