feat: add stock-lab service for financial news scraping and analysis

stock-lab/Dockerfile

@@ -0,0 +1,9 @@
+FROM python:3.12-alpine
+
+WORKDIR /app
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

stock-lab/app/db.py

@@ -0,0 +1,54 @@
+import sqlite3
+import os
+import hashlib
+from typing import List, Dict, Any
+
+DB_PATH = "/app/data/stock.db"
+
+def _conn() -> sqlite3.Connection:
+    os.makedirs(os.path.dirname(DB_PATH), exist_ok=True)
+    conn = sqlite3.connect(DB_PATH)
+    conn.row_factory = sqlite3.Row
+    return conn
+
+def init_db():
+    with _conn() as conn:
+        conn.execute("""
+            CREATE TABLE IF NOT EXISTS articles (
+                id INTEGER PRIMARY KEY AUTOINCREMENT,
+                hash TEXT UNIQUE NOT NULL,
+                title TEXT NOT NULL,
+                link TEXT,
+                summary TEXT,
+                press TEXT,
+                pub_date TEXT,
+                crawled_at TEXT
+            )
+        """)
+        conn.execute("CREATE INDEX IF NOT EXISTS idx_articles_crawled ON articles(crawled_at DESC)")
+
+def save_articles(articles: List[Dict[str, str]]) -> int:
+    count = 0
+    with _conn() as conn:
+        for a in articles:
+            # 중복 체크용 해시 (제목+링크)
+            unique_str = f"{a['title']}|{a['link']}"
+            h = hashlib.md5(unique_str.encode()).hexdigest()
+            
+            try:
+                conn.execute("""
+                    INSERT INTO articles (hash, title, link, summary, press, pub_date, crawled_at)
+                    VALUES (?, ?, ?, ?, ?, ?, ?)
+                """, (h, a['title'], a['link'], a['summary'], a['press'], a['date'], a['crawled_at']))
+                count += 1
+            except sqlite3.IntegrityError:
+                pass # 이미 존재함
+    return count
+
+def get_latest_articles(limit: int = 20) -> List[Dict[str, Any]]:
+    with _conn() as conn:
+        rows = conn.execute(
+            "SELECT * FROM articles ORDER BY crawled_at DESC, id DESC LIMIT ?", 
+            (limit,)
+        ).fetchall()
+        return [dict(r) for r in rows]

stock-lab/app/main.py

@@ -0,0 +1,47 @@
+import os
+from fastapi import FastAPI
+from apscheduler.schedulers.background import BackgroundScheduler
+
+from .db import init_db, save_articles, get_latest_articles
+from .scraper import fetch_market_news
+
+app = FastAPI()
+scheduler = BackgroundScheduler(timezone=os.getenv("TZ", "Asia/Seoul"))
+
+@app.on_event("startup")
+def on_startup():
+    init_db()
+    
+    # 매일 아침 8시 뉴스 스크랩
+    scheduler.add_job(run_scraping_job, "cron", hour="8", minute="0")
+    
+    # 앱 시작 시에도 한 번 실행 (데이터 없으면)
+    if not get_latest_articles(1):
+        run_scraping_job()
+        
+    scheduler.start()
+
+def run_scraping_job():
+    print("[StockLab] Starting news scraping...")
+    articles = fetch_market_news()
+    count = save_articles(articles)
+    print(f"[StockLab] Saved {count} new articles.")
+
+@app.get("/health")
+def health():
+    return {"ok": True}
+
+@app.get("/api/stock/news")
+def get_news(limit: int = 20):
+    """최신 주식 뉴스 조회"""
+    return get_latest_articles(limit)
+
+@app.post("/api/admin/stock/scrap")
+def trigger_scrap():
+    """수동 스크랩 트리거"""
+    run_scraping_job()
+    return {"ok": True}
+
+@app.get("/api/version")
+def version():
+    return {"version": os.getenv("APP_VERSION", "dev")}

stock-lab/app/scraper.py

@@ -0,0 +1,78 @@
+import requests
+from bs4 import BeautifulSoup
+from typing import List, Dict
+import time
+
+# 네이버 파이낸스 주요 뉴스
+NAVER_FINANCE_NEWS_URL = "https://finance.naver.com/news/mainnews.naver"
+
+def fetch_market_news() -> List[Dict[str, str]]:
+    """
+    네이버 금융 '주요 뉴스' 크롤링
+    반환: [{"title": "...", "link": "...", "summary": "...", "date": "..."}, ...]
+    """
+    try:
+        headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36"
+        }
+        resp = requests.get(NAVER_FINANCE_NEWS_URL, headers=headers, timeout=10)
+        resp.raise_for_status()
+
+        soup = BeautifulSoup(resp.content, "html.parser", from_encoding="cp949")
+        
+        # 주요 뉴스 리스트 추출
+        # 구조: div.mainNewsList > ul > li
+        articles = []
+        news_list = soup.select(".mainNewsList ul li")
+        
+        for li in news_list:
+            # 썸네일 있을 수도 있고 없을 수도 있음
+            dl = li.select_one("dl")
+            if not dl:
+                continue
+                
+            # 제목 (dd.articleSubject > a)
+            subject_tag = dl.select_one(".articleSubject a")
+            if not subject_tag:
+                continue
+                
+            title = subject_tag.get_text(strip=True)
+            link = "https://finance.naver.com" + subject_tag["href"]
+            
+            # 요약 (dd.articleSummary)
+            summary_tag = dl.select_one(".articleSummary")
+            summary = ""
+            press = ""
+            date = ""
+            
+            if summary_tag:
+                # 불필요한 태그 제거
+                for child in summary_tag.select(".press, .wdate"):
+                    if "press" in child.get("class", []):
+                        press = child.get_text(strip=True)
+                    if "wdate" in child.get("class", []):
+                        date = child.get_text(strip=True)
+                    child.extract()
+                summary = summary_tag.get_text(strip=True)
+
+            articles.append({
+                "title": title,
+                "link": link,
+                "summary": summary,
+                "press": press,
+                "date": date,
+                "crawled_at": time.strftime("%Y-%m-%d %H:%M:%S")
+            })
+            
+        return articles
+
+    except Exception as e:
+        print(f"[StockLab] Scraping failed: {e}")
+        return []
+
+def fetch_major_indices() -> Dict[str, Any]:
+    """
+    KOSPI, KOSDAQ, USD/KRW 등 주요 지표 (네이버 금융 홈)
+    """
+    # ... (추후 구현, 일단 빈 딕셔너리)
+    return {}

stock-lab/requirements.txt

@@ -0,0 +1,5 @@
+fastapi
+uvicorn
+requests
+beautifulsoup4
+apscheduler