Spaces:
Sleeping
Sleeping
Update data/schedule.py
Browse files- data/schedule.py +156 -74
data/schedule.py
CHANGED
|
@@ -1,78 +1,160 @@
|
|
| 1 |
from __future__ import annotations
|
| 2 |
|
| 3 |
-
import
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
WBC_STANDINGS_URL = "https://www.mlb.com/world-baseball-classic/standings"
|
| 18 |
-
|
| 19 |
-
# Baseball Savant WBC Statcast
|
| 20 |
-
WBC_STATCAST_SEARCH_URL = "https://baseballsavant.mlb.com/statcast-search-world-baseball-classic"
|
| 21 |
-
STATCAST_SEARCH_URL = "https://baseballsavant.mlb.com/statcast_search/csv"
|
| 22 |
-
|
| 23 |
-
# MLB enrichment / fallback
|
| 24 |
-
MLB_SCHEDULE_URL = "https://statsapi.mlb.com/api/v1/schedule"
|
| 25 |
-
MLB_TEAMS_URL = "https://statsapi.mlb.com/api/v1/teams"
|
| 26 |
-
|
| 27 |
-
# Weather
|
| 28 |
-
OPENWEATHER_URL = "https://api.openweathermap.org/data/2.5/weather"
|
| 29 |
-
|
| 30 |
-
# Odds
|
| 31 |
-
ODDS_SPORT_KEY = "baseball_mlb"
|
| 32 |
-
ODDS_BASE_URL = "https://api.the-odds-api.com/v4"
|
| 33 |
-
ODDS_REGIONS = "us"
|
| 34 |
-
ODDS_FEATURED_MARKETS = "h2h,spreads,totals"
|
| 35 |
-
ODDS_FORMAT = "american"
|
| 36 |
-
|
| 37 |
-
ODDS_API_KEY = os.getenv("ODDS_API_KEY", "")
|
| 38 |
-
OPENWEATHER_API_KEY = os.getenv("OPENWEATHER_API_KEY", "")
|
| 39 |
-
|
| 40 |
-
SUPPORTED_BOOKS = [
|
| 41 |
-
"DraftKings",
|
| 42 |
-
"FanDuel",
|
| 43 |
-
"BetMGM",
|
| 44 |
-
"Caesars",
|
| 45 |
-
"bet365",
|
| 46 |
-
"Pinnacle",
|
| 47 |
-
]
|
| 48 |
-
|
| 49 |
-
WBC_2026_VENUES = {
|
| 50 |
-
"Hiram Bithorn Stadium": {"lat": 18.3982, "lon": -66.0600, "city": "San Juan"},
|
| 51 |
-
"Daikin Park": {"lat": 29.7573, "lon": -95.3555, "city": "Houston"},
|
| 52 |
-
"Tokyo Dome": {"lat": 35.7056, "lon": 139.7519, "city": "Tokyo"},
|
| 53 |
-
"loanDepot park": {"lat": 25.7781, "lon": -80.2197, "city": "Miami"},
|
| 54 |
}
|
| 55 |
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
from __future__ import annotations
|
| 2 |
|
| 3 |
+
import json
|
| 4 |
+
import re
|
| 5 |
+
from datetime import datetime
|
| 6 |
+
from typing import Any
|
| 7 |
+
|
| 8 |
+
import pandas as pd
|
| 9 |
+
import requests
|
| 10 |
+
|
| 11 |
+
from config.settings import WBC_SCHEDULE_PAGE_URL
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
HEADERS = {
|
| 15 |
+
"User-Agent": "Mozilla/5.0",
|
| 16 |
+
"Accept-Language": "en-US,en;q=0.9",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
}
|
| 18 |
|
| 19 |
+
|
| 20 |
+
def _safe_text(value: Any) -> str:
|
| 21 |
+
if value is None:
|
| 22 |
+
return ""
|
| 23 |
+
return str(value).strip()
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
def _extract_next_data_json(html: str) -> dict[str, Any] | None:
|
| 27 |
+
patterns = [
|
| 28 |
+
r'<script id="__NEXT_DATA__" type="application/json">(.+?)</script>',
|
| 29 |
+
r'window\.__PRELOADED_STATE__\s*=\s*({.+?});',
|
| 30 |
+
]
|
| 31 |
+
|
| 32 |
+
for pattern in patterns:
|
| 33 |
+
match = re.search(pattern, html, flags=re.DOTALL)
|
| 34 |
+
if match:
|
| 35 |
+
raw = match.group(1)
|
| 36 |
+
try:
|
| 37 |
+
return json.loads(raw)
|
| 38 |
+
except json.JSONDecodeError:
|
| 39 |
+
continue
|
| 40 |
+
return None
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
def _rows_from_embedded_json(payload: dict[str, Any]) -> list[dict[str, Any]]:
|
| 44 |
+
rows: list[dict[str, Any]] = []
|
| 45 |
+
|
| 46 |
+
def walk(obj: Any) -> None:
|
| 47 |
+
if isinstance(obj, dict):
|
| 48 |
+
keys = set(obj.keys())
|
| 49 |
+
|
| 50 |
+
possible_game = (
|
| 51 |
+
("homeTeam" in keys or "home_team" in keys or "home" in keys)
|
| 52 |
+
and ("awayTeam" in keys or "away_team" in keys or "away" in keys)
|
| 53 |
+
)
|
| 54 |
+
|
| 55 |
+
if possible_game:
|
| 56 |
+
home_team = (
|
| 57 |
+
obj.get("homeTeam")
|
| 58 |
+
or obj.get("home_team")
|
| 59 |
+
or (obj.get("home") or {}).get("name")
|
| 60 |
+
or ""
|
| 61 |
+
)
|
| 62 |
+
away_team = (
|
| 63 |
+
obj.get("awayTeam")
|
| 64 |
+
or obj.get("away_team")
|
| 65 |
+
or (obj.get("away") or {}).get("name")
|
| 66 |
+
or ""
|
| 67 |
+
)
|
| 68 |
+
venue = obj.get("venue") or obj.get("venueName") or ""
|
| 69 |
+
status = obj.get("status") or obj.get("detailedState") or ""
|
| 70 |
+
game_id = obj.get("id") or obj.get("gamePk") or obj.get("game_id") or ""
|
| 71 |
+
game_date = obj.get("gameDate") or obj.get("date") or obj.get("commence_time") or ""
|
| 72 |
+
home_score = obj.get("homeScore")
|
| 73 |
+
away_score = obj.get("awayScore")
|
| 74 |
+
|
| 75 |
+
if home_team and away_team:
|
| 76 |
+
rows.append(
|
| 77 |
+
{
|
| 78 |
+
"fetched_at": datetime.utcnow(),
|
| 79 |
+
"game_id": _safe_text(game_id),
|
| 80 |
+
"game_date": _safe_text(game_date),
|
| 81 |
+
"status": _safe_text(status),
|
| 82 |
+
"away_team": _safe_text(away_team),
|
| 83 |
+
"home_team": _safe_text(home_team),
|
| 84 |
+
"away_score": away_score,
|
| 85 |
+
"home_score": home_score,
|
| 86 |
+
"venue": _safe_text(venue),
|
| 87 |
+
}
|
| 88 |
+
)
|
| 89 |
+
|
| 90 |
+
for value in obj.values():
|
| 91 |
+
walk(value)
|
| 92 |
+
|
| 93 |
+
elif isinstance(obj, list):
|
| 94 |
+
for item in obj:
|
| 95 |
+
walk(item)
|
| 96 |
+
|
| 97 |
+
walk(payload)
|
| 98 |
+
return rows
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
def _rows_from_schedule_text(html: str) -> list[dict[str, Any]]:
|
| 102 |
+
rows: list[dict[str, Any]] = []
|
| 103 |
+
|
| 104 |
+
lines = [line.strip() for line in html.splitlines() if line.strip()]
|
| 105 |
+
joined = "\n".join(lines)
|
| 106 |
+
|
| 107 |
+
matches = re.findall(r"([A-Z][A-Za-z .]+)\s+vs\.\s+([A-Z][A-Za-z .]+)", joined)
|
| 108 |
+
seen = set()
|
| 109 |
+
|
| 110 |
+
for away_team, home_team in matches:
|
| 111 |
+
key = (away_team, home_team)
|
| 112 |
+
if key in seen:
|
| 113 |
+
continue
|
| 114 |
+
seen.add(key)
|
| 115 |
+
rows.append(
|
| 116 |
+
{
|
| 117 |
+
"fetched_at": datetime.utcnow(),
|
| 118 |
+
"game_id": "",
|
| 119 |
+
"game_date": "",
|
| 120 |
+
"status": "",
|
| 121 |
+
"away_team": away_team.strip(),
|
| 122 |
+
"home_team": home_team.strip(),
|
| 123 |
+
"away_score": None,
|
| 124 |
+
"home_score": None,
|
| 125 |
+
"venue": "",
|
| 126 |
+
}
|
| 127 |
+
)
|
| 128 |
+
|
| 129 |
+
return rows
|
| 130 |
+
|
| 131 |
+
|
| 132 |
+
def fetch_wbc_schedule() -> pd.DataFrame:
|
| 133 |
+
response = requests.get(WBC_SCHEDULE_PAGE_URL, headers=HEADERS, timeout=30)
|
| 134 |
+
response.raise_for_status()
|
| 135 |
+
html = response.text
|
| 136 |
+
|
| 137 |
+
payload = _extract_next_data_json(html)
|
| 138 |
+
rows: list[dict[str, Any]] = []
|
| 139 |
+
|
| 140 |
+
if payload is not None:
|
| 141 |
+
rows = _rows_from_embedded_json(payload)
|
| 142 |
+
|
| 143 |
+
if not rows:
|
| 144 |
+
rows = _rows_from_schedule_text(html)
|
| 145 |
+
|
| 146 |
+
df = pd.DataFrame(rows)
|
| 147 |
+
|
| 148 |
+
if df.empty:
|
| 149 |
+
return df
|
| 150 |
+
|
| 151 |
+
df = df.drop_duplicates(subset=["game_id", "away_team", "home_team", "game_date"]).copy()
|
| 152 |
+
|
| 153 |
+
if "game_date" in df.columns:
|
| 154 |
+
try:
|
| 155 |
+
df["game_date_sort"] = pd.to_datetime(df["game_date"], errors="coerce")
|
| 156 |
+
df = df.sort_values(["game_date_sort", "away_team", "home_team"]).drop(columns=["game_date_sort"])
|
| 157 |
+
except Exception:
|
| 158 |
+
pass
|
| 159 |
+
|
| 160 |
+
return df.reset_index(drop=True)
|