fix(insta-lab): trend_collector — Google Trends RSS + seed placeholder filter

(1) pytrends 4.x가 Google API 변경으로 trending_searches(pn='south_korea')
가 404 반환 → daily trending searches RSS endpoint를 requests로 직접 호출
하도록 교체. pytrends 의존성 제거.

(2) category_seeds 프롬프트 템플릿에 placeholder ('...', 'TBD' 등) 또는
2자 미만 값이 들어가면 NAVER가 400 Bad Request 반환 → _seeds_for에
_is_valid_seed 가드 추가, 모두 invalid면 DEFAULT_CATEGORY_SEEDS 폴백.

테스트 8/8 PASS (기존 6 + placeholder/fallback 2 신규).

insta-lab/app/trend_collector.py

@@ -1,17 +1,19 @@
-"""외부 트렌드 수집 — NAVER 인기 + Google Trends + LLM 카테고리 분류.
+"""외부 트렌드 수집 — NAVER 인기 + Google Trends RSS + LLM 카테고리 분류.
 
-Phase B Task 3: Google Trends integration via pytrends + Anthropic Haiku 분류 캐시 (24h TTL).
+NAVER: 카테고리별 시드 키워드로 인기 검색 → 빈도 상위 추출.
+Google Trends: pytrends 4.x가 Google API 변경으로 깨진 상태라 daily RSS endpoint 직접 호출.
+LLM 분류 결과는 24h in-memory 캐시.
 """
 
 import json
 import logging
 import re
 import time
+import xml.etree.ElementTree as ET
 from typing import Any, Dict, List, Optional
 
 import requests
 from anthropic import Anthropic
-from pytrends.request import TrendReq
 
 from .config import (
     NAVER_CLIENT_ID, NAVER_CLIENT_SECRET, DEFAULT_CATEGORY_SEEDS,
@@ -29,16 +31,36 @@ _NAVER_HEADERS = {
     "X-Naver-Client-Secret": NAVER_CLIENT_SECRET,
 }
 
+GOOGLE_TRENDS_RSS_URL = "https://trends.google.com/trends/trendingsearches/daily/rss?geo=KR"
+
+_PLACEHOLDER_SEEDS = {"...", "…", "tbd", "todo", "placeholder", "example"}
+
+
+def _is_valid_seed(s: str) -> bool:
+    """프롬프트 템플릿에 placeholder/빈 값이 들어가 NAVER에 400을 유발하는 일을 막는 가드."""
+    if not s:
+        return False
+    s = s.strip()
+    if len(s) < 2:
+        return False
+    if s.lower() in _PLACEHOLDER_SEEDS:
+        return False
+    return True
+
 
 def _seeds_for(category: str) -> List[str]:
+    """category_seeds 프롬프트 템플릿이 있으면 사용, 없거나 모두 invalid면 config DEFAULT 폴백."""
     pt = db.get_prompt_template("category_seeds")
     if pt and pt.get("template"):
         try:
             data = json.loads(pt["template"])
             if category in data:
-                return list(data[category])
-        except Exception:
-            pass
+                filtered = [s for s in (data[category] or []) if _is_valid_seed(s)]
+                if filtered:
+                    return filtered
+                logger.warning("category_seeds[%s]에 유효한 시드 없음 → DEFAULT 폴백", category)
+        except Exception as e:
+            logger.warning("category_seeds JSON 파싱 실패 → DEFAULT 폴백: %s", e)
     return list(DEFAULT_CATEGORY_SEEDS.get(category, []))
 
 
@@ -143,23 +165,38 @@ def classify_keyword(keyword: str) -> str:
 
 
 # ── Google Trends ─────────────────────────────────────────────────────────────
+# pytrends 4.x가 Google API 변경(404)으로 자주 깨지므로 daily trending searches
+# RSS endpoint를 직접 호출. RSS는 공식 Google Trends 서비스가 제공하며 pn=geo
+# 파라미터로 region 지정 가능.
 
 def fetch_google_trends() -> List[Dict[str, Any]]:
-    """pytrends 한국 daily trending searches. 실패 시 빈 리스트."""
+    """Google Trends Daily RSS (한국) 직접 호출. 실패 시 빈 리스트로 graceful degrade."""
     try:
-        pytrends = TrendReq(hl="ko-KR", tz=540)
-        df = pytrends.trending_searches(pn="south_korea")
+        resp = requests.get(
+            GOOGLE_TRENDS_RSS_URL,
+            timeout=15,
+            headers={"User-Agent": "Mozilla/5.0 (insta-lab trend collector)"},
+        )
+        resp.raise_for_status()
+        root = ET.fromstring(resp.text)
+        titles = [
+            (item.findtext("title") or "").strip()
+            for item in root.iter("item")
+        ]
+        titles = [t for t in titles if t]
     except Exception as e:
-        logger.warning("Google Trends fetch failed: %s", e)
+        logger.warning("Google Trends RSS fetch failed: %s", e)
         return []
 
     items: List[Dict[str, Any]] = []
-    for idx, row in df.iterrows():
-        kw = str(row.iloc[0]).strip()
-        if not kw:
-            continue
-        cat = classify_keyword(kw)
-        rank_score = round(max(0.0, 1.0 - (idx / max(1, len(df)))), 4)
+    total = max(1, len(titles))
+    for idx, kw in enumerate(titles):
+        try:
+            cat = classify_keyword(kw)
+        except Exception as e:
+            logger.warning("classify_keyword(%s) 실패: %s", kw, e)
+            cat = "uncategorized"
+        rank_score = round(max(0.0, 1.0 - (idx / total)), 4)
         items.append({
             "keyword": kw,
             "category": cat,

insta-lab/requirements.txt

@@ -7,4 +7,3 @@ jinja2>=3.1.4
 playwright==1.48.0
 pytest>=8.0
 pytest-asyncio>=0.24
-pytrends>=4.9

insta-lab/tests/test_trend_collector.py

@@ -77,16 +77,20 @@ def test_classify_keyword_with_cache(monkeypatch):
     assert calls["n"] == 1
 
 
-def test_fetch_google_trends_parses_and_classifies(tmp_db, monkeypatch):
-    class FakePyTrends:
-        def __init__(self, *_a, **_kw):
-            pass
-
-        def trending_searches(self, pn="south_korea"):
-            import pandas as pd
-            return pd.DataFrame({"0": ["기준금리", "BTS 컴백", "스트레스 관리"]})
-
-    monkeypatch.setattr(trend_collector, "TrendReq", FakePyTrends)
+def test_fetch_google_trends_parses_rss_and_classifies(tmp_db, monkeypatch):
+    fake_rss = """<?xml version="1.0" encoding="UTF-8"?>
+<rss version="2.0">
+  <channel>
+    <title>Daily Search Trends</title>
+    <item><title>기준금리</title></item>
+    <item><title>BTS 컴백</title></item>
+    <item><title>스트레스 관리</title></item>
+  </channel>
+</rss>"""
+    fake_resp = MagicMock()
+    fake_resp.text = fake_rss
+    fake_resp.raise_for_status.return_value = None
+    monkeypatch.setattr(trend_collector.requests, "get", lambda *a, **kw: fake_resp)
     monkeypatch.setattr(trend_collector, "classify_keyword",
                         lambda kw: {"기준금리": "economy", "BTS 컴백": "celebrity",
                                     "스트레스 관리": "psychology"}.get(kw, "uncategorized"))
@@ -108,14 +112,36 @@ def test_collect_all_invokes_both_sources(tmp_db, monkeypatch):
     assert out == {"naver_popular": 5, "google_trends": 3}
 
 
-def test_fetch_google_trends_graceful_on_pytrends_failure(monkeypatch):
-    class FakePyTrends:
-        def __init__(self, *_a, **_kw):
-            pass
-
-        def trending_searches(self, pn="south_korea"):
-            raise RuntimeError("rate limited")
-
-    monkeypatch.setattr(trend_collector, "TrendReq", FakePyTrends)
+def test_fetch_google_trends_graceful_on_rss_failure(monkeypatch):
+    fake_resp = MagicMock()
+    fake_resp.raise_for_status.side_effect = RuntimeError("Google returned 404")
+    monkeypatch.setattr(trend_collector.requests, "get", lambda *a, **kw: fake_resp)
     out = trend_collector.fetch_google_trends()
     assert out == []
+
+
+def test_seeds_for_filters_placeholder(tmp_db, monkeypatch):
+    """category_seeds 템플릿에 placeholder '...'가 들어가도 DEFAULT 폴백."""
+    from app import db as db_module
+    db_module.upsert_prompt_template(
+        "category_seeds",
+        '{"economy": ["...", "…", "a", "real_keyword"]}',
+        "test",
+    )
+    out = trend_collector._seeds_for("economy")
+    # '...', '…', 'a'(2자 미만)는 필터링되고 'real_keyword'만 남음
+    assert out == ["real_keyword"]
+
+
+def test_seeds_for_falls_back_when_all_invalid(tmp_db, monkeypatch):
+    """모든 시드가 invalid면 DEFAULT_CATEGORY_SEEDS 폴백."""
+    from app import db as db_module
+    db_module.upsert_prompt_template(
+        "category_seeds",
+        '{"economy": ["...", "TBD", ""]}',
+        "test",
+    )
+    out = trend_collector._seeds_for("economy")
+    # DEFAULT_CATEGORY_SEEDS["economy"] 가 반환되어야 함
+    from app.config import DEFAULT_CATEGORY_SEEDS
+    assert out == list(DEFAULT_CATEGORY_SEEDS["economy"])