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/crawler/pipelines.py

@@ -0,0 +1,74 @@
+import hashlib
+import json
+from typing import Any
+
+from scrapy.crawler import Crawler
+from sqlalchemy import func, select
+
+from alphapulse.core.db import SessionLocal
+from alphapulse.core.redis import redis
+from alphapulse.crawler.events import NEWS_CHANNEL
+from alphapulse.models import NewsItem, NewsRevision
+
+UPDATABLE_FIELDS = ("url", "title", "summary", "content_html", "content_text", "author", "tags",
+                    "is_paywalled", "published_at", "source_updated_at", "extra")
+
+
+def content_hash(item: dict[str, Any]) -> str:
+    return hashlib.sha256("\0".join((item["title"], item["summary"], item["content_html"])).encode()).hexdigest()
+
+
+class NewsPipeline:
+    """按 (source_code, external_id) 幂等落库；内容变化写一条修订"""
+
+    def __init__(self, crawler: Crawler) -> None:
+        self.crawler = crawler
+
+    @classmethod
+    def from_crawler(cls, crawler: Crawler) -> "NewsPipeline":
+        return cls(crawler)
+
+    async def process_item(self, item: dict[str, Any]) -> dict[str, Any]:
+        spider = self.crawler.spider
+        digest = content_hash(item)
+        raw_response_id = item.pop("raw_response_id")
+        async with SessionLocal() as session:
+            news = await session.scalar(
+                select(NewsItem)
+                .where(NewsItem.source_code == item["source_code"], NewsItem.external_id == item["external_id"])
+                .with_for_update()
+            )
+            if news is None:
+                kind = "new"
+                news = NewsItem(**item, content_hash=digest, revision_no=1)
+                session.add(news)
+                await session.flush()
+            elif news.content_hash != digest:
+                kind = "revised"
+                for field in UPDATABLE_FIELDS:
+                    setattr(news, field, item[field])
+                news.content_hash = digest
+                news.revision_no += 1
+                news.last_seen_at = func.now()
+            else:
+                kind = None
+                news.last_seen_at = func.now()
+
+            if kind:
+                session.add(NewsRevision(
+                    news_id=news.id,
+                    revision_no=news.revision_no,
+                    title=item["title"],
+                    summary=item["summary"],
+                    content_html=item["content_html"],
+                    content_hash=digest,
+                    raw_response_id=raw_response_id,
+                ))
+            news_id = news.id
+            await session.commit()
+
+        spider.run.items_seen += 1
+        if kind:
+            setattr(spider.run, f"items_{kind}", getattr(spider.run, f"items_{kind}") + 1)
+            await redis.publish(NEWS_CHANNEL, json.dumps({"id": news_id, "source_code": item["source_code"], "kind": kind}))
+        return item