gendesign/backend/app/workers/tasks/scrape_kn.py
lekss361 79070bfe99 add interactive parser of наш.дом.рф ЖК+flats with stealth Playwright
- Discovered real endpoints via chrome-devtools: /сервисы/api/kn/object
  (offset/limit/place/objStatus) + /portal-kn/api/sales/portal/table.
  Server-side filter ignored — local filter by developer.companyGroup.
- Pure Playwright in-context fetch (httpx blocked by ServicePipe TLS-fp).
- Saved fingerprint state in data/playwright_state.json for server reuse.
- Celery beat (configurable cron + jitter) + admin trigger endpoint
  + /admin/scrape UI page.
- Schema migration: UNIQUE(id, snapshot_date) for versioned snapshots,
  kn_scrape_runs journal.
- Smoke-tested on PRINZIP: 28 ЖК / 826 квартир as expected.
2026-04-27 17:58:40 +03:00

52 lines
1.7 KiB
Python

"""Celery task wrapper for naш.дом.рф kn-API sweeps."""
from __future__ import annotations
import asyncio
import logging
import random
import time
from pathlib import Path
from typing import Any
from app.core.config import settings
from app.services.scrapers.domrf_kn import run_region_sweep
from app.workers.celery_app import celery_app
logger = logging.getLogger(__name__)
@celery_app.task(bind=True, name="tasks.scrape_kn.scrape_kn_region", max_retries=2)
def scrape_kn_region(
self: Any,
region_code: int,
developers: list[str] | None = None,
skip_jitter: bool = False,
) -> dict[str, Any]:
"""Run a full kn-API sweep for one region. Returns summary dict.
For scheduled runs (skip_jitter=False), sleeps a random 0..SCRAPE_KN_JITTER_SECONDS
interval before starting so multiple workers / repeated weekly cycles don't hit
DOM.РФ at exactly the same minute. Manual triggers pass skip_jitter=True for
immediate execution.
"""
if not skip_jitter and settings.scrape_kn_jitter_seconds > 0:
delay = random.uniform(0, settings.scrape_kn_jitter_seconds)
logger.info("jitter delay %.0fs before scrape", delay)
time.sleep(delay)
state_path: str | None = settings.scrape_kn_state_path or None
if state_path and not Path(state_path).exists():
logger.warning("storage_state %s not found — bootstrap will run cold", state_path)
state_path = None
logger.info(
"scrape_kn_region start region=%s devs=%s state=%s", region_code, developers, state_path
)
return asyncio.run(
run_region_sweep(
region_code=region_code,
developers=developers,
load_state=state_path,
)
)