fix(branding): logo URL 컬럼 일관성 + 잘못된 로고 묘사 회피

- 채널 collectors (instagram/facebook/youtube/tiktok) 가 profileImage 를 raw_info.logo_url 컬럼에도 저장
- collect_brand_basics 가 공식 로고 URL 을 branding row 가 아니라 mainpage row 의 logo_url 컬럼에 저장
- select_branding_logo_url 가 mainpage row 의 logo_url 조회하도록 SQL 수정
- select_run_raw_data 가 logo_url 컬럼도 반환 (_logo_url 합성키) → branding._describe_channel_logos 가 컬럼에서 통일된 이름으로 읽음
- _describe_logo candidates 에서 firecrawl ogImage 제거 (이벤트 배너 잘못 잡히던 케이스)
- extra_channels (tiktok/kakaotalk/naver_cafe) language='KR' 박음

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

app/api/analysis.py

@@ -82,9 +82,9 @@ async def start_analysis(body: AnalysisCreate, background_tasks: BackgroundTasks
     extra_channels = [
         (SourceType.INSTAGRAM, "EN", _with_scheme(body.channels.instagram_en) or mock.get("instagram_en")),
         (SourceType.FACEBOOK,  "EN", _with_scheme(body.channels.facebook_en)  or mock.get("facebook_en")),
-        (SourceType.TIKTOK,    None, _with_scheme(body.channels.tiktok)       or mock.get("tiktok")),
-        (SourceType.KAKAOTALK, None, _with_scheme(body.channels.kakao_talk)   or mock.get("kakao_talk")),
-        (SourceType.NAVER_CAFE, None, _with_scheme(body.channels.naver_cafe)  or mock.get("naver_cafe")),
+        (SourceType.TIKTOK,    "KR", _with_scheme(body.channels.tiktok)       or mock.get("tiktok")),
+        (SourceType.KAKAOTALK, "KR", _with_scheme(body.channels.kakao_talk)   or mock.get("kakao_talk")),
+        (SourceType.NAVER_CAFE, "KR", _with_scheme(body.channels.naver_cafe)  or mock.get("naver_cafe")),
     ]
     for source_type, language, url in extra_channels:
         if url:

app/common/db/source.py

@@ -63,9 +63,8 @@ async def select_run_sources(analysis_run_id: str) -> list[dict]:
 
 
 async def select_run_raw_data(analysis_run_id: str) -> dict:
-    # language='EN' 인 row 는 dict key 를 "<source_type>_en" 으로 합성 (KR/EN 동시 수집 시 키 충돌 방지).
     rows = await fetchall(
-        "SELECT rs.source_type, rs.language, ri.raw_data"
+        "SELECT rs.source_type, rs.language, ri.raw_data, ri.logo_url"
         " FROM raw_info ri JOIN remote_source rs USING (source_id)"
         " WHERE ri.analysis_run_id = %s",
         (analysis_run_id,),
@@ -76,7 +75,10 @@ async def select_run_raw_data(analysis_run_id: str) -> dict:
         key = row["source_type"]
         if (row.get("language") or "").upper() == "EN":
             key = f"{key}_en"
-        result[key] = json.loads(raw) if isinstance(raw, str) else raw
+        data = json.loads(raw) if isinstance(raw, str) else (raw or {})
+        if isinstance(data, dict) and row.get("logo_url"):
+            data["_logo_url"] = row["logo_url"]
+        result[key] = data
     return result
 
 
@@ -118,7 +120,7 @@ async def select_branding_info_id(analysis_run_id: str) -> int | None:
 async def select_branding_logo_url(analysis_run_id: str) -> str | None:
     row = await fetchone(
         "SELECT ri.logo_url FROM raw_info ri JOIN remote_source rs USING (source_id)"
-        " WHERE ri.analysis_run_id = %s AND rs.source_type = 'branding' LIMIT 1",
+        " WHERE ri.analysis_run_id = %s AND rs.source_type = 'mainpage' LIMIT 1",
         (analysis_run_id,),
     )
     return (row or {}).get("logo_url")

app/services/branding.py

@@ -23,7 +23,6 @@ async def _describe_logo(analysis_run_id: str, info_id: int, vc: VisionClient) -
     candidates = [u for u in [
         column_logo,
         branding_meta.get("logoUrl"),
-        branding_meta.get("ogImage"),
         branding_meta.get("faviconUrl"),
     ] if u]
     if homepage_url:
@@ -59,7 +58,7 @@ async def _describe_channel_logos(analysis_run_id: str, info_id: int, vc: Vision
     }
     logos = [{"channel": label, "url": img}
              for key, label in _label.items()
-             if (img := (raw.get(key) or {}).get("profileImage"))]
+             if (img := (raw.get(key) or {}).get("_logo_url"))]
     if not logos:
         logger.info("[channel_logos] skip — no channel profileImages")
         return

app/services/collect.py

@@ -11,11 +11,18 @@ from models.status import SourceType
 from integrations.site_fetcher import fetch_html_and_css
 from services.brand_parser import find_logo_url_in_html, extract_brand_colors_from_text
 from common.db.source import update_raw_info_merge, update_raw_info_logo_url, select_run_raw_data
+from common.db.base import fetchone
 from services.facebook_audit import transform_for_storage as transform_facebook
 
 logger = logging.getLogger(__name__)
 
 
+async def _save_with_logo(info_id: int, data: dict) -> None:
+    await update_raw_info(info_id, data)
+    if data.get("profileImage"):
+        await update_raw_info_logo_url(info_id, data["profileImage"])
+
+
 async def collect_instagram(analysis_run_id: str, info_id: int, url: str) -> None:
     logger.info("[instagram] start run=%s url=%s", analysis_run_id, url)
     await update_raw_info_status(info_id, "processing")
@@ -24,7 +31,7 @@ async def collect_instagram(analysis_run_id: str, info_id: int, url: str) -> Non
         await update_raw_info_status(info_id, "failed")
         logger.warning("[instagram] failed run=%s", analysis_run_id)
         return
-    await update_raw_info(info_id, data)
+    await _save_with_logo(info_id, data)
     logger.info("[instagram] done run=%s", analysis_run_id)
 
 
@@ -37,7 +44,7 @@ async def collect_facebook(analysis_run_id: str, info_id: int, url: str) -> None
         logger.warning("[facebook] failed run=%s", analysis_run_id)
         return
     data = transform_facebook(data)
-    await update_raw_info(info_id, data)
+    await _save_with_logo(info_id, data)
     logger.info("[facebook] done run=%s", analysis_run_id)
 
 
@@ -61,7 +68,7 @@ async def collect_youtube(analysis_run_id: str, info_id: int, url: str) -> None:
         await update_raw_info_status(info_id, "failed")
         logger.warning("[youtube] failed run=%s", analysis_run_id)
         return
-    await update_raw_info(info_id, data)
+    await _save_with_logo(info_id, data)
     logger.info("[youtube] done run=%s", analysis_run_id)
 
 
@@ -101,7 +108,7 @@ async def collect_tiktok(analysis_run_id: str, info_id: int, url: str) -> None:
         await update_raw_info_status(info_id, "failed")
         logger.warning("[tiktok] failed run=%s", analysis_run_id)
         return
-    await update_raw_info(info_id, data)
+    await _save_with_logo(info_id, data)
     logger.info("[tiktok] done run=%s", analysis_run_id)
 
 
@@ -125,8 +132,6 @@ async def collect_kakaotalk(analysis_run_id: str, info_id: int, url: str) -> Non
 
 
 async def collect_brand_basics(analysis_run_id: str, info_id: int) -> None:
-    """branding 단계 collect — HTML/CSS 한 번 fetch → logo URL(컬럼) + brand 색상(JSON).
-    mainpage 수집 결과 의존이라 main wave gather 끝난 뒤 호출."""
     logger.info("[brand_basics] start run=%s info=%s", analysis_run_id, info_id)
     raw = await select_run_raw_data(analysis_run_id)
     mainpage = raw.get("mainpage") or {}
@@ -139,7 +144,13 @@ async def collect_brand_basics(analysis_run_id: str, info_id: int) -> None:
 
     logo_url = html_logo_url or branding_meta.get("logoUrl") or branding_meta.get("ogImage")
     if logo_url:
-        await update_raw_info_logo_url(info_id, logo_url)
+        mainpage_row = await fetchone(
+            "SELECT ri.info_id FROM raw_info ri JOIN remote_source rs USING (source_id)"
+            " WHERE ri.analysis_run_id = %s AND rs.source_type = 'mainpage' LIMIT 1",
+            (analysis_run_id,),
+        )
+        if mainpage_row:
+            await update_raw_info_logo_url(mainpage_row["info_id"], logo_url)
 
     payload: dict = {}
     if css_colors: