Update services/news_service.py

services/news_service.py

@@ -1,39 +1,68 @@
-import requests
 import os
-from datetime import datetime, timedelta
-from services.sdg_llm import analyze_sdg_text
+import requests
+from dotenv import load_dotenv
 
-FINNHUB_API_KEY = os.environ.get("FINNHUB_API_KEY")
+# Load environment variables from .env file
+load_dotenv()
 
-def get_company_news(symbol):
-    try:
-        # Use last 7 days of news
-        today = datetime.now()
-        last_week = today - timedelta(days=7)
+NEWS_API_KEY = os.environ.get("NEWS_API_KEY")
 
-        url = (
-            f"https://finnhub.io/api/v1/company-news?symbol={symbol}"
-            f"&from={last_week.strftime('%Y-%m-%d')}"
-            f"&to={today.strftime('%Y-%m-%d')}&token={FINNHUB_API_KEY}"
-        )
-        res = requests.get(url)
-        data = res.json()
 
-        articles = []
+def get_company_news(query="GOOG", limit=5):
+    """
+    Fetches latest news articles using a specific query string (symbol or full company name).
+    Always returns a list. Never raises exceptions.
+    """
 
-        for a in data[:10]:  # limit to 10 items
-            text = f"{a.get('headline','')} {a.get('summary','')}"
-            sdg = analyze_sdg_text(text)
+    # ✅ Safety: Key missing
+    if not NEWS_API_KEY:
+        print("Warning: NEWS_API_KEY is not set. News fetching skipped.")
+        return []
 
-            articles.append({
-                "title": a.get("headline", ""),
-                "description": a.get("summary", ""),
-                "url": a.get("url", ""),
-                "sdg": sdg   # ✅ SDG data added
-            })
+    # ✅ Quotes improve multi-word search
+    url = (
+        f"https://newsapi.org/v2/everything?"
+        f"q=\"{query}\"&sortBy=publishedAt&language=en&apiKey={NEWS_API_KEY}"
+    )
 
-        return articles
+    try:
+        response = requests.get(url)
+        # ✅ If API returns HTML (rate limit, outage)
+        if response.headers.get("content-type", "").startswith("text/html"):
+            print("NewsAPI returned HTML instead of JSON → ignoring.")
+            return []
+
+        resp = response.json()
 
     except Exception as e:
-        print("News fetch error:", e)
+        print(f"Exception while fetching news: {e}")
         return []
+
+    # ✅ Safety: API error or invalid key
+    if resp.get("status") != "ok":
+        print(f"NewsAPI Error: {resp.get('message')}")
+        return []
+
+    # ✅ Extract clean articles
+    articles = []
+    for a in resp.get("articles", []):
+        if len(articles) >= limit:
+            break
+
+        title = a.get("title")
+        desc = a.get("description")
+
+        # ✅ Safety: ensure both title & description exist AND are strings
+        if not title or not isinstance(title, str):
+            continue
+        if not desc or not isinstance(desc, str):
+            continue
+
+        articles.append({
+            "title": title.strip(),
+            "description": desc.strip(),
+            "url": a.get("url", "")
+        })
+
+    print(f"Fetched {len(articles)} articles from NewsAPI for query: \"{query}\"")
+    return articles