gendesign/tradein-mvp/backend/tests/test_scraper_proxy.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

450 lines
18 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.

"""Tests for scraper proxy wiring (#806 + follow-up).
Covers:
- scraper_proxy_url property: SCRAPER_PROXY_URL takes precedence over AVITO_PROXY_URL
- AVITO_PROXY_URL fallback works when SCRAPER_PROXY_URL is absent
- None/empty → direct connection (no proxies dict)
- _avito_proxies() helper returns correct dict shape
- per-scraper proxy wiring: YandexRealty, YandexValuation (kit), CianValuation,
CianNewbuilding (fetch_newbuilding — now BrowserFetcher, proxy is browser-level),
AvitoDetail
Легаси `app.services.scrapers.yandex_valuation` / `avito_imv` удалены (#2277
финальный шаг scraper_kit-миграции). YandexValuation proxy-wiring тесты переведены
на kit-эквивалент (`config=` DI вместо патча `app.core.config.settings`).
`test_avito_imv_own_session_receives_proxies` (легаси, patch-based) удалён —
эквивалентная и более точная kit-регрессия (config footgun: с/без `config=`) уже
покрыта в `tests/scrapers/test_avito_imv_kit_parity.py::
test_kit_evaluate_via_imv_{with,without}_config_{uses,drops}_proxy`.
"""
from __future__ import annotations
import os
os.environ.setdefault("DATABASE_URL", "postgresql+psycopg://test:test@localhost:5432/test")
from types import SimpleNamespace
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
def _mock_settings(
scraper_proxy_url: str | None,
yandex_cookies_file: str | None = None,
) -> SimpleNamespace:
"""Minimal settings stand-in with fields read by proxy helpers and scraper __aenter__."""
return SimpleNamespace(
scraper_proxy_url=scraper_proxy_url,
# Cian scrapers read settings.cian_proxy_url (property: CIAN_PROXY_URL or
# scraper_proxy_url fallback). Mirror scraper_proxy_url here so the existing
# cian proxy-wiring assertions keep passing (#923 follow-up).
cian_proxy_url=scraper_proxy_url,
# Yandex scrapers read settings.yandex_proxy_url (property: YANDEX_PROXY_URL or
# scraper_proxy_url fallback). Mirror scraper_proxy_url here for test compat.
yandex_proxy_url=scraper_proxy_url,
yandex_cookies_file=yandex_cookies_file,
)
# ── Settings.scraper_proxy_url property ──────────────────────────────────────
# Test the property logic directly via inline replica — avoids instantiating
# pydantic-settings (requires DATABASE_URL) for pure unit tests of the rule.
def _resolve_scraper_proxy_url(
scraper_proxy_url_env: str | None, avito_proxy_url: str | None
) -> str | None:
"""Inline replica of Settings.scraper_proxy_url property logic."""
return scraper_proxy_url_env or avito_proxy_url
def test_scraper_proxy_url_uses_scraper_env_when_set():
result = _resolve_scraper_proxy_url(
scraper_proxy_url_env="http://scraper-proxy:1234",
avito_proxy_url="http://avito-proxy:5678",
)
assert result == "http://scraper-proxy:1234"
def test_scraper_proxy_url_falls_back_to_avito_proxy_url():
"""AVITO_PROXY_URL used when SCRAPER_PROXY_URL absent — zero env change on prod."""
result = _resolve_scraper_proxy_url(
scraper_proxy_url_env=None,
avito_proxy_url="http://avito-proxy:5678",
)
assert result == "http://avito-proxy:5678"
def test_scraper_proxy_url_none_when_both_absent():
result = _resolve_scraper_proxy_url(scraper_proxy_url_env=None, avito_proxy_url=None)
assert result is None
def test_scraper_proxy_url_empty_string_falls_through_to_avito():
"""Empty string is falsy — falls through to avito_proxy_url."""
result = _resolve_scraper_proxy_url(
scraper_proxy_url_env="",
avito_proxy_url="http://avito-proxy:5678",
)
assert result == "http://avito-proxy:5678"
# ── _avito_proxies() dict shape ───────────────────────────────────────────────
def test_avito_proxies_returns_correct_dict_shape():
"""Kit `_avito_proxies(config)` — DI параметр вместо module-level settings patch."""
from scraper_kit.orchestration.pipeline import _avito_proxies
proxy_url = "http://user:pass@proxy.example.com:8080"
result = _avito_proxies(_mock_settings(proxy_url))
assert result == {"http": proxy_url, "https": proxy_url}
def test_avito_proxies_returns_none_when_no_proxy():
from scraper_kit.orchestration.pipeline import _avito_proxies
result = _avito_proxies(_mock_settings(None))
assert result is None
def test_avito_proxies_fallback_via_avito_proxy_url():
"""_avito_proxies(config) uses AVITO_PROXY_URL via scraper_proxy_url fallback.
When config.scraper_proxy_url resolves to the avito URL (fallback path),
the dict shape must be {"http": url, "https": url}.
"""
from scraper_kit.orchestration.pipeline import _avito_proxies
avito_url = "http://mobile-proxy.space:9090"
result = _avito_proxies(_mock_settings(avito_url))
assert result == {"http": avito_url, "https": avito_url}
# ── Real pydantic env-binding (regression for #806 fixup) ─────────────────────
# The inline-replica tests above prove the OR-logic but NOT that the field
# actually binds to env SCRAPER_PROXY_URL. `validation_alias` is what makes that
# work — without it pydantic-settings reads SCRAPER_PROXY_URL_ENV (the field
# name), so setting SCRAPER_PROXY_URL would be a silent no-op. These tests
# construct a real Settings and assert end-to-end env binding.
def _fresh_settings():
from app.core.config import Settings
return Settings(_env_file=None)
def test_settings_binds_scraper_proxy_url_env(monkeypatch):
monkeypatch.setenv("SCRAPER_PROXY_URL", "http://scraper-proxy:1234")
monkeypatch.delenv("AVITO_PROXY_URL", raising=False)
assert _fresh_settings().scraper_proxy_url == "http://scraper-proxy:1234"
def test_settings_scraper_env_overrides_avito(monkeypatch):
monkeypatch.setenv("SCRAPER_PROXY_URL", "http://scraper-proxy:1234")
monkeypatch.setenv("AVITO_PROXY_URL", "http://avito-proxy:5678")
assert _fresh_settings().scraper_proxy_url == "http://scraper-proxy:1234"
def test_settings_falls_back_to_avito_env(monkeypatch):
monkeypatch.delenv("SCRAPER_PROXY_URL", raising=False)
monkeypatch.setenv("AVITO_PROXY_URL", "http://avito-proxy:5678")
assert _fresh_settings().scraper_proxy_url == "http://avito-proxy:5678"
def test_settings_ignores_misnamed_scraper_proxy_url_env(monkeypatch):
"""Regression: the old wrong env name SCRAPER_PROXY_URL_ENV must NOT bind."""
monkeypatch.delenv("SCRAPER_PROXY_URL", raising=False)
monkeypatch.delenv("AVITO_PROXY_URL", raising=False)
monkeypatch.setenv("SCRAPER_PROXY_URL_ENV", "http://wrong-name:1111")
assert _fresh_settings().scraper_proxy_url is None
# ── Per-scraper proxy wiring (follow-up: yandex/valuation/imv/newbuilding) ────
# Each test: patch settings.scraper_proxy_url, mock AsyncSession constructor,
# invoke __aenter__ / create-session path, assert proxies= kwarg is forwarded.
# proxy=None path: assert proxies kwarg is None / not passed as non-None.
_PROXY_URL = "http://mobile.proxy:8080"
_EXPECTED_PROXIES = {"http": _PROXY_URL, "https": _PROXY_URL}
# ── YandexRealtyScraper ──────────────────────────────────────────────────────
@pytest.mark.asyncio
async def test_yandex_realty_opens_browser_fetcher(monkeypatch):
"""YandexRealtyScraper.__aenter__ opens ONE BrowserFetcher (camoufox) session.
Transport moved off the proxied curl_cffi session to BrowserFetcher (camoufox);
the mobile proxy is applied server-side by the tradein-browser service, not via a
proxies= kwarg here.
"""
from app.services.scrapers.yandex_realty import YandexRealtyScraper
mock_browser = MagicMock()
mock_browser.__aenter__ = AsyncMock(return_value=mock_browser)
mock_browser.__aexit__ = AsyncMock(return_value=None)
monkeypatch.setattr(
"app.services.scrapers.yandex_realty.BrowserFetcher", lambda *a, **k: mock_browser
)
scraper = YandexRealtyScraper()
await scraper.__aenter__()
mock_browser.__aenter__.assert_awaited_once()
assert scraper._browser is mock_browser
# ── YandexValuationScraper ───────────────────────────────────────────────────
@pytest.mark.asyncio
async def test_yandex_valuation_session_receives_proxies():
"""Kit YandexValuationScraper.__aenter__ forwards proxies= kwarg from config."""
from scraper_kit.providers.yandex.valuation import YandexValuationScraper
mock_session = MagicMock()
mock_session.close = AsyncMock()
captured_kwargs: dict = {}
def _fake_session(*args, **kwargs):
captured_kwargs.update(kwargs)
return mock_session
cfg = SimpleNamespace(use_proxy_pool_curl=False, scraper_proxy_url=_PROXY_URL)
with patch("scraper_kit.providers.yandex.valuation._CurlCffiSession", _fake_session):
async with YandexValuationScraper(cfg):
pass
assert captured_kwargs.get("proxies") == _EXPECTED_PROXIES
@pytest.mark.asyncio
async def test_yandex_valuation_session_no_proxies_when_none():
"""Kit YandexValuationScraper.__aenter__: proxies=None when no proxy configured."""
from scraper_kit.providers.yandex.valuation import YandexValuationScraper
mock_session = MagicMock()
mock_session.close = AsyncMock()
captured_kwargs: dict = {}
def _fake_session(*args, **kwargs):
captured_kwargs.update(kwargs)
return mock_session
cfg = SimpleNamespace(use_proxy_pool_curl=False, scraper_proxy_url=None)
with patch("scraper_kit.providers.yandex.valuation._CurlCffiSession", _fake_session):
async with YandexValuationScraper(cfg):
pass
assert captured_kwargs.get("proxies") is None
# ── CianNewbuilding — fetch_newbuilding ───────────────────────────────────────
# После #972 fetch_newbuilding тянет страницу ЖК через BrowserFetcher (camoufox),
# а НЕ через curl_cffi AsyncSession. Прокси применяются на уровне браузер-контейнера,
# а не через proxies= kwarg. AsyncSession для page-fetch больше НЕ создаётся.
@pytest.mark.asyncio
async def test_cian_newbuilding_own_session_receives_proxies():
"""fetch_newbuilding использует BrowserFetcher для page-fetch, не AsyncSession.
Проверяем:
- BrowserFetcher.fetch(url) вызывается с правильным URL
- curl_cffi AsyncSession НЕ создаётся для page-fetch (прокси — browser-level)
"""
from app.services.scrapers import cian_newbuilding
zhk_url = "https://zhk-test.cian.ru/"
fetch_calls: list[str] = []
session_ctor_calls: list[dict] = []
mock_fetcher = MagicMock()
mock_fetcher.fetch = AsyncMock(
side_effect=lambda url: fetch_calls.append(url) or "<html></html>"
)
mock_fetcher.__aenter__ = AsyncMock(return_value=mock_fetcher)
mock_fetcher.__aexit__ = AsyncMock(return_value=None)
def _fake_async_session(*args, **kwargs):
session_ctor_calls.append(kwargs)
return MagicMock()
with patch.object(cian_newbuilding, "BrowserFetcher", lambda *a, **k: mock_fetcher):
with patch.object(cian_newbuilding, "AsyncSession", _fake_async_session):
await cian_newbuilding.fetch_newbuilding(zhk_url)
# BrowserFetcher.fetch вызван с ЖК-url
assert fetch_calls == [zhk_url]
# curl_cffi AsyncSession НЕ создавался для page-fetch
assert session_ctor_calls == []
@pytest.mark.asyncio
async def test_cian_newbuilding_shared_session_not_recreated():
"""fetch_newbuilding принимает session= для backward-compat, но использует BrowserFetcher.
Даже когда передан внешний session — страница ЖК тянется через BrowserFetcher,
AsyncSession не пересоздаётся, session.get не вызывается.
"""
from app.services.scrapers import cian_newbuilding
zhk_url = "https://zhk-test.cian.ru/"
fetch_calls: list[str] = []
session_ctor_calls: list[dict] = []
mock_fetcher = MagicMock()
mock_fetcher.fetch = AsyncMock(
side_effect=lambda url: fetch_calls.append(url) or "<html></html>"
)
mock_fetcher.__aenter__ = AsyncMock(return_value=mock_fetcher)
mock_fetcher.__aexit__ = AsyncMock(return_value=None)
def _fake_async_session(*args, **kwargs):
session_ctor_calls.append(kwargs)
return MagicMock()
sentinel_session = MagicMock(name="external_session")
with patch.object(cian_newbuilding, "BrowserFetcher", lambda *a, **k: mock_fetcher):
with patch.object(cian_newbuilding, "AsyncSession", _fake_async_session):
await cian_newbuilding.fetch_newbuilding(zhk_url, session=sentinel_session)
# BrowserFetcher.fetch вызван — именно через него тянется страница
assert fetch_calls == [zhk_url]
# Ни нового AsyncSession, ни вызова переданного session.get — proxy browser-level
assert session_ctor_calls == []
sentinel_session.get.assert_not_called()
# ── AvitoDetail — fetch_detail own-session ───────────────────────────────────
@pytest.mark.asyncio
async def test_avito_detail_own_session_receives_proxies():
"""fetch_detail creates own session with proxies= when no cffi_session passed."""
from app.services.scrapers import avito_detail
mock_session = MagicMock()
mock_resp = MagicMock()
mock_resp.status_code = 200
# Minimal HTML that parse_detail_html won't raise ValueError (item_id required)
mock_resp.text = "<html><body></body></html>"
mock_session.get = AsyncMock(return_value=mock_resp)
mock_session.close = AsyncMock()
captured_kwargs: dict = {}
def _fake_session(*args, **kwargs):
captured_kwargs.update(kwargs)
return mock_session
with patch.object(avito_detail, "AsyncSession", _fake_session):
with patch("app.core.config.settings", _mock_settings(_PROXY_URL)):
try:
await avito_detail.fetch_detail("/ekaterinburg/kvartiry/test-1234")
except ValueError:
pass # parse_detail_html raises ValueError (no item_id) — that's ok
assert captured_kwargs.get("proxies") == _EXPECTED_PROXIES
@pytest.mark.asyncio
async def test_avito_detail_shared_session_not_patched():
"""fetch_detail does NOT build own session when cffi_session is provided."""
from app.services.scrapers import avito_detail
mock_session = MagicMock()
mock_resp = MagicMock()
mock_resp.status_code = 200
mock_resp.text = "<html><body></body></html>"
mock_session.get = AsyncMock(return_value=mock_resp)
mock_session.close = AsyncMock()
ctor_calls = []
def _fake_session(*args, **kwargs):
ctor_calls.append(kwargs)
return MagicMock()
with patch.object(avito_detail, "AsyncSession", _fake_session):
with patch("app.core.config.settings", _mock_settings(_PROXY_URL)):
try:
await avito_detail.fetch_detail(
"/ekaterinburg/kvartiry/test-1234",
cffi_session=mock_session,
)
except ValueError:
pass
# No own session created — shared session was used as-is
assert ctor_calls == []
# ── Settings.cian_proxy_url property ─────────────────────────────────────────
# cian_proxy_url: CIAN_PROXY_URL > scraper_proxy_url (fallback) > None.
def _resolve_cian_proxy_url(
cian_proxy_url_env: str | None, scraper_proxy_url: str | None
) -> str | None:
"""Inline replica of Settings.cian_proxy_url property logic."""
return cian_proxy_url_env or scraper_proxy_url
def test_cian_proxy_url_uses_cian_env_when_set():
"""CIAN_PROXY_URL takes precedence over shared scraper_proxy_url."""
result = _resolve_cian_proxy_url(
cian_proxy_url_env="http://cian-proxy:2222",
scraper_proxy_url="http://shared-proxy:1111",
)
assert result == "http://cian-proxy:2222"
def test_cian_proxy_url_falls_back_to_scraper_proxy_url():
"""Falls back to shared scraper_proxy_url when CIAN_PROXY_URL is absent."""
result = _resolve_cian_proxy_url(
cian_proxy_url_env=None,
scraper_proxy_url="http://shared-proxy:1111",
)
assert result == "http://shared-proxy:1111"
def test_cian_proxy_url_none_when_both_absent():
result = _resolve_cian_proxy_url(cian_proxy_url_env=None, scraper_proxy_url=None)
assert result is None
def test_settings_binds_cian_proxy_url_env(monkeypatch):
"""CIAN_PROXY_URL env binds to cian_proxy_url_env via validation_alias."""
monkeypatch.setenv("CIAN_PROXY_URL", "http://cian-proxy:2222")
monkeypatch.delenv("SCRAPER_PROXY_URL", raising=False)
monkeypatch.delenv("AVITO_PROXY_URL", raising=False)
assert _fresh_settings().cian_proxy_url == "http://cian-proxy:2222"
def test_settings_cian_env_overrides_scraper_proxy(monkeypatch):
"""CIAN_PROXY_URL overrides shared SCRAPER_PROXY_URL for Cian scrapers."""
monkeypatch.setenv("CIAN_PROXY_URL", "http://cian-proxy:2222")
monkeypatch.setenv("SCRAPER_PROXY_URL", "http://shared-proxy:1111")
monkeypatch.delenv("AVITO_PROXY_URL", raising=False)
s = _fresh_settings()
assert s.cian_proxy_url == "http://cian-proxy:2222"
assert s.scraper_proxy_url == "http://shared-proxy:1111"
def test_settings_cian_proxy_falls_back_to_scraper(monkeypatch):
"""Without CIAN_PROXY_URL, cian_proxy_url falls back to scraper_proxy_url."""
monkeypatch.delenv("CIAN_PROXY_URL", raising=False)
monkeypatch.setenv("SCRAPER_PROXY_URL", "http://shared-proxy:1111")
monkeypatch.delenv("AVITO_PROXY_URL", raising=False)
assert _fresh_settings().cian_proxy_url == "http://shared-proxy:1111"