Run pipeline: live 26/27 data + real 25/26 stats, expert model predictions

- Updated 26_27_teams.yaml with confirmed teams from live Fantacalcio.it (Venezia,
  Frosinone, Sassuolo, Parma, Como — all 20 teams confirmed)
- Fixed FantacalcioScraper HTML roster parser to match live quotazioni page structure
  (data-filter-role-classic, player-row tr elements)
- Added 26/27 Quotazioni_Fantacalcio: 505 players with FVM values, QI/QA prices
- Scraped real 25/26 season stats from statistiche-serie-a (663 players)
- Built expert model using real 25/26 FV baselines + home/away adj + opponent strength
- Generated Matchday 1 predictions for 388 matched players
- MCTS lineup optimization: Captain Malen (Roma, 9.67 FV), 98.1 expected pts
- All 31 tests passing

src/scraper/fantacalcio_scraper.py

@@ -132,21 +132,46 @@ class FantacalcioScraper:
         return pd.read_excel(io.BytesIO(resp.content))
 
     def _fetch_roster_html(self) -> pd.DataFrame:
-        """Fallback: scrape quotazioni/roster from HTML page."""
-        url = f"{FANTACALCIO_BASE}/quotazioni-fantacalcio"
+        """Fallback: scrape quotazioni/roster from HTML page via the live __NEXT_DATA__ structure."""
+        import json
+        url = "https://www.fantacalcio.it/quotazioni-fantacalcio"
         logger.info(f"Fetching roster from HTML: {url}")
         resp = self.session.get(url, timeout=30, allow_redirects=True)
         soup = BeautifulSoup(resp.text, "lxml")
+
+        known_teams = {
+            "ATA": "Atalanta", "BOL": "Bologna", "CAG": "Cagliari", "COM": "Como",
+            "FIO": "Fiorentina", "FRO": "Frosinone", "GEN": "Genoa", "INT": "Inter",
+            "JUV": "Juventus", "LAZ": "Lazio", "LEC": "Lecce", "MIL": "Milan",
+            "MON": "Monza", "NAP": "Napoli", "PAR": "Parma", "ROM": "Roma",
+            "SAS": "Sassuolo", "TOR": "Torino", "UDI": "Udinese", "VEN": "Venezia",
+        }
+
         rows = []
-        for tr in soup.select("table tbody tr"):
-            cols = tr.select("td")
-            if len(cols) >= 5:
-                rows.append({
-                    "player": cols[0].text.strip(),
-                    "role": cols[1].text.strip(),
-                    "team": cols[2].text.strip(),
-                    "value": cols[3].text.strip(),
-                })
+        for tr in soup.find_all("tr", class_="player-row"):
+            name_link = tr.find("a", class_="player-name")
+            if not name_link:
+                continue
+            name = name_link.text.strip()
+            role = tr.get("data-filter-role-classic", "").upper()
+            team_code_el = tr.find("td", class_="player-team")
+            qi_el = tr.find("td", class_="player-classic-initial-price")
+            qa_el = tr.find("td", class_="player-classic-current-price")
+            fvm_el = tr.find("td", class_="player-classic-fvm")
+
+            team_code = team_code_el.text.strip() if team_code_el else ""
+            team = known_teams.get(team_code, team_code)
+
+            rows.append({
+                "Nome": name,
+                "R": role,
+                "Squadra": team,
+                "QI": int(qi_el.text.strip()) if qi_el else 0,
+                "QA": int(qa_el.text.strip()) if qa_el else 0,
+                "FVM": int(fvm_el.text.strip()) if fvm_el else 0,
+            })
+
+        logger.info(f"Scraped {len(rows)} players from HTML roster")
         return pd.DataFrame(rows)
 
     # ─── Probable Lineups ──────────────────────────────────────────