feat(blog-lab): 네이버 블로그 본문 크롤링 모듈 추가

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

blog-lab/tests/conftest.py

@@ -0,0 +1,9 @@
+"""공통 테스트 픽스처."""
+import os
+import sys
+
+# app 패키지를 blog_lab_app으로도 import 가능하게
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
+if "blog_lab_app" not in sys.modules:
+    import app as blog_lab_app
+    sys.modules["blog_lab_app"] = blog_lab_app

blog-lab/tests/test_web_crawler.py

@@ -0,0 +1,68 @@
+"""web_crawler 모듈 테스트."""
+import pytest
+from unittest.mock import patch, AsyncMock
+from app.web_crawler import crawl_blog_content, enrich_top_blogs, _parse_naver_blog_url
+
+
+def test_parse_naver_blog_url_valid():
+    """blog.naver.com URL에서 blogId와 logNo를 올바르게 파싱."""
+    result = _parse_naver_blog_url("https://blog.naver.com/testuser/123456")
+    assert result == ("testuser", "123456")
+
+
+def test_parse_returns_none_for_invalid_url():
+    """잘못된 URL은 None 반환."""
+    result = _parse_naver_blog_url("https://example.com/post")
+    assert result is None
+
+
+@pytest.mark.asyncio
+async def test_crawl_returns_empty_on_non_naver_url():
+    """네이버 블로그가 아닌 URL은 빈 문자열 반환."""
+    result = await crawl_blog_content("https://example.com/post")
+    assert result == ""
+
+
+@pytest.mark.asyncio
+async def test_crawl_truncates_to_2000_chars():
+    """본문이 2000자를 초과하면 잘라낸다."""
+    long_html = f'<div class="se-main-container"><p>{"가" * 3000}</p></div>'
+    with patch("app.web_crawler._fetch_html", new_callable=AsyncMock, return_value=long_html):
+        result = await crawl_blog_content("https://blog.naver.com/testuser/123")
+    assert len(result) <= 2000
+
+
+@pytest.mark.asyncio
+async def test_crawl_returns_empty_on_fetch_failure():
+    """HTTP 요청 실패 시 빈 문자열 반환."""
+    with patch("app.web_crawler._fetch_html", new_callable=AsyncMock, side_effect=Exception("timeout")):
+        result = await crawl_blog_content("https://blog.naver.com/testuser/123")
+    assert result == ""
+
+
+@pytest.mark.asyncio
+async def test_enrich_top_blogs_adds_content_field():
+    """enrich_top_blogs가 각 블로그에 content 필드를 추가."""
+    blogs = [
+        {"title": "테스트", "link": "https://blog.naver.com/user1/111", "bloggername": "유저1", "description": "설명"},
+        {"title": "테스트2", "link": "https://blog.naver.com/user2/222", "bloggername": "유저2", "description": "설명2"},
+    ]
+    with patch("app.web_crawler.crawl_blog_content", new_callable=AsyncMock, return_value="크롤링된 본문"):
+        result = await enrich_top_blogs(blogs)
+    assert len(result) == 2
+    assert result[0]["content"] == "크롤링된 본문"
+    assert result[1]["content"] == "크롤링된 본문"
+
+
+@pytest.mark.asyncio
+async def test_enrich_top_blogs_handles_partial_failure():
+    """일부 크롤링 실패 시에도 나머지는 정상 처리."""
+    blogs = [
+        {"title": "성공", "link": "https://blog.naver.com/user1/111"},
+        {"title": "실패", "link": "https://blog.naver.com/user2/222"},
+    ]
+    side_effects = ["성공 본문", Exception("fail")]
+    with patch("app.web_crawler.crawl_blog_content", new_callable=AsyncMock, side_effect=side_effects):
+        result = await enrich_top_blogs(blogs)
+    assert result[0]["content"] == "성공 본문"
+    assert result[1]["content"] == ""