perfect-postcode/finder/main.py
2026-02-15 22:39:54 +00:00

111 lines
3.2 KiB
Python

import logging
import threading
import time
from pathlib import Path
from flask import Flask, Response, jsonify, send_from_directory
from prometheus_client import generate_latest, CONTENT_TYPE_LATEST
from constants import DATA_DIR
from rightmove import outcode_cache
from scraper import (
_sync_gauges,
build_postcode_index,
load_outcodes,
run_scrape,
status,
status_lock,
)
# ---------------------------------------------------------------------------
# Logging
# ---------------------------------------------------------------------------
LOG_DIR = Path("/app/data")
LOG_DIR.mkdir(parents=True, exist_ok=True)
logging.basicConfig(
level=logging.DEBUG,
format="%(asctime)s [%(levelname)s] %(message)s",
handlers=[
logging.StreamHandler(),
logging.FileHandler(LOG_DIR / "rightmove.log"),
],
)
log = logging.getLogger("rightmove")
log.setLevel(logging.DEBUG)
logging.getLogger("httpx").setLevel(logging.WARNING)
logging.getLogger("httpcore").setLevel(logging.WARNING)
# ---------------------------------------------------------------------------
# Startup: load data
# ---------------------------------------------------------------------------
log.info("Loading arcgis data...")
OUTCODES = load_outcodes()
PC_INDEX = build_postcode_index()
log.info("Ready — %d outcodes, postcode index built", len(OUTCODES))
# ---------------------------------------------------------------------------
# Flask app
# ---------------------------------------------------------------------------
app = Flask(__name__)
@app.route("/run", methods=["POST"])
def trigger_run():
with status_lock:
if status.state == "running":
return jsonify({"error": "Scrape already running"}), 409
status.state = "running"
thread = threading.Thread(target=run_scrape, args=(OUTCODES, PC_INDEX), daemon=True)
thread.start()
return jsonify({"message": "Scrape started"}), 200
@app.route("/status")
def get_status():
with status_lock:
elapsed = 0.0
if status.started_at:
end = status.finished_at if status.finished_at else time.time()
elapsed = end - status.started_at
return jsonify({
"state": status.state,
"channel": status.channel,
"outcode": status.outcode,
"outcodes_done": status.outcodes_done,
"outcodes_total": status.outcodes_total,
"properties_buy": status.properties_buy,
"properties_rent": status.properties_rent,
"errors": status.errors[-20:], # last 20 errors
"elapsed_seconds": round(elapsed, 1),
})
@app.route("/debug")
def get_debug():
return jsonify({
"outcode_cache_size": len(outcode_cache),
"outcode_cache_sample": dict(list(outcode_cache.items())[:20]),
})
@app.route("/metrics")
def metrics():
with status_lock:
_sync_gauges()
return Response(generate_latest(), mimetype=CONTENT_TYPE_LATEST)
@app.route("/data/<filename>")
def serve_data(filename):
if not filename.endswith(".parquet"):
return jsonify({"error": "Only parquet files served"}), 400
return send_from_directory(DATA_DIR, filename)
if __name__ == "__main__":
app.run(host="0.0.0.0", port=1234, debug=False)