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

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 {}