feat(insta-lab): news_collector with NAVER news.json + dedupe

This commit is contained in:
2026-05-16 00:27:13 +09:00
parent d1245d040c
commit c057304981
2 changed files with 171 additions and 0 deletions

View File

@@ -0,0 +1,89 @@
from unittest.mock import patch, MagicMock
import os
import tempfile
import pytest
from app import db as db_module
from app import news_collector
@pytest.fixture
def tmp_db(monkeypatch):
fd, path = tempfile.mkstemp(suffix=".db")
os.close(fd)
monkeypatch.setattr(db_module, "DB_PATH", path)
db_module.init_db()
yield path
# Close all SQLite WAL files before removal (needed on Windows)
import gc
gc.collect()
for ext in ("", "-wal", "-shm"):
try:
os.remove(path + ext)
except FileNotFoundError:
pass
SAMPLE_RESPONSE = {
"items": [
{
"title": "<b>금리</b> 인상 단행",
"originallink": "https://news.example.com/1",
"link": "https://n.news.naver.com/article/1",
"description": "한국은행이 <b>기준금리</b>를 25bp 올렸다.",
"pubDate": "Fri, 15 May 2026 08:00:00 +0900",
},
{
"title": "환율 급등",
"originallink": "https://news.example.com/2",
"link": "https://n.news.naver.com/article/2",
"description": "원달러 환율이 1400원을 돌파했다.",
"pubDate": "Fri, 15 May 2026 09:00:00 +0900",
},
],
}
def test_strip_html_and_decode_entities():
out = news_collector._clean(' <b>"테스트"</b> &amp; 아이템 ')
assert out == '"테스트" & 아이템'
def test_search_news_parses_items(tmp_db):
fake_resp = MagicMock()
fake_resp.json.return_value = SAMPLE_RESPONSE
fake_resp.raise_for_status.return_value = None
with patch.object(news_collector.requests, "get", return_value=fake_resp):
items = news_collector.search_news("금리", display=10)
assert len(items) == 2
assert items[0]["title"] == "금리 인상 단행"
assert items[0]["summary"].startswith("한국은행")
def test_collect_for_category_inserts(tmp_db):
fake_resp = MagicMock()
fake_resp.json.return_value = SAMPLE_RESPONSE
fake_resp.raise_for_status.return_value = None
with patch.object(news_collector.requests, "get", return_value=fake_resp):
news_collector.collect_for_category("economy", seed_keywords=["금리"], per_keyword=10)
rows = db_module.list_news_articles(category="economy", days=7)
assert {r["link"] for r in rows} == {
"https://n.news.naver.com/article/1",
"https://n.news.naver.com/article/2",
}
def test_collect_dedupes_existing(tmp_db):
db_module.add_news_article({
"category": "economy", "title": "기존",
"link": "https://n.news.naver.com/article/1", "summary": ""
})
fake_resp = MagicMock()
fake_resp.json.return_value = SAMPLE_RESPONSE
fake_resp.raise_for_status.return_value = None
with patch.object(news_collector.requests, "get", return_value=fake_resp):
news_collector.collect_for_category("economy", seed_keywords=["금리"])
rows = db_module.list_news_articles(category="economy", days=7)
# 1 pre-existing + 1 newly added (the other link); UNIQUE link blocks duplicate insert
assert len(rows) == 2