bot-backend
52fc920507
Old HTML scraper dead: /search?city_id retired in DomClick redesign + VPS IP QRATOR-banned (prod domclick_city_sweep reported done/0 every run). New path: - GET bff-search-web.domclick.ru/api/offers/v1 + count/v1 via BrowserFetcher(source="domclick") -> generic provider -> shared mobile proxy -> bypasses QRATOR (prod-verified live: 20 items returned, no block). - Sweeps 6 room buckets (st/1/2/3/4/5+); recursive binary price-split for oversized buckets (rooms=2 ~2215 > offset cap 2000); count/v1 sizes buckets. - Maps SERP JSON -> ScrapedLot with lat/lon at ~100% (closes avito 54% NULL-lat gap); per-card EKB geo-guard. - Honest status (#1968): QRATOR block OR fetch errors with 0 lots -> mark_failed, not mark_done. Parse failures are per-page resilient (break bucket, keep partial lots) so a transient bad page never aborts the whole sweep. - Schedule shipped DORMANT (enabled=false, pages=100) via 138_domclick_bff_rewrite_schedule.sql; operator enables after prod smoke. 42 scraper tests (price-split boundaries, parse-error resilience, honest status); full backend suite green; ruff clean. Layer B (detail renovation/wallType/ priceHistory) deferred to #1846 follow-up.
372 lines
13 KiB
Python
372 lines
13 KiB
Python
"""Offline unit tests for run_domclick_city_sweep + DomClick parser.
|
||
|
||
Pure & fast: NO live network, NO DB. Mirrors test_cian_city_sweep orchestration
|
||
semantics, but DomClick is CITYWIDE (no anchor-loop) и SERP-only (no detail/houses).
|
||
|
||
Coverage:
|
||
- fetch_city вызывается, save_listings получает накопленные lots с source='domklik'
|
||
- DomClickCitySweepCounters корректно заполняется (lots_fetched/inserted/updated)
|
||
- Cooperative cancel прерывает sweep перед SERP
|
||
- fetch_city exception не валит sweep (graceful, errors_count++, mark_done)
|
||
- _parse_html: минимальная DomClick карточка → ScrapedLot с rooms/area/floor/price
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import os
|
||
|
||
os.environ.setdefault("DATABASE_URL", "postgresql+psycopg://test:test@localhost:5432/test")
|
||
|
||
from typing import Any
|
||
from unittest.mock import MagicMock
|
||
|
||
import pytest
|
||
|
||
from app.services import scrape_pipeline
|
||
from app.services.scrapers.base import ScrapedLot
|
||
from app.services.scrapers.domclick import DomClickScraper
|
||
|
||
|
||
def _fake_lot(offer_id: str) -> ScrapedLot:
|
||
return ScrapedLot(
|
||
source="domklik",
|
||
source_url=f"https://domclick.ru/card/sale__flat__{offer_id}",
|
||
source_id=offer_id,
|
||
address="Екатеринбург, улица Тестовая, 1",
|
||
price_rub=5_000_000,
|
||
area_m2=50.0,
|
||
rooms=2,
|
||
lat=None,
|
||
lon=None,
|
||
)
|
||
|
||
|
||
class _FakeRuns:
|
||
"""Stub для scrape_runs: отслеживает вызовы, поддерживает cooperative cancel."""
|
||
|
||
def __init__(self, *, cancel: bool = False) -> None:
|
||
self.cancel = cancel
|
||
self.heartbeats: list[dict[str, int]] = []
|
||
self.done: dict[str, int] | None = None
|
||
self.failed: tuple[str, dict[str, int]] | None = None
|
||
|
||
def is_cancelled(self, _db: Any, _run_id: int) -> bool:
|
||
return self.cancel
|
||
|
||
def update_heartbeat(self, _db: Any, _run_id: int, counters: dict[str, int]) -> None:
|
||
self.heartbeats.append(dict(counters))
|
||
|
||
def mark_done(self, _db: Any, _run_id: int, counters: dict[str, int]) -> None:
|
||
self.done = dict(counters)
|
||
|
||
def mark_failed(self, _db: Any, _run_id: int, error: str, counters: dict[str, int]) -> None:
|
||
self.failed = (error, dict(counters))
|
||
|
||
|
||
@pytest.fixture(autouse=True)
|
||
def _no_sleep(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
async def _instant(_secs: float) -> None:
|
||
return None
|
||
|
||
monkeypatch.setattr(scrape_pipeline.asyncio, "sleep", _instant)
|
||
|
||
|
||
@pytest.fixture(autouse=True)
|
||
def _stub_domclick_lifecycle(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
"""Нейтрализуем DomClickScraper.__init__/__aenter__/__aexit__ — нет DB/browser."""
|
||
|
||
def _init(self: DomClickScraper) -> None:
|
||
self.request_delay_sec = 0.0
|
||
self.parse_failures = 0
|
||
self.geo_filtered = 0
|
||
self.blocked = False
|
||
self.fetch_errors = 0
|
||
|
||
async def _aenter(self: DomClickScraper) -> DomClickScraper:
|
||
return self
|
||
|
||
async def _aexit(self: DomClickScraper, *_args: Any) -> None:
|
||
return None
|
||
|
||
monkeypatch.setattr(DomClickScraper, "__init__", _init)
|
||
monkeypatch.setattr(DomClickScraper, "__aenter__", _aenter)
|
||
monkeypatch.setattr(DomClickScraper, "__aexit__", _aexit)
|
||
|
||
|
||
def _install_runs(monkeypatch: pytest.MonkeyPatch, fake: _FakeRuns) -> None:
|
||
monkeypatch.setattr(scrape_pipeline.scrape_runs, "is_cancelled", fake.is_cancelled)
|
||
monkeypatch.setattr(scrape_pipeline.scrape_runs, "update_heartbeat", fake.update_heartbeat)
|
||
monkeypatch.setattr(scrape_pipeline.scrape_runs, "mark_done", fake.mark_done)
|
||
monkeypatch.setattr(scrape_pipeline.scrape_runs, "mark_failed", fake.mark_failed)
|
||
|
||
|
||
# ── DomClickCitySweepCounters ───────────────────────────────────────────────
|
||
|
||
|
||
def test_domclick_sweep_counters_defaults() -> None:
|
||
from app.services.scrape_pipeline import DomClickCitySweepCounters
|
||
|
||
c = DomClickCitySweepCounters()
|
||
assert c.lots_fetched == 0
|
||
assert c.lots_inserted == 0
|
||
assert c.lots_updated == 0
|
||
assert c.pages_fetched == 0
|
||
assert c.errors_count == 0
|
||
assert c.blocked == 0
|
||
assert c.geo_filtered == 0
|
||
|
||
|
||
def test_domclick_sweep_counters_to_dict_all_keys() -> None:
|
||
from dataclasses import fields
|
||
|
||
from app.services.scrape_pipeline import DomClickCitySweepCounters
|
||
|
||
c = DomClickCitySweepCounters()
|
||
d = c.to_dict()
|
||
expected = {f.name for f in fields(c)}
|
||
assert set(d.keys()) == expected
|
||
|
||
|
||
# ── Full sweep — фазы и агрегация ──────────────────────────────────────────
|
||
|
||
|
||
async def test_sweep_fetches_and_saves_with_source(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
"""fetch_city → save_listings получает 2 lots с source='domklik', counters заполнены."""
|
||
fetch_calls: list[tuple[int, int]] = []
|
||
save_calls: list[list[ScrapedLot]] = []
|
||
|
||
async def fake_fetch_city(
|
||
self: DomClickScraper,
|
||
city_id: int,
|
||
rooms: list[int] | None = None,
|
||
pages: int = 20,
|
||
) -> list[ScrapedLot]:
|
||
fetch_calls.append((city_id, pages))
|
||
return [_fake_lot("100"), _fake_lot("101")]
|
||
|
||
def fake_save(_db: Any, lots: list, *, run_id: int | None = None) -> tuple[int, int]:
|
||
save_calls.append(list(lots))
|
||
return len(lots), 0
|
||
|
||
monkeypatch.setattr(DomClickScraper, "fetch_city", fake_fetch_city)
|
||
monkeypatch.setattr(scrape_pipeline, "save_listings", fake_save)
|
||
|
||
fake = _FakeRuns()
|
||
_install_runs(monkeypatch, fake)
|
||
|
||
counters = await scrape_pipeline.run_domclick_city_sweep(
|
||
db=MagicMock(),
|
||
run_id=1,
|
||
city_id=4,
|
||
rooms=[1, 2],
|
||
pages=3,
|
||
request_delay_sec=0.0,
|
||
)
|
||
|
||
assert len(fetch_calls) == 1
|
||
assert fetch_calls[0] == (4, 3)
|
||
assert len(save_calls) == 1
|
||
assert len(save_calls[0]) == 2
|
||
assert all(lot.source == "domklik" for lot in save_calls[0])
|
||
assert counters.lots_fetched == 2
|
||
assert counters.lots_inserted == 2
|
||
assert counters.lots_updated == 0
|
||
assert counters.errors_count == 0
|
||
assert fake.done is not None
|
||
assert fake.done["lots_fetched"] == 2
|
||
assert fake.failed is None
|
||
|
||
|
||
async def test_sweep_empty_serp_still_mark_done(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
"""Пустой SERP → save не вызывается, но mark_done всё равно вызывается."""
|
||
save_called = False
|
||
|
||
async def fake_fetch_empty(
|
||
self: DomClickScraper,
|
||
city_id: int,
|
||
rooms: list[int] | None = None,
|
||
pages: int = 20,
|
||
) -> list[ScrapedLot]:
|
||
return []
|
||
|
||
def fake_save(_db: Any, lots: list, *, run_id: int | None = None) -> tuple[int, int]:
|
||
nonlocal save_called
|
||
save_called = True
|
||
return 0, 0
|
||
|
||
monkeypatch.setattr(DomClickScraper, "fetch_city", fake_fetch_empty)
|
||
monkeypatch.setattr(scrape_pipeline, "save_listings", fake_save)
|
||
|
||
fake = _FakeRuns()
|
||
_install_runs(monkeypatch, fake)
|
||
|
||
counters = await scrape_pipeline.run_domclick_city_sweep(
|
||
db=MagicMock(), run_id=2, request_delay_sec=0.0
|
||
)
|
||
|
||
assert save_called is False
|
||
assert counters.lots_fetched == 0
|
||
assert fake.done is not None
|
||
|
||
|
||
async def test_cancel_before_serp_skips_fetch(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
"""Cooperative cancel перед SERP → fetch_city НЕ вызывается, mark_done НЕ вызывается."""
|
||
fetch_called = False
|
||
|
||
async def fake_fetch(
|
||
self: DomClickScraper,
|
||
city_id: int,
|
||
rooms: list[int] | None = None,
|
||
pages: int = 20,
|
||
) -> list[ScrapedLot]:
|
||
nonlocal fetch_called
|
||
fetch_called = True
|
||
return [_fake_lot("1")]
|
||
|
||
monkeypatch.setattr(DomClickScraper, "fetch_city", fake_fetch)
|
||
monkeypatch.setattr(scrape_pipeline, "save_listings", lambda *a, **k: (0, 0))
|
||
|
||
fake = _FakeRuns(cancel=True)
|
||
_install_runs(monkeypatch, fake)
|
||
|
||
counters = await scrape_pipeline.run_domclick_city_sweep(
|
||
db=MagicMock(), run_id=3, request_delay_sec=0.0
|
||
)
|
||
|
||
assert fetch_called is False
|
||
assert counters.lots_fetched == 0
|
||
assert fake.done is None
|
||
|
||
|
||
async def test_fetch_city_exception_no_reraise(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
"""Исключение в fetch_city → errors_count++, sweep НЕ ре-райзит (graceful).
|
||
|
||
Honest-status (#1968): полный крах SERP-фазы (errors_count=1, 0 lots) → mark_failed,
|
||
НЕ mark_done. Run без единого листинга по внешней причине — это реальный failure,
|
||
а не успешный пустой прогон. Re-raise при этом НЕ происходит (task завершается чисто).
|
||
"""
|
||
|
||
async def fake_fetch_fail(
|
||
self: DomClickScraper,
|
||
city_id: int,
|
||
rooms: list[int] | None = None,
|
||
pages: int = 20,
|
||
) -> list[ScrapedLot]:
|
||
raise RuntimeError("browser crashed")
|
||
|
||
monkeypatch.setattr(DomClickScraper, "fetch_city", fake_fetch_fail)
|
||
monkeypatch.setattr(scrape_pipeline, "save_listings", lambda *a, **k: (0, 0))
|
||
|
||
fake = _FakeRuns()
|
||
_install_runs(monkeypatch, fake)
|
||
|
||
counters = await scrape_pipeline.run_domclick_city_sweep(
|
||
db=MagicMock(), run_id=4, request_delay_sec=0.0
|
||
)
|
||
|
||
assert counters.errors_count == 1
|
||
assert counters.lots_fetched == 0
|
||
# 0 lots + error → honest mark_failed (не маскируем как done)
|
||
assert fake.failed is not None
|
||
assert fake.done is None
|
||
|
||
|
||
async def test_fetch_errors_and_no_lots_marks_failed(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
"""Scraper fetch_errors>0 + 0 лотов (без block) → mark_failed (FIX 3 / closes #1968).
|
||
|
||
Нераспознанный block-вариант приходит как fetch_error (не blocked=True), но
|
||
honest-status всё равно обязан пометить run failed при пустом результате.
|
||
"""
|
||
|
||
async def fake_fetch_errs(
|
||
self: DomClickScraper,
|
||
city_id: int,
|
||
rooms: list[int] | None = None,
|
||
pages: int = 100,
|
||
) -> list[ScrapedLot]:
|
||
# Имитируем не-block ошибки извлечения JSON: blocked остаётся False
|
||
self.fetch_errors = 3
|
||
return []
|
||
|
||
monkeypatch.setattr(DomClickScraper, "fetch_city", fake_fetch_errs)
|
||
monkeypatch.setattr(scrape_pipeline, "save_listings", lambda *a, **k: (0, 0))
|
||
|
||
fake = _FakeRuns()
|
||
_install_runs(monkeypatch, fake)
|
||
|
||
counters = await scrape_pipeline.run_domclick_city_sweep(
|
||
db=MagicMock(), run_id=6, request_delay_sec=0.0
|
||
)
|
||
|
||
assert counters.lots_fetched == 0
|
||
assert counters.blocked == 0
|
||
assert counters.errors_count >= 3 # fetch_errors свёрнуты в errors_count
|
||
assert fake.failed is not None
|
||
assert fake.done is None
|
||
|
||
|
||
async def test_blocked_and_no_lots_marks_failed(monkeypatch: pytest.MonkeyPatch) -> None:
|
||
"""QRATOR-блок + 0 лотов → mark_failed (честный статус, closes #1968)."""
|
||
|
||
async def fake_fetch_blocked(
|
||
self: DomClickScraper,
|
||
city_id: int,
|
||
rooms: list[int] | None = None,
|
||
pages: int = 100,
|
||
) -> list[ScrapedLot]:
|
||
# Имитируем QRATOR-блок: установим флаг на scraper и вернём пустой список
|
||
self.blocked = True
|
||
return []
|
||
|
||
monkeypatch.setattr(DomClickScraper, "fetch_city", fake_fetch_blocked)
|
||
monkeypatch.setattr(scrape_pipeline, "save_listings", lambda *a, **k: (0, 0))
|
||
|
||
fake = _FakeRuns()
|
||
_install_runs(monkeypatch, fake)
|
||
|
||
counters = await scrape_pipeline.run_domclick_city_sweep(
|
||
db=MagicMock(), run_id=5, request_delay_sec=0.0
|
||
)
|
||
|
||
assert counters.lots_fetched == 0
|
||
assert counters.blocked == 1
|
||
# Честный статус: mark_failed должен быть вызван, mark_done — нет
|
||
assert fake.failed is not None
|
||
assert "QRATOR" in fake.failed[0]
|
||
assert fake.done is None
|
||
|
||
|
||
# ── _map_item via sweep — quick integration smoke ────────────────────────────
|
||
|
||
|
||
def test_map_item_basic_mapping() -> None:
|
||
"""DomClickScraper._map_item маппит BFF offer-item → ScrapedLot корректно."""
|
||
scraper = DomClickScraper() # __init__ stubbed
|
||
item = {
|
||
"id": 111222333,
|
||
"path": "https://domclick.ru/card/sale__flat__111222333",
|
||
"location": {"lat": 56.838, "lon": 60.612},
|
||
"address": {"displayName": "Екатеринбург, улица Ленина, 10"},
|
||
"objectInfo": {"area": 52.3, "rooms": 2, "floor": 5},
|
||
"house": {"floors": 16, "buildYear": 2010},
|
||
"price": 6_500_000,
|
||
"squarePrice": 124282,
|
||
"flatComplex": None,
|
||
"isRosreestrApproved": False,
|
||
"publishedDate": "2026-06-01T10:00:00+05:00",
|
||
"updatedDate": None,
|
||
"lastPriceHistoryState": None,
|
||
"offerRegionName": "Екатеринбург",
|
||
}
|
||
lot = scraper._map_item(item)
|
||
assert lot is not None
|
||
assert lot.source == "domklik"
|
||
assert lot.source_id == "111222333"
|
||
assert lot.rooms == 2
|
||
assert lot.area_m2 == pytest.approx(52.3)
|
||
assert lot.floor == 5
|
||
assert lot.total_floors == 16
|
||
assert lot.price_rub == 6_500_000
|
||
assert lot.listing_segment == "vtorichka"
|
||
assert lot.lat == pytest.approx(56.838)
|
||
assert lot.lon == pytest.approx(60.612)
|