gendesign/tradein-mvp/backend/tests/scrapers/test_domclick_detail.py
bot-backend a9b87aa311
All checks were successful
CI Trade-In / changes (pull_request) Successful in 8s
CI / changes (pull_request) Successful in 8s
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 1m36s
chore(tradein/scraper-kit): удалить 5 orphaned legacy-модулей (#2277 финальный шаг, частичный)
Удалены (0 runtime importers в app/, scripts/, packages/; проверено grep'ом,
включая intra-legacy импорты в оставшихся 21 legacy-модуле scrapers/):
- backend/app/services/scrapers/avito_imv.py
- backend/app/services/scrapers/domclick_detail.py
- backend/app/services/scrapers/ekb_geoportal_client.py
- backend/app/services/scrapers/yandex_detail.py
- backend/app/services/scrapers/yandex_valuation.py

Тесты — удалены (pure legacy-vs-kit parity, kit-only coverage уже есть в другом
месте):
- tests/scrapers/test_ekb_geoportal_client_kit_parity.py
- tests/scrapers/test_domclick_detail_kit_parity.py

Тесты — конвертированы в kit-only (импорт легаси заменён на scraper_kit.*,
покрытие сохранено без потерь):
- tests/scrapers/test_avito_imv_kit_parity.py (parity-тесты убраны, config-footgun
  regression на kit-стороне оставлен)
- tests/scrapers/test_avito_imv_browser_transport.py
- tests/scrapers/test_yandex_valuation_kit_migration.py (parity убрана, footgun-
  регрессия mandatory config/delay_provider оставлена)
- tests/scrapers/test_domclick_detail.py (+ exceptions переведены на
  scraper_kit.domclick_exceptions, т.к. kit parse_detail_html поднимает их)
- tests/test_avito_imv_parse.py
- tests/test_ekb_geoportal_ingest.py (client-часть; ingest/geocoder-часть не
  трогали — не зависят от удалённого модуля)
- tests/test_yandex_detail.py
- tests/test_yandex_detail_structural.py
- tests/test_yandex_valuation.py (YandexValuationScraper() → config=_KIT_CONFIG,
  kit конструктор требует обязательный config)
- tests/test_yandex_valuation_save.py
- tests/test_extval_house_id_write_path.py (только yandex_valuation-часть;
  cian_valuation остался нетронутым — живой легаси-модуль)
- tests/test_yandex_history_area_filter.py

Тесты — частично отредактированы (убраны только части про удалённые модули,
живые легаси-модули/их parity не тронуты):
- tests/scrapers/test_admin_domclick_ingest_kit_parity.py (base.py/ScrapedLot
  parity остался)
- tests/scrapers/test_admin_yandex_kit_parity.py (yandex_realty parity остался)
- tests/scrapers/test_admin_avito_kit_parity.py (avito.py/avito_houses.py parity
  остался; _parse_price parity убран)
- tests/scrapers/test_avito_unix_date_tz_consistency.py (IMV-ветка переведена на
  kit avito.imv, легаси avito/avito_houses/avito_shared/avito_detail не тронуты)
- tests/tasks/test_yandex_detail_backfill.py (subject — kit-задача, уже вызывает
  scraper_kit.providers.yandex.detail; save_detail_enrichment coverage-тесты
  внизу файла переведены на kit)
- tests/test_scraper_kit_yandex_golden_parity.py (detail/valuation parity убраны;
  serp/newbuilding/house_type_normalizer/build_url для yandex_realty/
  yandex_newbuilding не тронуты)
- tests/test_scraper_proxy.py (YandexValuation proxy-тесты переведены на kit
  config= DI; test_avito_imv_own_session_receives_proxies удалён — дублирует
  test_avito_imv_kit_parity.py footgun-тесты)
- tests/test_yandex_scrapers_delay_wiring.py (yandex_detail/yandex_valuation →
  kit delay_provider=; yandex_realty/yandex_newbuilding не тронуты)
- tests/test_scraper_kit_group_c_backfill_kit_parity.py (docstring уточнение,
  без функциональных изменений)

Полный backend-suite зелёный (3253 passed, 6 skipped) кроме известного
pre-existing flake test_search_api.py::test_search_cache_hit (#2208, не
регрессия этого PR). ruff check + ruff format — чисто на всех изменённых файлах.
2026-07-04 10:41:46 +03:00

411 lines
17 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.

"""Unit-тесты для DomClick Layer B detail-scraper (scraper_kit.providers.domclick.detail).
Offline: parse/SSR-тесты без сети/БД; save-тест через MagicMock (зеркало
test_cian_detail.py — в проекте нет live-DB фикстуры, идемпотентность
гарантируется ON CONFLICT-клаузой, которая проверяется на уровне SQL-строки).
Покрытие:
- _extract_ssr_state: bare `undefined` → null; in-string "undefined" выживает;
скобки/эскейпы внутри строк не ломают balanced-scan; missing marker →
DomClickParseError; challenge → DomClickBlockedError; unbalanced/невалидный
JSON → DomClickParseError.
- parse_detail_html (REAL __SSR_STATE__ paths, live card 2075729321):
productCard.objectInfo.{renovation→repair_state+repair_type,livingArea,kitchenArea};
balconies absent→None; productCard.legalOptions.saleType; egrnData snake_case
owners_count + encumbrances инверсия (collateral); houseInfo.info.{wallType,floorType}
→ raw_extra (НЕ house_type); productCard.viewsCount; priceInfo.priceHistory
(ISO8601+offset kept tz-aware / bad-date + no-price skipped); top-level
pricePrediction → raw_extra.avm (плоский + nested .result); raw_extra без None;
item_id из URL.
- fetch_detail: browser-branch + проброс ошибок.
- save_detail_enrichment: UPDATE-параметры, detail_enriched_at, price-history INSERT.
Легаси `app.services.scrapers.domclick_detail` удалён (#2277 финальный шаг
scraper_kit-миграции, 0 runtime importers) — тесты переведены на kit-эквивалент
`scraper_kit.providers.domclick.detail` без изменения покрытия. Exceptions тоже
переведены на `scraper_kit.domclick_exceptions` (kit держит свою независимую копию,
`parse_detail_html`(kit) поднимает именно её — legacy `app.services.scrapers.
domclick_exceptions` остаётся живым модулем для `domclick.py`, но здесь больше не
подходящий класс для `pytest.raises`).
"""
from __future__ import annotations
import json
from datetime import UTC, datetime, timedelta
from unittest.mock import AsyncMock, MagicMock
import pytest
from scraper_kit.domclick_exceptions import DomClickBlockedError, DomClickParseError
from scraper_kit.providers.domclick.detail import (
DomClickDetailEnrichment,
_extract_ssr_state,
fetch_detail,
parse_detail_html,
save_detail_enrichment,
)
_CARD_URL = "https://ekaterinburg.domclick.ru/card/sale__flat__2075729321"
# Литерал с bare `undefined` (value-позиция), in-string "undefined", скобкой
# внутри строки и эскейп-кавычками — написан вручную, json.dumps использовать
# нельзя (нужен именно НЕвалидный-для-json undefined).
# Real __SSR_STATE__ shape (ground truth, live card 2075729321, 2026-06-27).
# bare `undefined` (value-pos), in-string "undefined", '{' внутри строки и
# эскейп-кавычки оставлены для проверки санитайзера/balanced-scan; json.dumps
# использовать нельзя (нужен именно НЕвалидный-для-json undefined).
# priceHistory[0].date намеренно flush-left (длинная ISO+offset строка) — отступ
# в литерале не влияет на парсер, но держит физическую строку ≤100 для ruff.
_SSR_LITERAL = """{
"productCard": {
"objectInfo": {
"area": 38.0,
"rooms": 1,
"floor": 5,
"isApartment": false,
"renovation": "евроремонт",
"livingArea": 22.37,
"kitchenArea": 10.13,
"description": "Состояние пока undefined.",
"note": "угол {da}",
"quote": "сказал \\"привет\\" сосед"
},
"legalOptions": {"saleType": "Свободная продажа"},
"egrnData": {
"area": 38.2,
"floor": 5,
"owners_count": 1,
"collateral": true,
"collateral_sber": false
},
"priceInfo": {
"priceHistory": [
{"date": "2026-04-15T09:02:26.548728+03:00", "price": 13400000, "diff": -400000, "state": "less"},
{"date": "not-a-date", "price": 4800000, "diff": -1.0, "state": "less"},
{"date": "2026-05-01T10:00:00Z", "price": null, "diff": 0, "state": "more"}
]
},
"viewsCount": 338,
"callsCount": 5,
"favoriteOfferUsersCount": 12,
"duplicatesOfferCount": 0,
"address": {"guid": "abc-guid-123"},
"unknownField": undefined
},
"houseInfo": {
"info": {
"buildYear": 2015,
"wallType": "Кирпично-монолитный",
"floorType": "Железобетонный",
"entranceCount": 3,
"quartersCount": 120,
"energyEfficiency": "B",
"buildingSeries": "индивидуальный"
}
},
"pricePrediction": {
"market_price": 13000000,
"min_market_price": 12000000,
"max_market_price": 14000000,
"rent_short": 50000,
"rent_long": 35000,
"repair_quality": "good"
}
}"""
_HTML = (
"<html><head></head><body><script>"
f"window.__SSR_STATE__ = {_SSR_LITERAL};"
"</script></body></html>"
)
def _wrap(state: dict) -> str:
"""Заворачивает валидный dict в SSR-HTML (для variant-фикстур без undefined)."""
literal = json.dumps(state, ensure_ascii=False)
return f"<html><body><script>window.__SSR_STATE__ = {literal};</script></body></html>"
# ── _extract_ssr_state ────────────────────────────────────────────────────────
def test_extract_ssr_state_parses_despite_undefined() -> None:
state = _extract_ssr_state(_HTML)
# bare undefined в value-позиции → null → None
assert state["productCard"]["unknownField"] is None
# in-string "undefined" НЕ испорчен санитайзером
assert state["productCard"]["objectInfo"]["description"] == "Состояние пока undefined."
def test_extract_ssr_state_brace_and_escape_in_string() -> None:
state = _extract_ssr_state(_HTML)
oi = state["productCard"]["objectInfo"]
# '{' внутри строки не ломает balanced-brace scan
assert oi["note"] == "угол {da}"
# эскейп-кавычки внутри строки обработаны
assert oi["quote"] == 'сказал "привет" сосед'
def test_extract_ssr_state_missing_marker_raises_parse() -> None:
with pytest.raises(DomClickParseError):
_extract_ssr_state("<html><body>no ssr state here</body></html>")
def test_extract_ssr_state_challenge_raises_blocked() -> None:
html = "<html><body>Access denied by DataDome captcha</body></html>"
with pytest.raises(DomClickBlockedError):
_extract_ssr_state(html)
def test_extract_ssr_state_unbalanced_raises_parse() -> None:
with pytest.raises(DomClickParseError):
_extract_ssr_state('window.__SSR_STATE__ = {"a": 1')
def test_extract_ssr_state_invalid_json_raises_parse() -> None:
with pytest.raises(DomClickParseError):
_extract_ssr_state("window.__SSR_STATE__ = {this: is, not: json}")
# ── parse_detail_html — полная карточка ───────────────────────────────────────
def test_parse_detail_html_full() -> None:
e = parse_detail_html(_HTML, _CARD_URL)
assert e.item_id == "2075729321"
assert e.source_url == _CARD_URL
assert e.repair_state == "good" # евроремонт → good (LOCAL map)
assert e.repair_type == "евроремонт" # сырое значение сохранено
assert e.living_area_m2 == 22.37
assert e.kitchen_area_m2 == 10.13
# На реальной карточке нет ключа balconies в objectInfo → optional/None.
assert e.balconies_count is None
assert e.has_balcony is None
assert e.sale_type == "Свободная продажа"
assert e.owners_count == 1
assert e.encumbrances_clean is False # collateral=true → есть обременение
assert e.year_built == 2015
assert e.views_total == 338
def test_parse_detail_html_price_changes() -> None:
e = parse_detail_html(_HTML, _CARD_URL)
# entry1 ок; entry2 bad-date skip; entry3 price=null skip → 1 запись
assert len(e.price_changes) == 1
change = e.price_changes[0]
assert change["price_rub"] == 13400000
assert change["diff_percent"] == -400000
assert isinstance(change["change_time"], datetime)
# ISO8601-with-offset: tz-aware, offset СОХРАНЁН (+03:00), НЕ сконвертирован в UTC.
assert change["change_time"].tzinfo is not None
assert change["change_time"].utcoffset() == timedelta(hours=3)
def test_parse_detail_html_raw_extra() -> None:
e = parse_detail_html(_HTML, _CARD_URL)
raw = e.raw_extra
assert raw["wall_type"] == "Кирпично-монолитный"
assert raw["floor_type"] == "Железобетонный"
# wall/floor type живут ТОЛЬКО в raw_extra, НЕ в listings.house_type.
assert "house_type" not in raw
assert raw["domclick_building_guid"] == "abc-guid-123"
assert raw["egrn_area"] == 38.2
assert raw["demand"]["calls"] == 5
assert raw["demand"]["favorites"] == 12
# AVM (Layer C, top-level pricePrediction) → raw_extra.avm
assert raw["avm"]["market_price"] == 13000000
assert raw["avm"]["min"] == 12000000
assert raw["avm"]["max"] == 14000000
assert raw["avm"]["repair_quality"] == "good"
# нет ключа balconies → raw_extra НЕ содержит balconies_raw
assert "balconies_raw" not in raw
# никаких None-значений на верхнем уровне (компактность)
assert all(v is not None for v in raw.values())
# ── parse_detail_html — частные ветки ─────────────────────────────────────────
def test_parse_balconies_string_goes_to_raw_extra() -> None:
html = _wrap({"productCard": {"objectInfo": {"balconies": "есть"}}})
e = parse_detail_html(html, _CARD_URL)
assert e.balconies_count is None
assert e.has_balcony is None
assert e.raw_extra["balconies_raw"] == "есть"
def test_parse_encumbrances_clean_true_when_no_collateral() -> None:
html = _wrap({"productCard": {"egrnData": {"collateral": False, "collateral_sber": False}}})
e = parse_detail_html(html, _CARD_URL)
assert e.encumbrances_clean is True
def test_parse_encumbrances_none_when_egrn_missing() -> None:
html = _wrap({"productCard": {"objectInfo": {"livingArea": 30}}})
e = parse_detail_html(html, _CARD_URL)
assert e.encumbrances_clean is None
def test_parse_repair_map_hit() -> None:
html = _wrap({"productCard": {"objectInfo": {"renovation": "Косметический"}}})
e = parse_detail_html(html, _CARD_URL)
assert e.repair_state == "standard"
assert e.repair_type == "Косметический"
def test_parse_repair_fallback_to_inference() -> None:
# Не точное совпадение в карте → инференс из текста (евроремонт → good)
html = _wrap({"productCard": {"objectInfo": {"renovation": "сделан свежий евроремонт"}}})
e = parse_detail_html(html, _CARD_URL)
assert e.repair_state == "good"
assert e.repair_type == "сделан свежий евроремонт"
def test_parse_owners_count_camelcase_key() -> None:
html = _wrap({"productCard": {"egrnData": {"ownersCount": 3}}})
e = parse_detail_html(html, _CARD_URL)
assert e.owners_count == 3
def test_parse_avm_nested_under_result() -> None:
# pricePrediction может приходить обёрнутым в .result — unwrap должен сработать.
html = _wrap(
{
"productCard": {},
"pricePrediction": {"result": {"marketPrice": 9000000, "repairQuality": "fine"}},
}
)
e = parse_detail_html(html, _CARD_URL)
assert e.raw_extra["avm"]["market_price"] == 9000000
assert e.raw_extra["avm"]["repair_quality"] == "fine"
def test_parse_avm_absent_no_key() -> None:
# Нет pricePrediction → raw_extra без ключа avm (компактность).
e = parse_detail_html(_wrap({"productCard": {}}), _CARD_URL)
assert "avm" not in e.raw_extra
def test_parse_item_id_none_for_bad_url() -> None:
e = parse_detail_html(_wrap({"productCard": {}}), "https://domclick.ru/card/rent__room__1")
assert e.item_id is None
def test_dataclass_defaults() -> None:
e = DomClickDetailEnrichment()
assert e.item_id is None
assert e.price_changes == []
assert e.raw_extra == {}
# ── fetch_detail (browser-branch) ─────────────────────────────────────────────
@pytest.mark.asyncio
async def test_fetch_detail_parses_via_browser() -> None:
bf = MagicMock()
bf.fetch = AsyncMock(return_value=_HTML)
e = await fetch_detail(_CARD_URL, browser_fetcher=bf)
assert e.item_id == "2075729321"
assert e.repair_state == "good"
bf.fetch.assert_called_once_with(_CARD_URL)
@pytest.mark.asyncio
async def test_fetch_detail_browser_failure_raises_blocked() -> None:
bf = MagicMock()
bf.fetch = AsyncMock(side_effect=RuntimeError("502 bad gateway"))
with pytest.raises(DomClickBlockedError):
await fetch_detail(_CARD_URL, browser_fetcher=bf)
@pytest.mark.asyncio
async def test_fetch_detail_propagates_parse_error() -> None:
bf = MagicMock()
bf.fetch = AsyncMock(return_value="<html><body>no state</body></html>")
with pytest.raises(DomClickParseError):
await fetch_detail(_CARD_URL, browser_fetcher=bf)
@pytest.mark.asyncio
async def test_fetch_detail_propagates_blocked_from_html() -> None:
bf = MagicMock()
bf.fetch = AsyncMock(return_value="<html><body>Access denied datadome</body></html>")
with pytest.raises(DomClickBlockedError):
await fetch_detail(_CARD_URL, browser_fetcher=bf)
# ── save_detail_enrichment (MagicMock — зеркало test_cian_detail) ─────────────
def test_save_detail_enrichment_writes_columns() -> None:
db = MagicMock()
db.execute.return_value.rowcount = 1
ct = datetime(2026, 4, 1, tzinfo=UTC)
e = DomClickDetailEnrichment(
item_id="2075729321",
source_url=_CARD_URL,
repair_state="good",
repair_type="Евроремонт",
living_area_m2=45.5,
kitchen_area_m2=12.3,
balconies_count=2,
has_balcony=True,
sale_type="свободная",
owners_count=1,
encumbrances_clean=False,
year_built=2015,
views_total=1234,
price_changes=[{"change_time": ct, "price_rub": 5000000, "diff_percent": -2.5}],
raw_extra={"wall_type": "монолит"},
)
ok = save_detail_enrichment(db, 999, e)
assert ok is True
# UPDATE — первый execute
update_sql = str(db.execute.call_args_list[0][0][0])
update_params = db.execute.call_args_list[0][0][1]
assert "detail_enriched_at = NOW()" in update_sql
assert update_params["lid"] == 999
assert update_params["repair_state"] == "good"
assert update_params["living_area_m2"] == 45.5
assert update_params["balconies_count"] == 2
assert update_params["has_balcony"] is True
assert update_params["encumbrances_clean"] is False
assert "монолит" in update_params["raw_extra"]
# price-history INSERT с ON CONFLICT (идемпотентность)
insert_calls = [c for c in db.execute.call_args_list if "offer_price_history" in str(c[0][0])]
assert len(insert_calls) == 1
assert "ON CONFLICT ON CONSTRAINT offer_price_history_listing_change_uq" in str(
insert_calls[0][0][0]
)
ins_params = insert_calls[0][0][1]
assert ins_params["price"] == 5000000
assert ins_params["ct"] == ct
db.commit.assert_called_once()
def test_save_detail_enrichment_listing_not_found() -> None:
db = MagicMock()
db.execute.return_value.rowcount = 0
e = DomClickDetailEnrichment(item_id="x", source_url=_CARD_URL, repair_state="good")
assert save_detail_enrichment(db, 123, e) is False
def test_save_detail_enrichment_none_passthrough() -> None:
db = MagicMock()
db.execute.return_value.rowcount = 1
e = DomClickDetailEnrichment(item_id="x", source_url=_CARD_URL) # все поля None
save_detail_enrichment(db, 1, e)
params = db.execute.call_args_list[0][0][1]
assert params["repair_state"] is None
assert params["living_area_m2"] is None
# пустой raw_extra → "{}" (merge no-op, не затирает)
assert params["raw_extra"] == "{}"