Phase 1: initial codes

2026-05-26 11:04:27 -04:00
parent 03bff49523
commit f49a283059
32 changed files with 4194 additions and 0 deletions
@@ -0,0 +1,93 @@
+from __future__ import annotations
+from datetime import datetime, timedelta
+from newsapi import NewsApiClient
+from ai.claude_client import ClaudeClient
+from ai.prompts import SENTIMENT_SCORE_SYSTEM, SENTIMENT_SCORE_PROMPT
+
+
+def fetch_news(symbol: str, api_key: str, page_size: int = 10) -> list[dict]:
+    try:
+        client = NewsApiClient(api_key=api_key)
+        from_date = (datetime.now() - timedelta(days=7)).strftime("%Y-%m-%d")
+        response = client.get_everything(
+            q=symbol,
+            language="en",
+            sort_by="publishedAt",
+            page_size=page_size,
+            from_param=from_date,
+        )
+        articles = response.get("articles", [])
+        return [
+            {
+                "title": a.get("title", ""),
+                "description": a.get("description", ""),
+                "url": a.get("url", ""),
+                "source": a.get("source", {}).get("name", ""),
+                "published_at": a.get("publishedAt", ""),
+            }
+            for a in articles
+            if a.get("title")
+        ]
+    except Exception as e:
+        return []
+
+
+def analyze_sentiment(symbol: str, articles: list[dict], claude: ClaudeClient) -> tuple[str, dict]:
+    if not articles:
+        return "No news available for sentiment analysis.", {}
+
+    headlines = "\n".join(
+        f"{i + 1}. {a['title']}" for i, a in enumerate(articles[:15])
+    )
+    prompt = SENTIMENT_SCORE_PROMPT.format(symbol=symbol, headlines=headlines)
+    text, usage = claude.ask(prompt, system=SENTIMENT_SCORE_SYSTEM, max_tokens=800)
+    return text, usage
+
+
+def cache_news(symbol: str, articles: list[dict], sentiment: str = "") -> None:
+    from db.database import get_session
+    from db.models import NewsCache
+    from datetime import datetime
+
+    with get_session() as session:
+        session.query(NewsCache).filter_by(symbol=symbol).delete()
+        for a in articles:
+            session.add(NewsCache(
+                symbol=symbol,
+                title=a.get("title", ""),
+                description=a.get("description", ""),
+                url=a.get("url", ""),
+                source=a.get("source", ""),
+                published_at=a.get("published_at", ""),
+                sentiment=sentiment,
+                fetched_at=datetime.utcnow(),
+            ))
+        session.commit()
+
+
+def get_cached_news(symbol: str, max_age_hours: int = 1) -> list[dict] | None:
+    from db.database import get_session
+    from db.models import NewsCache
+    from datetime import datetime, timedelta
+
+    cutoff = datetime.utcnow() - timedelta(hours=max_age_hours)
+    with get_session() as session:
+        rows = (
+            session.query(NewsCache)
+            .filter(NewsCache.symbol == symbol, NewsCache.fetched_at > cutoff)
+            .order_by(NewsCache.published_at.desc())
+            .all()
+        )
+        if not rows:
+            return None
+        return [
+            {
+                "title": r.title,
+                "description": r.description,
+                "url": r.url,
+                "source": r.source,
+                "published_at": r.published_at,
+                "sentiment": r.sentiment,
+            }
+            for r in rows
+        ]