gendesign/tradein-mvp/backend/tests/test_cian_city_sweep.py
bot-backend 79a77200d7
All checks were successful
CI Trade-In / changes (pull_request) Successful in 10s
CI / changes (pull_request) Successful in 9s
CI Trade-In / frontend-checks (pull_request) Has been skipped
CI / backend-tests (pull_request) Has been skipped
CI / frontend-tests (pull_request) Has been skipped
CI / openapi-codegen-check (pull_request) Has been skipped
CI Trade-In / backend-tests (pull_request) Successful in 1m43s
refactor(tradein/scrapers): удалить legacy scrape_pipeline.py + тест-хирургия (#2397 Part E1)
app.services.scrape_pipeline (3734 строк) имел 0 runtime-импортёров — Part C убрал
последнего вызывающего (admin.py, scheduler_main.py уже на
scraper_kit.orchestration.pipeline). Удаление:

- backend/app/services/scrape_pipeline.py — удалён целиком

Тесты (18 файлов, импортировавших scrape_pipeline):

DELETE (чистая legacy-оркестрация, kit-эквивалент покрыт в
test_scraper_kit_pipeline_parity{,2}.py):
- test_scrape_pipeline.py, test_scrape_pipeline_proxy_pool.py (proxy-pool DB-lease
  вытеснен RealProxyProvider DI-адаптером, покрытым test_scraper_adapters_contracts.py)
- test_anchor_watchdog.py, test_ban_rotation_1790.py, test_provider_rotation_1848.py
- test_scraper_resilience_1949_1950.py, test_sweep_drain.py

CONVERT (parity-сравнение убрано, kit-only regression оставлен/усилен):
- test_scraper_kit_pipeline_parity.py, test_scraper_kit_pipeline_parity2.py —
  _drive_old убран, _drive_new стал единственной веткой; ассёрты на конкретные
  значения counters сохранены (это теперь основное regression-покрытие kit
  orchestration)
- test_sweep_imv_phase.py — 6 IMV-phase тестов (enrich_imv true/false/no-touched/
  crash/failed-counter/cancel) переведены на run_avito_city_sweep (kit) с DI
  (config/matcher/enrichment); enrichment.process_houses_imv_batch — инжектируемый
  Protocol-метод вместо прямого импорта app.services.house_imv_backfill

PARTIAL-EDIT (легаси sweep-behavior вырезан, admin/kit-DI/несвязанные тесты
оставлены):
- test_city_sweep.py — только retarget 4 импортов на scraper_kit.orchestration.pipeline
- test_cian_city_sweep.py, test_yandex_city_sweep.py — sweep-behavior секции удалены,
  admin endpoint тесты (уже kit-DI) + anchor-timeout/watchdog формулы (retarget import)
  оставлены
- test_domclick_sweep.py — sweep-wiring тесты удалены, Counters + _map_item оставлены
- test_avito_newbuilding_sweep.py — sweep-wiring тест #5 удалён, retarget
  NewbuildingSweepCounters
- test_pipeline_browser_routing.py — 3 run_avito_pipeline теста удалены, browser-routing
  на уровне fetch_detail/fetch_house_catalog/AvitoScraper не тронут
- test_scraper_proxy.py, tests/scrapers/test_avito_anti_bot.py — _avito_proxies()
  переведён на kit (DI-параметр вместо settings-patch); pipeline-level тесты удалены

Stale-комментарии (scrape_pipeline.py как текущая реальность) поправлены в
admin.py, avito_detail_backfill.py, house_imv_backfill.py, yandex_price_history.py,
scrapers/avito_detail.py + kit-пакете (orchestration/__init__.py, orchestration
/pipeline.py, providers/avito/detail.py — strangler завершён, легаси удалён).

grep -rn scrape_pipeline app/ scripts/ packages/ — только past-tense упоминания
("удалён в Part E1", "перед его удалением") + один historical footnote
(contracts.py:138, provenance-заметка "собраны grep'ом по ... .py").

Backend suite: 3088 passed, 6 skipped (известный flake test_search_cache_hit #2208 —
не регрессия). ruff check чист на всех изменённых файлах.
2026-07-04 13:56:06 +03:00

217 lines
7.6 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""Offline unit tests for CianCitySweepCounters + admin sweep endpoints (#860).
Pure & fast: NO live network, NO DB.
Legacy `run_cian_city_sweep` orchestration behavior (SERP→save→detail→houses phase
sequencing, cooperative cancel, consecutive-SERP-failure abort, per-item error
tolerance) удалён вместе с `app.services.scrape_pipeline` (#2397 Part E1) —
эквивалентная regression-coverage теперь в
`test_scraper_kit_pipeline_parity2.py::test_cian_city_sweep` (kit
`run_cian_city_sweep`).
Coverage:
- CianCitySweepCounters корректно заполняются (dataclass shape)
- _cian_anchor_timeout_s watchdog-формула (#2160)
- Admin endpoints (start/cancel/list-runs) — kit sweep вызван с DI (config/matcher)
"""
from __future__ import annotations
import os
os.environ.setdefault("DATABASE_URL", "postgresql+psycopg://test:test@localhost:5432/test")
import pytest
# ── CianCitySweepCounters ───────────────────────────────────────────────────
def test_cian_sweep_counters_defaults() -> None:
from scraper_kit.orchestration.pipeline import CianCitySweepCounters
c = CianCitySweepCounters()
assert c.anchors_total == 0
assert c.lots_fetched == 0
assert c.detail_attempted == 0
assert c.houses_attempted == 0
assert c.errors_count == 0
def test_cian_sweep_counters_to_dict_all_keys() -> None:
from dataclasses import fields
from scraper_kit.orchestration.pipeline import CianCitySweepCounters
c = CianCitySweepCounters()
d = c.to_dict()
expected = {f.name for f in fields(c)}
assert set(d.keys()) == expected
# ── Admin endpoint tests (offline) ──────────────────────────────────────────
@pytest.fixture
def app_with_admin():
from unittest.mock import MagicMock
from fastapi import FastAPI
from fastapi.testclient import TestClient
from app.api.v1 import admin as admin_module
from app.core.db import get_db
app = FastAPI()
app.include_router(admin_module.router, prefix="/api/v1/admin")
def fake_db():
yield MagicMock()
app.dependency_overrides[get_db] = fake_db
return TestClient(app)
def test_cian_start_endpoint_validates_pages_per_anchor(app_with_admin) -> None:
"""pages_per_anchor=99 превышает max=10 → 422."""
r = app_with_admin.post(
"/api/v1/admin/scrape/cian-city-sweep",
json={"pages_per_anchor": 99},
)
assert r.status_code == 422
def test_cian_start_endpoint_validates_delay_too_low(app_with_admin) -> None:
"""request_delay_sec=1.0 меньше min=3.0 → 422."""
r = app_with_admin.post(
"/api/v1/admin/scrape/cian-city-sweep",
json={"request_delay_sec": 1.0},
)
assert r.status_code == 422
def test_cian_start_endpoint_ok(app_with_admin) -> None:
"""Valid request → 200, run_id; kit sweep вызван с DI (config/matcher, БЕЗ enrichment)."""
from unittest.mock import AsyncMock, patch
from app.services.scraper_adapters import RealMatcherAdapter, RealScraperConfig
with (
patch("app.services.scrape_runs.create_run", return_value=42),
patch("app.api.v1.admin.run_cian_city_sweep", new_callable=AsyncMock) as mock_sweep,
):
r = app_with_admin.post(
"/api/v1/admin/scrape/cian-city-sweep",
json={"pages_per_anchor": 2, "detail_top_n": 5, "enrich_houses": False},
)
assert r.status_code == 200
body = r.json()
assert body["run_id"] == 42
assert body["status"] == "running"
assert body["pages_per_anchor"] == 2
assert body["detail_top_n"] == 5
mock_sweep.assert_called_once()
kw = mock_sweep.call_args.kwargs
assert isinstance(kw["config"], RealScraperConfig)
assert isinstance(kw["matcher"], RealMatcherAdapter)
assert "proxy_provider" in kw
assert "enrichment" not in kw
def test_cian_cancel_endpoint(app_with_admin) -> None:
"""Cancel endpoint возвращает run_id + cancelled=True."""
from unittest.mock import patch
with patch("app.services.scrape_runs.mark_cancelled", return_value=True):
r = app_with_admin.post("/api/v1/admin/scrape/cian-city-sweep/77/cancel")
assert r.status_code == 200
body = r.json()
assert body["run_id"] == 77
assert body["cancelled"] is True
assert body["ok"] is True
def test_cian_cancel_endpoint_not_running(app_with_admin) -> None:
"""Cancel на не-running sweep → cancelled=False."""
from unittest.mock import patch
with patch("app.services.scrape_runs.mark_cancelled", return_value=False):
r = app_with_admin.post("/api/v1/admin/scrape/cian-city-sweep/88/cancel")
assert r.status_code == 200
assert r.json()["cancelled"] is False
def test_cian_list_runs_endpoint(app_with_admin) -> None:
"""List runs endpoint возвращает список."""
from datetime import UTC, datetime
from unittest.mock import patch
fake_rows = [
{
"run_id": 10,
"source": "cian_city_sweep",
"status": "done",
"params": {"pages_per_anchor": 3},
"counters": {"lots_fetched": 150},
"error": None,
"started_at": datetime(2025, 5, 1, tzinfo=UTC),
"finished_at": datetime(2025, 5, 1, 1, tzinfo=UTC),
"heartbeat_at": datetime(2025, 5, 1, 1, tzinfo=UTC),
}
]
with patch("app.services.scrape_runs.list_recent", return_value=fake_rows):
r = app_with_admin.get("/api/v1/admin/scrape/cian-city-sweep/runs")
assert r.status_code == 200
body = r.json()
assert len(body) == 1
assert body[0]["run_id"] == 10
assert body[0]["source"] == "cian_city_sweep"
assert "2025-05-01" in body[0]["started_at"]
# ── #2160: масштабируемый per-anchor watchdog для proxy-pool browser ──────────
def test_cian_anchor_timeout_defaults() -> None:
"""Формула watchdog даёт worst-case ~1580s при дефолтных параметрах.
4 room-buckets × 3 pages × (5s delay + 70s serp-fetch) + 10 detail × 50s + 180s houses
= 900 + 500 + 180 = 1580s. Фиксированный ANCHOR_TIMEOUT_SEC=240 гильотинил бы якорь в
SERP-фазе (#2160): каждый SERP-фетч через camoufox 13-45s.
"""
from scraper_kit.orchestration.pipeline import ANCHOR_TIMEOUT_SEC, _cian_anchor_timeout_s
t = _cian_anchor_timeout_s(
pages_per_anchor=3,
request_delay_sec=5.0,
detail_top_n=10,
enrich_houses=True,
)
assert t == pytest.approx(1580.0)
assert t > ANCHOR_TIMEOUT_SEC
def test_cian_anchor_timeout_no_houses() -> None:
"""enrich_houses=False убирает houses-бюджет (180s) из формулы."""
from scraper_kit.orchestration.pipeline import _cian_anchor_timeout_s
t = _cian_anchor_timeout_s(
pages_per_anchor=3,
request_delay_sec=5.0,
detail_top_n=10,
enrich_houses=False,
)
assert t == pytest.approx(1400.0) # 900 + 500 + 0
def test_cian_anchor_timeout_floor_at_anchor_timeout_sec() -> None:
"""Малые параметры не опускают таймаут ниже ANCHOR_TIMEOUT_SEC (max-ветка)."""
from scraper_kit.orchestration.pipeline import ANCHOR_TIMEOUT_SEC, _cian_anchor_timeout_s
t = _cian_anchor_timeout_s(
pages_per_anchor=0,
request_delay_sec=0.0,
detail_top_n=0,
enrich_houses=False,
)
assert t == float(ANCHOR_TIMEOUT_SEC)