feat: 뉴스 자동 수집 시스템 — 6개국 신문 RSS/API

- news_sources 테이블 (소스 관리, UI 동적 제어)
- news_collector 워커: RSS(feedparser) + NYT API
  - 중복 체크: hash(title+date+source) + URL normalize
  - category 표준화, summary HTML 정제, timezone UTC
  - 30일 이내만 embed, source별 try/catch
- News API: 소스 CRUD + 수동 수집 트리거
- APScheduler: 6시간 간격 자동 수집
- 대상: 경향/아사히/NYT/르몽드/신화/슈피겔

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Hyungi Ahn
2026-04-06 13:38:07 +09:00
parent bf8efd1cd3
commit a6c19ef76c
6 changed files with 405 additions and 0 deletions

109
app/api/news.py Normal file
View File

@@ -0,0 +1,109 @@
"""뉴스 소스 관리 API"""
from typing import Annotated
from fastapi import APIRouter, Depends, HTTPException
from pydantic import BaseModel
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from core.auth import get_current_user
from core.database import get_session
from models.news_source import NewsSource
from models.user import User
router = APIRouter()
class NewsSourceResponse(BaseModel):
id: int
name: str
country: str | None
feed_url: str
feed_type: str
category: str | None
language: str | None
enabled: bool
last_fetched_at: str | None
created_at: str
class Config:
from_attributes = True
class NewsSourceCreate(BaseModel):
name: str
country: str | None = None
feed_url: str
feed_type: str = "rss"
category: str | None = None
language: str | None = None
class NewsSourceUpdate(BaseModel):
name: str | None = None
feed_url: str | None = None
category: str | None = None
enabled: bool | None = None
@router.get("/sources")
async def list_sources(
user: Annotated[User, Depends(get_current_user)],
session: Annotated[AsyncSession, Depends(get_session)],
):
result = await session.execute(select(NewsSource).order_by(NewsSource.id))
return [NewsSourceResponse.model_validate(s) for s in result.scalars().all()]
@router.post("/sources")
async def create_source(
body: NewsSourceCreate,
user: Annotated[User, Depends(get_current_user)],
session: Annotated[AsyncSession, Depends(get_session)],
):
source = NewsSource(**body.model_dump())
session.add(source)
await session.commit()
return NewsSourceResponse.model_validate(source)
@router.patch("/sources/{source_id}")
async def update_source(
source_id: int,
body: NewsSourceUpdate,
user: Annotated[User, Depends(get_current_user)],
session: Annotated[AsyncSession, Depends(get_session)],
):
source = await session.get(NewsSource, source_id)
if not source:
raise HTTPException(status_code=404)
for field, value in body.model_dump(exclude_unset=True).items():
setattr(source, field, value)
await session.commit()
return NewsSourceResponse.model_validate(source)
@router.delete("/sources/{source_id}")
async def delete_source(
source_id: int,
user: Annotated[User, Depends(get_current_user)],
session: Annotated[AsyncSession, Depends(get_session)],
):
source = await session.get(NewsSource, source_id)
if not source:
raise HTTPException(status_code=404)
await session.delete(source)
await session.commit()
return {"message": f"소스 {source_id} 삭제됨"}
@router.post("/collect")
async def trigger_collect(
user: Annotated[User, Depends(get_current_user)],
):
"""수동 수집 트리거"""
from workers.news_collector import run
import asyncio
asyncio.create_task(run())
return {"message": "뉴스 수집 시작됨"}