Initial AlphaPulse implementation: news crawler and Binance klines

- Backend (FastAPI, SQLAlchemy 2, Alembic): single-admin cookie auth,
  news/crawler/market APIs with SSE and WebSocket streaming
- Crawler (Scrapy + Scrapy-Redis): wscn_news, wscn_live, cls_depth,
  cls_telegraph spiders, idempotent upserts with revisions, raw response
  archiving, per-source subprocess supervision, restart and backoff
- Market worker: full-history Binance spot/USD-M kline backfill,
  realtime WS stream, hourly and on-reconnect catch-up
- Frontend (Vue 3, Element Plus, UnoCSS, KLineChart): news feed,
  crawler console with live logs, Binance-style chart page
- Deploy: docker compose, nginx site, migrate and daily backup scripts

backend/src/alphapulse/api/news.py

@@ -0,0 +1,110 @@
+from collections.abc import AsyncIterator
+from datetime import datetime
+from typing import Annotated
+
+from fastapi import APIRouter, Depends, HTTPException, Query, status
+from fastapi.sse import EventSourceResponse, ServerSentEvent
+from pydantic import BaseModel
+from sqlalchemy import func, or_, select, tuple_
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from alphapulse.core.auth import require_admin
+from alphapulse.core.db import get_session
+from alphapulse.core.redis import redis
+from alphapulse.crawler.events import NEWS_CHANNEL
+from alphapulse.models import NewsItem, NewsRevision
+
+router = APIRouter(prefix="/api/news", tags=["news"], dependencies=[Depends(require_admin)])
+
+EXCERPT_LENGTH = 300
+
+
+class NewsBrief(BaseModel):
+    id: int
+    source_code: str
+    url: str
+    title: str
+    summary: str
+    excerpt: str
+    author: str | None
+    tags: list
+    is_paywalled: bool
+    published_at: datetime
+    first_seen_at: datetime
+    revision_no: int
+
+
+class NewsPage(BaseModel):
+    items: list[NewsBrief]
+    # 形如 "<published_at ISO>|<id>"，原样传回即可取下一页
+    next_cursor: str | None
+
+
+class NewsDetail(NewsBrief):
+    content_html: str
+    source_updated_at: datetime | None
+    last_seen_at: datetime
+    extra: dict
+
+
+class Revision(BaseModel):
+    revision_no: int
+    title: str
+    summary: str
+    content_html: str
+    captured_at: datetime
+
+
+@router.get("")
+async def list_news(
+    session: Annotated[AsyncSession, Depends(get_session)],
+    source: Annotated[list[str] | None, Query()] = None,
+    q: str | None = None,
+    start: datetime | None = None,
+    end: datetime | None = None,
+    cursor: str | None = None,
+    limit: Annotated[int, Query(ge=1, le=100)] = 30,
+) -> NewsPage:
+    stmt = select(NewsItem, func.left(NewsItem.content_text, EXCERPT_LENGTH).label("excerpt"))
+    if source:
+        stmt = stmt.where(NewsItem.source_code.in_(source))
+    if q:
+        pattern = f"%{q}%"
+        stmt = stmt.where(or_(NewsItem.title.ilike(pattern), NewsItem.content_text.ilike(pattern)))
+    if start:
+        stmt = stmt.where(NewsItem.published_at >= start)
+    if end:
+        stmt = stmt.where(NewsItem.published_at < end)
+    if cursor:
+        published_at, news_id = cursor.rsplit("|", 1)
+        stmt = stmt.where(tuple_(NewsItem.published_at, NewsItem.id) < (datetime.fromisoformat(published_at), int(news_id)))
+    rows = (await session.execute(stmt.order_by(NewsItem.published_at.desc(), NewsItem.id.desc()).limit(limit))).all()
+
+    items = [NewsBrief.model_validate({**news.__dict__, "excerpt": excerpt}) for news, excerpt in rows]
+    next_cursor = f"{items[-1].published_at.isoformat()}|{items[-1].id}" if len(items) == limit else None
+    return NewsPage(items=items, next_cursor=next_cursor)
+
+
+@router.get("/stream", response_class=EventSourceResponse)
+async def stream_news() -> AsyncIterator[ServerSentEvent]:
+    async with redis.pubsub() as pubsub:
+        await pubsub.subscribe(NEWS_CHANNEL)
+        async for message in pubsub.listen():
+            if message["type"] == "message":
+                yield ServerSentEvent(raw_data=message["data"], event="news")
+
+
+@router.get("/{news_id}")
+async def get_news(news_id: int, session: Annotated[AsyncSession, Depends(get_session)]) -> NewsDetail:
+    news = await session.get(NewsItem, news_id)
+    if news is None:
+        raise HTTPException(status.HTTP_404_NOT_FOUND, "新闻不存在")
+    return NewsDetail.model_validate({**news.__dict__, "excerpt": news.content_text[:EXCERPT_LENGTH]})
+
+
+@router.get("/{news_id}/revisions")
+async def list_revisions(news_id: int, session: Annotated[AsyncSession, Depends(get_session)]) -> list[Revision]:
+    rows = await session.scalars(
+        select(NewsRevision).where(NewsRevision.news_id == news_id).order_by(NewsRevision.revision_no.desc())
+    )
+    return [Revision.model_validate(r, from_attributes=True) for r in rows]