完全跑通1.0版本

backend/alembic.ini

@@ -0,0 +1,37 @@
+[alembic]
+script_location = alembic
+sqlalchemy.url = postgresql+asyncpg://ai_news:PrDTEr6tGcyWX6G2@chenwuzhu.cn:5432/ai_news
+
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

backend/alembic/env.py

@@ -0,0 +1,55 @@
+import asyncio
+from logging.config import fileConfig
+
+from sqlalchemy import pool
+from sqlalchemy.ext.asyncio import async_engine_from_config
+
+from alembic import context
+
+config = context.config
+
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# Import all models so Alembic can detect schema changes
+from app.models.news import Base  # noqa: E402
+target_metadata = Base.metadata
+
+
+def run_migrations_offline() -> None:
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def do_run_migrations(connection):
+    context.configure(connection=connection, target_metadata=target_metadata)
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+async def run_async_migrations() -> None:
+    connectable = async_engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+    async with connectable.connect() as connection:
+        await connection.run_sync(do_run_migrations)
+    await connectable.dispose()
+
+
+def run_migrations_online() -> None:
+    asyncio.run(run_async_migrations())
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

backend/alembic/script.py.mako

@@ -0,0 +1,25 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

backend/alembic/versions/0001_initial_schema.py

@@ -0,0 +1,95 @@
+"""initial schema
+
+Revision ID: 0001
+Revises:
+Create Date: 2026-05-26
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+revision: str = "0001"
+down_revision: Union[str, None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "news_sources",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("name", sa.String(100), nullable=False),
+        sa.Column("url", sa.String(500), nullable=False),
+        sa.Column("source_type", sa.String(20), nullable=False, server_default="rss"),
+        sa.Column("language", sa.String(5), nullable=False, server_default="zh"),
+        sa.Column("category", sa.String(50), nullable=True),
+        sa.Column("is_active", sa.Boolean(), nullable=False, server_default="true"),
+        sa.Column("created_at", sa.DateTime(), nullable=False),
+    )
+
+    op.create_table(
+        "raw_news",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("source_id", sa.Integer(), sa.ForeignKey("news_sources.id"), nullable=True),
+        sa.Column("title", sa.String(500), nullable=False),
+        sa.Column("url", sa.String(1000), nullable=False, unique=True),
+        sa.Column("raw_content", sa.Text(), nullable=True),
+        sa.Column("published_at", sa.DateTime(), nullable=True),
+        sa.Column("crawled_at", sa.DateTime(), nullable=False),
+        sa.Column("status", sa.String(20), nullable=False, server_default="pending"),
+    )
+
+    op.create_table(
+        "processed_news",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("raw_news_id", sa.Integer(), sa.ForeignKey("raw_news.id"), nullable=False),
+        sa.Column("title_zh", sa.String(500), nullable=False),
+        sa.Column("summary", sa.Text(), nullable=False),
+        sa.Column("opinion", sa.Text(), nullable=True),
+        sa.Column("keywords", postgresql.ARRAY(sa.String()), nullable=True),
+        sa.Column("importance_score", sa.Float(), nullable=False, server_default="5.0"),
+        sa.Column("importance_reason", sa.Text(), nullable=True),
+        sa.Column("category", sa.String(50), nullable=False, server_default="行业动态"),
+        sa.Column("is_featured", sa.Boolean(), nullable=False, server_default="false"),
+        sa.Column("featured_rank", sa.Integer(), nullable=True),
+        sa.Column("source_name", sa.String(200), nullable=True),
+        sa.Column("source_url", sa.String(1000), nullable=True),
+        sa.Column("published_at", sa.DateTime(), nullable=True),
+        sa.Column("processed_at", sa.DateTime(), nullable=False),
+    )
+
+    op.create_table(
+        "llm_config",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("name", sa.String(100), nullable=False),
+        sa.Column("provider", sa.String(50), nullable=False),
+        sa.Column("api_key", sa.String(500), nullable=False),
+        sa.Column("base_url", sa.String(500), nullable=False),
+        sa.Column("model_name", sa.String(200), nullable=False),
+        sa.Column("is_active", sa.Boolean(), nullable=False, server_default="true"),
+        sa.Column("created_at", sa.DateTime(), nullable=False),
+    )
+
+    op.create_table(
+        "system_logs",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("event_type", sa.String(50), nullable=False),
+        sa.Column("message", sa.Text(), nullable=False),
+        sa.Column("level", sa.String(20), nullable=False, server_default="INFO"),
+        sa.Column("created_at", sa.DateTime(), nullable=False),
+    )
+
+    op.create_index("ix_raw_news_status", "raw_news", ["status"])
+    op.create_index("ix_processed_news_processed_at", "processed_news", ["processed_at"])
+    op.create_index("ix_processed_news_is_featured", "processed_news", ["is_featured"])
+
+
+def downgrade() -> None:
+    op.drop_table("system_logs")
+    op.drop_table("llm_config")
+    op.drop_table("processed_news")
+    op.drop_table("raw_news")
+    op.drop_table("news_sources")

backend/app/api/news.py

@@ -1,17 +1,16 @@
-from datetime import date, datetime
+from datetime import date
 from typing import Optional
-from fastapi import APIRouter, Depends, Query
-from sqlalchemy import select, func, distinct
+from fastapi import APIRouter, Depends, HTTPException, Query
+from sqlalchemy import select, func
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from ..database import get_db
-from ..models.news import ProcessedNews, RawNews
+from ..models.news import ProcessedNews
 
 router = APIRouter()
 
 
 def _serialize(n: ProcessedNews) -> dict:
-    raw = n.raw_news
     return {
         "id": n.id,
         "title_zh": n.title_zh,
@@ -23,8 +22,8 @@ def _serialize(n: ProcessedNews) -> dict:
         "category": n.category,
         "is_featured": n.is_featured,
         "featured_rank": n.featured_rank,
-        "source_name": n.source_name or (raw.source.name if raw and raw.source else ""),
-        "source_url": n.source_url or (raw.url if raw else ""),
+        "source_name": n.source_name or "",
+        "source_url": n.source_url or "",
         "published_at": n.published_at.isoformat() if n.published_at else None,
         "processed_at": n.processed_at.isoformat() if n.processed_at else None,
     }
@@ -38,7 +37,6 @@ async def get_featured(
     target = date.fromisoformat(news_date) if news_date else date.today()
     stmt = (
         select(ProcessedNews)
-        .join(ProcessedNews.raw_news)
         .where(ProcessedNews.is_featured == True)
         .where(func.date(ProcessedNews.processed_at) == target)
         .order_by(ProcessedNews.featured_rank)
@@ -57,11 +55,7 @@ async def get_news(
     db: AsyncSession = Depends(get_db),
 ):
     target = date.fromisoformat(news_date) if news_date else date.today()
-    stmt = (
-        select(ProcessedNews)
-        .join(ProcessedNews.raw_news)
-        .where(func.date(ProcessedNews.processed_at) == target)
-    )
+    stmt = select(ProcessedNews).where(func.date(ProcessedNews.processed_at) == target)
     if category:
         stmt = stmt.where(ProcessedNews.category == category)
 
@@ -87,10 +81,9 @@ async def get_dates(db: AsyncSession = Depends(get_db)):
 
 @router.get("/{news_id}")
 async def get_news_detail(news_id: int, db: AsyncSession = Depends(get_db)):
-    stmt = select(ProcessedNews).join(ProcessedNews.raw_news).where(ProcessedNews.id == news_id)
+    stmt = select(ProcessedNews).where(ProcessedNews.id == news_id)
     result = await db.execute(stmt)
     news = result.scalar_one_or_none()
     if not news:
-        from fastapi import HTTPException
         raise HTTPException(status_code=404, detail="Not found")
     return _serialize(news)

backend/app/config.py

@@ -2,7 +2,7 @@ from pydantic_settings import BaseSettings
 
 
 class Settings(BaseSettings):
-    database_url: str = "postgresql+asyncpg://pharma:pharma123@localhost/pharma_news"
+    database_url: str = "postgresql+asyncpg://ai_news:PrDTEr6tGcyWX6G2@chenwuzhu.cn:5432/ai_news"
     admin_token: str = "change-me-admin-token"
 
     initial_llm_provider: str = "deepseek"

backend/app/crawler/rss_fetcher.py

@@ -60,14 +60,15 @@ async def fetch_rss(url: str, max_items: int = 30) -> list[dict]:
     return items
 
 
-# 默认新闻源（管理页可增删）
+# 默认新闻源（管理页可增删）— URLs 经过验证可用
 DEFAULT_SOURCES = [
     # 中文
-    {"name": "国家药监局", "url": "https://www.nmpa.gov.cn/rss/yaopinxinxi.xml", "language": "zh", "category": "药品监管"},
-    {"name": "丁香园", "url": "https://www.dxy.cn/bbs/feed.xml", "language": "zh", "category": "临床研究"},
-    {"name": "医学界", "url": "https://www.yxj.org.cn/rss.xml", "language": "zh", "category": "行业动态"},
+    {"name": "中国新闻网·健康", "url": "https://www.chinanews.com.cn/rss/health.xml", "language": "zh", "category": "行业动态"},
     # 英文
     {"name": "STAT News", "url": "https://www.statnews.com/feed/", "language": "en", "category": "临床研究"},
     {"name": "FiercePharma", "url": "https://www.fiercepharma.com/rss/xml", "language": "en", "category": "行业动态"},
-    {"name": "FDA News", "url": "https://www.fda.gov/about-fda/contact-fda/stay-informed/rss-feeds/fda-news-feed/rss.xml", "language": "en", "category": "药品监管"},
+    {"name": "FierceBiotech", "url": "https://www.fiercebiotech.com/rss/xml", "language": "en", "category": "临床研究"},
+    {"name": "FDA MedWatch", "url": "https://www.fda.gov/about-fda/contact-fda/stay-informed/rss-feeds/medwatch/rss.xml", "language": "en", "category": "药品监管"},
+    {"name": "FDA Press Releases", "url": "https://www.fda.gov/about-fda/contact-fda/stay-informed/rss-feeds/press-releases/rss.xml", "language": "en", "category": "药品监管"},
+    {"name": "Nature Medicine", "url": "https://www.nature.com/nm.rss", "language": "en", "category": "临床研究"},
 ]

backend/app/main.py

@@ -6,18 +6,38 @@ from .database import create_tables, AsyncSessionLocal
 from .scheduler import start_scheduler, shutdown_scheduler
 from .api import news, admin
 from .config import settings
-from .models.news import LLMConfig
+from .models.news import LLMConfig, NewsSource
 
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     await create_tables()
     await seed_initial_llm_config()
+    await seed_default_sources()
     start_scheduler()
     yield
     shutdown_scheduler()
 
 
+async def seed_default_sources():
+    """Insert default news sources on first run if the table is empty."""
+    from .crawler.rss_fetcher import DEFAULT_SOURCES
+    from sqlalchemy import select
+    async with AsyncSessionLocal() as db:
+        result = await db.execute(select(NewsSource).limit(1))
+        if result.scalar_one_or_none():
+            return
+        for src in DEFAULT_SOURCES:
+            db.add(NewsSource(
+                name=src["name"],
+                url=src["url"],
+                source_type="rss",
+                language=src["language"],
+                category=src["category"],
+            ))
+        await db.commit()
+
+
 async def seed_initial_llm_config():
     """Insert default LLM config on first run if none exists."""
     from sqlalchemy import select