diff --git a/.gitignore b/.gitignore index 3f485da..ef505aa 100644 --- a/.gitignore +++ b/.gitignore @@ -10,7 +10,7 @@ __pycache__/ .idea # C extensions *.so - +.vscode/ # Distribution / packaging .Python build/ diff --git a/backend/app/api/dependencies.py b/backend/app/api/dependencies.py index e69de29..fa5fd34 100644 --- a/backend/app/api/dependencies.py +++ b/backend/app/api/dependencies.py @@ -0,0 +1,13 @@ +# app/api/dependencies.py +from app.database import SessionLocal + +def get_db(): + """ + FastAPI 依赖注入：为每个 HTTP 请求提供独立的数据库会话。 + 请求处理完成后自动关闭，防止连接泄漏。 + """ + db = SessionLocal() + try: + yield db + finally: + db.close() \ No newline at end of file diff --git a/backend/app/api/endpoints/auth.py b/backend/app/api/endpoints/auth.py new file mode 100644 index 0000000..c143cee --- /dev/null +++ b/backend/app/api/endpoints/auth.py @@ -0,0 +1,238 @@ +import os +from datetime import timedelta +from typing import Tuple + +from fastapi import APIRouter, Depends, HTTPException, status +from sqlalchemy.orm import Session + +from app.api.dependencies import get_db +from app.core.security import ( + create_access_token, + generate_verification_code, + hash_password, + hash_verification_code, + verify_password, + verify_verification_code, +) +from app.models.models import AppUser, EmailVerificationCode, VerificationPurpose, utcnow +from app.schemas.auth_schema import ( + AuthTokenResponse, + LoginCodeSendRequest, + LoginRequest, + LoginWithCodeRequest, + MessageResponse, + RegisterCodeSendRequest, + RegisterRequest, + UserProfileResponse, +) +from app.utils.email_utils import send_html_email + + +router = APIRouter() + +REGISTER_CODE_EXPIRE_MINUTES = int(os.getenv("REGISTER_CODE_EXPIRE_MINUTES", "10")) +LOGIN_CODE_EXPIRE_MINUTES = int(os.getenv("LOGIN_CODE_EXPIRE_MINUTES", "10")) + + +def _normalize_email(email: str) -> str: + return email.strip().lower() + + +def _build_verification_email(code: str, purpose_text: str, expire_minutes: int) -> str: + return f""" +
+

InsightRadar Email Verification

+

Your {purpose_text} verification code is:

+

{code}

+

The code is valid for {expire_minutes} minutes. Do not share it with others.

+
+ """ + + +def _invalidate_unused_codes(db: Session, email: str, purpose: VerificationPurpose) -> None: + db.query(EmailVerificationCode).filter( + EmailVerificationCode.email == email, + EmailVerificationCode.purpose == purpose, + EmailVerificationCode.is_used.is_(False), + ).update({EmailVerificationCode.is_used: True}, synchronize_session=False) + db.commit() + + +def _create_code_record( + db: Session, + *, + email: str, + purpose: VerificationPurpose, + expire_minutes: int, +) -> Tuple[EmailVerificationCode, str]: + code = generate_verification_code() + now = utcnow() + code_record = EmailVerificationCode( + email=email, + purpose=purpose, + code_hash=hash_verification_code(code), + expires_at=now + timedelta(minutes=expire_minutes), + ) + db.add(code_record) + db.commit() + return code_record, code + + +def _build_auth_response(user: AppUser) -> AuthTokenResponse: + token, expires_in = create_access_token(user_id=user.id, email=user.email) + return AuthTokenResponse( + access_token=token, + expires_in=expires_in, + user=UserProfileResponse.model_validate(user), + ) + + +@router.post("/register/send-code", response_model=MessageResponse) +async def send_register_code(payload: RegisterCodeSendRequest, db: Session = Depends(get_db)): + email = _normalize_email(payload.email) + + existing_user = db.query(AppUser).filter(AppUser.email == email).first() + if existing_user: + raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Email is already registered") + + _invalidate_unused_codes(db, email, VerificationPurpose.REGISTER) + code_record, code = _create_code_record( + db, + email=email, + purpose=VerificationPurpose.REGISTER, + expire_minutes=REGISTER_CODE_EXPIRE_MINUTES, + ) + + email_sent = await send_html_email( + to_email=email, + subject="InsightRadar Registration Code", + html_content=_build_verification_email(code, "registration", REGISTER_CODE_EXPIRE_MINUTES), + ) + if not email_sent: + code_record.is_used = True + db.add(code_record) + db.commit() + raise HTTPException( + status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, + detail="Failed to send verification code", + ) + + return MessageResponse(message="Verification code sent") + + +@router.post("/login/send-code", response_model=MessageResponse) +async def send_login_code(payload: LoginCodeSendRequest, db: Session = Depends(get_db)): + email = _normalize_email(payload.email) + user = db.query(AppUser).filter(AppUser.email == email).first() + + if not user: + raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Email is not registered") + + _invalidate_unused_codes(db, email, VerificationPurpose.LOGIN) + code_record, code = _create_code_record( + db, + email=email, + purpose=VerificationPurpose.LOGIN, + expire_minutes=LOGIN_CODE_EXPIRE_MINUTES, + ) + + email_sent = await send_html_email( + to_email=email, + subject="InsightRadar Login Code", + html_content=_build_verification_email(code, "login", LOGIN_CODE_EXPIRE_MINUTES), + ) + if not email_sent: + code_record.is_used = True + db.add(code_record) + db.commit() + raise HTTPException( + status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, + detail="Failed to send verification code", + ) + + return MessageResponse(message="Verification code sent") + + +@router.post( + "/register", + response_model=AuthTokenResponse, + status_code=status.HTTP_201_CREATED, +) +async def register(payload: RegisterRequest, db: Session = Depends(get_db)): + email = _normalize_email(payload.email) + existing_user = db.query(AppUser).filter(AppUser.email == email).first() + if existing_user: + raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Email is already registered") + + now = utcnow() + code_record = db.query(EmailVerificationCode).filter( + EmailVerificationCode.email == email, + EmailVerificationCode.purpose == VerificationPurpose.REGISTER, + EmailVerificationCode.is_used.is_(False), + EmailVerificationCode.expires_at >= now, + ).order_by(EmailVerificationCode.created_at.desc()).first() + + if not code_record: + raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Verification code does not exist or expired") + + if not verify_verification_code(payload.verification_code, code_record.code_hash): + raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid verification code") + + nickname = payload.nickname or email.split("@")[0] + user = AppUser( + email=email, + password_hash=hash_password(payload.password), + nickname=nickname, + metadata_={"email_verified_at": now.isoformat()}, + ) + + code_record.is_used = True + db.add(user) + db.add(code_record) + db.commit() + db.refresh(user) + + return _build_auth_response(user) + + +@router.post("/login", response_model=AuthTokenResponse) +async def login(payload: LoginRequest, db: Session = Depends(get_db)): + email = _normalize_email(payload.email) + user = db.query(AppUser).filter(AppUser.email == email).first() + + if not user or not user.password_hash: + raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="Invalid email or password") + + if not verify_password(payload.password, user.password_hash): + raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="Invalid email or password") + + return _build_auth_response(user) + + +@router.post("/login/code", response_model=AuthTokenResponse) +async def login_with_code(payload: LoginWithCodeRequest, db: Session = Depends(get_db)): + email = _normalize_email(payload.email) + user = db.query(AppUser).filter(AppUser.email == email).first() + + if not user: + raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="Invalid email or verification code") + + now = utcnow() + code_record = db.query(EmailVerificationCode).filter( + EmailVerificationCode.email == email, + EmailVerificationCode.purpose == VerificationPurpose.LOGIN, + EmailVerificationCode.is_used.is_(False), + EmailVerificationCode.expires_at >= now, + ).order_by(EmailVerificationCode.created_at.desc()).first() + + if not code_record: + raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Verification code does not exist or expired") + + if not verify_verification_code(payload.verification_code, code_record.code_hash): + raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="Invalid email or verification code") + + code_record.is_used = True + db.add(code_record) + db.commit() + + return _build_auth_response(user) diff --git a/backend/app/api/endpoints/events.py b/backend/app/api/endpoints/events.py new file mode 100644 index 0000000..f09f161 --- /dev/null +++ b/backend/app/api/endpoints/events.py @@ -0,0 +1,69 @@ +# app/api/endpoints/events.py +from fastapi import APIRouter, Depends, Query +from sqlalchemy.orm import Session +from datetime import timedelta +from typing import List + +from app.api.dependencies import get_db +from app.models.models import UnifiedEvent, TrendingEvent, InfoSource, RankingLog, utcnow +# 导入你上传的 Schema +from app.schemas.event_schema import UnifiedEventResponse, PlatformTrendResponse + +router = APIRouter() + + +@router.get("/unified", response_model=List[UnifiedEventResponse]) +def list_unified_events( + min_hot: int = Query(5, description="热度过滤阈值"), + hours: int = Query(24, description="查询过去 X 小时的数据"), + db: Session = Depends(get_db) +): + """ + 获取聚合大事件列表，完全适配前端 template.html 所需的数据结构 + """ + # 计算时间水位线 + time_limit = utcnow() - timedelta(hours=hours) + + # 1. 查询大事件（按热度降序，且满足时间范围） + events = db.query(UnifiedEvent).filter( + UnifiedEvent.hot_score >= min_hot, + UnifiedEvent.created_at >= time_limit + ).order_by(UnifiedEvent.hot_score.desc()).all() + + results = [] + for ev in events: + # 2. 联表查询：获取该大事件下关联的所有平台及其具体热搜信息 + trends = db.query(TrendingEvent, InfoSource.source_name).join( + InfoSource, TrendingEvent.source_id == InfoSource.id + ).filter(TrendingEvent.unified_event_id == ev.id).all() + + platform_list = [] + for trend, s_name in trends: + # 3. 获取排名历史轨迹 (用于前端渲染) + # 这里的排序顺序 asc 保证了数组从旧到新 + logs = db.query(RankingLog.ranking_position).filter( + RankingLog.event_id == trend.id, + RankingLog.observed_at >= time_limit + ).order_by(RankingLog.observed_at.asc()).all() + + # 组装符合 PlatformTrendResponse 结构的字典 + platform_list.append(PlatformTrendResponse( + source_id=trend.source_id, + platform_name=s_name, + headline=trend.current_headline, + url=trend.event_url, + current_ranking=trend.current_ranking, + ranking_history=[log[0] for log in logs] + )) + + # 4. 组装符合 UnifiedEventResponse 结构的字典 + results.append(UnifiedEventResponse( + event_id=ev.id, + unified_title=ev.unified_title if ev.unified_title else "暂无标题", + summary=ev.ai_comprehensive_summary, + hot_score=ev.hot_score, + created_at=ev.created_at, + platforms=platform_list + )) + + return results diff --git a/backend/app/api/endpoints/sources.py b/backend/app/api/endpoints/sources.py index eda2606..d086738 100644 --- a/backend/app/api/endpoints/sources.py +++ b/backend/app/api/endpoints/sources.py @@ -4,7 +4,7 @@ from sqlalchemy.orm import Session from typing import List from app.database import get_db -from app.schemas.schemas import ( +from app.schemas.source_schema import ( InfoSourceCreate, InfoSourceUpdate, InfoSourceResponse, PaginatedResponse ) from app.crud import crud_source diff --git a/backend/app/api/endpoints/trends.py b/backend/app/api/endpoints/trends.py deleted file mode 100644 index e69de29..0000000 diff --git a/backend/app/api/router.py b/backend/app/api/router.py index 000e9bd..70239de 100644 --- a/backend/app/api/router.py +++ b/backend/app/api/router.py @@ -1,8 +1,12 @@ # app/api/router.py from fastapi import APIRouter -from app.api.endpoints import sources +from app.api.endpoints import auth, sources, events api_router = APIRouter() # 信息源管理 -api_router.include_router(sources.router, prefix="/sources", tags=["信息源管理"]) \ No newline at end of file +api_router.include_router(sources.router, prefix="/sources", tags=["信息源管理"]) + +# 注册大事件相关的路由 +api_router.include_router(events.router, prefix="/events", tags=["Unified Events"]) +api_router.include_router(auth.router, prefix="/auth", tags=["Auth"]) diff --git a/backend/app/core/security.py b/backend/app/core/security.py new file mode 100644 index 0000000..cf545f3 --- /dev/null +++ b/backend/app/core/security.py @@ -0,0 +1,79 @@ +import base64 +import hashlib +import hmac +import json +import os +import secrets +import time +from typing import Tuple + + +PASSWORD_HASH_ITERATIONS = int(os.getenv("PASSWORD_HASH_ITERATIONS", "120000")) +AUTH_SECRET_KEY = os.getenv("AUTH_SECRET_KEY", "change-this-secret-in-env") +AUTH_TOKEN_EXPIRE_MINUTES = int(os.getenv("AUTH_TOKEN_EXPIRE_MINUTES", "10080")) + + +def hash_password(password: str) -> str: + salt = secrets.token_hex(16) + digest = hashlib.pbkdf2_hmac( + "sha256", + password.encode("utf-8"), + salt.encode("utf-8"), + PASSWORD_HASH_ITERATIONS, + ) + return ( + f"pbkdf2_sha256${PASSWORD_HASH_ITERATIONS}${salt}$" + f"{base64.urlsafe_b64encode(digest).decode('utf-8')}" + ) + + +def verify_password(plain_password: str, password_hash: str) -> bool: + try: + algorithm, iterations, salt, expected = password_hash.split("$", 3) + if algorithm != "pbkdf2_sha256": + return False + + digest = hashlib.pbkdf2_hmac( + "sha256", + plain_password.encode("utf-8"), + salt.encode("utf-8"), + int(iterations), + ) + calculated = base64.urlsafe_b64encode(digest).decode("utf-8") + return hmac.compare_digest(calculated, expected) + except Exception: + return False + + +def generate_verification_code(length: int = 6) -> str: + return "".join(secrets.choice("0123456789") for _ in range(length)) + + +def hash_verification_code(code: str) -> str: + return hashlib.sha256(code.encode("utf-8")).hexdigest() + + +def verify_verification_code(code: str, expected_hash: str) -> bool: + return hmac.compare_digest(hash_verification_code(code), expected_hash) + + +def _urlsafe_b64encode(raw: bytes) -> str: + return base64.urlsafe_b64encode(raw).decode("utf-8").rstrip("=") + + +def create_access_token(user_id: int, email: str) -> Tuple[str, int]: + expires_in = AUTH_TOKEN_EXPIRE_MINUTES * 60 + payload = { + "sub": str(user_id), + "email": email, + "exp": int(time.time()) + expires_in, + } + payload_bytes = json.dumps(payload, separators=(",", ":"), ensure_ascii=True).encode("utf-8") + encoded_payload = _urlsafe_b64encode(payload_bytes) + signature = hmac.new( + AUTH_SECRET_KEY.encode("utf-8"), + encoded_payload.encode("utf-8"), + hashlib.sha256, + ).digest() + token = f"{encoded_payload}.{_urlsafe_b64encode(signature)}" + return token, expires_in diff --git a/backend/app/crud/crud_source.py b/backend/app/crud/crud_source.py index 6bcaa54..a8dbfe4 100644 --- a/backend/app/crud/crud_source.py +++ b/backend/app/crud/crud_source.py @@ -3,7 +3,7 @@ from sqlalchemy.orm import Session from typing import List, Optional from app.models.models import InfoSource -from app.schemas.schemas import InfoSourceCreate, InfoSourceUpdate +from app.schemas.source_schema import InfoSourceCreate, InfoSourceUpdate def get(db: Session, source_id: int) -> Optional[InfoSource]: diff --git a/backend/app/main.py b/backend/app/main.py index 221589f..861479c 100644 --- a/backend/app/main.py +++ b/backend/app/main.py @@ -6,6 +6,7 @@ from dotenv import load_dotenv from apscheduler.schedulers.asyncio import AsyncIOScheduler from app.services.fetcher_service import fetch_and_save_trending_data +from app.services.summary_service import generate_unified_summaries from app.database import engine from app.models.models import Base @@ -14,6 +15,7 @@ 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)) scheduler = AsyncIOScheduler() @@ -36,15 +38,27 @@ async def lifespan(app: FastAPI): id='trending_fetch_job', replace_existing=True ) + + # 平台摘要 + scheduler.add_job( + generate_unified_summaries, + 'interval', + minutes=SUMMARY_INTERVAL, + id='ai_summary_job', + replace_existing=True + ) scheduler.start() print(f"定时抓取任务已启动，每 {CRAWL_INTERVAL} 分钟执行一次") + print(f"AI 摘要生成任务已启动，每 {SUMMARY_INTERVAL} 分钟执行一次") # 为了测试方便，启动时立即执行一次 await fetch_and_save_trending_data() + await generate_unified_summaries() + yield # 此时 FastAPI 开始接受请求 - # 3. 优雅关闭 + # 优雅关闭 scheduler.shutdown() print("定时任务已安全关闭") diff --git a/backend/app/models/models.py b/backend/app/models/models.py index 69736ba..30bab54 100644 --- a/backend/app/models/models.py +++ b/backend/app/models/models.py @@ -29,35 +29,40 @@ BigIntType = BigInteger().with_variant(Integer, "sqlite") class SourceType(str, enum.Enum): """信息源的抓取方式""" - HOT_TREND = "HOT_TREND" # 热搜榜单类 - RSS_FEED = "RSS_FEED" # 传统RSS订阅 - API = "API" # 接口抓取类 + HOT_TREND = "HOT_TREND" # 热搜榜单类 (如微博热搜) + RSS_FEED = "RSS_FEED" # 传统RSS订阅 (如36氪、纽约时报) + API = "API" # 接口直接接入类 class TargetType(str, enum.Enum): """ 多态目标类型 (Polymorphic Target) - 用于标记一条评论或一个标签到底是挂载在哪个实体下的。 + 用于标记一条评论、标签或推送记录，到底是挂载在哪个实体下的。 """ - EVENT = "EVENT" # 挂载在单个热搜事件下 - TREND = "TREND" # 挂载在宏观趋势下 - ARTICLE = "ARTICLE" # 挂载在具体新闻文章下 + EVENT = "EVENT" # 挂载在AI聚合后的大事件下 + TREND = "TREND" # 挂载在单个平台的热搜条目下 + ARTICLE = "ARTICLE" # 挂载在具体的长篇新闻文章下 class TaskStatus(str, enum.Enum): - """后台任务状态""" - SUCCESS = "SUCCESS" - ERROR = "ERROR" + """后台爬虫/推送任务的执行状态""" + SUCCESS = "SUCCESS" # 执行成功 + ERROR = "ERROR" # 发生报错 class GenderType(str, enum.Enum): - """用户性别枚举""" + """用户性别枚举，常用于给AI提供Prompt背景信息以生成个性化摘要""" MALE = "MALE" FEMALE = "FEMALE" OTHER = "OTHER" UNKNOWN = "UNKNOWN" +class VerificationPurpose(str, enum.Enum): + REGISTER = "REGISTER" + LOGIN = "LOGIN" + + def utcnow(): """ 获取带UTC时区的当前时间 (最佳实践) @@ -77,10 +82,14 @@ class InfoSource(Base): __tablename__ = "info_sources" id: Mapped[int] = mapped_column(primary_key=True, autoincrement=True) - source_name: Mapped[str] = mapped_column(String(100), comment="信息源名称") - source_type: Mapped[SourceType] = mapped_column(Enum(SourceType)) - home_url: Mapped[Optional[str]] = mapped_column(String(255)) - is_enabled: Mapped[bool] = mapped_column(Boolean, default=True) + # 信息源的展示名称，例如 "微博热搜", "今日头条" + source_name: Mapped[str] = mapped_column(String(100), comment="信息源中文名称") + # 抓取类型，决定爬虫调用哪个解析逻辑 + source_type: Mapped[SourceType] = mapped_column(Enum(SourceType), comment="抓取方式枚举") + # 极其重要：原意存官网链接，但实际开发中常借用来存放 API的专属标识(如 'weibo', 'toutiao') + home_url: Mapped[Optional[str]] = mapped_column(String(255), comment="官网链接或API的平台标识ID") + # 爬虫开关：如果某平台封禁了我们，可以直接置为False，爬虫将自动跳过该平台 + is_enabled: Mapped[bool] = mapped_column(Boolean, default=True, comment="是否开启定时抓取") created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow) @@ -91,19 +100,22 @@ class InfoSource(Base): # ========================================== class UnifiedEvent(Base): """ - AI 统一事件表 - 核心业务逻辑：比如微博热搜叫“苹果发布会”，知乎热搜叫“iPhone 16 测评”， - 它们在子表(TrendingEvent)是两条记录，但通过 AI 语义向量对比后， - 会将它们统一挂载到这个表的一个 UnifiedEvent ID 下，实现跨平台事件聚合。 + AI 统一事件表 (核心大脑) + 逻辑：微博的“苹果发布会”和知乎的“iPhone 16 测评”，通过语义相似度碰撞后，统一归入此表的一行记录中。 """ __tablename__ = "unified_events" id: Mapped[int] = mapped_column(BigIntType, primary_key=True, autoincrement=True) - unified_title: Mapped[str] = mapped_column(String(255), comment="AI统一标题") - ai_comprehensive_summary: Mapped[Optional[str]] = mapped_column(Text, comment="AI全局深度总结") + # 经过AI润色去重后的中立、客观的标准大标题 + unified_title: Mapped[str] = mapped_column(String(255), comment="AI生成的客观统一大标题") + # AI阅读子新闻后生成的千字长文摘要，直接用于早报推送 + ai_comprehensive_summary: Mapped[Optional[str]] = mapped_column(Text, comment="AI综合全网子新闻生成的深度总结") - center_embedding: Mapped[Optional[str]] = mapped_column(Text, comment="中心向量") # 用于高维空间相似度计算 - hot_score: Mapped[int] = mapped_column(Integer, default=0, comment="聚合热度得分") + # [高阶字段] 将文本转化成高维浮点数向量，爬虫抓到新新闻时，跟这个向量算余弦相似度来判断是不是同一个事件 + center_embedding: Mapped[Optional[str]] = mapped_column(Text, comment="该事件簇的中心语义向量") + # 事件热度值：挂载的平台越多、相关评论越多，分数越高，用于首页的热榜排序 + hot_score: Mapped[int] = mapped_column(Integer, default=0, comment="聚合热度得分(分数越高排名越靠前)") + last_summarized_trends_count: Mapped[int] = mapped_column(Integer, default=0, comment="用于判断是否需要重新调用LLM") created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow) @@ -115,51 +127,71 @@ class UnifiedEvent(Base): class TrendingEvent(Base): """ 各平台热搜数据明细表 + 存放从爬虫直接拉取下来的最原始的热搜数据。 """ __tablename__ = "trending_events" __table_args__ = ( - # 联合唯一索引：同一个来源(比如微博)的同一条外部ID(MD5)只能存在一条记录，防重插核心保障 + # 联合唯一索引：同一个来源的同一个哈希只能存一条，完美实现 UPSERT (去重更新) UniqueConstraint("source_id", "external_id", name="idx_unique_external_trend"), ) id: Mapped[int] = mapped_column(BigIntType, primary_key=True, autoincrement=True) - source_id: Mapped[int] = mapped_column(ForeignKey("info_sources.id")) - unified_event_id: Mapped[Optional[int]] = mapped_column(ForeignKey("unified_events.id")) + # 关联：这条热搜是从哪个平台(InfoSource)抓来的 + source_id: Mapped[int] = mapped_column(ForeignKey("info_sources.id"), comment="所属信息源ID") + # 关联：它被AI归类到了哪个大事件(UnifiedEvent)之下 (可为空，表示未归类的新鲜事) + unified_event_id: Mapped[Optional[int]] = mapped_column(ForeignKey("unified_events.id"), + comment="所属的聚合大事件ID") - external_id: Mapped[str] = mapped_column(String(32), comment="32位MD5哈希指纹防重") - title_embedding: Mapped[Optional[str]] = mapped_column(Text) + # 极其核心：将第三方易变的标题/URL，强制压平为32位不变的 MD5 字符串，用作唯一防重指纹 + external_id: Mapped[str] = mapped_column(String(32), comment="通过平台ID+原始ID生成的32位MD5防重指纹") + # 这条特定热搜标题的独立语义向量，用于和 unified_events 做碰撞 + title_embedding: Mapped[Optional[str]] = mapped_column(Text, comment="标题的语义向量") - icon_url: Mapped[Optional[str]] = mapped_column(String(500)) - current_headline: Mapped[str] = mapped_column(String(255)) - event_url: Mapped[Optional[str]] = mapped_column(String(500)) - app_link: Mapped[Optional[str]] = mapped_column(String(500)) - current_ranking: Mapped[Optional[int]] = mapped_column(Integer) - brief_snippet: Mapped[Optional[str]] = mapped_column(Text) + # 爬虫抓下来的热搜配图、带'爆'或'热'字的角标链接 + icon_url: Mapped[Optional[str]] = mapped_column(String(500), comment="热榜附带的小图标或配图链接") + # 最新标题 (注意：小编随时可能改标题，所以绝不能放入唯一索引) + current_headline: Mapped[str] = mapped_column(String(255), comment="当前最新的热搜标题") + # 该热点在PC/H5端的访问链接 + event_url: Mapped[Optional[str]] = mapped_column(String(500), comment="浏览器访问链接") + # 该热点专门用于手机App唤醒的 DeepLink (如 sinaweibo://...) + app_link: Mapped[Optional[str]] = mapped_column(String(500), comment="移动端App唤醒专属链接") + # 本次抓取时，它在平台上的名次 (如 1, 2, 3) + current_ranking: Mapped[Optional[int]] = mapped_column(Integer, comment="当前最新排名(可能随时上下浮动)") + # 有些平台在热搜底下会配一句话简介 + brief_snippet: Mapped[Optional[str]] = mapped_column(Text, comment="平台自带的一句话简介或导语") created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow) class NewsArticle(Base): - """新闻文章明细表 (与 TrendingEvent 类似，但侧重长文本阅读)""" + """ + 新闻文章明细表 (长篇资讯) + 与 TrendingEvent 类似，但它主要用来存放 36氪、纽约时报等长篇正文，用于提供深度的阅读素材。 + """ __tablename__ = "news_articles" __table_args__ = ( UniqueConstraint("source_id", "external_id", name="idx_unique_external_article"), ) id: Mapped[int] = mapped_column(BigIntType, primary_key=True, autoincrement=True) - source_id: Mapped[int] = mapped_column(ForeignKey("info_sources.id")) - unified_event_id: Mapped[Optional[int]] = mapped_column(ForeignKey("unified_events.id")) + 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"), + comment="深度文章也可归入大事件分析") - external_id: Mapped[str] = mapped_column(String(32)) - title_embedding: Mapped[Optional[str]] = mapped_column(Text) + external_id: Mapped[str] = mapped_column(String(32), comment="RSS原文生成的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") - cover_image_url: Mapped[Optional[str]] = mapped_column(String(500)) - article_title: Mapped[str] = mapped_column(String(255)) - article_url: Mapped[Optional[str]] = mapped_column(String(500)) - author_name: Mapped[Optional[str]] = mapped_column(String(100)) - original_summary: Mapped[Optional[str]] = mapped_column(Text) - publish_time: Mapped[Optional[datetime]] = mapped_column(DateTime(timezone=True)) + # 新闻文章的封面大图，很适合前端做瀑布流展示 + cover_image_url: Mapped[Optional[str]] = mapped_column(String(500), comment="新闻封面大图链接") + article_title: Mapped[str] = mapped_column(String(255), comment="新闻原文标题") + article_url: Mapped[Optional[str]] = mapped_column(String(500), comment="新闻原文链接") + # 作者或发布机构 (如 "澎湃新闻", "虎嗅作者X") + author_name: Mapped[Optional[str]] = mapped_column(String(100), comment="作者或发布机构名称") + # RSS原文中附带的长摘要，甚至是完整的 HTML 格式正文 + original_summary: Mapped[Optional[str]] = mapped_column(Text, comment="原文自带的长摘要或正文片段") + # 新闻在平台上的真实发布时间 (可能比我们爬取的时间要早几天) + publish_time: Mapped[Optional[datetime]] = mapped_column(DateTime(timezone=True), comment="新闻实际发布的时间") created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow) @@ -171,33 +203,40 @@ class NewsArticle(Base): class HeadlineRevision(Base): """ 标题修订历史表 - 用于记录平台方暗戳戳修改热搜词条的行为（例如公关介入改标题）。 + 当系统通过哈希发现某条新闻是老熟人，但标题发生了改变时，会自动往这里插一条记录。 + 常用于公关监测(看看谁半夜偷偷改了标题)。 """ __tablename__ = "headline_revisions" id: Mapped[int] = mapped_column(BigIntType, primary_key=True, autoincrement=True) - event_id: Mapped[int] = mapped_column(ForeignKey("trending_events.id")) - previous_headline: Mapped[str] = mapped_column(String(255)) - revised_headline: Mapped[str] = mapped_column(String(255)) + # 属于哪一条被修改的热搜 + event_id: Mapped[int] = mapped_column(ForeignKey("trending_events.id"), comment="关联的热搜ID") + 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") class RankingLog(Base): """ 热搜排名时间序列化日志 - 每一次抓取都会生成一条记录，可以用于前端绘制热搜“排名起伏折线图”。 + 每次爬虫运行(例如每10分钟)，都会往这里塞一堆数据，记录某热搜当时的具体名次。 + 前端可以通过这张表画出非常漂亮的“名次起伏折线图(K线图)”。 """ __tablename__ = "ranking_logs" __table_args__ = ( - # 针对时间序列查询优化的复合索引，加速类似 "查询某事件在过去24小时内的排名变化" 的操作 + # 复合索引，加速 "查询某事件在某段时间内的走势" Index("idx_event_time", "event_id", "observed_at"), ) id: Mapped[int] = mapped_column(BigIntType, primary_key=True, autoincrement=True) - event_id: Mapped[int] = mapped_column(ForeignKey("trending_events.id")) - ranking_position: Mapped[int] = mapped_column(Integer) - observed_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) + event_id: Mapped[int] = mapped_column(ForeignKey("trending_events.id"), comment="关联的热搜ID") + # 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, + comment="观察到该名次的准确时间") created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) @@ -205,44 +244,49 @@ class RankingLog(Base): # ========================================== # 模块五：多态话题与多态评论 # ========================================== -# 【设计模式】：多态设计 -# 通过 target_type (存表名/类型) + target_id (存主键ID) 的组合， -# 让这两个表既能挂载在"单一热搜"下，也能挂载在"新闻文章"下，甚至挂在"统一大事件"下，避免了建立无数个外键的冗余。 - class ExtractedTopic(Base): - """AI 提取的核心话题标签表""" + """ + AI 提取的核心话题标签表 + 设计模式(多态)：一条标签("AI")既能打在大事件上，也能打在单篇文章上。 + """ __tablename__ = "extracted_topics" __table_args__ = ( Index("idx_topic_keyword", "topic_keyword"), - # 多态查询索引，加速 target_type + target_id 的组合查询 Index("idx_polymorphic_topics", "target_type", "target_id"), ) id: Mapped[int] = mapped_column(BigIntType, primary_key=True, autoincrement=True) - target_type: Mapped[TargetType] = mapped_column(Enum(TargetType)) - target_id: Mapped[int] = mapped_column(BigIntType) - topic_keyword: Mapped[str] = mapped_column(String(100)) - relevance_score: Mapped[Optional[float]] = mapped_column(Float) + target_type: Mapped[TargetType] = mapped_column(Enum(TargetType), comment="挂载目标的类型(大事件/热点/文章)") + target_id: Mapped[int] = mapped_column(BigIntType, comment="对应的具体主键ID") + # 提取出的标签词，例如 "自动驾驶", "马斯克" + topic_keyword: Mapped[str] = mapped_column(String(100), comment="提取出的核心关键词汇") + # AI 认为这个词和这篇文章的相关程度(0~100)，方便以后做精准度过滤 + relevance_score: Mapped[Optional[float]] = mapped_column(Float, comment="AI计算的相关度得分") created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) class DiscussionComment(Base): - """全平台统一评论表""" + """ + 全平台统一评论库 + 不论是微博网友的短评，还是新闻网站的长评，全部扔进这张多态表。 + """ __tablename__ = "discussion_comments" __table_args__ = ( Index("idx_polymorphic_comments", "target_type", "target_id"), ) id: Mapped[int] = mapped_column(BigIntType, primary_key=True, autoincrement=True) - target_type: Mapped[TargetType] = mapped_column(Enum(TargetType)) - target_id: Mapped[int] = mapped_column(BigIntType) + target_type: Mapped[TargetType] = mapped_column(Enum(TargetType), comment="被评论内容的类型") + target_id: Mapped[int] = mapped_column(BigIntType, comment="被评论内容的主键ID") - commenter_name: Mapped[Optional[str]] = mapped_column(String(100)) - comment_content: Mapped[str] = mapped_column(Text) - likes_count: Mapped[int] = mapped_column(Integer, default=0) - external_comment_id: Mapped[Optional[str]] = mapped_column(String(32)) - comment_time: Mapped[Optional[datetime]] = mapped_column(DateTime(timezone=True)) + commenter_name: Mapped[Optional[str]] = mapped_column(String(100), comment="发评人昵称") + comment_content: Mapped[str] = mapped_column(Text, comment="评论正文内容") + # 这条评论本身获得的点赞数，可用于筛选出“神评论”一并推送给用户 + likes_count: Mapped[int] = mapped_column(Integer, default=0, comment="评论被点赞的数量") + # 防复抓：用第三方平台原生评论ID做的MD5哈希 + external_comment_id: Mapped[Optional[str]] = mapped_column(String(32), comment="第三方评论ID的MD5指纹") + comment_time: Mapped[Optional[datetime]] = mapped_column(DateTime(timezone=True), comment="评论实际发布时间") created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) @@ -251,29 +295,53 @@ class DiscussionComment(Base): # 模块六：用户画像与多渠道高可用推送系统 # ========================================== class AppUser(Base): - """系统核心用户表""" + """ + 系统核心用户表 + 不仅存放密码，还包含用户的基础画像，供大模型做个性化阅读推荐。 + """ __tablename__ = "app_users" id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True) - email: Mapped[str] = mapped_column(String(150), unique=True, index=True) - password_hash: Mapped[Optional[str]] = mapped_column(String(255)) + email: Mapped[str] = mapped_column(String(150), unique=True, index=True, comment="主账号邮箱") + password_hash: Mapped[Optional[str]] = mapped_column(String(255), comment="密码哈希(第三方登录可为空)") - nickname: Mapped[Optional[str]] = mapped_column(String(100)) - avatar_url: Mapped[Optional[str]] = mapped_column(String(500)) - gender: Mapped[GenderType] = mapped_column(Enum(GenderType), default=GenderType.UNKNOWN) + 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, + comment="用户性别(用于AI调整行文语气)") - # 预留的 JSON 字段，可以存放未来灵活变化的用户配置，避免频繁修改表结构 - metadata_: Mapped[Optional[Any]] = mapped_column("metadata", JSON, comment="自定义扩展偏好") + # 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, + comment="JSON扩展字段: 存放灵活多变的前端用户偏好设置") - timezone: Mapped[str] = mapped_column(String(50), default="Asia/Shanghai") + # 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") + created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) + updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow) + + +class EmailVerificationCode(Base): + __tablename__ = "email_verification_codes" + __table_args__ = ( + Index("idx_email_code_lookup", "email", "purpose", "is_used", "expires_at"), + ) + + id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True) + email: Mapped[str] = mapped_column(String(150), index=True, nullable=False) + purpose: Mapped[VerificationPurpose] = mapped_column(Enum(VerificationPurpose), nullable=False) + code_hash: Mapped[str] = mapped_column(String(64), nullable=False) + is_used: Mapped[bool] = mapped_column(Boolean, default=False, nullable=False) + expires_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False) created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow) class UserPushEndpoint(Base): """ - 多渠道推送端点配置表 - 一个用户可能绑定了邮箱(EMAIL)和微信(WECHAT)，支持配置降级重试(priority_level)。 + 多渠道推送端点配置表 (高可用解耦设计) + 一个用户可以配置好几个推送渠道（邮箱、微信、钉钉）， + 万一主渠道今天报错了，系统会自动按优先级(priority)降级寻找备用渠道重发。 """ __tablename__ = "user_push_endpoints" __table_args__ = ( @@ -281,63 +349,76 @@ class UserPushEndpoint(Base): ) id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True) - user_id: Mapped[int] = mapped_column(ForeignKey("app_users.id")) - channel_type: Mapped[str] = mapped_column(String(50), comment="如 EMAIL, WECHAT") - channel_account: Mapped[str] = mapped_column(String(255)) - is_active: Mapped[bool] = mapped_column(Boolean, default=True) - priority_level: Mapped[int] = mapped_column(Integer, default=1, comment="1最高，降级重试") + user_id: Mapped[int] = mapped_column(ForeignKey("app_users.id"), comment="所属用户ID") + # 填入大写的纯字符串，如 EMAIL, WECHAT_BOT, TELEGRAM + channel_type: Mapped[str] = mapped_column(String(50), comment="推送渠道类型标识") + # 具体的发送目标地址 + channel_account: Mapped[str] = mapped_column(String(255), comment="具体的接收账号(邮箱号/微信号/Webhook)") + is_active: Mapped[bool] = mapped_column(Boolean, default=True, comment="用户是否临时关闭了该渠道") + # 高可用容灾：比如 1 代表必须先发微信，如果报错了，再去找 priority=2 的邮箱补发 + priority_level: Mapped[int] = mapped_column(Integer, default=1, comment="推送优先级(1最高，用于错误降级重试)") created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow) class UserTopicPreference(Base): - """用户订阅的兴趣标签库""" + """ + 用户订阅的兴趣标签库 + 当这里的标签和 ExtractedTopic 表里的标签匹配上时，就会触发相关新闻的推送。 + """ __tablename__ = "user_topic_preferences" __table_args__ = ( + # 联合防抖限制：防止用户在界面卡顿时连点两次，订阅了两个同样的词 UniqueConstraint("user_id", "interested_keyword", name="idx_unique_preference"), ) id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True) - user_id: Mapped[int] = mapped_column(ForeignKey("app_users.id")) - interested_keyword: Mapped[str] = mapped_column(String(100)) + user_id: Mapped[int] = mapped_column(ForeignKey("app_users.id"), comment="所属用户ID") + interested_keyword: Mapped[str] = mapped_column(String(100), comment="用户填写的感兴趣标签(如'马斯克')") created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) class UserDeliverySchedule(Base): - """用户勿扰/定时推送时间表""" + """ + 用户专属的定时推送时间表 + 如果用户设定了早上 08:30，后台的定时任务就会在每天 08:30 精准地把匹配到的聚合新闻发出去。 + """ __tablename__ = "user_delivery_schedules" __table_args__ = ( UniqueConstraint("user_id", "delivery_time", name="idx_unique_schedule"), ) id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True) - user_id: Mapped[int] = mapped_column(ForeignKey("app_users.id")) - delivery_time: Mapped[time] = mapped_column(Time, comment="如 08:30:00") - is_active: Mapped[bool] = mapped_column(Boolean, default=True) + user_id: Mapped[int] = mapped_column(ForeignKey("app_users.id"), comment="所属用户ID") + delivery_time: Mapped[time] = mapped_column(Time, comment="每天期望收到推送的具体时间") + is_active: Mapped[bool] = mapped_column(Boolean, default=True, comment="是否启用此时段") created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) class DeliveryHistory(Base): """ - 推送历史防刷表 - 核心用途：一旦给某个用户推送过某条新闻/事件，就记录在这里。 - 下次再触发推荐时，检查这个表，防止给同一个用户反复发送相同的内容。 + 推送历史防刷表 (推送系统的绝对底线) + 核心业务逻辑：一旦大事件或者文章通过某个渠道成功发给用户，就记一笔帐。 + 明天如果这条旧新闻还在热搜上，系统查一下这个表，发现发过了，直接抛弃，绝不轰炸用户。 """ __tablename__ = "delivery_history" __table_args__ = ( + # 终极去重约束：一个用户，针对同一篇新闻，永远只允许存在一条记录 UniqueConstraint("user_id", "target_type", "target_id", name="idx_prevent_duplicate_push"), ) id: Mapped[int] = mapped_column(BigIntType, primary_key=True, autoincrement=True) - user_id: Mapped[int] = mapped_column(ForeignKey("app_users.id")) - target_type: Mapped[TargetType] = mapped_column(Enum(TargetType)) - target_id: Mapped[int] = mapped_column(BigIntType) - status: Mapped[TaskStatus] = mapped_column(Enum(TaskStatus)) + user_id: Mapped[int] = mapped_column(ForeignKey("app_users.id"), comment="接收推送的用户") + target_type: Mapped[TargetType] = mapped_column(Enum(TargetType), comment="推送出去的具体内容类型") + target_id: Mapped[int] = mapped_column(BigIntType, comment="推送内容的主键ID") + # 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") # ========================================== @@ -345,15 +426,17 @@ class DeliveryHistory(Base): # ========================================== class DataSyncTask(Base): """ - 数据同步健康度监控表 - 这就是爬虫脚本每次运行都要写入记录的地方，用于后台 Dashboard 监控爬虫健康状态和错误堆栈。 + 数据同步健康度监控表 (运维巡检专用) + 爬虫每跑完一个平台的轮询，就在这里打卡上报。 + 方便后台画出爬虫成功率的饼图，一旦 error_trace 堆积，能迅速报警排查。 """ __tablename__ = "data_sync_tasks" id: Mapped[int] = mapped_column(BigIntType, primary_key=True, autoincrement=True) - source_id: Mapped[int] = mapped_column(ForeignKey("info_sources.id")) - items_fetched: Mapped[int] = mapped_column(Integer, default=0) - task_status: Mapped[TaskStatus] = mapped_column(Enum(TaskStatus)) - error_trace: Mapped[Optional[str]] = mapped_column(Text) + source_id: Mapped[int] = mapped_column(ForeignKey("info_sources.id"), comment="本次运行爬取的哪个源") + items_fetched: Mapped[int] = mapped_column(Integer, default=0, comment="本次爬虫成功插入或更新的新闻条数") + task_status: Mapped[TaskStatus] = mapped_column(Enum(TaskStatus), comment="该平台的宏观抓取状态") + # 如果代码意外崩溃、或是遭遇403/502，把 Python的 traceback 堆栈原封不动存进这里 + error_trace: Mapped[Optional[str]] = mapped_column(Text, comment="若失败则保存完整报错堆栈") - created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow) + created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, comment="任务执行的发生时间") diff --git a/backend/app/prompts/summary_prompts.py b/backend/app/prompts/summary_prompts.py new file mode 100644 index 0000000..e69d1f5 --- /dev/null +++ b/backend/app/prompts/summary_prompts.py @@ -0,0 +1,14 @@ +SUMMARY_SYSTEM_PROMPT = "你是一个输出严格 JSON 格式的后台引擎。" + +SUMMARY_USER_PROMPT_TEMPLATE = """ +你是一个专业的新闻聚合编辑。请根据以下同一个大事件在不同平台的热搜标题， +为该事件生成一个客观、吸睛的【统一大标题】，以及一段【多平台视角的综合摘要】。 + +要求： +1. 摘要结构类似："该事件在多平台发酵。微博侧重讨论...，知乎硬核解析...，科技媒体关注..."。 +2. 提炼出各平台的讨论侧重点，不要简单罗列标题。 +3. 必须以严格的 JSON 格式返回，只包含 "unified_title" 和 "ai_comprehensive_summary" 两个字段，不要有多余的说明。 + +各平台热搜标题数据： +{platform_data_text} +""" diff --git a/backend/app/schemas/auth_schema.py b/backend/app/schemas/auth_schema.py new file mode 100644 index 0000000..5a5417d --- /dev/null +++ b/backend/app/schemas/auth_schema.py @@ -0,0 +1,56 @@ +from datetime import datetime +from typing import Optional + +from pydantic import BaseModel, ConfigDict, Field + +from app.models.models import GenderType + + +EMAIL_PATTERN = r"^[^@\s]+@[^@\s]+\.[^@\s]+$" + + +class RegisterCodeSendRequest(BaseModel): + email: str = Field(..., max_length=150, pattern=EMAIL_PATTERN) + + +class LoginCodeSendRequest(BaseModel): + email: str = Field(..., max_length=150, pattern=EMAIL_PATTERN) + + +class RegisterRequest(BaseModel): + email: str = Field(..., max_length=150, pattern=EMAIL_PATTERN) + password: str = Field(..., min_length=8, max_length=128) + verification_code: str = Field(..., pattern=r"^\d{6}$") + nickname: Optional[str] = Field(default=None, max_length=100) + + +class LoginRequest(BaseModel): + email: str = Field(..., max_length=150, pattern=EMAIL_PATTERN) + password: str = Field(..., min_length=8, max_length=128) + + +class LoginWithCodeRequest(BaseModel): + email: str = Field(..., max_length=150, pattern=EMAIL_PATTERN) + verification_code: str = Field(..., pattern=r"^\d{6}$") + + +class UserProfileResponse(BaseModel): + id: int + email: str + nickname: Optional[str] + avatar_url: Optional[str] + gender: GenderType + created_at: datetime + + model_config = ConfigDict(from_attributes=True) + + +class AuthTokenResponse(BaseModel): + access_token: str + token_type: str = "bearer" + expires_in: int + user: UserProfileResponse + + +class MessageResponse(BaseModel): + message: str diff --git a/backend/app/schemas/event_schema.py b/backend/app/schemas/event_schema.py new file mode 100644 index 0000000..2a48517 --- /dev/null +++ b/backend/app/schemas/event_schema.py @@ -0,0 +1,23 @@ +# app/schemas/event_schema.py +from pydantic import BaseModel +from typing import List, Optional +from datetime import datetime + + +class PlatformTrendResponse(BaseModel): + source_id: int + platform_name: str # 平台名称，如 "微博热搜" + headline: str # 平台对应的具体热搜标题 + url: Optional[str] # 跳转链接 + current_ranking: Optional[int] # 当前排名 + ranking_history: List[int] # 排名历史轨迹，如 [50, 45, 20, 5, 1]，供 ApexCharts 渲染 + + +class UnifiedEventResponse(BaseModel): + event_id: int + unified_title: str # AI 生成的统一大标题 + summary: Optional[str] # AI 生成的摘要 + hot_score: int # 总热度值 + created_at: datetime # 事件发现时间 + platforms: List[PlatformTrendResponse] # 挂载的各个平台子热搜 + # tags: List[str] = [] # 如果后续打通了 ExtractedTopic，可以在这里返回标签 diff --git a/backend/app/schemas/schemas.py b/backend/app/schemas/source_schema.py similarity index 98% rename from backend/app/schemas/schemas.py rename to backend/app/schemas/source_schema.py index 98e9115..621c7cf 100644 --- a/backend/app/schemas/schemas.py +++ b/backend/app/schemas/source_schema.py @@ -1,4 +1,4 @@ -# app/schemas/schemas.py +# app/schemas/source_schema.py from pydantic import BaseModel, ConfigDict, Field from typing import Optional from datetime import datetime diff --git a/backend/app/services/fetcher_service.py b/backend/app/services/fetcher_service.py index a6b7423..b41a15e 100644 --- a/backend/app/services/fetcher_service.py +++ b/backend/app/services/fetcher_service.py @@ -1,62 +1,222 @@ # app/services/fetcher_service.py import os import hashlib -import httpx -from dotenv import load_dotenv +from datetime import timedelta +import httpx +import json +import numpy as np +from dotenv import load_dotenv +from sklearn.metrics.pairwise import cosine_similarity +from sentence_transformers import SentenceTransformer from app.database import SessionLocal from app.models.models import ( InfoSource, TrendingEvent, NewsArticle, DataSyncTask, TaskStatus, - HeadlineRevision, RankingLog, SourceType, utcnow + HeadlineRevision, RankingLog, SourceType, utcnow, UnifiedEvent ) -# ========================================== -# 环境变量与全局配置 -# ========================================== # 加载环境变量 load_dotenv() - -# 从环境变量获取 API 基础地址，如果没有配置则提供默认回退地址 +hf_token = os.getenv("HF_TOKEN") +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...") +# 全局单例 +embedder_model = SentenceTransformer(EMBEDDING_MODEL_PATH, local_files_only=True, device="cuda") +print("模型加载完成。") def generate_md5(text: str) -> str: - """ - 生成32位MD5哈希值 - 维护说明： - 各个平台（微博、知乎、微信等）返回的原始 ID 格式千奇百怪（有长数字、有UUID、有URL）。 - 为了方便数据库建立统一的高性能唯一索引（UniqueConstraint）， - 我们统一将其转为长度固定的 32 位 MD5 字符串作为 external_id。 - """ + """生成32位MD5哈希值作为全局唯一指纹""" return hashlib.md5(text.encode('utf-8')).hexdigest() +def generate_embedding_json(text: str) -> str: + """辅助函数：调用大模型生成向量，并序列化为 JSON 字符串""" + raw_vec = embedder_model.encode([text], normalize_embeddings=True)[0] + truncated_vec = [round(float(x), 5) for x in raw_vec] + return json.dumps(truncated_vec, separators=(',', ':')) + + +def match_or_create_unified_event(db, title: str, embedding_json: str) -> int: + """ + 辅助函数：大事件聚类中枢。 + 拿着新计算的向量去数据库里碰，碰到了就返回老 ID，碰不到就建新的。 + """ + # 提取刚算出来的向量 + new_vec = np.array(json.loads(embedding_json)) + + # 只取最近 3 天的活跃大事件进行比对 + three_days_ago = utcnow() - timedelta(days=3) + recent_events = db.query(UnifiedEvent).filter( + UnifiedEvent.created_at >= three_days_ago + ).order_by(UnifiedEvent.created_at.desc()).limit(200).all() + + if recent_events: + valid_events = [ev for ev in recent_events if ev.center_embedding] + if valid_events: + event_vectors = [json.loads(ev.center_embedding) for ev in valid_events] + + # 批量矩阵计算相似度 + sim_scores = cosine_similarity([new_vec], event_vectors)[0] + max_idx = np.argmax(sim_scores) + + if sim_scores[max_idx] >= SIMILARITY_THRESHOLD: + matched_event = valid_events[max_idx] + + matched_event.hot_score += 1 + return matched_event.id + + # 没匹配到，创建一个新的统一大事件 + new_unified = UnifiedEvent( + unified_title=title, + center_embedding=embedding_json, + hot_score=1 # 初始热度 + ) + db.add(new_unified) + db.flush() # 获取自增的主键 ID + return new_unified.id + + +def process_hot_trend_item(db, source, item, index: int, external_id: str): + """ + 处理【热搜/短新闻】的业务逻辑，现已加入 AI 聚类功能 + """ + title = item.get("title") + item_url = item.get("url", "") + + existing_event = db.query(TrendingEvent).filter( + TrendingEvent.source_id == source.id, + TrendingEvent.external_id == external_id + ).first() + + event_to_log = None + + # 核心逻辑：查重后再决定是否调用模型 + if existing_event: + # 场景 A1：老熟人 + if existing_event.current_headline != title: + # 标题被暗改，此时需要重新算一次 Embedding + new_embedding_json = generate_embedding_json(title) + + revision = HeadlineRevision( + event_id=existing_event.id, + previous_headline=existing_event.current_headline, + revised_headline=title + ) + db.add(revision) + existing_event.current_headline = title + existing_event.title_embedding = new_embedding_json # 更新为新标题的语义向量 + # 注：这里不改变它所属的 unified_event_id，因为大体还是同一件事 + + existing_event.current_ranking = index + existing_event.event_url = item_url + event_to_log = existing_event + + else: + # 场景 A2：这是一条彻底的全新热搜 + # 1. 计算向量 + new_embedding_json = generate_embedding_json(title) + + # 2. 扔进聚类中枢找归宿 + matched_event_id = match_or_create_unified_event(db, title, new_embedding_json) + + # 3. 落库 + new_event = TrendingEvent( + source_id=source.id, + external_id=external_id, + current_headline=title, + event_url=item_url, + current_ranking=index, + title_embedding=new_embedding_json, # 存入向量 + unified_event_id=matched_event_id # 挂载到大事件下 + ) + db.add(new_event) + db.flush() + event_to_log = new_event + + # 强制记录排名轨迹 + rank_log = RankingLog( + event_id=event_to_log.id, + ranking_position=index + ) + db.add(rank_log) + + +def process_rss_feed_item(db, source, item, external_id: str): + """ + 处理【长文章/传统订阅】分支的核心业务逻辑 (写入 NewsArticle 表) + """ + title = item.get("title") + item_url = item.get("url", "") + + existing_article = db.query(NewsArticle).filter( + NewsArticle.source_id == source.id, + NewsArticle.external_id == external_id + ).first() + + if existing_article: + # 文章若存在，仅更新基础字段 + existing_article.article_title = title + existing_article.article_url = item_url + else: + # 全新文章入库 + new_article = NewsArticle( + source_id=source.id, + external_id=external_id, + article_title=title, + article_url=item_url, + ) + db.add(new_article) + + +def process_source_data(db, source, items: list) -> int: + """ + 数据清洗与路由分发层： + 遍历 API 返回的 items，生成唯一指纹，并路由到不同的处理模块。 + 返回成功处理的条目数量。 + """ + saved_count = 0 + platform_id = source.home_url + + for index, item in enumerate(items, 1): + title = item.get("title") + if not title: + continue + + item_url = item.get("url", "") + + # ID 兜底策略：接口ID -> URL -> Title + raw_id = item.get("id") or item_url or title + external_id = generate_md5(f"{platform_id}_{raw_id}") + + # 核心路由分流 + if source.source_type in (SourceType.HOT_TREND, SourceType.API): + process_hot_trend_item(db, source, item, index, external_id) + elif source.source_type == SourceType.RSS_FEED: + process_rss_feed_item(db, source, item, external_id) + + saved_count += 1 + + return saved_count + + async def fetch_and_save_trending_data(): """ - 核心定时任务：从数据库读取信息源 -> 抓取API -> 解析 -> 根据业务类型分流存入对应的数据库表 - - 执行流程： - 1. 查询所有配置为“已启用”的信息源 (is_enabled == True)。 - 2. 伪装 HTTP 请求头，规避目标服务器的反爬机制。 - 3. 遍历解析数据，生成 MD5 唯一指纹进行全局去重。 - 4. 核心路由分流： - - 若源为 HOT_TREND/API，按热搜逻辑处理（记录名次轨迹、标题变更）。 - - 若源为 RSS_FEED，按长文章逻辑处理（忽略名次，直接落库）。 - 5. 严格的事务管理：成功则统一提交，报错则回滚业务数据并独立提交错误日志。 + 调度层：负责网络请求、数据库事务管理和异常监控隔离。 """ print(f"[{utcnow()}] 开始执行定时抓取任务...") - # 使用上下文管理器确保数据库连接池正确获取和归还连接 with SessionLocal() as db: - # 1. 动态获取抓取源。 - # 优势：在后台修改数据库的信息源开关，下一次定时任务立刻生效，无需重启服务。 + # 获取启用的信息源 sources = db.query(InfoSource).filter(InfoSource.is_enabled == True).all() if not sources: print("没有找到启用的信息源，任务结束。") return - # 2. 伪装成真实的浏览器 HTTP 请求头 - # 维护注意：如果抓取接口返回 403 Forbidden，通常是这里的反爬策略失效了，需要更新 User-Agent 或 Cookie + # 伪装请求头，规避反爬 custom_headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/145.0.0.0 Safari/537.36", "Accept": "application/json, text/plain, */*", @@ -64,157 +224,40 @@ async def fetch_and_save_trending_data(): "Origin": "https://newsnow.busiyi.world" } - # 复用异步 HTTP 客户端，比每次循环新建 Client 性能更高 async with httpx.AsyncClient(timeout=15.0, headers=custom_headers) as client: for source in sources: - # platform_id 对应第三方接口的入参标识，如 "weibo", "zhihu" 等 platform_id = source.home_url if not platform_id: continue - # ========================================== - # 【技术债预警 / TODO】 - # 目前无论 source_type 是什么，都统一请求了这个 JSON API。 - # 未来如果加入了真正的外部 RSS 订阅源（返回的是 XML 格式）， - # 这里需要增加判断逻辑：如果是 RSS_FEED，应当使用 feedparser 库去解析 XML，而不是用 httpx 获取 JSON。 - # ========================================== url = f"{API_BASE_URL}?id={platform_id}&latest" - # 初始化本次特定信息源抓取任务的系统监控日志 + # 初始化监控日志 task_log = DataSyncTask(source_id=source.id, items_fetched=0) try: - # 发起请求并校验 HTTP 状态码 (非 2xx 会抛出异常进入 except 块) + # 发起网络请求 response = await client.get(url) response.raise_for_status() data_json = response.json() - items = data_json.get("items", []) - saved_count = 0 - for index, item in enumerate(items, 1): - title = item.get("title") - if not title: - continue + # 调用数据处理层 + saved_count = process_source_data(db, source, items) - item_url = item.get("url", "") - - # 3. ID 兜底与去重策略 - # 优先用接口自带的 ID -> 没有则用 URL 代替 -> 最差情况用 title 兜底 - raw_id = item.get("id") or item_url or title - # 组合“平台标识+原始ID”算出全局唯一的 MD5 外部标识 - external_id = generate_md5(f"{platform_id}_{raw_id}") - - # ========================================== - # 4. 核心数据分流路由 - # 根据信息源的业务类型，将数据推入不同的物理表 - # ========================================== - - if source.source_type in (SourceType.HOT_TREND, SourceType.API): - # -------------------------------------------------- - # 分支 A：热搜/短新闻逻辑 -> 写入 TrendingEvent 表 - # -------------------------------------------------- - existing_event = db.query(TrendingEvent).filter( - TrendingEvent.source_id == source.id, - TrendingEvent.external_id == external_id - ).first() - - event_to_log = None # 临时指针，用于后续绑定排名轨迹 - - if existing_event: - # 场景 A1：该热搜已经在数据库中 - - # 监控并记录“标题暗改”（常见于热搜公关介入） - if existing_event.current_headline != title: - revision = HeadlineRevision( - event_id=existing_event.id, - previous_headline=existing_event.current_headline, - revised_headline=title - ) - db.add(revision) - existing_event.current_headline = title # 覆盖为主表最新标题 - - # 更新当前的实时排名和 URL - existing_event.current_ranking = index - existing_event.event_url = item_url - event_to_log = existing_event - else: - # 场景 A2：发现全新热搜 - new_event = TrendingEvent( - source_id=source.id, - external_id=external_id, - current_headline=title, - event_url=item_url, - current_ranking=index, - ) - db.add(new_event) - # db.flush() 是关键：它将数据推给数据库生成了自增的主键 ID，但尚未最终 commit。 - # 拿到合法的 event_to_log.id - db.flush() - event_to_log = new_event - - # 排名轨迹强制记录 - # 只要抓到了热搜（无论新旧），必须打点记录当前名次，用于前端绘制排名趋势图 - rank_log = RankingLog( - event_id=event_to_log.id, - ranking_position=index - ) - db.add(rank_log) - - elif source.source_type == SourceType.RSS_FEED: - # -------------------------------------------------- - # 分支 B：长文章/传统订阅逻辑 -> 写入 NewsArticle 表 - # -------------------------------------------------- - existing_article = db.query(NewsArticle).filter( - NewsArticle.source_id == source.id, - NewsArticle.external_id == external_id - ).first() - - if existing_article: - # 文章如果已存在，通常只需要更新基础字段（文章一般不涉及排名起伏） - existing_article.article_title = title - existing_article.article_url = item_url - # 预留位置：如果以后接口返回了摘要，可以在这里 update existing_article.original_summary - else: - # 全新文章入库 - new_article = NewsArticle( - source_id=source.id, - external_id=external_id, - article_title=title, - article_url=item_url, - # original_summary=item.get("desc", ""), - # author_name=item.get("author", "") - ) - db.add(new_article) - - - - saved_count += 1 - - # -------------------------------------------------- - # 5. 业务事务成功提交 - # -------------------------------------------------- - # 只有当前平台（source）的所有 item 都顺畅走完，才标记成功 + # 业务事务成功提交 task_log.items_fetched = saved_count task_log.task_status = TaskStatus.SUCCESS db.add(task_log) - - # 统一将当前信息源爬取的所有业务数据持久化到硬盘 db.commit() print(f"[{source.source_name}] ({source.source_type}) 成功抓取并更新了 {saved_count} 条数据") except Exception as e: - # -------------------------------------------------- - # 6. 异常拦截与错误隔离机制 - # -------------------------------------------------- - # 回滚本次抓取的全部脏数据， + # 异常拦截与错误隔离 db.rollback() - # 错误日志记下来 task_log.task_status = TaskStatus.ERROR task_log.error_trace = str(e) db.add(task_log) - - db.commit() - print(f"[{source.source_name}] 抓取失败: {e}") \ No newline at end of file + print(f"[{source.source_name}] 抓取失败: {e}") diff --git a/backend/app/services/summary_service.py b/backend/app/services/summary_service.py new file mode 100644 index 0000000..f8d5ef0 --- /dev/null +++ b/backend/app/services/summary_service.py @@ -0,0 +1,104 @@ +# app/services/summary_service.py +import os +import json +from datetime import timedelta +from openai import AsyncOpenAI + +from app.database import SessionLocal +from app.models.models import UnifiedEvent, TrendingEvent, InfoSource, utcnow +from app.prompts.summary_prompts import ( + SUMMARY_SYSTEM_PROMPT, + SUMMARY_USER_PROMPT_TEMPLATE, +) + +HOT_SCORE_THRESHOLD = int(os.getenv("HOT_SCORE_THRESHOLD", 3)) +AI_API_KEY = os.getenv("AI_API_KEY", '') + +# 1. 初始化异步客户端 (全局复用) +deepseek_client = AsyncOpenAI( + api_key=AI_API_KEY, + base_url="https://api.deepseek.com" +) + + +async def call_llm_for_summary(platform_data_text: str) -> dict: + """调用 DeepSeek 生成统一标题和多平台视角摘要""" + prompt = SUMMARY_USER_PROMPT_TEMPLATE.format( + platform_data_text=platform_data_text + ) + + # await + response = await deepseek_client.chat.completions.create( + model="deepseek-chat", + messages=[ + {"role": "system", "content": SUMMARY_SYSTEM_PROMPT}, + {"role": "user", "content": prompt} + ], + response_format={"type": "json_object"}, + temperature=1 + ) + + result_text = response.choices[0].message.content + return json.loads(result_text) + + +async def generate_unified_summaries(): + """定时任务：扫描高热度事件并生成/更新摘要""" + print(f"[{utcnow()}] 开始执行 DeepSeek 摘要生成任务...") + + with SessionLocal() as db: + recent_threshold = utcnow() - timedelta(days=3) + + # 必须满足：热度达标 AND (当前热度 > 上次生成摘要时的热度) AND 近期活跃 + events = db.query(UnifiedEvent).filter( + UnifiedEvent.hot_score >= HOT_SCORE_THRESHOLD, + UnifiedEvent.hot_score > UnifiedEvent.last_summarized_trends_count, + UnifiedEvent.created_at >= recent_threshold + ).all() + + if not events: + print("当前没有需要更新摘要的大事件，任务结束。") + return + + for event in events: + # 联合查询获取该事件在各平台的子新闻 + trends = db.query(TrendingEvent, InfoSource.source_name) \ + .join(InfoSource, TrendingEvent.source_id == InfoSource.id) \ + .filter(TrendingEvent.unified_event_id == event.id) \ + .all() + + if not trends: + continue + + # 按平台归类标题并去重 + platform_dict = {} + for trend_record, source_name in trends: + if source_name not in platform_dict: + platform_dict[source_name] = set() + platform_dict[source_name].add(trend_record.current_headline) + + # 组装给大模型的 Prompt 数据 + prompt_lines = [f"【{platform}】: {', '.join(headlines)}" for platform, headlines in platform_dict.items()] + platform_data_text = "\n".join(prompt_lines) + + try: + # 调用封装好的异步函数 + llm_result = await call_llm_for_summary(platform_data_text) + + if "unified_title" in llm_result: + event.unified_title = llm_result["unified_title"] + if "ai_comprehensive_summary" in llm_result: + event.ai_comprehensive_summary = llm_result["ai_comprehensive_summary"] + + # 成功后更新水位线 + # 将最后一次总结时的热搜数量，更新为当前最新的 hot_score + event.last_summarized_trends_count = event.hot_score + + print(f"成功更新大事件 ID {event.id} 的深度摘要 (当前热度: {event.hot_score})。") + + except Exception as e: + print(f"大事件 ID {event.id} 摘要生成失败: {e}") + continue + + # 提交事务 + db.commit() diff --git a/backend/app/crud/__init__.py b/backend/app/utils/__init__.py similarity index 100% rename from backend/app/crud/__init__.py rename to backend/app/utils/__init__.py diff --git a/backend/app/utils/email_utils.py b/backend/app/utils/email_utils.py new file mode 100644 index 0000000..5f22ea0 --- /dev/null +++ b/backend/app/utils/email_utils.py @@ -0,0 +1,49 @@ +# app/utils/email_utils.py +import os +from email.message import EmailMessage +import aiosmtplib +from dotenv import load_dotenv +import asyncio + +load_dotenv() + +SMTP_HOST = os.getenv("SMTP_HOST", "smtp.qiye.aliyun.com") +SMTP_PORT = int(os.getenv("SMTP_PORT", 465)) +SMTP_USER = os.getenv("SMTP_USER", "noreply@yourdomain.com") +SMTP_PASS = os.getenv("SMTP_PASS", "your_password") + + +async def send_html_email( + to_email: str, + subject: str, + html_content: str, + sender_name: str = "AI 新闻早报", + sender_email: str = None +) -> bool: + """底层纯异步发送邮件工具""" + # 如果未指定发送者邮箱，默认使用环境配置中的认证邮箱 + if sender_email is None: + sender_email = SMTP_USER + + message = EmailMessage() + # 动态拼接 From 字段 + message["From"] = f"{sender_name} <{sender_email}>" + message["To"] = to_email + message["Subject"] = subject + + # 设定内容为 HTML + message.set_content(html_content, subtype="html") + + try: + await aiosmtplib.send( + message, + hostname=SMTP_HOST, + port=SMTP_PORT, + username=SMTP_USER, + password=SMTP_PASS, + use_tls=True, + ) + return True + except Exception as e: + print(f"邮件发送至 {to_email} 失败: {str(e)}") + return False diff --git a/backend/run.py b/backend/run.py index b22127e..868c2d2 100644 --- a/backend/run.py +++ b/backend/run.py @@ -2,11 +2,11 @@ import uvicorn if __name__ == "__main__": - # 调用 uvicorn.run() 启动服务 + # 启动服务 uvicorn.run( app="app.main:app", host="0.0.0.0", port=8000, - reload=True, + # reload=True, workers=1 ) diff --git a/frontend/src/App.vue b/frontend/src/App.vue index 7905b05..174064d 100644 --- a/frontend/src/App.vue +++ b/frontend/src/App.vue @@ -1,85 +1,24 @@ - - - diff --git a/frontend/src/assets/main.css b/frontend/src/assets/main.css index 36fb845..239310c 100644 --- a/frontend/src/assets/main.css +++ b/frontend/src/assets/main.css @@ -1,35 +1,240 @@ -@import './base.css'; +@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'); + +/* ========================================= + 1. 现代 SaaS 风格主题变量 +========================================= */ +:root { + /* 明亮模式 - 极简白与浅灰 */ + --bg-base: #f8fafc; + --bg-surface: #ffffff; + --bg-input: #f1f5f9; + + --border-subtle: #e2e8f0; + --border-strong: #cbd5e1; + + --text-primary: #0f172a; + --text-secondary: #64748b; + --text-placeholder: #94a3b8; + + --brand-primary: #4f46e5; + --brand-primary-hover: #4338ca; + --brand-primary-alpha: rgba(79, 70, 229, 0.1); + + --status-error: #ef4444; + --status-success: #10b981; + + /* 现代柔和扩散阴影 */ + --shadow-sm: 0 1px 2px 0 rgba(0, 0, 0, 0.05); + --shadow-md: 0 4px 6px -1px rgba(0, 0, 0, 0.05), 0 2px 4px -2px rgba(0, 0, 0, 0.05); + --shadow-xl: 0 20px 25px -5px rgba(0, 0, 0, 0.05), 0 8px 10px -6px rgba(0, 0, 0, 0.01); + + --radius-md: 8px; + --radius-lg: 12px; + --radius-xl: 16px; +} + +html.dark { + /* 暗黑模式 - 深邃黑与暗石板色 */ + --bg-base: #020617; + --bg-surface: #0f172a; + --bg-input: #1e293b; + + --border-subtle: #1e293b; + --border-strong: #334155; + + --text-primary: #f8fafc; + --text-secondary: #94a3b8; + --text-placeholder: #475569; + + --brand-primary: #6366f1; + --brand-primary-hover: #818cf8; + --brand-primary-alpha: rgba(99, 102, 241, 0.15); + + --status-error: #f87171; + + --shadow-md: 0 4px 6px -1px rgba(0, 0, 0, 0.2); + --shadow-xl: 0 20px 25px -5px rgba(0, 0, 0, 0.3); +} + +/* ========================================= + 2. 全局重置与排版基准 +========================================= */ +*, *::before, *::after { + box-sizing: border-box; +} + +html, body { + margin: 0; + padding: 0; + min-height: 100vh; + font-family: 'Inter', 'Noto Sans SC', sans-serif; + background-color: var(--bg-base); + color: var(--text-primary); + -webkit-font-smoothing: antialiased; + -moz-osx-font-smoothing: grayscale; + transition: background-color 0.3s ease, color 0.3s ease; +} #app { - max-width: 1280px; - margin: 0 auto; - padding: 2rem; - font-weight: normal; + min-height: 100vh; + background: transparent; + position: relative; + z-index: 1; } -a, -.green { +a { + color: inherit; text-decoration: none; - color: hsla(160, 100%, 37%, 1); - transition: 0.4s; - padding: 3px; } -@media (hover: hover) { - a:hover { - background-color: hsla(160, 100%, 37%, 0.2); +button { + cursor: pointer; + border: none; + background: none; + font-family: inherit; +} + +/* ========================================= + 高级背景环境光与数据网格 +========================================= */ +body::before { + content: ''; + position: fixed; + inset: 0; + z-index: -2; + /* 绘制点阵网格 */ + background-image: radial-gradient(var(--border-strong) 1px, transparent 1px); + background-size: 24px 24px; + /* 使用遮罩让网格在四周自然淡出，避免边缘生硬 */ + mask-image: radial-gradient(ellipse 80% 80% at 50% -20%, black 20%, transparent 80%); + -webkit-mask-image: radial-gradient(ellipse 80% 80% at 50% -20%, black 20%, transparent 80%); + opacity: 0.4; + pointer-events: none; +} + +html.dark body::before { + opacity: 0.15; +} + +/* 极弱的雷达扫射呼吸环境光 */ +body::after { + content: ''; + position: fixed; + top: -50%; + left: -20%; + right: -20%; + height: 100vh; + z-index: -3; + background: radial-gradient(ellipse at bottom, var(--brand-primary-alpha) 0%, transparent 60%); + opacity: 0.6; + pointer-events: none; + animation: ambient-pulse 8s ease-in-out infinite alternate; +} + +@keyframes ambient-pulse { + 0% { + transform: scale(1); + opacity: 0.4; + } + 100% { + transform: scale(1.05); + opacity: 0.7; } } -@media (min-width: 1024px) { - body { - display: flex; - place-items: center; - } - - #app { - display: grid; - grid-template-columns: 1fr 1fr; - padding: 0 2rem; - } +/* ========================================= + 3. 现代表单控件体系 +========================================= */ +.input-group { + display: flex; + flex-direction: column; + gap: 8px; + margin-bottom: 20px; +} + +.input-label { + font-size: 14px; + font-weight: 500; + color: var(--text-primary); +} + +.input-wrapper { + position: relative; + display: flex; + align-items: center; +} + +.input-field { + width: 100%; + padding: 12px 14px; + background-color: var(--bg-input); + border: 1px solid var(--border-subtle); + border-radius: var(--radius-md); + color: var(--text-primary); + font-size: 15px; + transition: all 0.2s ease; +} + +.input-field::placeholder { + color: var(--text-placeholder); +} + +.input-field:hover { + border-color: var(--border-strong); +} + +.input-field:focus { + outline: none; + border-color: var(--brand-primary); + box-shadow: 0 0 0 3px var(--brand-primary-alpha); + background-color: var(--bg-surface); +} + +.input-action-btn { + position: absolute; + right: 12px; + font-size: 13px; + font-weight: 500; + color: var(--brand-primary); + padding: 4px 8px; + border-radius: 4px; + transition: background 0.2s; +} + +.input-action-btn:hover:not(:disabled) { + background: var(--brand-primary-alpha); +} + +.input-action-btn:disabled { + color: var(--text-placeholder); + cursor: not-allowed; +} + +.btn-primary { + width: 100%; + padding: 12px; + background-color: var(--brand-primary); + color: #ffffff; + font-size: 15px; + font-weight: 600; + border-radius: var(--radius-md); + transition: all 0.2s ease; + display: flex; + justify-content: center; + align-items: center; +} + +.btn-primary:hover:not(:disabled) { + background-color: var(--brand-primary-hover); + transform: translateY(-1px); + box-shadow: var(--shadow-md); +} + +.btn-primary:active:not(:disabled) { + transform: translateY(0); +} + +.btn-primary:disabled { + opacity: 0.6; + cursor: not-allowed; } diff --git a/frontend/src/auth.api.ts b/frontend/src/auth.api.ts new file mode 100644 index 0000000..53993a2 --- /dev/null +++ b/frontend/src/auth.api.ts @@ -0,0 +1,80 @@ +import type { + AuthTokenResponse, + LoginPayload, + LoginWithCodePayload, + MessageResponse, + RegisterPayload, +} from './auth.types' + +const API_BASE_URL = (import.meta.env.VITE_API_BASE_URL as string | undefined) ?? '/api/v1' + +type JsonValue = object | null + +const MESSAGE_MAP: Record = { + 'Email is already registered': '该邮箱已注册', + 'Email is not registered': '该邮箱未注册', + 'Failed to send verification code': '验证码发送失败，请稍后重试', + 'Verification code sent': '验证码已发送', + 'Verification code does not exist or expired': '验证码不存在或已过期', + 'Invalid verification code': '验证码错误', + 'Invalid email or password': '邮箱或密码错误', + 'Invalid email or verification code': '邮箱或验证码错误', +} + +function localizeMessage(message: string): string { + return MESSAGE_MAP[message] ?? message +} + +async function request(path: string, payload: JsonValue): Promise { + const response = await fetch(`${API_BASE_URL}${path}`, { + method: 'POST', + headers: { + 'Content-Type': 'application/json', + }, + body: payload ? JSON.stringify(payload) : undefined, + }) + + const raw = await response.text() + let data: Record = {} + if (raw) { + try { + data = JSON.parse(raw) as Record + } catch { + data = {} + } + } + + if (!response.ok) { + const detail = data.detail + if (typeof detail === 'string') { + throw new Error(localizeMessage(detail)) + } + throw new Error('请求失败，请稍后重试') + } + + if (typeof data.message === 'string') { + data.message = localizeMessage(data.message) + } + + return data as T +} + +export function sendRegisterCode(email: string): Promise { + return request('/auth/register/send-code', { email }) +} + +export function sendLoginCode(email: string): Promise { + return request('/auth/login/send-code', { email }) +} + +export function register(payload: RegisterPayload): Promise { + return request('/auth/register', payload) +} + +export function login(payload: LoginPayload): Promise { + return request('/auth/login', payload) +} + +export function loginWithCode(payload: LoginWithCodePayload): Promise { + return request('/auth/login/code', payload) +} diff --git a/frontend/src/auth.types.ts b/frontend/src/auth.types.ts new file mode 100644 index 0000000..845ea0c --- /dev/null +++ b/frontend/src/auth.types.ts @@ -0,0 +1,36 @@ +export interface UserProfile { + id: number + email: string + nickname: string | null + avatar_url: string | null + gender: string + created_at: string +} + +export interface AuthTokenResponse { + access_token: string + token_type: string + expires_in: number + user: UserProfile +} + +export interface MessageResponse { + message: string +} + +export interface LoginPayload { + email: string + password: string +} + +export interface LoginWithCodePayload { + email: string + verification_code: string +} + +export interface RegisterPayload { + email: string + password: string + verification_code: string + nickname?: string +} diff --git a/frontend/src/components/BrandLogo.vue b/frontend/src/components/BrandLogo.vue new file mode 100644 index 0000000..dd0990c --- /dev/null +++ b/frontend/src/components/BrandLogo.vue @@ -0,0 +1,123 @@ + + + diff --git a/frontend/src/components/HelloWorld.vue b/frontend/src/components/HelloWorld.vue deleted file mode 100644 index d174cf8..0000000 --- a/frontend/src/components/HelloWorld.vue +++ /dev/null @@ -1,41 +0,0 @@ - - - - - diff --git a/frontend/src/components/TheWelcome.vue b/frontend/src/components/TheWelcome.vue deleted file mode 100644 index 8b731d9..0000000 --- a/frontend/src/components/TheWelcome.vue +++ /dev/null @@ -1,95 +0,0 @@ - - - diff --git a/frontend/src/components/ThemeToggle.vue b/frontend/src/components/ThemeToggle.vue new file mode 100644 index 0000000..70b165a --- /dev/null +++ b/frontend/src/components/ThemeToggle.vue @@ -0,0 +1,392 @@ + + + + + diff --git a/frontend/src/components/WelcomeItem.vue b/frontend/src/components/WelcomeItem.vue deleted file mode 100644 index 6d7086a..0000000 --- a/frontend/src/components/WelcomeItem.vue +++ /dev/null @@ -1,87 +0,0 @@ - - - diff --git a/frontend/src/main.ts b/frontend/src/main.ts index 5dcad83..793c39b 100644 --- a/frontend/src/main.ts +++ b/frontend/src/main.ts @@ -1,14 +1,18 @@ import './assets/main.css' import { createApp } from 'vue' -import { createPinia } from 'pinia' import App from './App.vue' import router from './router' +import { pinia } from './stores' +import { useThemeStore } from './stores/theme' const app = createApp(App) -app.use(createPinia()) +app.use(pinia) +const themeStore = useThemeStore(pinia) +themeStore.initTheme() + app.use(router) app.mount('#app') diff --git a/frontend/src/router/index.ts b/frontend/src/router/index.ts index 3e49915..03787ab 100644 --- a/frontend/src/router/index.ts +++ b/frontend/src/router/index.ts @@ -1,5 +1,10 @@ import { createRouter, createWebHistory } from 'vue-router' -import HomeView from '../views/HomeView.vue' + +import { pinia } from '@/stores' +import { useAuthStore } from '@/stores/auth' +import HomeView from '@/views/HomeView.vue' +import LoginView from '@/views/LoginView.vue' +import RegisterView from '@/views/RegisterView.vue' const router = createRouter({ history: createWebHistory(import.meta.env.BASE_URL), @@ -8,16 +13,47 @@ const router = createRouter({ path: '/', name: 'home', component: HomeView, + meta: { + requiresAuth: true, + }, }, { - path: '/about', - name: 'about', - // route level code-splitting - // this generates a separate chunk (About.[hash].js) for this route - // which is lazy-loaded when the route is visited. - component: () => import('../views/AboutView.vue'), + path: '/login', + name: 'login', + component: LoginView, + meta: { + guestOnly: true, + }, + }, + { + path: '/register', + name: 'register', + component: RegisterView, + meta: { + guestOnly: true, + }, }, ], }) +router.beforeEach((to) => { + const authStore = useAuthStore(pinia) + authStore.restore() + + if (to.meta.requiresAuth && !authStore.isAuthenticated) { + return { + name: 'login', + query: { + redirect: to.fullPath, + }, + } + } + + if (to.meta.guestOnly && authStore.isAuthenticated) { + return { name: 'home' } + } + + return true +}) + export default router diff --git a/frontend/src/router/route-meta.d.ts b/frontend/src/router/route-meta.d.ts new file mode 100644 index 0000000..99f8492 --- /dev/null +++ b/frontend/src/router/route-meta.d.ts @@ -0,0 +1,8 @@ +import 'vue-router' + +declare module 'vue-router' { + interface RouteMeta { + requiresAuth?: boolean + guestOnly?: boolean + } +} diff --git a/frontend/src/stores/auth.ts b/frontend/src/stores/auth.ts new file mode 100644 index 0000000..8313f08 --- /dev/null +++ b/frontend/src/stores/auth.ts @@ -0,0 +1,164 @@ +import { computed, ref } from 'vue' +import { defineStore } from 'pinia' + +import { login, loginWithCode, register, sendLoginCode, sendRegisterCode } from '@/auth.api' +import type { LoginPayload, LoginWithCodePayload, RegisterPayload, UserProfile } from '@/auth.types' + +interface PersistedAuthState { + accessToken: string + expiresAt: number + user: UserProfile +} + +const AUTH_STORAGE_KEY = 'insight-radar-auth' + +function loadPersistedState(): PersistedAuthState | null { + const raw = localStorage.getItem(AUTH_STORAGE_KEY) + if (!raw) { + return null + } + + try { + const parsed = JSON.parse(raw) as PersistedAuthState + if (!parsed.accessToken || !parsed.expiresAt || !parsed.user) { + return null + } + return parsed + } catch { + return null + } +} + +export const useAuthStore = defineStore('auth', () => { + const persisted = loadPersistedState() + + const accessToken = ref(persisted?.accessToken ?? null) + const expiresAt = ref(persisted?.expiresAt ?? null) + const user = ref(persisted?.user ?? null) + const loading = ref(false) + + const isExpired = computed(() => { + if (!expiresAt.value) { + return true + } + return Date.now() >= expiresAt.value + }) + + const isAuthenticated = computed(() => Boolean(accessToken.value && user.value && !isExpired.value)) + + function persist() { + if (!accessToken.value || !expiresAt.value || !user.value) { + localStorage.removeItem(AUTH_STORAGE_KEY) + return + } + + const payload: PersistedAuthState = { + accessToken: accessToken.value, + expiresAt: expiresAt.value, + user: user.value, + } + localStorage.setItem(AUTH_STORAGE_KEY, JSON.stringify(payload)) + } + + function setSession(params: { accessToken: string; expiresIn: number; user: UserProfile }) { + accessToken.value = params.accessToken + expiresAt.value = Date.now() + params.expiresIn * 1000 + user.value = params.user + persist() + } + + function clearSession() { + accessToken.value = null + expiresAt.value = null + user.value = null + persist() + } + + async function loginWithPassword(payload: LoginPayload) { + loading.value = true + try { + const data = await login(payload) + setSession({ + accessToken: data.access_token, + expiresIn: data.expires_in, + user: data.user, + }) + return data + } finally { + loading.value = false + } + } + + async function loginWithVerificationCode(payload: LoginWithCodePayload) { + loading.value = true + try { + const data = await loginWithCode(payload) + setSession({ + accessToken: data.access_token, + expiresIn: data.expires_in, + user: data.user, + }) + return data + } finally { + loading.value = false + } + } + + async function registerAccount(payload: RegisterPayload) { + loading.value = true + try { + const data = await register(payload) + setSession({ + accessToken: data.access_token, + expiresIn: data.expires_in, + user: data.user, + }) + return data + } finally { + loading.value = false + } + } + + async function sendCode(email: string) { + loading.value = true + try { + return await sendRegisterCode(email) + } finally { + loading.value = false + } + } + + async function sendLoginVerificationCode(email: string) { + loading.value = true + try { + return await sendLoginCode(email) + } finally { + loading.value = false + } + } + + function restore() { + if (isExpired.value) { + clearSession() + } + } + + function logout() { + clearSession() + } + + return { + accessToken, + expiresAt, + user, + loading, + isAuthenticated, + loginWithPassword, + loginWithVerificationCode, + registerAccount, + sendCode, + sendLoginVerificationCode, + restore, + logout, + } +}) diff --git a/frontend/src/stores/index.ts b/frontend/src/stores/index.ts new file mode 100644 index 0000000..c569ef7 --- /dev/null +++ b/frontend/src/stores/index.ts @@ -0,0 +1,3 @@ +import { createPinia } from 'pinia' + +export const pinia = createPinia() diff --git a/frontend/src/stores/theme.ts b/frontend/src/stores/theme.ts new file mode 100644 index 0000000..b7a7de0 --- /dev/null +++ b/frontend/src/stores/theme.ts @@ -0,0 +1,66 @@ +import { computed, ref } from 'vue' +import { defineStore } from 'pinia' + +type ThemeMode = 'dark' | 'light' + +const THEME_STORAGE_KEY = 'insight-radar-theme' + +export const useThemeStore = defineStore('theme', () => { + const mode = ref('light') + const initialized = ref(false) + let transitionTimer: number | null = null + + const isDark = computed(() => mode.value === 'dark') + + function applyTheme(nextMode: ThemeMode) { + mode.value = nextMode + document.documentElement.classList.toggle('dark', nextMode === 'dark') + localStorage.setItem(THEME_STORAGE_KEY, nextMode) + } + + function runTransition(nextMode: ThemeMode) { + const root = document.documentElement + root.dataset.themeTransition = nextMode === 'dark' ? 'to-dark' : 'to-light' + root.classList.add('theme-switching') + + if (transitionTimer) { + window.clearTimeout(transitionTimer) + } + + transitionTimer = window.setTimeout(() => { + root.classList.remove('theme-switching') + delete root.dataset.themeTransition + transitionTimer = null + }, 760) + } + + function initTheme() { + if (initialized.value) { + return + } + + const savedTheme = localStorage.getItem(THEME_STORAGE_KEY) + if (savedTheme === 'dark' || savedTheme === 'light') { + applyTheme(savedTheme) + initialized.value = true + return + } + + const prefersDark = window.matchMedia('(prefers-color-scheme: dark)').matches + applyTheme(prefersDark ? 'dark' : 'light') + initialized.value = true + } + + function toggleTheme() { + const nextMode: ThemeMode = isDark.value ? 'light' : 'dark' + runTransition(nextMode) + applyTheme(nextMode) + } + + return { + mode, + isDark, + initTheme, + toggleTheme, + } +}) diff --git a/frontend/src/views/HomeView.vue b/frontend/src/views/HomeView.vue index d5c0217..cb92c9b 100644 --- a/frontend/src/views/HomeView.vue +++ b/frontend/src/views/HomeView.vue @@ -1,9 +1,300 @@ + + diff --git a/frontend/src/views/LoginView.vue b/frontend/src/views/LoginView.vue new file mode 100644 index 0000000..ee2c753 --- /dev/null +++ b/frontend/src/views/LoginView.vue @@ -0,0 +1,447 @@ + + + + + diff --git a/frontend/src/views/RegisterView.vue b/frontend/src/views/RegisterView.vue new file mode 100644 index 0000000..6148f79 --- /dev/null +++ b/frontend/src/views/RegisterView.vue @@ -0,0 +1,414 @@ + + + + + diff --git a/frontend/vite.config.ts b/frontend/vite.config.ts index 4217010..76d3f5b 100644 --- a/frontend/vite.config.ts +++ b/frontend/vite.config.ts @@ -10,6 +10,14 @@ export default defineConfig({ vue(), vueDevTools(), ], + server: { + proxy: { + '/api': { + target: 'http://127.0.0.1:8000', + changeOrigin: true, + }, + }, + }, resolve: { alias: { '@': fileURLToPath(new URL('./src', import.meta.url))