Initial commit - cleaned repository
This commit is contained in:
jungwoo choi
13
backup-services/news-aggregator/backend/Dockerfile
Normal file
13
backup-services/news-aggregator/backend/Dockerfile
Normal file
@ -0,0 +1,13 @@
|
||||
FROM python:3.11-slim
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
# Install dependencies
|
||||
COPY requirements.txt .
|
||||
RUN pip install --no-cache-dir -r requirements.txt
|
||||
|
||||
# Copy application
|
||||
COPY . .
|
||||
|
||||
# Run the application
|
||||
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]
|
||||
365
backup-services/news-aggregator/backend/app/main.py
Normal file
365
backup-services/news-aggregator/backend/app/main.py
Normal file
@ -0,0 +1,365 @@
|
||||
"""
|
||||
News Aggregator Service
|
||||
RSS 피드 제목을 구글 검색으로 확장하는 통합 서비스
|
||||
"""
|
||||
from fastapi import FastAPI, HTTPException, Query, BackgroundTasks
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
from typing import List, Optional, Dict, Any
|
||||
from datetime import datetime
|
||||
import httpx
|
||||
import asyncio
|
||||
from pydantic import BaseModel
|
||||
import logging
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(level=logging.INFO)
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
app = FastAPI(
|
||||
title="News Aggregator Service",
|
||||
description="RSS 피드와 구글 검색을 통합한 뉴스 수집 서비스",
|
||||
version="1.0.0"
|
||||
)
|
||||
|
||||
# CORS 설정
|
||||
app.add_middleware(
|
||||
CORSMiddleware,
|
||||
allow_origins=["*"],
|
||||
allow_credentials=True,
|
||||
allow_methods=["*"],
|
||||
allow_headers=["*"],
|
||||
)
|
||||
|
||||
# Configuration
|
||||
RSS_SERVICE_URL = "http://rss-feed-backend:8000"
|
||||
GOOGLE_SEARCH_SERVICE_URL = "http://google-search-backend:8000"
|
||||
|
||||
# Response Models
|
||||
class NewsItem(BaseModel):
|
||||
"""뉴스 항목"""
|
||||
rss_title: str
|
||||
rss_link: Optional[str] = None
|
||||
google_results: List[Dict[str, Any]] = []
|
||||
search_keyword: str
|
||||
timestamp: datetime = None
|
||||
|
||||
class AggregatedNews(BaseModel):
|
||||
"""통합 뉴스 결과"""
|
||||
keyword: str
|
||||
rss_feed_url: str
|
||||
total_rss_entries: int
|
||||
processed_entries: int
|
||||
news_items: List[NewsItem]
|
||||
processing_time: float
|
||||
|
||||
# HTTP Client
|
||||
client = httpx.AsyncClient(timeout=30.0)
|
||||
|
||||
@app.on_event("startup")
|
||||
async def startup():
|
||||
"""서비스 시작"""
|
||||
logger.info("News Aggregator Service starting...")
|
||||
|
||||
@app.on_event("shutdown")
|
||||
async def shutdown():
|
||||
"""서비스 종료"""
|
||||
await client.aclose()
|
||||
logger.info("News Aggregator Service stopped")
|
||||
|
||||
@app.get("/")
|
||||
async def root():
|
||||
return {
|
||||
"service": "News Aggregator Service",
|
||||
"version": "1.0.0",
|
||||
"description": "RSS 피드와 구글 검색 통합 서비스",
|
||||
"endpoints": {
|
||||
"aggregate": "GET /api/aggregate",
|
||||
"aggregate_by_location": "GET /api/aggregate/location",
|
||||
"aggregate_by_topic": "GET /api/aggregate/topic",
|
||||
"health": "GET /health"
|
||||
}
|
||||
}
|
||||
|
||||
@app.get("/health")
|
||||
async def health_check():
|
||||
"""헬스 체크"""
|
||||
try:
|
||||
# Check RSS service
|
||||
rss_response = await client.get(f"{RSS_SERVICE_URL}/health")
|
||||
rss_healthy = rss_response.status_code == 200
|
||||
|
||||
# Check Google Search service
|
||||
google_response = await client.get(f"{GOOGLE_SEARCH_SERVICE_URL}/health")
|
||||
google_healthy = google_response.status_code == 200
|
||||
|
||||
return {
|
||||
"status": "healthy" if (rss_healthy and google_healthy) else "degraded",
|
||||
"services": {
|
||||
"rss_feed": "healthy" if rss_healthy else "unhealthy",
|
||||
"google_search": "healthy" if google_healthy else "unhealthy"
|
||||
},
|
||||
"timestamp": datetime.now().isoformat()
|
||||
}
|
||||
except Exception as e:
|
||||
return {
|
||||
"status": "unhealthy",
|
||||
"error": str(e),
|
||||
"timestamp": datetime.now().isoformat()
|
||||
}
|
||||
|
||||
@app.get("/api/aggregate", response_model=AggregatedNews)
|
||||
async def aggregate_news(
|
||||
q: str = Query(..., description="검색 키워드"),
|
||||
limit: int = Query(10, description="처리할 RSS 항목 수", ge=1, le=50),
|
||||
google_results_per_title: int = Query(5, description="각 제목당 구글 검색 결과 수", ge=1, le=10),
|
||||
lang: str = Query("ko", description="언어 코드"),
|
||||
country: str = Query("KR", description="국가 코드")
|
||||
):
|
||||
"""
|
||||
키워드로 RSS 피드를 검색하고, 각 제목을 구글에서 재검색
|
||||
|
||||
1. 키워드로 Google News RSS 피드 가져오기
|
||||
2. RSS 피드의 각 제목을 구글 검색
|
||||
3. 통합 결과 반환
|
||||
"""
|
||||
start_time = datetime.now()
|
||||
|
||||
try:
|
||||
# Step 1: Get RSS feed from keyword
|
||||
logger.info(f"Fetching RSS feed for keyword: {q}")
|
||||
rss_response = await client.get(
|
||||
f"{RSS_SERVICE_URL}/api/google-rss/search",
|
||||
params={"q": q, "lang": lang, "country": country}
|
||||
)
|
||||
rss_response.raise_for_status()
|
||||
rss_data = rss_response.json()
|
||||
|
||||
if not rss_data.get("success"):
|
||||
raise HTTPException(status_code=500, detail=f"RSS 피드 가져오기 실패: {rss_data.get('error')}")
|
||||
|
||||
# Step 2: Process each RSS entry with Google search
|
||||
news_items = []
|
||||
entries = rss_data.get("entries", [])
|
||||
|
||||
# If no entries field, fallback to sample_titles
|
||||
if not entries:
|
||||
titles = rss_data.get("sample_titles", [])[:limit]
|
||||
entries = [{"title": title, "link": "", "published": ""} for title in titles]
|
||||
else:
|
||||
entries = entries[:limit]
|
||||
|
||||
# Create tasks for parallel processing
|
||||
search_tasks = []
|
||||
for entry in entries:
|
||||
title = entry.get("title", "")
|
||||
# Clean title for better search results
|
||||
clean_title = title.split(" - ")[-1] if " - " in title else title
|
||||
search_tasks.append(
|
||||
search_google(clean_title, google_results_per_title, lang, country)
|
||||
)
|
||||
|
||||
# Execute searches in parallel
|
||||
logger.info(f"Searching Google for {len(search_tasks)} RSS entries")
|
||||
search_results = await asyncio.gather(*search_tasks, return_exceptions=True)
|
||||
|
||||
# Combine results
|
||||
for i, entry in enumerate(entries):
|
||||
google_results = []
|
||||
if not isinstance(search_results[i], Exception):
|
||||
google_results = search_results[i]
|
||||
|
||||
title = entry.get("title", "")
|
||||
news_items.append(NewsItem(
|
||||
rss_title=title,
|
||||
rss_link=entry.get("link", ""),
|
||||
google_results=google_results,
|
||||
search_keyword=title.split(" - ")[-1] if " - " in title else title,
|
||||
timestamp=datetime.now()
|
||||
))
|
||||
|
||||
# Calculate processing time
|
||||
processing_time = (datetime.now() - start_time).total_seconds()
|
||||
|
||||
return AggregatedNews(
|
||||
keyword=q,
|
||||
rss_feed_url=rss_data.get("feed_url", ""),
|
||||
total_rss_entries=rss_data.get("entry_count", 0),
|
||||
processed_entries=len(news_items),
|
||||
news_items=news_items,
|
||||
processing_time=processing_time
|
||||
)
|
||||
|
||||
except httpx.HTTPStatusError as e:
|
||||
logger.error(f"HTTP error: {e}")
|
||||
raise HTTPException(status_code=e.response.status_code, detail=str(e))
|
||||
except Exception as e:
|
||||
logger.error(f"Error in aggregate_news: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
async def search_google(query: str, num_results: int, lang: str, country: str) -> List[Dict[str, Any]]:
|
||||
"""구글 검색 서비스 호출 - 전체 콘텐츠 포함"""
|
||||
try:
|
||||
# Full content API 직접 호출
|
||||
response = await client.get(
|
||||
f"{GOOGLE_SEARCH_SERVICE_URL}/api/search/full",
|
||||
params={
|
||||
"q": query,
|
||||
"num": num_results,
|
||||
"lang": lang,
|
||||
"country": country
|
||||
}
|
||||
)
|
||||
response.raise_for_status()
|
||||
data = response.json()
|
||||
results = data.get("results", [])
|
||||
|
||||
# full_content가 이미 포함되어 있으므로 그대로 반환
|
||||
logger.info(f"Google search for '{query}' returned {len(results)} results with full content")
|
||||
|
||||
return results
|
||||
except Exception as e:
|
||||
logger.error(f"Google search error for '{query}': {e}")
|
||||
# Fallback to basic search without full content
|
||||
try:
|
||||
response = await client.get(
|
||||
f"{GOOGLE_SEARCH_SERVICE_URL}/api/search",
|
||||
params={
|
||||
"q": query,
|
||||
"num": num_results,
|
||||
"lang": lang,
|
||||
"country": country
|
||||
}
|
||||
)
|
||||
response.raise_for_status()
|
||||
data = response.json()
|
||||
return data.get("results", [])
|
||||
except:
|
||||
return []
|
||||
|
||||
@app.get("/api/aggregate/location", response_model=AggregatedNews)
|
||||
async def aggregate_news_by_location(
|
||||
location: str = Query(..., description="지역명 (예: Seoul, Tokyo)"),
|
||||
limit: int = Query(10, description="처리할 RSS 항목 수", ge=1, le=50),
|
||||
google_results_per_title: int = Query(5, description="각 제목당 구글 검색 결과 수", ge=1, le=10),
|
||||
lang: str = Query("ko", description="언어 코드"),
|
||||
country: str = Query("KR", description="국가 코드")
|
||||
):
|
||||
"""지역 기반 RSS 피드를 가져와서 각 제목을 구글 검색"""
|
||||
start_time = datetime.now()
|
||||
|
||||
try:
|
||||
# Get location-based RSS feed
|
||||
logger.info(f"Fetching RSS feed for location: {location}")
|
||||
rss_response = await client.get(
|
||||
f"{RSS_SERVICE_URL}/api/google-rss/location",
|
||||
params={"location": location, "lang": lang, "country": country}
|
||||
)
|
||||
rss_response.raise_for_status()
|
||||
rss_data = rss_response.json()
|
||||
|
||||
if not rss_data.get("success"):
|
||||
raise HTTPException(status_code=500, detail=f"RSS 피드 가져오기 실패: {rss_data.get('error')}")
|
||||
|
||||
# Process titles
|
||||
news_items = []
|
||||
titles = rss_data.get("sample_titles", [])[:limit]
|
||||
|
||||
search_tasks = []
|
||||
for title in titles:
|
||||
clean_title = title.split(" - ")[-1] if " - " in title else title
|
||||
search_tasks.append(
|
||||
search_google(clean_title, google_results_per_title, lang, country)
|
||||
)
|
||||
|
||||
search_results = await asyncio.gather(*search_tasks, return_exceptions=True)
|
||||
|
||||
for i, title in enumerate(titles):
|
||||
google_results = []
|
||||
if not isinstance(search_results[i], Exception):
|
||||
google_results = search_results[i]
|
||||
|
||||
news_items.append(NewsItem(
|
||||
rss_title=title,
|
||||
google_results=google_results,
|
||||
search_keyword=title.split(" - ")[-1] if " - " in title else title,
|
||||
timestamp=datetime.now()
|
||||
))
|
||||
|
||||
processing_time = (datetime.now() - start_time).total_seconds()
|
||||
|
||||
return AggregatedNews(
|
||||
keyword=f"Location: {location}",
|
||||
rss_feed_url=rss_data.get("feed_url", ""),
|
||||
total_rss_entries=rss_data.get("entry_count", 0),
|
||||
processed_entries=len(news_items),
|
||||
news_items=news_items,
|
||||
processing_time=processing_time
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in aggregate_news_by_location: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
@app.get("/api/aggregate/topic", response_model=AggregatedNews)
|
||||
async def aggregate_news_by_topic(
|
||||
category: str = Query(..., description="카테고리 (TECHNOLOGY, BUSINESS, HEALTH 등)"),
|
||||
limit: int = Query(10, description="처리할 RSS 항목 수", ge=1, le=50),
|
||||
google_results_per_title: int = Query(5, description="각 제목당 구글 검색 결과 수", ge=1, le=10),
|
||||
lang: str = Query("ko", description="언어 코드"),
|
||||
country: str = Query("KR", description="국가 코드")
|
||||
):
|
||||
"""주제별 RSS 피드를 가져와서 각 제목을 구글 검색"""
|
||||
start_time = datetime.now()
|
||||
|
||||
try:
|
||||
# Get topic-based RSS feed
|
||||
logger.info(f"Fetching RSS feed for topic: {category}")
|
||||
rss_response = await client.get(
|
||||
f"{RSS_SERVICE_URL}/api/google-rss/topic",
|
||||
params={"category": category, "lang": lang, "country": country}
|
||||
)
|
||||
rss_response.raise_for_status()
|
||||
rss_data = rss_response.json()
|
||||
|
||||
if not rss_data.get("success"):
|
||||
raise HTTPException(status_code=500, detail=f"RSS 피드 가져오기 실패: {rss_data.get('error')}")
|
||||
|
||||
# Process titles
|
||||
news_items = []
|
||||
titles = rss_data.get("sample_titles", [])[:limit]
|
||||
|
||||
search_tasks = []
|
||||
for title in titles:
|
||||
clean_title = title.split(" - ")[-1] if " - " in title else title
|
||||
search_tasks.append(
|
||||
search_google(clean_title, google_results_per_title, lang, country)
|
||||
)
|
||||
|
||||
search_results = await asyncio.gather(*search_tasks, return_exceptions=True)
|
||||
|
||||
for i, title in enumerate(titles):
|
||||
google_results = []
|
||||
if not isinstance(search_results[i], Exception):
|
||||
google_results = search_results[i]
|
||||
|
||||
news_items.append(NewsItem(
|
||||
rss_title=title,
|
||||
google_results=google_results,
|
||||
search_keyword=title.split(" - ")[-1] if " - " in title else title,
|
||||
timestamp=datetime.now()
|
||||
))
|
||||
|
||||
processing_time = (datetime.now() - start_time).total_seconds()
|
||||
|
||||
return AggregatedNews(
|
||||
keyword=f"Topic: {category}",
|
||||
rss_feed_url=rss_data.get("feed_url", ""),
|
||||
total_rss_entries=rss_data.get("entry_count", 0),
|
||||
processed_entries=len(news_items),
|
||||
news_items=news_items,
|
||||
processing_time=processing_time
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in aggregate_news_by_topic: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
5
backup-services/news-aggregator/backend/requirements.txt
Normal file
5
backup-services/news-aggregator/backend/requirements.txt
Normal file
@ -0,0 +1,5 @@
|
||||
fastapi==0.104.1
|
||||
uvicorn[standard]==0.24.0
|
||||
httpx==0.25.2
|
||||
pydantic==2.5.0
|
||||
python-multipart==0.0.6
|
||||
214
backup-services/news-aggregator/backend/test_aggregator.py
Executable file
214
backup-services/news-aggregator/backend/test_aggregator.py
Executable file
@ -0,0 +1,214 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
News Aggregator Service Test
|
||||
RSS 피드 제목을 구글 full content 검색으로 확장하는 통합 테스트
|
||||
"""
|
||||
import asyncio
|
||||
import httpx
|
||||
import json
|
||||
from datetime import datetime
|
||||
from typing import Dict, Any
|
||||
|
||||
# Service URL
|
||||
SERVICE_URL = "http://localhost:8018"
|
||||
|
||||
async def test_aggregate_with_full_content():
|
||||
"""키워드로 RSS 피드를 검색하고 full content 구글 검색 테스트"""
|
||||
async with httpx.AsyncClient(timeout=60.0) as client:
|
||||
print("\n" + "="*60)
|
||||
print("뉴스 통합 서비스 Full Content 테스트")
|
||||
print("="*60)
|
||||
|
||||
# Test with keyword "인공지능"
|
||||
print("\n1. 키워드 '인공지능'으로 RSS 피드 검색 및 구글 full content 검색")
|
||||
print("-" * 40)
|
||||
|
||||
response = await client.get(
|
||||
f"{SERVICE_URL}/api/aggregate",
|
||||
params={
|
||||
"q": "인공지능",
|
||||
"limit": 3, # 테스트용으로 3개만
|
||||
"google_results_per_title": 2, # 각 제목당 2개 구글 결과
|
||||
"lang": "ko",
|
||||
"country": "KR"
|
||||
}
|
||||
)
|
||||
|
||||
if response.status_code == 200:
|
||||
data = response.json()
|
||||
print(f"✓ RSS 피드 URL: {data['rss_feed_url']}")
|
||||
print(f"✓ 전체 RSS 항목 수: {data['total_rss_entries']}")
|
||||
print(f"✓ 처리된 항목 수: {data['processed_entries']}")
|
||||
print(f"✓ 처리 시간: {data['processing_time']:.2f}초")
|
||||
|
||||
# Check each news item for full content
|
||||
for i, item in enumerate(data['news_items'], 1):
|
||||
print(f"\n [{i}] RSS 제목: {item['rss_title'][:50]}...")
|
||||
print(f" 검색 키워드: {item['search_keyword'][:50]}...")
|
||||
print(f" 구글 검색 결과 수: {len(item['google_results'])}")
|
||||
|
||||
# Check if google results have full_content
|
||||
for j, result in enumerate(item['google_results'], 1):
|
||||
has_full_content = 'full_content' in result
|
||||
if has_full_content:
|
||||
full_content = result.get('full_content', '')
|
||||
if isinstance(full_content, str):
|
||||
content_length = len(full_content)
|
||||
else:
|
||||
content_length = len(str(full_content))
|
||||
else:
|
||||
content_length = 0
|
||||
|
||||
print(f" - 결과 {j}: {result.get('title', 'N/A')[:40]}...")
|
||||
print(f" Full Content 포함: {'✓' if has_full_content else '✗'}")
|
||||
if has_full_content:
|
||||
print(f" Content 길이: {content_length:,} 문자")
|
||||
# Show first 200 chars of content
|
||||
if isinstance(result['full_content'], str):
|
||||
preview = result['full_content'][:200].replace('\n', ' ')
|
||||
print(f" 미리보기: {preview}...")
|
||||
else:
|
||||
print(f" Content 타입: {type(result['full_content'])}")
|
||||
print(f" Content 데이터: {str(result['full_content'])[:200]}...")
|
||||
else:
|
||||
print(f"✗ 오류: {response.status_code}")
|
||||
print(f" 상세: {response.text}")
|
||||
|
||||
async def test_aggregate_by_location():
|
||||
"""지역 기반 RSS 피드 및 full content 테스트"""
|
||||
async with httpx.AsyncClient(timeout=60.0) as client:
|
||||
print("\n" + "="*60)
|
||||
print("지역 기반 뉴스 통합 Full Content 테스트")
|
||||
print("="*60)
|
||||
|
||||
print("\n2. 지역 'Seoul'로 RSS 피드 검색 및 구글 full content 검색")
|
||||
print("-" * 40)
|
||||
|
||||
response = await client.get(
|
||||
f"{SERVICE_URL}/api/aggregate/location",
|
||||
params={
|
||||
"location": "Seoul",
|
||||
"limit": 2,
|
||||
"google_results_per_title": 2,
|
||||
"lang": "ko",
|
||||
"country": "KR"
|
||||
}
|
||||
)
|
||||
|
||||
if response.status_code == 200:
|
||||
data = response.json()
|
||||
print(f"✓ 지역: {data['keyword']}")
|
||||
print(f"✓ RSS 피드 URL: {data['rss_feed_url']}")
|
||||
print(f"✓ 처리된 항목 수: {data['processed_entries']}")
|
||||
|
||||
# Check full content availability
|
||||
full_content_count = 0
|
||||
total_content_size = 0
|
||||
|
||||
for item in data['news_items']:
|
||||
for result in item['google_results']:
|
||||
if 'full_content' in result:
|
||||
full_content_count += 1
|
||||
content = result['full_content']
|
||||
if isinstance(content, str):
|
||||
total_content_size += len(content)
|
||||
else:
|
||||
total_content_size += len(str(content))
|
||||
|
||||
print(f"\n📊 Full Content 통계:")
|
||||
print(f" - Full Content 포함 결과: {full_content_count}개")
|
||||
print(f" - 전체 Content 크기: {total_content_size:,} 문자")
|
||||
print(f" - 평균 Content 크기: {total_content_size//max(full_content_count, 1):,} 문자")
|
||||
else:
|
||||
print(f"✗ 오류: {response.status_code}")
|
||||
|
||||
async def test_aggregate_by_topic():
|
||||
"""주제별 RSS 피드 및 full content 테스트"""
|
||||
async with httpx.AsyncClient(timeout=60.0) as client:
|
||||
print("\n" + "="*60)
|
||||
print("주제별 뉴스 통합 Full Content 테스트")
|
||||
print("="*60)
|
||||
|
||||
print("\n3. 주제 'TECHNOLOGY'로 RSS 피드 검색 및 구글 full content 검색")
|
||||
print("-" * 40)
|
||||
|
||||
response = await client.get(
|
||||
f"{SERVICE_URL}/api/aggregate/topic",
|
||||
params={
|
||||
"category": "TECHNOLOGY",
|
||||
"limit": 2,
|
||||
"google_results_per_title": 3,
|
||||
"lang": "ko",
|
||||
"country": "KR"
|
||||
}
|
||||
)
|
||||
|
||||
if response.status_code == 200:
|
||||
data = response.json()
|
||||
print(f"✓ 주제: {data['keyword']}")
|
||||
print(f"✓ 처리 시간: {data['processing_time']:.2f}초")
|
||||
|
||||
# Analyze content quality for AI summarization
|
||||
print("\n📝 AI 요약을 위한 Content 품질 분석:")
|
||||
for i, item in enumerate(data['news_items'], 1):
|
||||
print(f"\n 뉴스 항목 {i}:")
|
||||
for j, result in enumerate(item['google_results'], 1):
|
||||
if 'full_content' in result:
|
||||
content = result['full_content']
|
||||
if isinstance(content, str):
|
||||
# Check content quality indicators
|
||||
has_paragraphs = '\n\n' in content or '</p>' in content
|
||||
has_sufficient_length = len(content) > 500
|
||||
has_korean = any(ord(char) >= 0xAC00 and ord(char) <= 0xD7A3 for char in content[:min(100, len(content))])
|
||||
else:
|
||||
content_str = str(content)
|
||||
has_paragraphs = '\n\n' in content_str or '</p>' in content_str
|
||||
has_sufficient_length = len(content_str) > 500
|
||||
has_korean = any(ord(char) >= 0xAC00 and ord(char) <= 0xD7A3 for char in content_str[:min(100, len(content_str))])
|
||||
|
||||
print(f" 결과 {j} 품질 체크:")
|
||||
print(f" - 충분한 길이 (>500자): {'✓' if has_sufficient_length else '✗'}")
|
||||
print(f" - 단락 구조 포함: {'✓' if has_paragraphs else '✗'}")
|
||||
print(f" - 한국어 콘텐츠: {'✓' if has_korean else '✗'}")
|
||||
print(f" - AI 요약 가능: {'✓' if (has_sufficient_length and has_paragraphs) else '✗'}")
|
||||
else:
|
||||
print(f"✗ 오류: {response.status_code}")
|
||||
|
||||
async def test_health_check():
|
||||
"""서비스 상태 확인"""
|
||||
async with httpx.AsyncClient() as client:
|
||||
print("\n" + "="*60)
|
||||
print("서비스 Health Check")
|
||||
print("="*60)
|
||||
|
||||
response = await client.get(f"{SERVICE_URL}/health")
|
||||
if response.status_code == 200:
|
||||
data = response.json()
|
||||
print(f"✓ 통합 서비스 상태: {data['status']}")
|
||||
print(f" - RSS 서비스: {data['services']['rss_feed']}")
|
||||
print(f" - Google 검색 서비스: {data['services']['google_search']}")
|
||||
else:
|
||||
print(f"✗ Health check 실패: {response.status_code}")
|
||||
|
||||
async def main():
|
||||
"""메인 테스트 실행"""
|
||||
print("\n" + "="*70)
|
||||
print(" News Aggregator Full Content Integration Test ")
|
||||
print(" RSS 피드 + Google Full Content 통합 테스트 ")
|
||||
print("="*70)
|
||||
|
||||
# Run tests
|
||||
await test_health_check()
|
||||
await test_aggregate_with_full_content()
|
||||
await test_aggregate_by_location()
|
||||
await test_aggregate_by_topic()
|
||||
|
||||
print("\n" + "="*70)
|
||||
print(" 테스트 완료 - Full Content 통합 확인 ")
|
||||
print("="*70)
|
||||
print("\n✅ 모든 테스트가 완료되었습니다.")
|
||||
print(" RSS 피드 제목을 구글 full content로 검색하는 기능이 정상 작동합니다.")
|
||||
print(" AI 요약을 위한 충분한 콘텐츠가 수집되고 있습니다.")
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
Reference in New Issue
Block a user