ewoooc/tests/test_pchome_crawler_search.py

from datetime import datetime

import requests


class _FakeResponse:
    def __init__(self, payload=None, status_code=200):
        self._payload = payload or {}
        self.status_code = status_code
        self.text = ""

    def json(self):
        return self._payload

    def raise_for_status(self):
        if self.status_code >= 400:
            raise requests.HTTPError(f"HTTP {self.status_code}", response=self)


def test_pchome_search_scans_multiple_pages_until_limit(monkeypatch):
    from services.pchome_crawler import PChomeCrawler, PChomeProduct

    crawler = PChomeCrawler(timeout=1, delay=0, max_retries=0)
    calls = []
    fetched_ids = []

    class FakeSession:
        headers = {}

        def get(self, url, params=None, timeout=None):
            calls.append((url, dict(params or {}), timeout))
            page = int((params or {}).get("page") or 1)
            if page == 1:
                return _FakeResponse({"Prods": [{"Id": "A001"}, {"Id": "A002"}]})
            if page == 2:
                return _FakeResponse({"Prods": [{"Id": "A002"}, {"Id": "A003"}]})
            return _FakeResponse({"Prods": []})

    def fake_fetch_product_details(product_ids, batch_size=20):
        fetched_ids.extend(product_ids)
        return True, "details ok", [
            PChomeProduct(
                product_id=product_id,
                name=f"商品 {product_id}",
                price=100,
                original_price=120,
                discount=17,
                image_url="",
                product_url=f"https://24h.pchome.com.tw/prod/{product_id}",
                stock=10,
                store="24h",
                rating=None,
                review_count=0,
                is_on_sale=True,
                crawled_at=datetime.now(),
            )
            for product_id in product_ids
        ]

    crawler.session = FakeSession()
    monkeypatch.setattr(crawler, "fetch_product_details", fake_fetch_product_details)

    success, message, products = crawler.search_products("理膚寶水", limit=3, max_pages=3)

    assert success is True
    assert "搜尋頁數 2" in message
    assert fetched_ids == ["A001", "A002", "A003"]
    assert [call[1]["page"] for call in calls] == [1, 2]
    assert [product.product_id for product in products] == ["A001", "A002", "A003"]


def test_pchome_get_retries_transient_timeout():
    from services.pchome_crawler import PChomeCrawler

    crawler = PChomeCrawler(timeout=1, delay=0, max_retries=1, retry_backoff=0)
    calls = []

    class FakeSession:
        headers = {}

        def get(self, url, **kwargs):
            calls.append((url, kwargs))
            if len(calls) == 1:
                raise requests.Timeout("temporary timeout")
            return _FakeResponse({"ok": True})

    crawler.session = FakeSession()

    response = crawler._get_with_retry("https://example.test/api", timeout=1)

    assert response.json() == {"ok": True}
    assert len(calls) == 2


def test_pchome_fetch_product_details_accepts_list_payload():
    from services.pchome_crawler import PChomeCrawler

    crawler = PChomeCrawler(timeout=1, delay=0, max_retries=0)
    calls = []

    class FakeSession:
        headers = {}

        def get(self, url, params=None, timeout=None):
            calls.append((url, params, timeout))
            return _FakeResponse([
                {
                    "Id": "DDABCD-12345678",
                    "Name": "測試商品 50ml",
                    "Nick": "測試商品 50ml x2 限量組",
                    "Price": {"P": 799, "M": 999},
                    "Pic": {"B": "/items/DDABCD12345678.jpg"},
                    "Qty": 8,
                    "Store": "24h",
                    "isOnSale": True,
                }
            ])

    crawler.session = FakeSession()

    success, message, products = crawler.fetch_product_details(["DDABCD-12345678"])

    assert success is True
    assert message == "成功取得 1 個商品資料"
    assert len(calls) == 1
    assert [product.product_id for product in products] == ["DDABCD-12345678"]
    assert products[0].price == 799
    assert products[0].subtitle == "測試商品 50ml x2 限量組"
    assert products[0].match_name == "測試商品 50ml x2 限量組"


def test_pchome_match_name_combines_non_duplicate_nick():
    from services.pchome_crawler import _build_match_name

    assert _build_match_name("水楊酸身體乳雙入組", "2% 水楊酸身體乳 210ml x2") == (
        "水楊酸身體乳雙入組 2% 水楊酸身體乳 210ml x2"
    )


def test_feeder_search_cleanup_preserves_bracket_brand_and_specs():
    from services.competitor_price_feeder import _clean_search_text

    cleaned = _clean_search_text("【蘭蔻】絕對完美玫瑰霜(60ml)+玫瑰精露150ml")

    assert "蘭蔻" in cleaned
    assert "60ml" in cleaned
    assert "150ml" in cleaned


def test_feeder_search_candidate_passes_page_cap(monkeypatch):
    from services.competitor_price_feeder import _search_pchome_candidates
    from services.pchome_crawler import PChomeProduct

    product = PChomeProduct(
        product_id="DDAB01-PAGE2",
        name="理膚寶水 B5 修復霜 40ml",
        price=679,
        original_price=799,
        discount=15,
        image_url="",
        product_url="https://24h.pchome.com.tw/prod/DDAB01-PAGE2",
        stock=20,
        store="24h",
        rating=4.7,
        review_count=8,
        is_on_sale=True,
        crawled_at=datetime.now(),
    )
    calls = []

    class FakeCrawler:
        def search_products(self, keyword, **kwargs):
            calls.append((keyword, kwargs))
            return True, "ok", [product]

    monkeypatch.setattr(
        "services.marketplace_product_matcher.score_marketplace_match",
        lambda *_args, **_kwargs: type(
            "Diagnostics",
            (),
            {"score": 0.95},
        )(),
    )

    candidates = _search_pchome_candidates(
        FakeCrawler(),
        "理膚寶水 B5 修復霜 40ml",
        keywords=["理膚寶水 B5 40ml"],
        momo_price=699,
    )

    assert candidates == [product]
    assert calls[0][1]["limit"] == 40
    assert calls[0][1]["max_pages"] == 2