refactor: bzzoiro.py 按管线拆分为 5 个模块

单文件 852 行按职责拆分,保持 BzzoiroSource 与 get_source("bzzoiro") 行为不变:
- bzzoiro_common  HTTP 抓取(多 key 轮换) + 字段转换原语
- bzzoiro_events   fetch_bzzoiro_events + BzzoiroSource.ingest + Bronze 补写
- bzzoiro_standings  standings 管线
- bzzoiro_stats     stats 回填
- pipeline_write    RawEvent/IngestFailure/DataLineage 写入助手

子模块运行期经聚合门面 src.data.bzzoiro 解析可替换协作者,
单文件时代的 bz.* monkeypatch 语义完全保留。
路由 import 已指向新模块(ingest.py / schedules.py)。
This commit is contained in:
shangfangjian
2026-09-21 23:27:48 +08:00
parent 7a5c695b89
commit 317a5e338a
10 changed files with 984 additions and 796 deletions
+2 -1
View File
@@ -16,7 +16,8 @@ from fastapi import APIRouter, Depends, HTTPException
from src.api.deps import require_admin
from src.api.schemas import IngestBzzoiroRequest
from src.data.config import BZZOIRO_LEAGUE_IDS
from src.data.bzzoiro import ingest_bzzoiro_event_stats, ingest_bzzoiro_standings
from src.data.bzzoiro_standings import ingest_bzzoiro_standings
from src.data.bzzoiro_stats import ingest_bzzoiro_event_stats
from src.data.sources import get_source
from src.db.unit_of_work import get_uow
+2 -1
View File
@@ -10,7 +10,8 @@ from sqlalchemy import select, delete
from src.api.deps import require_admin
from src.api.schemas import ScheduleIn, ScheduleUpdate, ScheduleOut
from src.core.scheduler import scheduler
from src.data.bzzoiro import ingest_bzzoiro_event_stats, ingest_bzzoiro_standings
from src.data.bzzoiro_standings import ingest_bzzoiro_standings
from src.data.bzzoiro_stats import ingest_bzzoiro_event_stats
from src.data.sources import get_source
from src.data.config import BZZOIRO_LEAGUE_IDS
from src.db.base import AsyncSession, get_db_read
+65 -787
View File
@@ -1,793 +1,71 @@
"""Bzzoiro 数据源:抓取 + 入库(单一数据源)。
"""Bzzoiro 数据源:抓取 + 入库(单一数据源)—— 聚合门面
三条管线:
1. events — 比赛日程/比分(/events/),含 source_event_id 血缘
2. standings— 联赛积分榜快照(/leagues/{id}/standings/)
3. stats — 已完赛比赛详细统计回填(/events/{id}/stats/)
实现按管线拆分(单文件 → 多模块),本模块只做再导出,保持两个不变量:
1. sources._load_sources() 仍从本模块导入 BzzoiroSource(注册表入口不变);
2. 测试与脚本对 `bz.<名称>` 的 monkeypatch 语义不变 —— 子模块在运行期
经本门面解析可替换协作者(抓取函数 / Bronze 写入助手 / REQUEST_INTERVAL),
与拆分前的单文件行为一致。
三条管线(各自模块):
1. events — 比赛日程/比分(/events/),含 source_event_id 血缘 → bzzoiro_events.py
2. standings— 联赛积分榜快照(/leagues/{id}/standings/) → bzzoiro_standings.py
3. stats — 已完赛比赛详细统计回填(/events/{id}/stats/) → bzzoiro_stats.py
共享基础:HTTP 抓取(多 key 轮换)与字段转换 → bzzoiro_common.py;
Bronze 基础设施(RawEvent/IngestFailure/DataLineage)→ pipeline_write.py。
D4(工程债): Team/League/Match 的查找/创建经 Repository 层(src/db/repositories.py),
本模块不直接控制事务(commit/rollback 由调用方 UnitOfWork 控制,这里只 flush)。
Standing/RawEvent/Lineage 等管线内私有读写仍在本模块内实现,不强行 Repository 化。
各管线不直接控制事务(commit/rollback 由调用方 UnitOfWork 控制,只 flush)。
Standing/RawEvent/Lineage 等管线内私有读写仍不强行 Repository 化。
"""
from __future__ import annotations
import asyncio
import logging
import random
from collections.abc import Iterable
from datetime import datetime, timedelta, timezone
from sqlalchemy import select
import httpx
from src.core.runtime_config import get_runtime_value
from src.core.http_client import get_client
from src.data.config import BZZOIRO_LEAGUE_IDS, LEAGUE_COUNTRIES, LEAGUE_NAMES, REQUEST_INTERVAL
from src.data.key_ring import _mask, get_key_ring
from src.data.normalize import normalize_bzzoiro
from src.data.team_names_zh import zh_name
from src.data.sources import register
from src.db.models import Match, MatchStats, Standing, Team, RawEvent, IngestFailure, DataLineage
from src.db.repositories import LeagueRepository, MatchRepository, TeamRepository
logger = logging.getLogger(__name__)
def _to_date(value):
"""把 datetime / date / str 统一成 `date`。"""
if value is None:
return None
if hasattr(value, "date") and callable(value.date):
return value.date()
return value
def _to_int_or_none(value) -> int | None:
"""宽松转 int(用于上游 ID 解析,失败返回 None 不抛错)。"""
if value is None:
return None
try:
return int(str(value).strip())
except (TypeError, ValueError):
return None
def _match_key(home_team_id: int, away_team_id: int, match_date) -> tuple[int, int, str]:
"""比赛去重键:(主队, 客队, 天级日期 ISO 字符串)。
统一在这里构造,避免"预加载时用 str(date)、写入时用 isoformat()"这类
隐式格式依赖 —— 两者当前恰好相等,但一旦有人改动其一就会静默失配,
导致所有比赛被判为不存在而重复插入。
"""
d = _to_date(match_date)
return (home_team_id, away_team_id, d.isoformat() if d is not None else "")
async def _fetch_json_async(path: str, params: dict | None = None, max_retries: int = 3) -> dict | list:
"""异步 HTTP(bzzoiro 使用 httpx,不再阻塞事件循环线程池)。
多 key 轮换:遇到 429 自动切换到下一个 key;全部 key 冷却时等待最早恢复。
"""
base = (await get_runtime_value("BZZOIRO_BASE")).rstrip("/")
raw_keys = await get_runtime_value("BZZOIRO_KEY")
ring = get_key_ring(base, raw_keys)
url = f"{base}/{path.lstrip('/')}"
key = ring.get()
if not key:
raise RuntimeError("BZZOIRO_KEY 未设置")
last_exc: Exception | None = None
for attempt in range(max_retries):
headers = {
"Authorization": f"Token {key}",
"Accept": "application/json",
}
try:
client = get_client()
# 整请求兜底: httpx 无 total 超时,用 wait_for 防「滴水式」限速挂死
resp = await asyncio.wait_for(
client.get(
url, headers=headers, params=params,
timeout=httpx.Timeout(connect=10.0, read=30.0, write=10.0, pool=10.0),
),
timeout=60.0,
)
resp.raise_for_status()
return resp.json()
except Exception as e:
last_exc = e
status = getattr(getattr(e, "response", None), "status_code", None)
if status == 429:
# 限流:标记当前 key 冷却,切换到下一个
new_key = ring.report_rate_limited(key)
if new_key and new_key != key:
logger.info("bzzoiro 429 → 切换 key: %s%s,立即重试", _mask(key), _mask(new_key))
key = new_key
continue # 立即重试,不等待
# 单 key 或全部冷却:等待最早恢复的 key
wait = ring.wait_if_all_blocked()
if wait > 0:
logger.warning("bzzoiro 全部 key 冷却,等待 %.1fs 后重试", wait)
await asyncio.sleep(min(wait, 30.0))
else:
delay = min(2 ** attempt, 16) + random.uniform(0, 1)
logger.warning("bzzoiro 429, retry %d in %.1fs", attempt + 1, delay)
await asyncio.sleep(delay)
key = ring.get() or key
continue
if 500 <= (status or 0) < 600:
delay = min(2 ** attempt, 16) + random.uniform(0, 1)
logger.warning("bzzoiro %d, retry %d in %.1fs", status, attempt + 1, delay)
await asyncio.sleep(delay)
continue
# 网络错误(连接失败/超时)也退避重试
if isinstance(e, (TimeoutError, ConnectionError, OSError)):
delay = min(2 ** attempt, 16) + random.uniform(0, 1)
logger.warning("bzzoiro network error, retry %d in %.1fs: %s", attempt + 1, delay, e)
await asyncio.sleep(delay)
continue
raise
raise RuntimeError(f"bzzoiro request failed after {max_retries} attempts: {last_exc}")
async def fetch_bzzoiro_events(
league_code: str,
*,
status: str = "finished",
date_from: str | None = None,
date_to: str | None = None,
limit: int = 200,
) -> list[dict]:
"""抓取 bzzoiro 原始事件(纯异步,无需 run_in_executor)。"""
league_id = BZZOIRO_LEAGUE_IDS.get(league_code)
if league_id is None:
raise ValueError(f"未知联赛代码: {league_code}")
rows: list[dict] = []
offset = 0
while True:
params: dict = {
"league_id": league_id,
"status": status,
"limit": limit,
"offset": offset,
}
if date_from:
params["date_from"] = str(date_from)[:10]
if date_to:
params["date_to"] = str(date_to)[:10]
payload = await _fetch_json_async("/events/", params)
batch = payload.get("results") or []
if not batch:
break
rows.extend(batch)
total = payload.get("total")
offset += limit
if total is not None and offset >= total:
break
if len(batch) < limit:
break
await asyncio.sleep(REQUEST_INTERVAL)
return rows
@register
class BzzoiroSource:
"""bzzoiro 数据源(实现 DataSource 协议)。"""
name = "bzzoiro"
async def ingest(
self,
db,
*,
leagues: Iterable[str],
date_from: str | None = None,
date_to: str | None = None,
status: str = "finished",
) -> dict:
"""采集 bzzoiro → 入库。返回统计。
注意: 本方法不控制事务(commit/rollback),由调用方通过 UnitOfWork 控制。
"""
result: dict = {"leagues": {}, "total_inserted": 0, "total_updated": 0, "errors": []}
for code in leagues:
league_r: dict = {"inserted": 0, "updated": 0, "errors": []}
try:
raw_events = await fetch_bzzoiro_events(code, status=status, date_from=date_from, date_to=date_to)
except Exception as e:
# 单联赛抓取失败隔离:记录错误后继续其余联赛,不拖垮整批
logger.exception("bzzoiro fetch failed for %s", code)
league_r["errors"].append(f"fetch failed: {e}")
await _safe_write_ingest_failure(
db,
entity_type="events",
source_record_id=None,
error=e,
raw_payload={"league": code, "status": status, "date_from": date_from, "date_to": date_to},
)
result["leagues"][code] = league_r
continue
# D4: 联赛查找/创建经 LeagueRepository(事务仍由调用方 UoW 提交)
league = await LeagueRepository(db).get_or_create(
code, LEAGUE_NAMES.get(code, code), LEAGUE_COUNTRIES.get(code)
)
team_r = TeamRepository(db)
match_r = MatchRepository(db)
# === 批量优化: 预加载球队和已有比赛到内存 ===
team_name_to_id: dict[str, int] = {}
existing_matches: dict[tuple[int, int, str], Match] = {} # 完整对象,避免重复查询
# (NormalizedMatch, 原始 event) 成对保存:后续写 source_event_id 时
# 必须用配对的那条 event,不能依赖外层循环变量残留值。
normalized_matches: list[tuple] = []
if raw_events:
# 一次遍历: 收集球队名 + 规范化
all_team_names = set()
for raw in raw_events:
nm = normalize_bzzoiro(raw, code)
if nm is not None:
try:
nm.validate()
except Exception as e:
# P1-3: 统一使用 warning,不追加到 errors(仅运行时错误入 errors)
logger.warning("normalize skip: %s", e)
continue
normalized_matches.append((nm, raw))
all_team_names.add(nm.home_team)
all_team_names.add(nm.away_team)
if all_team_names:
team_name_to_id = {
name: t.id
for name, t in (await team_r.get_all_by_names(list(all_team_names))).items()
}
# P1-2: 按需加载,只加载 raw_events 涉及日期范围的比赛(加 30 天缓冲)
# 避免加载联赛全部历史比赛到内存(多赛季采集时内存溢出)
if normalized_matches:
# normalized_matches 存的是 (nm, raw) 元组,遍历需解包
dates = [nm.date for nm, _raw in normalized_matches if nm.date is not None]
if dates:
min_dt = min(dates) - timedelta(days=30)
max_dt = max(dates) + timedelta(days=30)
matches_in_range = await match_r.find_by_league_and_date_range(
league.id, min_dt, max_dt
)
existing_matches = {
_match_key(m.home_team_id, m.away_team_id, m.match_date_date): m
for m in matches_in_range
}
# else: existing_matches 保持空 dict(全量新比赛)
# D1: Bronze 层批次信息(每联赛每批次一个 batch_id;seen 防同批重复写入)
now = datetime.now(timezone.utc)
bronze_batch_id = f"bzzoiro-events-{code}-{now:%Y%m%d%H%M%S}"
bronze_written: set[str] = set()
for nm, raw in normalized_matches:
# D1: RawEvent 幂等键(上游 id 或合成键),插入/变更更新共用
record_id = _events_record_id(code, nm, raw)
# 球队: 内存查找 + 按需创建(D4: 经 TeamRepository)
home_team_id = team_name_to_id.get(nm.home_team)
if home_team_id is None:
home = await team_r.get_or_create(nm.home_team, name_zh=zh_name(nm.home_team))
home_team_id = home.id
team_name_to_id[nm.home_team] = home_team_id
away_team_id = team_name_to_id.get(nm.away_team)
if away_team_id is None:
away = await team_r.get_or_create(nm.away_team, name_zh=zh_name(nm.away_team))
away_team_id = away.id
team_name_to_id[nm.away_team] = away_team_id
# 查找已有比赛: 内存查找
match_key = _match_key(home_team_id, away_team_id, nm.date)
existing_match = existing_matches.get(match_key)
if existing_match is None:
m = Match(
league_id=league.id,
season=nm.season_label or None,
home_team_id=home_team_id,
away_team_id=away_team_id,
match_date=nm.date,
match_date_date=_to_date(nm.date),
match_status=nm.match_status,
home_goals=nm.home_goals,
away_goals=nm.away_goals,
home_ht_goals=nm.home_ht_goals,
away_ht_goals=nm.away_ht_goals,
match_stage=nm.match_stage,
source_event_id=_to_int_or_none(raw.get("id")),
)
db.add(m)
await db.flush()
existing_matches[match_key] = m # 防止同批重复
# 统计字段不在 /events/ 载荷中(单独由 stats 管线回填),
# 此处不再创建 MatchStats。
league_r["inserted"] += 1
# D1: 成功插入 → 补写 Bronze 层(原始载荷 + 血缘)
if record_id not in bronze_written:
bronze_written.add(record_id)
await _write_events_bronze(
db,
source_record_id=record_id,
raw_payload=raw,
target_match_id=m.id,
league_code=code,
match_status=nm.match_status,
batch_id=bronze_batch_id,
)
else:
# 已有比赛: 直接从内存获取对象更新(无需再查询)
changed = False
if existing_match.match_status != nm.match_status and nm.match_status == "finished":
existing_match.match_status = nm.match_status
changed = True
if existing_match.home_goals is None and nm.home_goals is not None:
existing_match.home_goals = nm.home_goals
existing_match.away_goals = nm.away_goals
existing_match.home_ht_goals = nm.home_ht_goals
existing_match.away_ht_goals = nm.away_ht_goals
changed = True
if existing_match.match_stage is None and nm.match_stage:
existing_match.match_stage = nm.match_stage
changed = True
if existing_match.source_event_id is None:
eid = _to_int_or_none(raw.get("id"))
if eid is not None:
existing_match.source_event_id = eid
changed = True
if changed:
league_r["updated"] += 1
# D1: 变更更新 → 补写血缘(RawEvent 幂等键不变,重复采集自动跳过)
if record_id not in bronze_written:
bronze_written.add(record_id)
await _write_events_bronze(
db,
source_record_id=record_id,
raw_payload=raw,
target_match_id=existing_match.id,
league_code=code,
match_status=nm.match_status,
batch_id=bronze_batch_id,
)
# 注意: 不在此处 commit,由调用方 UnitOfWork 控制事务
result["leagues"][code] = league_r
result["total_inserted"] += league_r["inserted"]
result["total_updated"] += league_r["updated"]
return result
# ============================================================
# 管线基础设施:RawEvent / IngestFailure / DataLineage
# ============================================================
async def _write_raw_event(db, source_system: str, source_record_id: str, raw_payload: dict, batch_id: str | None = None) -> None:
"""写入 Bronze 层原始事件(幂等:同 source_record_id 跳过)。"""
from sqlalchemy import select as _select
stmt = _select(RawEvent).where(
RawEvent.source_system == source_system,
RawEvent.source_record_id == source_record_id,
)
existing = (await db.execute(stmt)).scalar_one_or_none()
if existing is None:
db.add(RawEvent(
source_system=source_system,
source_record_id=source_record_id,
raw_payload=raw_payload,
ingest_batch_id=batch_id,
))
async def _write_ingest_failure(db, source_system: str, entity_type: str, source_record_id: str | None, error_type: str, error_detail: str | None, raw_payload: dict | None = None) -> None:
"""写入采集失败死信。"""
db.add(IngestFailure(
source_system=source_system,
entity_type=entity_type,
source_record_id=source_record_id,
error_type=error_type,
error_detail=error_detail,
raw_payload=raw_payload,
))
async def _safe_write_ingest_failure(
db,
*,
entity_type: str,
source_record_id: str | None,
error: Exception,
raw_payload: dict | None = None,
) -> None:
"""抓取失败时尽力写入死信表(失败不影响主流程)。
死信是「可观测性」基础设施,与 RawEvent/Lineage 同级:写入失败只记
warning,绝不能让原始抓取错误之外的新异常打断采集循环。
"""
try:
await _write_ingest_failure(
db, "bzzoiro", entity_type, source_record_id,
"fetch_error", str(error), raw_payload,
)
except Exception:
logger.warning(
"写入 ingest_failures 死信失败(entity=%s, record=%s): %s",
entity_type, source_record_id, error, exc_info=True,
)
async def _write_lineage(db, source_system: str, source_record_id: str, target_table: str, target_id: int | None, transform_name: str, transform_detail: dict | None = None, batch_id: str | None = None) -> None:
"""写入 ETL 血缘追踪。"""
db.add(DataLineage(
source_system=source_system,
source_record_id=source_record_id,
target_table=target_table,
target_id=target_id,
transform_name=transform_name,
transform_detail=transform_detail,
batch_id=batch_id,
))
def _events_record_id(league_code: str, nm, raw: dict) -> str:
"""events 载荷的 RawEvent 幂等键。
优先用上游 event id;缺失时用 (league:home:away:date) 合成稳定键 ——
取 normalize 后的队名与天级日期(与 _match_key 同口径),不依赖 DB 自增 id,
保证同一来源比赛重复采集时命中同一条 RawEvent,不产生重复原始载荷。
"""
eid = _to_int_or_none(raw.get("id"))
if eid is not None:
return str(eid)
d = _to_date(nm.date)
date_part = d.isoformat() if d is not None else "na"
return f"{league_code}:{nm.home_team}:{nm.away_team}:{date_part}"
async def _write_events_bronze(
db,
*,
source_record_id: str,
raw_payload: dict,
target_match_id: int | None,
league_code: str,
match_status: str | None,
batch_id: str,
) -> None:
"""events 成功插入/更新单场比赛后的 Bronze 层补写:RawEvent(幂等) + DataLineage。
D1(工程债):此前只有 stats 回填写 RawEvent/Lineage,events 管线作为比赛
主数据的唯一入口反而不留溯源记录。幂等性由 _write_raw_event 的
source_record_id 查重保证;best-effort:基础设施写入失败只记 warning,
绝不拖垮采集主流程(与 _safe_write_ingest_failure 同级约束)。
"""
try:
await _write_raw_event(db, "bzzoiro", source_record_id, raw_payload, batch_id)
await _write_lineage(
db, "bzzoiro", source_record_id,
"matches", target_match_id, "events_ingest",
{"league": league_code, "match_status": match_status},
batch_id,
)
except Exception:
logger.warning(
"events Bronze 写入失败(record=%s, match=%s),不影响采集主流程",
source_record_id, target_match_id, exc_info=True,
)
# ============================================================
# 积分榜管线:/leagues/{id}/standings/ → standings 表
# ============================================================
async def fetch_bzzoiro_standings(league_code: str, season: str | None = None) -> dict:
"""抓取联赛积分榜(纯抓取,不入库)。season 为 None 时取当前赛季。"""
league_id = BZZOIRO_LEAGUE_IDS.get(league_code)
if league_id is None:
raise ValueError(f"未知联赛代码: {league_code}")
params: dict = {}
if season:
params["season"] = season
return await _fetch_json_async(f"/leagues/{league_id}/standings/", params)
def _season_label_from_dates(start_date, end_date) -> str:
"""从赛季起止日期推导赛季标签(与 derive_season_label 语义一致)。"""
try:
if isinstance(start_date, str):
start = datetime.fromisoformat(start_date[:10])
else:
start = start_date
y = start.year
return f"{y}-{y + 1}" if start.month >= 8 else f"{y - 1}-{y}"
except (TypeError, ValueError):
return "?"
async def ingest_bzzoiro_standings(db, *, leagues: Iterable[str], season: str | None = None) -> dict:
"""采集积分榜 → upsert standings 表。
season 为 None 时采集当前赛季(bzzoiro 默认返回 is_current 赛季)。
球队名与 events 管线使用同一 normalize 规则,保证 Team 匹配。
"""
from src.data.team_names import normalize as normalize_name
result: dict = {"leagues": {}, "total_upserted": 0, "errors": []}
for code in leagues:
league_r: dict = {"upserted": 0, "teams_created": 0, "rows": 0, "errors": []}
try:
payload = await fetch_bzzoiro_standings(code, season=season)
except Exception as e:
logger.exception("bzzoiro standings fetch failed for %s", code)
league_r["errors"].append(str(e))
await _safe_write_ingest_failure(
db,
entity_type="standings",
source_record_id=None,
error=e,
raw_payload={"league": code, "season": season},
)
result["leagues"][code] = league_r
result["errors"].append(f"{code}: {e}")
continue
rows = payload.get("standings") or []
if not rows:
result["leagues"][code] = {"error": "无积分榜数据(赛季未开始或未提供)"}
result["errors"].append(f"{code}: 无积分榜数据")
continue
# 联赛(get-or-create,D4: 经 LeagueRepository)
league = await LeagueRepository(db).get_or_create(
code, LEAGUE_NAMES.get(code, code), LEAGUE_COUNTRIES.get(code)
)
team_r = TeamRepository(db)
# 赛季标签:优先用返回的 season 对象推导
season_obj = payload.get("season") or {}
season_label = _season_label_from_dates(
season_obj.get("start_date"), season_obj.get("end_date")
)
if season_label == "?":
season_label = season or ""
# 批量预载球队(与 events 管线使用同一 normalize 规则,保证 Team 匹配)
names = {normalize_name(str(r.get("team_name", ""))) for r in rows}
names.discard("")
team_map: dict[str, Team] = await team_r.get_all_by_names(list(names))
now = datetime.now(timezone.utc)
for r in rows:
team_name = normalize_name(str(r.get("team_name", "")))
if not team_name:
continue
team = team_map.get(team_name)
if team is None:
team = await team_r.get_or_create(team_name, name_zh=zh_name(team_name))
team_map[team_name] = team
league_r["teams_created"] += 1
zone = r.get("zone") or {}
values = dict(
position=_to_int_or_none(r.get("position")) or 0,
played=_to_int_or_none(r.get("played")) or 0,
won=_to_int_or_none(r.get("won")) or 0,
drawn=_to_int_or_none(r.get("drawn")) or 0,
lost=_to_int_or_none(r.get("lost")) or 0,
goals_for=_to_int_or_none(r.get("gf")) or 0,
goals_against=_to_int_or_none(r.get("ga")) or 0,
goal_diff=_to_int_or_none(r.get("gd")) or 0,
points=_to_int_or_none(r.get("pts")) or 0,
xg_for=_to_float_or_none(r.get("xgf")),
xg_against=_to_float_or_none(r.get("xga")),
form=r.get("form") or None,
zone=zone.get("label") or zone.get("key") or None,
updated_at=now,
retrieved_at=now,
)
# 同一联赛同一赛季只保留最新快照:按 (league, season, team) upsert
stmt = select(Standing).where(
Standing.league_id == league.id,
Standing.season == season_label,
Standing.team_id == team.id,
)
standing = (await db.execute(stmt)).scalar_one_or_none()
if standing is None:
standing = Standing(
league_id=league.id, season=season_label, team_id=team.id, **values
)
db.add(standing)
else:
for k, v in values.items():
setattr(standing, k, v)
league_r["upserted"] += 1
league_r["rows"] = len(rows)
result["leagues"][code] = league_r
result["total_upserted"] += league_r["upserted"]
logger.info(
"bzzoiro standings 采集完成: %s 赛季 %s, upsert %d/%d",
code, season_label, league_r["upserted"], league_r["rows"],
)
return result
# ============================================================
# 统计回填管线:/events/{id}/stats/ → match_stats 表
# ============================================================
# bzzoiro stats 字段 → MatchStats 字段映射(stats.home / stats.away 下)
_STATS_FIELD_MAP = {
"xg": ("home_xg", "away_xg"), # 回退 expected_goals
"ball_possession": ("home_possession", None), # 只取主队值,客队=100-home
"total_shots": ("home_shots", "away_shots"),
"shots_on_target": ("home_shots_on_target", "away_shots_on_target"),
"corner_kicks": ("home_corners", "away_corners"),
"yellow_cards": ("home_yellow_cards", "away_yellow_cards"),
"red_cards": ("home_red_cards", "away_red_cards"),
"big_chances": ("home_big_chances", "away_big_chances"),
"fouls": ("home_fouls", "away_fouls"),
}
def _pick(d: dict, *keys):
"""按优先级取第一个非空字段值。"""
for k in keys:
v = d.get(k)
if v is not None:
return v
return None
def _stats_from_payload(payload: dict) -> dict:
"""把 /events/{id}/stats/ 响应映射成 MatchStats 字段 dict。
响应结构: {"event_id": ..., "stats": {"home": {...}, "away": {...}}}
"""
stats = (payload or {}).get("stats") or {}
home = stats.get("home") or {}
away = stats.get("away") or {}
out: dict = {}
xg_h = _pick(home, "xg", "expected_goals")
xg_a = _pick(away, "xg", "expected_goals")
if xg_h is not None:
out["home_xg"] = _to_float_or_none(xg_h)
if xg_a is not None:
out["away_xg"] = _to_float_or_none(xg_a)
poss = home.get("ball_possession")
if poss is not None:
p = _to_float_or_none(poss)
if p is not None:
out["home_possession"] = p
for src, (h_fld, a_fld) in _STATS_FIELD_MAP.items():
if src in ("xg", "ball_possession"):
continue # 已处理
hv = home.get(src)
av = away.get(src)
if hv is not None and h_fld:
out[h_fld] = _to_int_or_none(hv)
if av is not None and a_fld:
out[a_fld] = _to_int_or_none(av)
return out
def _to_float_or_none(value) -> float | None:
if value is None:
return None
try:
return float(str(value).strip())
except (TypeError, ValueError):
return None
async def ingest_bzzoiro_event_stats(
db,
*,
leagues: Iterable[str],
limit: int = 100,
only_missing: bool = True,
) -> dict:
"""回填已完赛比赛的详细统计(逐场调 /events/{id}/stats/)。
筛选条件: match_status=finished 且 source_event_id 非空。
only_missing=True 时跳过已有统计的比赛(增量);False 则全量刷新。
limit 控制单次最多处理的比赛数(上游限速 1.2s/请求,大批量需分次触发)。
"""
result: dict = {"fetched": 0, "created": 0, "updated": 0, "skipped": 0, "errors": []}
league_ids = [BZZOIRO_LEAGUE_IDS[c] for c in leagues if c in BZZOIRO_LEAGUE_IDS]
if not league_ids:
result["errors"].append("无有效联赛代码")
return result
# D4: 候选比赛查询经 MatchRepository(含 stats 预加载,筛选/排序/limit 语义不变)
matches = await MatchRepository(db).find_finished_with_stats(
league_ids, limit=limit * 3 if only_missing else limit
)
now = datetime.now(timezone.utc)
processed = 0
for m in matches:
if processed >= limit:
break
if only_missing and m.stats is not None and m.stats.home_shots is not None:
result["skipped"] += 1
continue
processed += 1
try:
payload = await _fetch_json_async(f"/events/{m.source_event_id}/stats/")
except Exception as e:
logger.warning("stats fetch failed match=%s event=%s: %s", m.id, m.source_event_id, e)
result["errors"].append(f"match {m.id}: {e}")
await _safe_write_ingest_failure(
db,
entity_type="match_stats",
source_record_id=str(m.source_event_id),
error=e,
raw_payload={"match_id": m.id},
)
await asyncio.sleep(REQUEST_INTERVAL)
continue
result["fetched"] += 1
fields = _stats_from_payload(payload)
if not fields:
result["skipped"] += 1
await asyncio.sleep(REQUEST_INTERVAL)
continue
if m.stats is None:
available_at = m.match_date + timedelta(hours=2) if m.match_date else now
m.stats = MatchStats(
match_id=m.id,
source="bzzoiro",
source_record_id=str(m.source_event_id),
retrieved_at=now,
available_at=available_at,
)
db.add(m.stats)
result["created"] += 1
else:
result["updated"] += 1
if m.stats.source is None:
m.stats.source = "bzzoiro"
m.stats.source_record_id = str(m.source_event_id)
if m.stats.retrieved_at is None:
m.stats.retrieved_at = now
if m.stats.available_at is None and m.match_date:
m.stats.available_at = m.match_date + timedelta(hours=2)
for fld, v in fields.items():
if hasattr(m.stats, fld):
setattr(m.stats, fld, v)
# 管线基础设施:写入 RawEvent + DataLineage
batch_id = f"bzzoiro-stats-{m.source_event_id}-{now.strftime('%Y%m%d%H%M%S')}"
try:
await _write_raw_event(db, "bzzoiro", str(m.source_event_id), payload, batch_id)
await _write_lineage(db, "bzzoiro", str(m.source_event_id), "match_stats", m.stats.id if m.stats else None, "stats_backfill", {"match_id": m.id}, batch_id)
except Exception:
pass # 基础设施写入失败不影响主流程
await asyncio.sleep(REQUEST_INTERVAL)
logger.info(
"bzzoiro stats 回填完成: 抓取 %d, 新建 %d, 更新 %d, 跳过 %d, 错误 %d",
result["fetched"], result["created"], result["updated"],
result["skipped"], len(result["errors"]),
)
return result
# ── 配置常量(原文件即从 config 再导出,维持 bz.REQUEST_INTERVAL 等引用) ──
from src.data.config import ( # noqa: F401
BZZOIRO_LEAGUE_IDS,
LEAGUE_COUNTRIES,
LEAGUE_NAMES,
REQUEST_INTERVAL,
)
from src.data.key_ring import _mask # noqa: F401 (R1 测试引用 bz._mask)
from src.data.normalize import normalize_bzzoiro # noqa: F401
# ── 共享原语:HTTP 抓取 + 宽松字段转换 ──
from src.data.bzzoiro_common import ( # noqa: F401
_fetch_json_async,
_match_key,
_to_date,
_to_float_or_none,
_to_int_or_none,
)
# ── 管线基础设施:RawEvent / IngestFailure / DataLineage ──
from src.data.pipeline_write import ( # noqa: F401
_safe_write_ingest_failure,
_write_ingest_failure,
_write_lineage,
_write_raw_event,
)
# ── events 管线:BzzoiroSource(注册表入口)+ 抓取/入库 ──
from src.data.bzzoiro_events import ( # noqa: F401
BzzoiroSource,
_events_record_id,
_write_events_bronze,
fetch_bzzoiro_events,
)
# ── standings 管线 ──
from src.data.bzzoiro_standings import ( # noqa: F401
_season_label_from_dates,
_write_standings_bronze,
fetch_bzzoiro_standings,
ingest_bzzoiro_standings,
)
# ── stats 回填管线 ──
from src.data.bzzoiro_stats import ( # noqa: F401
_pick,
_stats_from_payload,
ingest_bzzoiro_event_stats,
)
+123
View File
@@ -0,0 +1,123 @@
"""bzzoiro 管线共享原语:HTTP 抓取(多 key 轮换)与宽松字段转换。
从 bzzoiro.py 拆出(单文件 → 多模块):仅放无业务语义的共享基础,
三条管线(events/standings/stats)与聚合门面见 bzzoiro.py。
"""
from __future__ import annotations
import asyncio
import logging
import random
import httpx
from src.core.http_client import get_client
from src.core.runtime_config import get_runtime_value
from src.data.key_ring import _mask, get_key_ring
logger = logging.getLogger(__name__)
def _to_date(value):
"""把 datetime / date / str 统一成 `date`。"""
if value is None:
return None
if hasattr(value, "date") and callable(value.date):
return value.date()
return value
def _to_int_or_none(value) -> int | None:
"""宽松转 int(用于上游 ID 解析,失败返回 None 不抛错)。"""
if value is None:
return None
try:
return int(str(value).strip())
except (TypeError, ValueError):
return None
def _to_float_or_none(value) -> float | None:
try:
return float(str(value).strip())
except (TypeError, ValueError):
return None
def _match_key(home_team_id: int, away_team_id: int, match_date) -> tuple[int, int, str]:
"""比赛去重键:(主队, 客队, 天级日期 ISO 字符串)。
统一在这里构造,避免"预加载时用 str(date)、写入时用 isoformat()"这类
隐式格式依赖 —— 两者当前恰好相等,但一旦有人改动其一就会静默失配,
导致所有比赛被判为不存在而重复插入。
"""
d = _to_date(match_date)
return (home_team_id, away_team_id, d.isoformat() if d is not None else "")
async def _fetch_json_async(path: str, params: dict | None = None, max_retries: int = 3) -> dict | list:
"""异步 HTTP(bzzoiro 使用 httpx,不再阻塞事件循环线程池)。
多 key 轮换:遇到 429 自动切换到下一个 key;全部 key 冷却时等待最早恢复。
"""
base = (await get_runtime_value("BZZOIRO_BASE")).rstrip("/")
raw_keys = await get_runtime_value("BZZOIRO_KEY")
ring = get_key_ring(base, raw_keys)
url = f"{base}/{path.lstrip('/')}"
key = ring.get()
if not key:
raise RuntimeError("BZZOIRO_KEY 未设置")
last_exc: Exception | None = None
for attempt in range(max_retries):
headers = {
"Authorization": f"Token {key}",
"Accept": "application/json",
}
try:
client = get_client()
# 整请求兜底: httpx 无 total 超时,用 wait_for 防「滴水式」限速挂死
resp = await asyncio.wait_for(
client.get(
url, headers=headers, params=params,
timeout=httpx.Timeout(connect=10.0, read=30.0, write=10.0, pool=10.0),
),
timeout=60.0,
)
resp.raise_for_status()
return resp.json()
except Exception as e:
last_exc = e
status = getattr(getattr(e, "response", None), "status_code", None)
if status == 429:
# 限流:标记当前 key 冷却,切换到下一个
new_key = ring.report_rate_limited(key)
if new_key and new_key != key:
logger.info("bzzoiro 429 → 切换 key: %s%s,立即重试", _mask(key), _mask(new_key))
key = new_key
continue # 立即重试,不等待
# 单 key 或全部冷却:等待最早恢复的 key
wait = ring.wait_if_all_blocked()
if wait > 0:
logger.warning("bzzoiro 全部 key 冷却,等待 %.1fs 后重试", wait)
await asyncio.sleep(min(wait, 30.0))
else:
delay = min(2 ** attempt, 16) + random.uniform(0, 1)
logger.warning("bzzoiro 429, retry %d in %.1fs", attempt + 1, delay)
await asyncio.sleep(delay)
key = ring.get() or key
continue
if 500 <= (status or 0) < 600:
delay = min(2 ** attempt, 16) + random.uniform(0, 1)
logger.warning("bzzoiro %d, retry %d in %.1fs", status, attempt + 1, delay)
await asyncio.sleep(delay)
continue
# 网络错误(连接失败/超时)也退避重试
if isinstance(e, (TimeoutError, ConnectionError, OSError)):
delay = min(2 ** attempt, 16) + random.uniform(0, 1)
logger.warning("bzzoiro network error, retry %d in %.1fs: %s", attempt + 1, delay, e)
await asyncio.sleep(delay)
continue
raise
raise RuntimeError(f"bzzoiro request failed after {max_retries} attempts: {last_exc}")
+310
View File
@@ -0,0 +1,310 @@
"""bzzoiro events 管线:比赛日程/比分抓取(/events/)与入库(matches 表)。
从 bzzoiro.py 拆出。比赛主数据唯一入口;Team/League/Match 查找/创建经
Repository 层,事务由调用方 UnitOfWork 控制(分批事务约定不变)。
可替换协作者(抓取函数 / Bronze 写入助手 / REQUEST_INTERVAL)在运行期
经聚合门面 src.data.bzzoiro 解析 —— 与拆分前的单文件 monkeypatch 语义一致。
"""
from __future__ import annotations
import asyncio
import logging
from collections.abc import Iterable
from datetime import datetime, timedelta, timezone
from src.data.bzzoiro_common import _match_key, _to_date, _to_int_or_none
from src.data.config import BZZOIRO_LEAGUE_IDS, LEAGUE_COUNTRIES, LEAGUE_NAMES
from src.data.normalize import normalize_bzzoiro
from src.data.sources import register
from src.data.team_names_zh import zh_name
from src.db.models import Match
from src.db.repositories import LeagueRepository, MatchRepository, TeamRepository
logger = logging.getLogger(__name__)
async def fetch_bzzoiro_events(
league_code: str,
*,
status: str = "finished",
date_from: str | None = None,
date_to: str | None = None,
limit: int = 200,
) -> list[dict]:
"""抓取 bzzoiro 原始事件(纯异步,无需 run_in_executor)。"""
from src.data import bzzoiro as bz
league_id = BZZOIRO_LEAGUE_IDS.get(league_code)
if league_id is None:
raise ValueError(f"未知联赛代码: {league_code}")
rows: list[dict] = []
offset = 0
while True:
params: dict = {
"league_id": league_id,
"status": status,
"limit": limit,
"offset": offset,
}
if date_from:
params["date_from"] = str(date_from)[:10]
if date_to:
params["date_to"] = str(date_to)[:10]
payload = await bz._fetch_json_async("/events/", params)
batch = payload.get("results") or []
if not batch:
break
rows.extend(batch)
total = payload.get("total")
offset += limit
if total is not None and offset >= total:
break
if len(batch) < limit:
break
await asyncio.sleep(bz.REQUEST_INTERVAL)
return rows
@register
class BzzoiroSource:
"""bzzoiro 数据源(实现 DataSource 协议)。"""
name = "bzzoiro"
async def ingest(
self,
db,
*,
leagues: Iterable[str],
date_from: str | None = None,
date_to: str | None = None,
status: str = "finished",
) -> dict:
"""采集 bzzoiro → 入库。返回统计。
注意: 本方法不控制事务(commit/rollback),由调用方通过 UnitOfWork 控制。
"""
from src.data import bzzoiro as bz
result: dict = {"leagues": {}, "total_inserted": 0, "total_updated": 0, "errors": []}
for code in leagues:
league_r: dict = {"inserted": 0, "updated": 0, "errors": []}
try:
raw_events = await bz.fetch_bzzoiro_events(code, status=status, date_from=date_from, date_to=date_to)
except Exception as e:
# 单联赛抓取失败隔离:记录错误后继续其余联赛,不拖垮整批
logger.exception("bzzoiro fetch failed for %s", code)
league_r["errors"].append(f"fetch failed: {e}")
await bz._safe_write_ingest_failure(
db,
entity_type="events",
source_record_id=None,
error=e,
raw_payload={"league": code, "status": status, "date_from": date_from, "date_to": date_to},
)
result["leagues"][code] = league_r
continue
# D4: 联赛查找/创建经 LeagueRepository(事务仍由调用方 UoW 提交)
league = await LeagueRepository(db).get_or_create(
code, LEAGUE_NAMES.get(code, code), LEAGUE_COUNTRIES.get(code)
)
team_r = TeamRepository(db)
match_r = MatchRepository(db)
# === 批量优化: 预加载球队和已有比赛到内存 ===
team_name_to_id: dict[str, int] = {}
existing_matches: dict[tuple[int, int, str], Match] = {} # 完整对象,避免重复查询
# (NormalizedMatch, 原始 event) 成对保存:后续写 source_event_id 时
# 必须用配对的那条 event,不能依赖外层循环变量残留值。
normalized_matches: list[tuple] = []
if raw_events:
# 一次遍历: 收集球队名 + 规范化
all_team_names = set()
for raw in raw_events:
nm = normalize_bzzoiro(raw, code)
if nm is not None:
try:
nm.validate()
except Exception:
continue
normalized_matches.append((nm, raw))
all_team_names.add(nm.home_team)
all_team_names.add(nm.away_team)
if all_team_names:
team_name_to_id = {
name: t.id
for name, t in (await team_r.get_all_by_names(list(all_team_names))).items()
}
# P1-2: 按需加载,只加载 raw_events 涉及日期范围的比赛(加 30 天缓冲)
# 避免加载联赛全部历史比赛到内存(多赛季采集时内存溢出)
if normalized_matches:
# normalized_matches 存的是 (nm, raw) 元组,遍历需解包
dates = [nm.date for nm, _raw in normalized_matches if nm.date is not None]
if dates:
min_dt = min(dates) - timedelta(days=30)
max_dt = max(dates) + timedelta(days=30)
matches_in_range = await match_r.find_by_league_and_date_range(
league.id, min_dt, max_dt
)
existing_matches = {
_match_key(m.home_team_id, m.away_team_id, m.match_date_date): m
for m in matches_in_range
}
# else: existing_matches 保持空 dict(全量新比赛)
# D1: Bronze 层批次信息(每联赛每批次一个 batch_id;seen 防同批重复写入)
now = datetime.now(timezone.utc)
bronze_batch_id = f"bzzoiro-events-{code}-{now:%Y%m%d%H%M%S}"
bronze_written: set[str] = set()
for nm, raw in normalized_matches:
# D1: RawEvent 幂等键(上游 id 或合成键),插入/变更更新共用
record_id = _events_record_id(code, nm, raw)
# 球队: 内存查找 + 按需创建(D4: 经 TeamRepository)
home_team_id = team_name_to_id.get(nm.home_team)
if home_team_id is None:
home = await team_r.get_or_create(nm.home_team, name_zh=zh_name(nm.home_team))
home_team_id = home.id
team_name_to_id[nm.home_team] = home_team_id
away_team_id = team_name_to_id.get(nm.away_team)
if away_team_id is None:
away = await team_r.get_or_create(nm.away_team, name_zh=zh_name(nm.away_team))
away_team_id = away.id
team_name_to_id[nm.away_team] = away_team_id
# 查找已有比赛: 内存查找
match_key = _match_key(home_team_id, away_team_id, nm.date)
existing_match = existing_matches.get(match_key)
if existing_match is None:
m = Match(
league_id=league.id,
season=nm.season_label or None,
home_team_id=home_team_id,
away_team_id=away_team_id,
match_date=nm.date,
match_date_date=_to_date(nm.date),
match_status=nm.match_status,
home_goals=nm.home_goals,
away_goals=nm.away_goals,
home_ht_goals=nm.home_ht_goals,
away_ht_goals=nm.away_ht_goals,
match_stage=nm.match_stage,
source_event_id=_to_int_or_none(raw.get("id")),
)
db.add(m)
await db.flush()
existing_matches[match_key] = m # 防止同批重复
# 统计字段不在 /events/ 载荷中(单独由 stats 管线回填),
# 此处不再创建 MatchStats。
league_r["inserted"] += 1
# D1: 成功插入 → 补写 Bronze 层(原始载荷 + 血缘)
if record_id not in bronze_written:
bronze_written.add(record_id)
await _write_events_bronze(
db,
source_record_id=record_id,
raw_payload=raw,
target_match_id=m.id,
league_code=code,
match_status=nm.match_status,
batch_id=bronze_batch_id,
)
else:
# 已有比赛: 直接从内存获取对象更新(无需再查询)
changed = False
if existing_match.match_status != nm.match_status and nm.match_status == "finished":
existing_match.match_status = nm.match_status
changed = True
if existing_match.home_goals is None and nm.home_goals is not None:
existing_match.home_goals = nm.home_goals
existing_match.away_goals = nm.away_goals
existing_match.home_ht_goals = nm.home_ht_goals
existing_match.away_ht_goals = nm.away_ht_goals
changed = True
if existing_match.match_stage is None and nm.match_stage:
existing_match.match_stage = nm.match_stage
changed = True
if existing_match.source_event_id is None:
eid = _to_int_or_none(raw.get("id"))
if eid is not None:
existing_match.source_event_id = eid
changed = True
if changed:
league_r["updated"] += 1
# D1: 变更更新 → 补写血缘(RawEvent 幂等键不变,重复采集自动跳过)
if record_id not in bronze_written:
bronze_written.add(record_id)
await _write_events_bronze(
db,
source_record_id=record_id,
raw_payload=raw,
target_match_id=existing_match.id,
league_code=code,
match_status=nm.match_status,
batch_id=bronze_batch_id,
)
# 注意: 不在此处 commit,由调用方 UnitOfWork 控制事务
result["leagues"][code] = league_r
result["total_inserted"] += league_r["inserted"]
result["total_updated"] += league_r["updated"]
return result
def _events_record_id(league_code: str, nm, raw: dict) -> str:
"""events 载荷的 RawEvent 幂等键。
优先用上游 event id;缺失时用 (league:home:away:date) 合成稳定键 ——
取 normalize 后的队名与天级日期(与 _match_key 同口径),不依赖 DB 自增 id,
保证同一来源比赛重复采集时命中同一条 RawEvent,不产生重复原始载荷。
"""
eid = _to_int_or_none(raw.get("id"))
if eid is not None:
return str(eid)
d = _to_date(nm.date)
date_part = d.isoformat() if d is not None else "na"
return f"{league_code}:{nm.home_team}:{nm.away_team}:{date_part}"
async def _write_events_bronze(
db,
*,
source_record_id: str,
raw_payload: dict,
target_match_id: int | None,
league_code: str,
match_status: str | None,
batch_id: str,
) -> None:
"""events 成功插入/更新单场比赛后的 Bronze 层补写:RawEvent(幂等) + DataLineage。
D1(工程债):此前只有 stats 回填写 RawEvent/Lineage,events 管线作为比赛
主数据的唯一入口反而不留溯源记录。幂等性由 _write_raw_event 的
source_record_id 查重保证;best-effort:基础设施写入失败只记 warning,
绝不拖垮采集主流程(与 _safe_write_ingest_failure 同级约束)。
"""
from src.data import bzzoiro as bz
try:
await bz._write_raw_event(db, "bzzoiro", source_record_id, raw_payload, batch_id)
await bz._write_lineage(
db, "bzzoiro", source_record_id,
"matches", target_match_id, "events_ingest",
{"league": league_code, "match_status": match_status},
batch_id,
)
except Exception:
logger.warning(
"events Bronze 写入失败(record=%s, match=%s),不影响采集主流程",
source_record_id, target_match_id, exc_info=True,
)
+215
View File
@@ -0,0 +1,215 @@
"""bzzoiro standings 管线:联赛积分榜快照(/leagues/{id}/standings/)→ standings 表。
从 bzzoiro.py 拆出。同一联赛同一赛季只保留最新快照(按 (league, season, team)
upsert);球队名与 events 管线使用同一 normalize 规则,保证 Team 匹配。
可替换协作者(抓取函数 / Bronze 写入助手)在运行期经聚合门面
src.data.bzzoiro 解析 —— 与拆分前的单文件 monkeypatch 语义一致。
"""
from __future__ import annotations
import logging
from collections.abc import Iterable
from datetime import datetime, timezone
from sqlalchemy import select
from src.data.bzzoiro_common import _to_float_or_none, _to_int_or_none
from src.data.config import BZZOIRO_LEAGUE_IDS, LEAGUE_COUNTRIES, LEAGUE_NAMES
from src.data.team_names_zh import zh_name
from src.db.models import Standing, Team
from src.db.repositories import LeagueRepository, TeamRepository
logger = logging.getLogger(__name__)
async def fetch_bzzoiro_standings(league_code: str, season: str | None = None) -> dict:
"""抓取联赛积分榜(纯抓取,不入库)。season 为 None 时取当前赛季。"""
from src.data import bzzoiro as bz
league_id = BZZOIRO_LEAGUE_IDS.get(league_code)
if league_id is None:
raise ValueError(f"未知联赛代码: {league_code}")
params: dict = {}
if season:
params["season"] = season
return await bz._fetch_json_async(f"/leagues/{league_id}/standings/", params)
def _season_label_from_dates(start_date, end_date) -> str:
"""从赛季起止日期推导赛季标签(与 derive_season_label 语义一致)。"""
try:
if isinstance(start_date, str):
start = datetime.fromisoformat(start_date[:10])
else:
start = start_date
if start is None:
return "?"
y = start.year
return f"{y}-{y + 1}" if start.month >= 8 else f"{y - 1}-{y}"
except (TypeError, ValueError):
return "?"
async def ingest_bzzoiro_standings(db, *, leagues: Iterable[str], season: str | None = None) -> dict:
"""采集积分榜 → upsert standings 表。
season 为 None 时采集当前赛季(bzzoiro 默认返回 is_current 赛季)。
球队名与 events 管线使用同一 normalize 规则,保证 Team 匹配。
"""
from src.data import bzzoiro as bz
from src.data.team_names import normalize as normalize_name
result: dict = {"leagues": {}, "total_upserted": 0, "errors": []}
for code in leagues:
league_r: dict = {"upserted": 0, "teams_created": 0, "rows": 0, "errors": []}
try:
payload = await bz.fetch_bzzoiro_standings(code, season=season)
except Exception as e:
logger.exception("bzzoiro standings fetch failed for %s", code)
league_r["errors"].append(str(e))
await bz._safe_write_ingest_failure(
db,
entity_type="standings",
source_record_id=None,
error=e,
raw_payload={"league": code, "season": season},
)
result["leagues"][code] = league_r
result["errors"].append(f"{code}: {e}")
continue
rows = payload.get("standings") or []
if not rows:
result["leagues"][code] = {"error": "无积分榜数据(赛季未开始或未提供)"}
result["errors"].append(f"{code}: 无积分榜数据")
continue
# 联赛(get-or-create,D4: 经 LeagueRepository)
league = await LeagueRepository(db).get_or_create(
code, LEAGUE_NAMES.get(code, code), LEAGUE_COUNTRIES.get(code)
)
team_r = TeamRepository(db)
# 赛季标签:优先用返回的 season 对象推导
season_obj = payload.get("season") or {}
season_label = _season_label_from_dates(
season_obj.get("start_date"), season_obj.get("end_date")
)
if season_label == "?":
season_label = season or ""
# 批量预载球队(与 events 管线使用同一 normalize 规则,保证 Team 匹配)
names = {normalize_name(str(r.get("team_name", ""))) for r in rows}
names.discard("")
team_map: dict[str, Team] = await team_r.get_all_by_names(list(names))
now = datetime.now(timezone.utc)
for r in rows:
team_name = normalize_name(str(r.get("team_name", "")))
if not team_name:
continue
team = team_map.get(team_name)
if team is None:
team = await team_r.get_or_create(team_name, name_zh=zh_name(team_name))
team_map[team_name] = team
league_r["teams_created"] += 1
zone = r.get("zone") or {}
values = dict(
position=_to_int_or_none(r.get("position")) or 0,
played=_to_int_or_none(r.get("played")) or 0,
won=_to_int_or_none(r.get("won")) or 0,
drawn=_to_int_or_none(r.get("drawn")) or 0,
lost=_to_int_or_none(r.get("lost")) or 0,
goals_for=_to_int_or_none(r.get("gf")) or 0,
goals_against=_to_int_or_none(r.get("ga")) or 0,
goal_diff=_to_int_or_none(r.get("gd")) or 0,
points=_to_int_or_none(r.get("pts")) or 0,
xg_for=_to_float_or_none(r.get("xgf")),
xg_against=_to_float_or_none(r.get("xga")),
form=r.get("form") or None,
zone=zone.get("label") or zone.get("key") or None,
updated_at=now,
retrieved_at=now,
)
# 同一联赛同一赛季只保留最新快照:按 (league, season, team) upsert
stmt = select(Standing).where(
Standing.league_id == league.id,
Standing.season == season_label,
Standing.team_id == team.id,
)
standing = (await db.execute(stmt)).scalar_one_or_none()
if standing is None:
standing = Standing(
league_id=league.id, season=season_label, team_id=team.id, **values
)
db.add(standing)
else:
for k, v in values.items():
setattr(standing, k, v)
league_r["upserted"] += 1
league_r["rows"] = len(rows)
# D1(对称 events/stats 管线): 联赛成功 upsert → 补写 Bronze 层。
# 幂等键 standings:{league}:{season}:积分榜是联赛级快照,一次成功
# 采集写一条 RawEvent(整份原始载荷)+ 一条血缘。season 用实际入库的
# 标签(由载荷推导,与 Standing.season 同口径),不依赖调用方传参,
# 保证不同调用方(season=None 或显式传参)对同一赛季命中同一条 RawEvent。
if league_r["upserted"] > 0:
bronze_batch_id = f"bzzoiro-standings-{code}-{now:%Y%m%d%H%M%S}"
await _write_standings_bronze(
db,
source_record_id=f"standings:{code}:{season_label}",
raw_payload=payload,
league_id=league.id,
league_code=code,
season_label=season_label,
rows_upserted=league_r["upserted"],
batch_id=bronze_batch_id,
)
result["leagues"][code] = league_r
result["total_upserted"] += league_r["upserted"]
logger.info(
"bzzoiro standings 采集完成: %s 赛季 %s, upsert %d/%d",
code, season_label, league_r["upserted"], league_r["rows"],
)
return result
async def _write_standings_bronze(
db,
*,
source_record_id: str,
raw_payload: dict,
league_id: int | None,
league_code: str,
season_label: str,
rows_upserted: int,
batch_id: str,
) -> None:
"""standings 成功 upsert 一个联赛后的 Bronze 层补写:RawEvent(幂等) + DataLineage。
与 _write_events_bronze 同级约束:幂等性由 _write_raw_event 的
source_record_id 查重保证(积分榜是联赛级快照,同联赛同赛季重复采集
命中同一条 RawEvent);best-effort:基础设施写入失败只记 warning,
绝不拖垮采集主流程。
"""
from src.data import bzzoiro as bz
try:
await bz._write_raw_event(db, "bzzoiro", source_record_id, raw_payload, batch_id)
await bz._write_lineage(
db, "bzzoiro", source_record_id,
"standings", league_id, "standings_ingest",
{"league": league_code, "season": season_label, "rows_upserted": rows_upserted},
batch_id,
)
except Exception:
logger.warning(
"standings Bronze 写入失败(record=%s, league=%s),不影响采集主流程",
source_record_id, league_code, exc_info=True,
)
+180
View File
@@ -0,0 +1,180 @@
"""bzzoiro stats 回填管线:已完赛比赛详细统计(/events/{id}/stats/)→ match_stats 表。
从 bzzoiro.py 拆出。上游限速(REQUEST_INTERVAL 秒/请求),大批量回填需分次触发;
只 add/flush 不 commit,事务由调用方 UnitOfWork 控制。
可替换协作者(_fetch_json_async / Bronze 写入助手 / REQUEST_INTERVAL)在运行期
经聚合门面 src.data.bzzoiro 解析 —— 与拆分前的单文件 monkeypatch 语义一致。
"""
from __future__ import annotations
import asyncio
import logging
from collections.abc import Iterable
from datetime import datetime, timedelta, timezone
from src.data.bzzoiro_common import _to_float_or_none, _to_int_or_none
from src.data.config import BZZOIRO_LEAGUE_IDS
from src.db.models import MatchStats
from src.db.repositories import MatchRepository
logger = logging.getLogger(__name__)
# bzzoiro stats 字段 → MatchStats 字段映射(stats.home / stats.away 下)
_STATS_FIELD_MAP = {
"xg": ("home_xg", "away_xg"), # 回退 expected_goals
"ball_possession": ("home_possession", None), # 只取主队值,客队=100-home
"total_shots": ("home_shots", "away_shots"),
"shots_on_target": ("home_shots_on_target", "away_shots_on_target"),
"corner_kicks": ("home_corners", "away_corners"),
"yellow_cards": ("home_yellow_cards", "away_yellow_cards"),
"red_cards": ("home_red_cards", "away_red_cards"),
"big_chances": ("home_big_chances", "away_big_chances"),
"fouls": ("home_fouls", "away_fouls"),
}
def _pick(d: dict, *keys):
"""按优先级取第一个非空字段值。"""
for k in keys:
v = d.get(k)
if v is not None:
return v
return None
def _stats_from_payload(payload: dict) -> dict:
"""把 /events/{id}/stats/ 响应映射成 MatchStats 字段 dict。
响应结构: {"event_id": ..., "stats": {"home": {...}, "away": {...}}}
"""
stats = (payload or {}).get("stats") or {}
home = stats.get("home") or {}
away = stats.get("away") or {}
out: dict = {}
xg_h = _pick(home, "xg", "expected_goals")
xg_a = _pick(away, "xg", "expected_goals")
if xg_h is not None:
out["home_xg"] = _to_float_or_none(xg_h)
if xg_a is not None:
out["away_xg"] = _to_float_or_none(xg_a)
poss = home.get("ball_possession")
if poss is not None:
p = _to_float_or_none(poss)
if p is not None:
out["home_possession"] = p
for src, (h_fld, a_fld) in _STATS_FIELD_MAP.items():
if src in ("xg", "ball_possession"):
continue # 已处理
hv = home.get(src)
av = away.get(src)
if hv is not None and h_fld:
out[h_fld] = _to_int_or_none(hv)
if av is not None and a_fld:
out[a_fld] = _to_int_or_none(av)
return out
async def ingest_bzzoiro_event_stats(
db,
*,
leagues: Iterable[str],
limit: int = 100,
only_missing: bool = True,
) -> dict:
"""回填已完赛比赛的详细统计(逐场调 /events/{id}/stats/)。
筛选条件: match_status=finished 且 source_event_id 非空。
only_missing=True 时跳过已有统计的比赛(增量);False 则全量刷新。
limit 控制单次最多处理的比赛数(上游限速 1.2s/请求,大批量需分次触发)。
"""
from src.data import bzzoiro as bz
result: dict = {"fetched": 0, "created": 0, "updated": 0, "skipped": 0, "errors": []}
league_ids = [BZZOIRO_LEAGUE_IDS[c] for c in leagues if c in BZZOIRO_LEAGUE_IDS]
if not league_ids:
result["errors"].append("无有效联赛代码")
return result
# D4: 候选比赛查询经 MatchRepository(含 stats 预加载,筛选/排序/limit 语义不变)
matches = await MatchRepository(db).find_finished_with_stats(
league_ids, limit=limit * 3 if only_missing else limit
)
now = datetime.now(timezone.utc)
processed = 0
for m in matches:
if processed >= limit:
break
if only_missing and m.stats is not None and m.stats.home_shots is not None:
result["skipped"] += 1
continue
processed += 1
try:
payload = await bz._fetch_json_async(f"/events/{m.source_event_id}/stats/")
except Exception as e:
logger.warning("stats fetch failed match=%s event=%s: %s", m.id, m.source_event_id, e)
result["errors"].append(f"match {m.id}: {e}")
await bz._safe_write_ingest_failure(
db,
entity_type="match_stats",
source_record_id=str(m.source_event_id),
error=e,
raw_payload={"match_id": m.id},
)
await asyncio.sleep(bz.REQUEST_INTERVAL)
continue
result["fetched"] += 1
fields = _stats_from_payload(payload)
if not fields:
result["skipped"] += 1
await asyncio.sleep(bz.REQUEST_INTERVAL)
continue
if m.stats is None:
available_at = m.match_date + timedelta(hours=2) if m.match_date else now
m.stats = MatchStats(
match_id=m.id,
source="bzzoiro",
source_record_id=str(m.source_event_id),
retrieved_at=now,
available_at=available_at,
)
db.add(m.stats)
result["created"] += 1
else:
result["updated"] += 1
if m.stats.source is None:
m.stats.source = "bzzoiro"
m.stats.source_record_id = str(m.source_event_id)
if m.stats.retrieved_at is None:
m.stats.retrieved_at = now
if m.stats.available_at is None and m.match_date:
m.stats.available_at = m.match_date + timedelta(hours=2)
for fld, v in fields.items():
if hasattr(m.stats, fld):
setattr(m.stats, fld, v)
# 管线基础设施:写入 RawEvent + DataLineage
batch_id = f"bzzoiro-stats-{m.source_event_id}-{now.strftime('%Y%m%d%H%M%S')}"
try:
await bz._write_raw_event(db, "bzzoiro", str(m.source_event_id), payload, batch_id)
await bz._write_lineage(db, "bzzoiro", str(m.source_event_id), "match_stats", m.stats.id if m.stats else None, "stats_backfill", {"match_id": m.id}, batch_id)
except Exception:
pass # 基础设施写入失败不影响主流程
await asyncio.sleep(bz.REQUEST_INTERVAL)
logger.info(
"bzzoiro stats 回填完成: 抓取 %d, 新建 %d, 更新 %d, 跳过 %d, 错误 %d",
result["fetched"], result["created"], result["updated"],
result["skipped"], len(result["errors"]),
)
return result
+80
View File
@@ -0,0 +1,80 @@
"""管线基础设施写入助手:RawEvent(Bronze 原始载荷)/ IngestFailure(死信)/ DataLineage(血缘)。
从 bzzoiro.py 拆出。约定(与拆分前一致):
- 只 add 不 commit —— 事务由调用方 UnitOfWork 控制,分批事务约定不变;
- 死信与 Bronze 写入同为 best-effort:失败只记 warning,绝不拖垮采集主流程。
"""
from __future__ import annotations
import logging
from src.db.models import DataLineage, IngestFailure, RawEvent
logger = logging.getLogger(__name__)
async def _write_raw_event(db, source_system: str, source_record_id: str, raw_payload: dict, batch_id: str | None = None) -> None:
"""写入 Bronze 层原始事件(幂等:同 source_record_id 跳过)。"""
from sqlalchemy import select as _select
stmt = _select(RawEvent).where(
RawEvent.source_system == source_system,
RawEvent.source_record_id == source_record_id,
)
existing = (await db.execute(stmt)).scalar_one_or_none()
if existing is None:
db.add(RawEvent(
source_system=source_system,
source_record_id=source_record_id,
raw_payload=raw_payload,
ingest_batch_id=batch_id,
))
async def _write_ingest_failure(db, source_system: str, entity_type: str, source_record_id: str | None, error_type: str, error_detail: str | None, raw_payload: dict | None = None) -> None:
"""写入采集失败死信。"""
db.add(IngestFailure(
source_system=source_system,
entity_type=entity_type,
source_record_id=source_record_id,
error_type=error_type,
error_detail=error_detail,
raw_payload=raw_payload,
))
async def _safe_write_ingest_failure(
db,
*,
entity_type: str,
source_record_id: str | None,
error: Exception,
raw_payload: dict | None = None,
) -> None:
"""抓取失败时尽力写入死信表(失败不影响主流程)。
死信是「可观测性」基础设施,与 RawEvent/Lineage 同级:写入失败只记
warning,绝不能让原始抓取错误之外的新异常打断采集循环。
"""
try:
await _write_ingest_failure(
db, "bzzoiro", entity_type, source_record_id,
"fetch_error", str(error), raw_payload,
)
except Exception:
logger.warning(
"写入 ingest_failures 死信失败(entity=%s, record=%s): %s",
entity_type, source_record_id, error, exc_info=True,
)
async def _write_lineage(db, source_system: str, source_record_id: str, target_table: str, target_id: int | None, transform_name: str, transform_detail: dict | None = None, batch_id: str | None = None) -> None:
"""写入 ETL 血缘追踪。"""
db.add(DataLineage(
source_system=source_system,
source_record_id=source_record_id,
target_table=target_table,
target_id=target_id,
transform_name=transform_name,
transform_detail=transform_detail,
batch_id=batch_id,
))
+4 -4
View File
@@ -79,18 +79,18 @@ class TestWriteBufferStrategy:
def test_bzzoirot_new_match_available_at_is_two_hours_after_kickoff(self):
"""bzzoiro 新建比赛(stats 回填创建 MatchStats)时 available_at 应为开球 + 2 小时。"""
import inspect
from src.data import bzzoiro
from src.data import bzzoiro_stats
source = inspect.getsource(bzzoiro)
source = inspect.getsource(bzzoiro_stats)
assert 'timedelta(hours=2)' in source, \
"bzzoiro 应使用 match_date + timedelta(hours=2) 作为 available_at"
def test_bzzoirot_multiple_writes_use_two_hour_buffer(self):
"""bzzoiro 多处写入(创建/更新)都应使用 2 小时缓冲。"""
import inspect
from src.data import bzzoiro
from src.data import bzzoiro_stats
source = inspect.getsource(bzzoiro)
source = inspect.getsource(bzzoiro_stats)
count = source.count('timedelta(hours=2)')
assert count >= 2, f"期望至少 2 处 timedelta(hours=2),实际 {count}"
+3 -3
View File
@@ -175,7 +175,7 @@ class TestBzzoiroLineage:
return bad
def test_normalized_matches_carries_raw(self):
src = _read("data/bzzoiro.py")
src = _read("data/bzzoiro_events.py")
# 规范化结果必须与原始 event 成对保存
assert "normalized_matches.append((nm, raw))" in src, (
"normalized_matches 未携带 (nm, raw) 元组 —— raw 变量泄漏会回归 (P0-3)"
@@ -193,7 +193,7 @@ class TestBzzoiroLineage:
它不是 `raw.get(` 同一行,但同样正确非法写法(回归)是直接
`existing_match.source_event_id = orphan_var`
"""
src = _read("data/bzzoiro.py")
src = _read("data/bzzoiro_events.py")
seg = self._consume_loop_body(src)
bad = self._bad_assignments(seg)
assert len(bad) == 0, (
@@ -206,7 +206,7 @@ class TestBzzoiroLineage:
下游 `_backfill_stats` 里合法地在 ORM 对象上访问 `m.source_event_id`
(与配对 raw 无关) seg 越界,test_no_orphan_raw_use 会误报
"""
src = _read("data/bzzoiro.py")
src = _read("data/bzzoiro_events.py")
seg = self._consume_loop_body(src)
assert "m.source_event_id" not in seg, (
"循环体截取越界,扫到了下游 stats 管线 —— 会误报 P0-3"