feat(screener): ai_news scraper (naver finance ticker news)

2026-05-13 23:29:52 +09:00
parent 658ed13571
commit 6ba29599aa
3 changed files with 94 additions and 0 deletions
--- a/stock-lab/app/screener/ai_news/init.py
+++ b/stock-lab/app/screener/ai_news/init.py
--- a/stock-lab/app/screener/ai_news/scraper.py
+++ b/stock-lab/app/screener/ai_news/scraper.py
@@ -0,0 +1,39 @@
+"""네이버 finance 종목 뉴스 스크래핑."""
+
+from __future__ import annotations
+
+import logging
+from typing import Any, Dict, List
+
+from bs4 import BeautifulSoup
+
+log = logging.getLogger(__name__)
+
+NAVER_NEWS_URL = "https://finance.naver.com/item/news_news.naver"
+NAVER_HEADERS = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
+    "Referer": "https://finance.naver.com/",
+}
+
+
+async def fetch_news(client, ticker: str, n: int = 5) -> List[Dict[str, Any]]:
+    """Scrape top N news headlines for a ticker. Returns [] on any failure."""
+    try:
+        r = await client.get(NAVER_NEWS_URL, params={"code": ticker, "page": 1})
+    except Exception as e:
+        log.warning("ai_news scrape http error for %s: %s", ticker, e)
+        return []
+    if r.status_code != 200:
+        return []
+    soup = BeautifulSoup(r.text, "lxml")
+    out: List[Dict[str, Any]] = []
+    for row in soup.select("table.type5 tbody tr")[:n]:
+        title_el = row.select_one("td.title a")
+        date_el = row.select_one("td.date")
+        if not title_el or not date_el:
+            continue
+        out.append({
+            "title": title_el.get_text(strip=True),
+            "date": date_el.get_text(strip=True),
+        })
+    return out
--- a/stock-lab/tests/test_ai_news_scraper.py
+++ b/stock-lab/tests/test_ai_news_scraper.py
@@ -0,0 +1,55 @@
+import pytest
+from unittest.mock import AsyncMock
+from app.screener.ai_news import scraper
+
+
+SAMPLE_HTML = """
+<html><body>
+<table class="type5"><tbody>
+<tr><td class="title"><a href="/news1">삼성전자, HBM 양산 가시화</a></td><td class="date">2026.05.13 07:30</td></tr>
+<tr><td class="title"><a href="/news2">삼성, 4분기 어닝 쇼크 우려</a></td><td class="date">2026.05.13 06:00</td></tr>
+<tr><td class="title"><a href="/news3">메모리 시장 회복세</a></td><td class="date">2026.05.12 18:00</td></tr>
+</tbody></table>
+</body></html>
+"""
+
+EMPTY_HTML = "<html><body><table class='type5'><tbody></tbody></table></body></html>"
+
+
+def _mk_client(status_code=200, text=SAMPLE_HTML):
+    client = AsyncMock()
+    resp = AsyncMock()
+    resp.status_code = status_code
+    resp.text = text
+    client.get = AsyncMock(return_value=resp)
+    return client
+
+
+@pytest.mark.asyncio
+async def test_fetch_news_success_returns_n_items():
+    client = _mk_client()
+    out = await scraper.fetch_news(client, "005930", n=2)
+    assert len(out) == 2
+    assert out[0]["title"] == "삼성전자, HBM 양산 가시화"
+    assert out[0]["date"] == "2026.05.13 07:30"
+
+
+@pytest.mark.asyncio
+async def test_fetch_news_404_returns_empty():
+    client = _mk_client(status_code=404, text="")
+    out = await scraper.fetch_news(client, "999999", n=5)
+    assert out == []
+
+
+@pytest.mark.asyncio
+async def test_fetch_news_empty_table_returns_empty():
+    client = _mk_client(text=EMPTY_HTML)
+    out = await scraper.fetch_news(client, "005930", n=5)
+    assert out == []
+
+
+@pytest.mark.asyncio
+async def test_fetch_news_n_caps_results():
+    client = _mk_client()
+    out = await scraper.fetch_news(client, "005930", n=2)
+    assert len(out) == 2  # 샘플에 3개 있지만 n=2로 잘림