Update data/schedule.py

data/schedule.py

@@ -7,7 +7,8 @@ from typing import Any
 import pandas as pd
 import requests
 
-SCHEDULE_URL_TEMPLATE = "https://www.mlb.com/world-baseball-classic/schedule/{date_str}"
+WBC_SCHEDULE_URL_TEMPLATE = "https://www.mlb.com/world-baseball-classic/schedule/{date_str}"
+SCHEDULE_API_URL = "https://statsapi.mlb.com/api/v1/schedule"
 
 HEADERS = {
     "User-Agent": "Mozilla/5.0",
@@ -38,12 +39,27 @@ TEAM_MAP = {
     "VEN": "Venezuela",
 }
 
+TEAM_NORMALIZATION = {
+    "Chinese Taipei": "Chinese Taipei",
+    "Czech Republic": "Czechia",
+    "South Korea": "Korea",
+    "USA": "United States",
+    "U.S.A.": "United States",
+}
+
 TV_MARKERS = {"FS1", "FS2", "FOX", "Tubi"}
 TIME_RE = re.compile(r"^\d{1,2}:\d{2}\s+[AP]M\s+ET$")
 ABBR_RE = re.compile(r"^[A-Z]{3}$")
 GAME_PK_RE = re.compile(r"/gameday/(\d+)")
 
 
+def _normalize_team_name(name: Any) -> str:
+    text = str(name or "").strip()
+    if not text:
+        return ""
+    return TEAM_NORMALIZATION.get(text, text)
+
+
 def _strip_html_to_lines(html: str) -> list[str]:
     text = re.sub(r"<script.*?</script>", " ", html, flags=re.DOTALL | re.IGNORECASE)
     text = re.sub(r"<style.*?</style>", " ", text, flags=re.DOTALL | re.IGNORECASE)
@@ -83,8 +99,8 @@ def _extract_game_pks(html: str) -> list[str]:
     return seen
 
 
-def fetch_schedule_for_date(date_str: str) -> pd.DataFrame:
-    url = SCHEDULE_URL_TEMPLATE.format(date_str=date_str)
+def _fetch_wbc_schedule_for_date(date_str: str) -> pd.DataFrame:
+    url = WBC_SCHEDULE_URL_TEMPLATE.format(date_str=date_str)
     response = requests.get(url, headers=HEADERS, timeout=30)
     response.raise_for_status()
 
@@ -168,6 +184,7 @@ def fetch_schedule_for_date(date_str: str) -> pd.DataFrame:
                     "venue": "",
                     "tv": tv,
                     "start_time_et": start_time_et,
+                    "sport_id": 51,
                 }
             )
 
@@ -176,4 +193,112 @@ def fetch_schedule_for_date(date_str: str) -> pd.DataFrame:
 
         i += 1
 
-    return pd.DataFrame(rows)
+    return pd.DataFrame(rows)
+
+
+def _fetch_mlb_schedule_for_date(date_str: str) -> pd.DataFrame:
+    params = {
+        "sportId": 1,
+        "date": date_str,
+        "hydrate": "broadcasts",
+    }
+
+    response = requests.get(SCHEDULE_API_URL, headers=HEADERS, params=params, timeout=30)
+    response.raise_for_status()
+    payload = response.json()
+
+    rows: list[dict[str, Any]] = []
+
+    for date_block in payload.get("dates", []) or []:
+        for game in date_block.get("games", []) or []:
+            game_pk = game.get("gamePk")
+
+            teams = game.get("teams", {}) or {}
+            away = teams.get("away", {}) or {}
+            home = teams.get("home", {}) or {}
+
+            away_team = _normalize_team_name((away.get("team", {}) or {}).get("name"))
+            home_team = _normalize_team_name((home.get("team", {}) or {}).get("name"))
+
+            status_info = game.get("status", {}) or {}
+            detailed_state = str(status_info.get("detailedState", "") or "").strip()
+            abstract_state = str(status_info.get("abstractGameState", "") or "").strip().lower()
+
+            status = ""
+            if abstract_state == "live":
+                status = "Live"
+            elif abstract_state == "final":
+                status = "Final"
+            elif abstract_state == "preview":
+                status = "Scheduled"
+            else:
+                status = detailed_state
+
+            game_datetime = game.get("gameDate", "")
+            start_time_et = ""
+            if game_datetime:
+                try:
+                    ts = pd.to_datetime(game_datetime, utc=True).tz_convert("America/New_York")
+                    start_time_et = ts.strftime("%-I:%M %p ET")
+                except Exception:
+                    start_time_et = ""
+
+            broadcasts = game.get("broadcasts", []) or []
+            tv = ""
+            if broadcasts:
+                names = []
+                for b in broadcasts:
+                    name = str((b.get("name") or "")).strip()
+                    if name and name not in names:
+                        names.append(name)
+                tv = ", ".join(names)
+
+            if away_team and home_team:
+                rows.append(
+                    {
+                        "fetched_at": datetime.utcnow(),
+                        "game_id": f"{date_str}:{away_team}:{home_team}",
+                        "game_date": date_str,
+                        "game_pk": str(game_pk) if game_pk is not None else "",
+                        "status": status,
+                        "away_team": away_team,
+                        "home_team": home_team,
+                        "away_score": None,
+                        "home_score": None,
+                        "away_hits": None,
+                        "home_hits": None,
+                        "away_errors": None,
+                        "home_errors": None,
+                        "venue": "",
+                        "tv": tv,
+                        "start_time_et": start_time_et,
+                        "sport_id": 1,
+                    }
+                )
+
+    return pd.DataFrame(rows)
+
+
+def fetch_schedule_for_date(date_str: str) -> pd.DataFrame:
+    parts: list[pd.DataFrame] = []
+
+    try:
+        wbc_df = _fetch_wbc_schedule_for_date(date_str)
+        if wbc_df is not None and not wbc_df.empty:
+            parts.append(wbc_df)
+    except Exception:
+        pass
+
+    try:
+        mlb_df = _fetch_mlb_schedule_for_date(date_str)
+        if mlb_df is not None and not mlb_df.empty:
+            parts.append(mlb_df)
+    except Exception:
+        pass
+
+    if not parts:
+        return pd.DataFrame()
+
+    df = pd.concat(parts, ignore_index=True)
+    df = df.drop_duplicates(subset=["game_pk", "away_team", "home_team"], keep="last")
+    return df.reset_index(drop=True)