Update app.py

app.py

@@ -92,25 +92,69 @@ def _extract_pairs_from_texts(texts):
                 pairs.append({"home": home, "away": away})
     return pairs
 
+def fetch_espn_pairs_for_date(d: str):
+    # d: YYYY-MM-DD -> ESPN expects YYYYMMDD
+    try:
+        y, m, day = d.split("-")
+        ymd = f"{y}{m}{day}"
+        url = f"https://site.web.api.espn.com/apis/v2/sports/basketball/nba/scoreboard?dates={ymd}"
+        r = requests.get(url, timeout=20)
+        r.raise_for_status()
+        data = r.json()
+        events = data.get("events", [])
+        pairs = []
+        for ev in events:
+            comps = (ev.get("competitions") or [{}])[0].get("competitors") or []
+            home = next((c for c in comps if c.get("homeAway") == "home"), None)
+            away = next((c for c in comps if c.get("homeAway") == "away"), None)
+            if home and away:
+                pairs.append({
+                    "home": home.get("team", {}).get("displayName") or home.get("team", {}).get("name"),
+                    "away": away.get("team", {}).get("displayName") or away.get("team", {}).get("name")
+                })
+        return pairs
+    except Exception:
+        return []
+
 def scrape_nba_preseason_pairs_for_dates(dates):
     found = []
     seen = set()
     headers = {"User-Agent": "Mozilla/5.0"}
+    queries = [
+        "NBA preseason {d}",
+        "NBA schedule {d}",
+        "NBA games {d}",
+        "site:espn.com NBA {d}",
+        "site:yahoo.com/sports NBA {d}"
+    ]
     for d in dates:
-        q = f"NBA preseason {d}"
-        url = f"https://www.google.com/search?q={q}"
-        try:
-            r = requests.get(url, headers=headers, timeout=20)
-            soup = BeautifulSoup(r.text, "html.parser")
-            h3s = [h.text for h in soup.select("h3")[:20]]
-            pairs = _extract_pairs_from_texts(h3s)
-            for p in pairs:
-                key = (p["home"].lower(), p["away"].lower())
-                if key not in seen:
-                    seen.add(key)
-                    found.append(p)
-        except Exception:
+        # First try ESPN JSON scoreboard (works for preseason too)
+        espn_pairs = fetch_espn_pairs_for_date(d)
+        for p in espn_pairs:
+            key = (p["home"].lower(), p["away"].lower())
+            if key not in seen:
+                seen.add(key)
+                found.append(p)
+        if espn_pairs:
             continue
+        # Fallback: lightweight Google scrape with multiple queries
+        for qtpl in queries:
+            q = qtpl.format(d=d)
+            url = f"https://www.google.com/search?q={q}"
+            try:
+                r = requests.get(url, headers=headers, timeout=20)
+                soup = BeautifulSoup(r.text, "html.parser")
+                h3s = [h.text for h in soup.select("h3")[:30]]
+                pairs = _extract_pairs_from_texts(h3s)
+                for p in pairs:
+                    key = (p["home"].lower(), p["away"].lower())
+                    if key not in seen:
+                        seen.add(key)
+                        found.append(p)
+                if found:
+                    break
+            except Exception:
+                continue
     return found
 
 # --- Verdict helpers ---
@@ -242,26 +286,25 @@ def aggregate_outcomes(prob_matrix, thresholds=(0.5, 1.5, 2.5, 3.5)):
 @app.get("/soccer-predictions")
 def soccer_predictions():
     from datetime import timedelta
-    
-    
+
     today = date.today()
     date_from = (today - timedelta(days=5)).isoformat()
     date_to = (today + timedelta(days=5)).isoformat()
-    
+
     predictions = []
     debug_info = []
 
     for league, code in SOCCER_LEAGUES.items():
         headers = {"X-Auth-Token": FOOTBALL_API_KEY}
         try:
-            resp = requests.get(
+        resp = requests.get(
                 f"{FOOTBALL_ENDPOINT}?competitions={code}&dateFrom={date_from}&dateTo={date_to}",
-                headers=headers
-            )
+            headers=headers
+        )
             resp.raise_for_status()
             data = resp.json()
             matches = data.get("matches", [])
-            
+
             debug_info.append({
                 "league": league,
                 "code": code,
@@ -269,7 +312,7 @@ def soccer_predictions():
                 "api_response_status": resp.status_code,
                 "date_range": f"{date_from} to {date_to}"
             })
-            
+
         except requests.exceptions.RequestException as e:
             debug_info.append({
                 "league": league,
@@ -331,7 +374,7 @@ def soccer_predictions():
             """
             reasoning = reasoning_model(
                 f"Provide a concise betting-style verdict (1X2, O/U, double chance) with rationale given the context. Context: {context}",
-                max_length=256
+                max_new_tokens=256
             )[0]['generated_text']
 
             predictions.append({
@@ -439,6 +482,7 @@ def nba_predictions():
     predictions = []
     debug_info = []
     
+    games = []
     try:
         # Test NBA API connectivity first
         games_response = nba_api.nba.games.list(dates=dates)
@@ -530,7 +574,7 @@ def nba_predictions():
         """
         reasoning = reasoning_model(
             f"Provide a concise NBA verdict: likely winner and Over/Under guidance. Context: {context}",
-            max_length=256
+            max_new_tokens=256
         )[0]['generated_text']
 
         predictions.append({