Files
Profeto/src/data/injuries.py
T
shangfangjian 0980c2242a feat: P0-02/P0-03/P0-05 数据库时间语义与约束
P0-02: MatchStats 增加 source/source_record_id/retrieved_at/available_at
        context_builder 过滤统计数据时检查 available_at <= cutoff
P0-03: Prediction 增加 match_kickoff_at/prediction_created_at/prediction_cutoff_at
        明确区分比赛时间/预测创建时间/数据截止时间
P0-05: Prediction 增加 status 字段(success/failed/degraded)
        数据库 CHECK 约束

Alembic: 0005_prediction_status_and_stats_provenance

P1-02: injuries as_of 不再截断为 date,保持 datetime 精度
2026-09-15 02:04:25 +08:00

219 lines
7.0 KiB
Python

"""伤停数据采集器(api-football / api-sports.io)。
采集伤停数据并入库(injuries 表),供 injuries agent 使用。
"""
from __future__ import annotations
import asyncio
import json
import logging
import random
import time
from datetime import datetime, timezone
from pathlib import Path
from typing import Any
import httpx
from src.core.config import settings
from src.core.http_client import get_client
logger = logging.getLogger(__name__)
API_BASE = "https://v3.football.api-sports.io"
DEFAULT_HOST = "v3.football.api-sports.io"
# 缓存目录
_CACHE_DIR = Path(__file__).resolve().parent.parent.parent / "data" / "injuries_cache"
async def fetch_injuries(*, date: str | None = None, fixture_id: int | None = None, league_id: int | None = None) -> list[dict]:
"""采集伤停数据。
Args:
date: 日期 (YYYY-MM-DD),返当天全部伤停
fixture_id: 指定比赛 ID
league_id: 指定联赛 ID
Returns:
伤停记录列表
"""
api_key = settings.API_FOOTBALL_KEY
if not api_key:
raise RuntimeError("API_FOOTBALL_KEY 未设置")
cache_dir = _CACHE_DIR
cache_dir.mkdir(parents=True, exist_ok=True)
# 缓存命中 (7 天内有效)
cache_key = f"injuries_{date}_{fixture_id}_{league_id}.json"
cache_file = cache_dir / cache_key
if cache_file.exists():
age_hours = (time.time() - cache_file.stat().st_mtime) / 3600
if age_hours < 168: # 7 天
logger.debug("injuries cache hit: %s (%.1fh old)", cache_key, age_hours)
with open(cache_file, encoding="utf-8") as f:
return json.load(f)
else:
logger.debug("injuries cache expired: %s (%.1fh old)", cache_key, age_hours)
headers = {
"x-apisports-key": api_key,
"x-rapidapi-host": DEFAULT_HOST,
}
params: dict[str, Any] = {}
if date:
params["date"] = date
if fixture_id:
params["fixture"] = fixture_id
if league_id:
params["league"] = league_id
url = f"{API_BASE}/injuries"
# 重试
last_exc: Exception | None = None
for attempt in range(3):
try:
client = get_client()
resp = await client.get(url, headers=headers, params=params, timeout=30)
resp.raise_for_status()
break
except Exception as e:
last_exc = e
if attempt == 2:
raise
delay = min(2 ** attempt, 8) + random.uniform(0, 1)
logger.warning("injuries fetch failed, retry %d in %.1fs: %s", attempt + 1, delay, e)
await asyncio.sleep(delay)
else:
raise RuntimeError(f"injuries fetch failed: {last_exc}")
data = resp.json()
injuries = data.get("response", [])
# 写缓存
with open(cache_file, "w", encoding="utf-8") as f:
json.dump(injuries, ensure_ascii=False, default=str, fp=f)
return injuries
async def ingest_injuries(db, *, date: str | None = None) -> dict:
"""采集伤停数据并入库(injuries 表)。
注意: 本方法不控制事务(commit/rollback),由调用方通过 UnitOfWork 控制。
"""
from sqlalchemy import select
from src.data.team_names import normalize as normalize_name
from src.db.models import Injury, Team
result = {"count": 0, "inserted": 0, "errors": []}
try:
raw_injuries = await fetch_injuries(date=date)
except Exception as e:
logger.exception("injuries fetch failed")
result["errors"].append(f"fetch failed: {e}")
return result
result["count"] = len(raw_injuries)
# 预加载所有球队(用于按名匹配)
teams = (await db.execute(select(Team))).scalars().all()
team_by_name = {t.name: t.id for t in teams}
for raw in raw_injuries:
try:
player = raw.get("player", {}) or {}
team = raw.get("team", {}) or {}
fixture = raw.get("fixture", {}) or {}
player_name = player.get("name", "")
team_name = normalize_name(team.get("name", ""))
team_id = team_by_name.get(team_name)
# 解析日期
fixture_date = fixture.get("date")
injury_date = None
if fixture_date:
try:
dt = datetime.fromisoformat(fixture_date.replace("Z", "+00:00"))
injury_date = dt.date()
except (ValueError, AttributeError):
pass
player_id = player.get("id")
fixture_id = fixture.get("id")
# 幂等: 已存在则跳过
existing = (
await db.execute(
select(Injury).where(
Injury.player_id == player_id,
Injury.fixture_id == fixture_id,
Injury.injury_type == player.get("type"),
)
)
).scalar_one_or_none()
if existing is not None:
continue
injury = Injury(
player_id=player_id,
player_name=player_name,
team_id=team_id,
fixture_id=fixture_id,
league_id=(raw.get("league") or {}).get("id"),
injury_type=player.get("type"),
reason=player.get("reason"),
injury_date=injury_date,
)
db.add(injury)
result["inserted"] += 1
except Exception as e:
result["errors"].append(f"parse error: {e}")
# 注意: 不在此处 commit,由调用方 UnitOfWork 控制事务
logger.info("injuries: fetched %d, inserted %d for %s", result["count"], result["inserted"], date)
return result
async def get_injuries_for_match(db, team_id: int, match_date, as_of=None) -> list[Injury]:
"""查询某场比赛前某队的伤停名单(比赛日仍缺阵的)。
Args:
db: 数据库 session
team_id: 球队 ID
match_date: 比赛日期
as_of: 截止时间(cutoff)。只返回 retrieved_at <= as_of 的记录。
用于回测时防止"未来采集的数据"泄漏到历史预测。
必须保持 timezone-aware datetime,不会截断为 date。
"""
from sqlalchemy import or_, select
from src.db.models import Injury
# 只处理 match_date:去掉时间部分,仅比较日期
if hasattr(match_date, "date"):
match_date = match_date.date()
stmt = (
select(Injury)
.where(Injury.team_id == team_id)
.where(Injury.injury_date <= match_date)
.where(or_(Injury.return_date.is_(None), Injury.return_date >= match_date))
)
# 回测防泄漏: 只使用 as_of 时间点之前已采集的数据
# 注意: as_of 保持 datetime,不截断为 date,避免错误排除同日合法数据
if as_of is not None:
stmt = stmt.where(Injury.retrieved_at.is_not(None))
stmt = stmt.where(Injury.retrieved_at <= as_of)
stmt = stmt.order_by(Injury.injury_date.desc())
result = await db.execute(stmt)
return list(result.scalars().all())