[V10.345] 收斂 PChome 搜尋詞特定品線

config.py

@@ -320,7 +320,7 @@ YOUTUBE_API_KEY = os.getenv('YOUTUBE_API_KEY', '')
 # ==========================================
 # 系統版本與路徑
 # ==========================================
-SYSTEM_VERSION = "V10.344"
+SYSTEM_VERSION = "V10.345"
 LOG_FILE_PATH = os.path.join(BASE_DIR, 'logs/system.log')
 public_url = PUBLIC_URL  # 用於模板顯示
 

docs/memory/code_modularization_inventory_20260430.md

@@ -27,6 +27,7 @@
 - 2026-05-20 追記：同步背景 PChome crawler 搜尋韌性擴充後的 `services/pchome_crawler.py` 行數；此處只更新 inventory，不變更 PChome crawler 行為。
 - 2026-05-20 追記：同步 PChome 近門檻候選重評與 matcher 系列/刀片數防錯配更新後的 `services/marketplace_product_matcher.py`、`services/competitor_price_feeder.py` 行數；此處只更新 inventory，不變更比價行為。
 - 2026-05-20 追記：同步 PChome 搜尋詞品質層、候選召回與 hard-veto 狀態分流更新後的 `services/marketplace_product_matcher.py`、`services/competitor_price_feeder.py` 行數；並補列背景市場情報 deployment readiness 大檔，僅更新 inventory。
+- 2026-05-20 追記：同步 PChome 搜尋詞特定品線優先級更新後的 `services/marketplace_product_matcher.py` 行數；此處只更新 inventory，不變更模組化決策。
 
 ## 達到或超過 800 行檔案清單
 
@@ -53,7 +54,7 @@
 | 940 | `services/import_service.py` | P2 import service | validators / import writers / report builders |
 | 933 | `services/telegram_templates.py` | P2 Telegram templates | alert template groups / channel-specific formatting / reusable render helpers |
 | 867 | `services/token_report_service.py` | P2 token report service | query / aggregation / chart payload / notification formatting |
-| 1356 | `services/marketplace_product_matcher.py` | P2 marketplace matcher | identity parsing / unit-comparable scoring / search term quality / persistence normalization |
+| 1387 | `services/marketplace_product_matcher.py` | P2 marketplace matcher | identity parsing / unit-comparable scoring / search term quality / persistence normalization |
 | 865 | `routes/daily_sales_routes.py` | P2 Daily Sales Blueprint | route glue / export helpers / daily query and formatting service |
 | 844 | `services/ollama_service.py` | P2 Ollama client | host health / request client / fallback policy / response parsing |
 | 849 | `services/pchome_crawler.py` | P2 PChome crawler | search fetch / parsing / fallback source handling / rate limit policy |

services/marketplace_product_matcher.py

@@ -138,6 +138,7 @@ SEARCH_NOISE_PHRASES = (
     "水光感",
     "官方直營",
     "官方",
+    "經典款",
 )
 
 SEARCH_NOISE_TOKENS = {
@@ -160,9 +161,23 @@ SEARCH_NOISE_TOKENS = {
     "防曬",
     "彩妝",
     "水光感",
+    "保濕",
+    "抗老",
+    "超品日",
+    "經典款",
+    "款",
+    "pdrn",
 }
 
 SEARCH_IDENTITY_ANCHORS = (
+    "絕對完美永生玫瑰逆齡乳霜",
+    "永生玫瑰逆齡乳霜",
+    "永生玫瑰霜",
+    "玫瑰精露",
+    "玫瑰霜",
+    "青春敷面膜",
+    "長效潤膚霜",
+    "小黑瓶",
     "免用水潔淨液",
     "身體按摩精油",
     "按摩精油",
@@ -196,6 +211,15 @@ SEARCH_IDENTITY_ANCHORS = (
     "香氛機",
 )
 
+SEARCH_BROAD_ANCHORS = {
+    "乳霜",
+    "面霜",
+    "面膜",
+    "精華",
+    "乳液",
+    "精油",
+}
+
 SEARCH_AMBIGUOUS_PRODUCT_TERMS = {
     "保護膜",
     "保護貼",
@@ -1234,6 +1258,8 @@ def _extract_anchor_phrases(token: str) -> list[str]:
         else:
             phrase = anchor
         phrase = _clean_search_phrase(phrase)
+        if phrase.startswith("款") and len(phrase) > 2:
+            phrase = phrase[1:]
         if any(existing in phrase and existing != phrase for existing in phrases):
             continue
         if len(phrase) >= 2 and phrase not in phrases:
@@ -1248,6 +1274,8 @@ def _search_core_score(token: str, all_tokens: set[str]) -> tuple[int, int, str]
     compact = cleaned.replace(" ", "")
     if compact in SEARCH_NOISE_TOKENS or compact in GENERIC_TOKENS:
         return (-900, 0, cleaned)
+    if re.fullmatch(r"\d+(?:\.\d+)?(?:ml|g|mg|kg|l)x\d+", compact, re.I):
+        return (-900, 0, cleaned)
 
     score = 0
     if re.search(r"[a-z][a-z0-9-]{2,}", cleaned):
@@ -1258,8 +1286,11 @@ def _search_core_score(token: str, all_tokens: set[str]) -> tuple[int, int, str]
     anchors = _extract_anchor_phrases(cleaned)
     if anchors:
         score += 90
+        score += min(24, len(anchors[0]) * 3)
         if anchors[0] == compact:
             score += 8
+        if compact in SEARCH_BROAD_ANCHORS:
+            score -= 28
     else:
         score += max(0, 24 - len(compact))
 

tests/test_marketplace_product_matcher.py

@@ -468,6 +468,26 @@ def test_marketplace_search_terms_keep_professional_product_phrase():
     assert not any("卸除防曬" in term or "外出清潔" in term for term in mustela_terms)
 
 
+def test_marketplace_search_terms_prefer_specific_line_over_generic_usage_words():
+    from services.marketplace_product_matcher import build_search_terms
+
+    mask_terms = build_search_terms("【SK-II】官方直營 青春敷面膜10+6+6送12(保濕/面膜/超品日)", max_terms=5)
+    bottle_terms = build_search_terms(
+        "【LANCOME 蘭蔻】官方直營 經典款小黑瓶100ml雙入組(LANCOME/經典款/抗老)",
+        max_terms=5,
+    )
+    rose_terms = build_search_terms(
+        "【蘭蔻】官方直營 玫瑰霜60ml+玫瑰精露150ml(LANCOME/永生玫瑰霜/抗老/PDRN)",
+        max_terms=5,
+    )
+
+    assert mask_terms[0] == "sk ii 青春敷面膜"
+    assert bottle_terms[0] == "蘭蔻 小黑瓶 100ml"
+    assert rose_terms[0] == "蘭蔻 永生玫瑰霜 60ml"
+    assert "抗老" not in " ".join(bottle_terms[:3] + rose_terms[:3])
+    assert "pdrn" not in " ".join(term.lower() for term in rose_terms[:3])
+
+
 def test_batch_compare_top_uses_latest_momo_price_not_revenue(monkeypatch):
     from services import pchome_crawler