Merge pull request #2 from stardrophere/backend_optimize

Backend optimize

.dockerignore

@@ -0,0 +1,18 @@
+# 前端
+frontend/dist
+frontend/node_modules
+
+# 后端
+backend/.venv
+backend/.git
+backend/__pycache__
+backend/*.pyc
+backend/*.pyo
+backend/*.pyd
+backend/.pytest_cache
+backend/.mypy_cache
+backend/.cache
+backend/.env
+backend/*.log
+backend/dist
+backend/build

.gitignore

@@ -44,6 +44,8 @@ MANIFEST
 pip-log.txt
 pip-delete-this-directory.txt
 
+**/logs/*
+
 # Unit test / coverage reports
 htmlcov/
 .tox/
@@ -190,3 +192,4 @@ cython_debug/
 
 **/data/*
 **/docker/*
+backend/app/static/*

backend/.dockerignore

@@ -1,13 +0,0 @@
-.venv
-.git
-__pycache__
-*.pyc
-*.pyo
-*.pyd
-.pytest_cache
-.mypy_cache
-.cache
-.env
-*.log
-dist
-build

backend/app/crud/crud_source.py

@@ -2,6 +2,8 @@
 """
 信息源 CRUD：对 InfoSource 的增删改查，供 API 与爬虫使用
 """
+from sqlite3 import IntegrityError
+
 from sqlalchemy.orm import Session
 from typing import List, Optional
 
@@ -22,10 +24,16 @@ def get_multi(db: Session, skip: int = 0, limit: int = 100) -> List[InfoSource]:
 def create(db: Session, obj_in: InfoSourceCreate) -> InfoSource:
     """创建新的信息源"""
     db_obj = InfoSource(**obj_in.model_dump())
+    try:
         db.add(db_obj)
         db.commit()
         db.refresh(db_obj)
         return db_obj
+    except IntegrityError:
+        db.rollback()
+    finally:
+        db.close()
+        return db_obj
 
 
 def update(db: Session, db_obj: InfoSource, obj_in: InfoSourceUpdate) -> InfoSource:

backend/app/initialize.py

@@ -1,14 +1,12 @@
-import requests
 import json
 
-# 请将此处的 URL 替换为您实际的 API 基础域名
+from app.database import SessionLocal
-api_url = "http://10.252.130.135:8000/api/v1/sources/"
+from app.crud.crud_source import create
+from app.models.models import SourceType
+from app.schemas.source_schema import InfoSourceCreate
 
-# 请求头
+
-headers = {
+def init():
-    "Content-Type": "application/json",
-    # "Authorization": "Bearer YOUR_TOKEN" # 如果接口需要鉴权，请取消注释并填入 Token
-}
 
     # 解析后的数据源列表
     sources_data = [
@@ -27,20 +25,18 @@ sources_data = [
 
     # 遍历数据并发送 POST 请求
     for item in sources_data:
-    payload = {
-        "source_name": item["name"],
-        "source_type": "HOT_TREND",
-        "home_url": item["url"],
-        "is_enabled": True
-    }
           
         try:
-        response = requests.post(api_url, headers=headers, data=json.dumps(payload))
+            
-        if response.status_code in (200, 201):
+            with SessionLocal() as db:
-            print(f"✅ 成功创建: {item['name']}")
+
-        else:
+                create(db, InfoSourceCreate(
-            print(f"❌ 创建失败: {item['name']} - 状态码: {response.status_code} - 详情: {response.text}")
+                    source_name=item["name"],
+                    source_type=SourceType.HOT_TREND,
+                    home_url=item["url"],
+                    is_enabled=True
+                ))
+                print(f"创建订阅源{item['name']}")
+
         except Exception as e:
             print(f"⚠️ 请求异常: {item['name']} - 错误: {e}")
-
-print("执行完毕！")

backend/app/main.py

@@ -1,8 +1,10 @@
 # app/main.py
 import logging
 import os
+from fastapi.responses import FileResponse
+import httpx
 from contextlib import asynccontextmanager
-from fastapi import FastAPI
+from fastapi import FastAPI, staticfiles
 from fastapi.middleware.cors import CORSMiddleware
 from dotenv import load_dotenv
 
@@ -21,11 +23,11 @@ from app.services.summary_service import generate_unified_summaries
 from app.services.delivery_service import check_and_deliver
 from app.database import engine
 from app.models.models import Base
+from app.initialize import init
 
 # 路由总线
 from app.api.router import api_router
 
-load_dotenv()
 CRAWL_INTERVAL = int(os.getenv("CRAWL_INTERVAL_MINUTES", 10))
 SUMMARY_INTERVAL = int(os.getenv("SUMMARY_INTERVAL_MINUTES", 30))
 
@@ -42,6 +44,10 @@ async def lifespan(app: FastAPI):
     Base.metadata.create_all(bind=engine)
     logging.info("数据库表初始化完成！")
     
+    logging.info("初始化订阅源")
+    init()
+    logging.info("订阅源初始化完毕")
+    
     # 2. 配置并启动定时任务
     scheduler.add_job(
         fetch_and_save_trending_data,
@@ -106,6 +112,13 @@ app.add_middleware(
 # 版本控制
 app.include_router(api_router, prefix="/api/v1")
 
+# 把目录改成static对应我们放dist内容的路径就可以
+app.mount("/", staticfiles.StaticFiles(directory="app/static", html=True), name="static")
+
+# 只需要保留API的优先匹配，catch_all可以简化成这样
+@app.get("/api/{full_path:path}")
+async def api_not_found(full_path: str):
+    return {"detail": "API Not Found"}
 
 # 健康检查
 @app.get("/", tags=["健康检查"])

backend/app/models/models.py

@@ -94,6 +94,10 @@ class InfoSource(Base):
     created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
     updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow)
     
+    __table_args__ = (
+        UniqueConstraint("source_name", name="uix_source_name"),
+    )
+
 
 # ==========================================
 # 模块二：AI 语义聚类中枢 (大事件池)
@@ -176,8 +180,7 @@ class NewsArticle(Base):
 
     id: Mapped[int] = mapped_column(BigIntType, primary_key=True, autoincrement=True)
     source_id: Mapped[int] = mapped_column(ForeignKey("info_sources.id"), comment="所属信息源ID")
-    unified_event_id: Mapped[Optional[int]] = mapped_column(ForeignKey("unified_events.id"),
+    unified_event_id: Mapped[Optional[int]] = mapped_column(ForeignKey("unified_events.id"), comment="深度文章也可归入大事件分析")
-                                                            comment="深度文章也可归入大事件分析")
 
     external_id: Mapped[str] = mapped_column(String(32), comment="RSS原文<guid>生成的MD5防重指纹")
     title_embedding: Mapped[Optional[str]] = mapped_column(Text, comment="新闻标题/摘要的语义向量")
@@ -214,8 +217,7 @@ class HeadlineRevision(Base):
     previous_headline: Mapped[str] = mapped_column(String(255), comment="修改前的旧标题")
     revised_headline: Mapped[str] = mapped_column(String(255), comment="修改后的新标题")
 
-    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow,
+    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, comment="系统发现被修改的时间")
-                                                 comment="系统发现被修改的时间")
 
 
 class RankingLog(Base):
@@ -235,8 +237,7 @@ class RankingLog(Base):
     # 当时它在第几名
     ranking_position: Mapped[int] = mapped_column(Integer, comment="当时抓取时的排名名次")
     # 爬虫看到它的那一瞬间的时间
-    observed_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow,
+    observed_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, comment="观察到该名次的准确时间")
-                                                  comment="观察到该名次的准确时间")
 
     created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
 
@@ -307,13 +308,11 @@ class AppUser(Base):
 
     nickname: Mapped[Optional[str]] = mapped_column(String(100), comment="用户展示昵称")
     avatar_url: Mapped[Optional[str]] = mapped_column(String(500), comment="用户头像地址")
-    gender: Mapped[GenderType] = mapped_column(Enum(GenderType), default=GenderType.UNKNOWN,
+    gender: Mapped[GenderType] = mapped_column(Enum(GenderType), default=GenderType.UNKNOWN, comment="用户性别(用于AI调整行文语气)")
-                                               comment="用户性别(用于AI调整行文语气)")
 
     # 极其强大：一个万能收纳箱！前端未来想加任何诸如“夜间模式”、“字体变大”的开关，
     # 全部丢进这个 JSON 字段即可，从此免去手动修改后端表结构的麻烦。
-    metadata_: Mapped[Optional[Any]] = mapped_column("metadata", JSON,
+    metadata_: Mapped[Optional[Any]] = mapped_column("metadata", JSON, comment="JSON扩展字段: 存放灵活多变的前端用户偏好设置")
-                                                     comment="JSON扩展字段: 存放灵活多变的前端用户偏好设置")
 
     # 时区对于定时推送系统极其重要！保证纽约的用户和北京的用户都能在早晨8点收到新闻。
     timezone: Mapped[str] = mapped_column(String(50), default="Asia/Shanghai", comment="用户所在地时区")
@@ -401,8 +400,7 @@ class DeliveryHistory(Base):
     # 记录这次推送是彻底成功了，还是由于渠道网络问题失败了
     status: Mapped[TaskStatus] = mapped_column(Enum(TaskStatus), comment="最终推送结果状态")
 
-    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow,
+    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, comment="记录或实际推送的准确时间")
-                                                 comment="记录或实际推送的准确时间")
 
 
 # ==========================================

backend/app/services/fetcher_service.py

@@ -26,7 +26,7 @@ SIMILARITY_THRESHOLD = float(os.getenv("SIMILARITY_THRESHOLD", 0.72))
 API_BASE_URL = os.getenv("API_BASE_URL", "https://newsnow.busiyi.world/api/s")
 EMBEDDING_MODEL_PATH = os.getenv("EMBEDDING_MODEL_PATH", "")
 
-print("正在加载 BAAI/bge-m3 向量模型...")
+print("正在加载向量模型...")
 # 全局单例
 embedder_model = SentenceTransformer(EMBEDDING_MODEL_PATH, local_files_only=True)
 print("模型加载完成。")

backend/dockerfile

@@ -1,31 +0,0 @@
-FROM python:3.11-slim AS builder
-
-WORKDIR /insightradar
-
-COPY pyproject.toml uv.lock ./
-
-RUN --mount=type=cache,target=/root/.cache/uv \
-    pip install --no-cache-dir uv && \
-    uv sync --frozen --no-dev
-
-COPY app app
-COPY main.py main.py
-
-#-----------------------------------------------
-
-FROM python:3.11-slim
-
-WORKDIR /insightradar
-
-# 👇 复制虚拟环境
-COPY --from=builder /insightradar/.venv /insightradar/.venv
-
-COPY app app
-COPY main.py main.py
-
-# 👇 关键：用 venv 里的 python
-ENV PATH="/insightradar/.venv/bin:$PATH"
-
-EXPOSE 8000
-
-CMD ["python","main.py"]

backend/main.py

@@ -1,12 +1,18 @@
 # run.py
 import uvicorn
+import os
+from dotenv import load_dotenv
 
 if __name__ == "__main__":
+    
+    load_dotenv()
+    PORT = int(os.getenv("PORT", 8000))
+    
     # 启动服务
     uvicorn.run(
         app="app.main:app",
         host="0.0.0.0",
-        port=8000,
+        port=PORT,
         # reload=True,
         workers=1
     )

dockerfile

@@ -0,0 +1,50 @@
+# ---------- 阶段1：前端编译（Node打包静态产物） ----------
+FROM node:22-alpine AS frontend-builder
+
+WORKDIR /frontend
+
+# 复制前端依赖，利用Docker缓存优化
+COPY frontend/package*.json ./
+RUN npm install --registry=https://registry.npmmirror.com
+
+# 复制前端代码，编译出静态产物
+COPY frontend/ .
+RUN npm run build
+
+# ---------- 阶段2：后端依赖构建（uv构建虚拟环境） ----------
+FROM python:3.11-slim AS backend-builder
+
+WORKDIR /backend
+
+# 安装uv，同步Python依赖
+COPY backend/pyproject.toml backend/uv.lock ./
+RUN --mount=type=cache,target=/root/.cache/uv \
+    pip install --no-cache-dir uv && \
+    uv sync --frozen --no-dev
+
+# 复制后端代码
+COPY backend/app ./app
+COPY backend/main.py ./
+
+# ---------- 阶段3：最终运行镜像（仅Python+Uvicorn，托管前端静态） ----------
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# 复制构建好的后端虚拟环境
+COPY --from=backend-builder /backend/.venv /app/.venv
+COPY --from=backend-builder /backend/app /app/app
+COPY --from=backend-builder /backend/main.py /app/main.py
+
+# 复制前端编译好的静态产物，放到后端能访问的目录
+# 这里我们把静态文件放到 /app/static 目录
+COPY --from=frontend-builder /frontend/dist /app/app/static
+
+# 把venv加入PATH
+ENV PATH="/app/.venv/bin:$PATH"
+
+# 暴露Uvicorn端口
+EXPOSE 8000
+
+# 直接启动Uvicorn，由Uvicorn配合后端框架托管静态文件
+CMD ["python3", "main.py"]

frontend/src/assets/main.css

@@ -1,4 +1,4 @@
-@import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700&family=Noto+Sans+SC:wght@400;500;600;700&display=swap');
+@import url(./font.css);
 
 /* =========================================
    1. 现代 SaaS 风格高级主题变量