Files
market_sync/app/tasks/task_industry_sector.py
T
gao 05635b76b9 chore: 重构前基线 — 9 个 sync task 全部 ok + akshare 移除 + mairui 资金流接入
状态:
- 9 个 sync task(stock_basic / kline_daily / kline_index / kline_5min /
  moneyflow / industry_sector / sector_features / share_snapshot / market_regime)
- 数据源:baostock + mairui + 雪球(pysnowball) + 新浪(4 个)
- 项目级约束:永远不用 akshare(已落实)
- kline_5min 改用 DB 快照统一全量/增量逻辑
- 零后端 Chrome 扩展 xueqiu_sync(独立项目)
2026-06-15 15:36:09 +08:00

123 lines
4.9 KiB
Python

"""同步任务:股票-行业映射(Baostock)。
数据流:Baostock query_stock_industry() → 写 industry / sectors / stock_sector_map 三张表。"""
from __future__ import annotations
import time
from typing import Any
from app.core.db import ops as db_ops
from app.core.datasource.base import registry as ds_registry
from app.core.datasource.registry import is_source_ready
from app.core.sync.base import SyncTask
from app.core.sync.registry import mark_sync_blocked
from app.core.utils.logging import get_logger
logger = get_logger("sync.industry_sector")
def _build_sector_key(taxonomy: str, sector_name: str) -> str:
tax = (taxonomy or "").strip() or "default"
name = (sector_name or "").strip()
return f"{tax}::{name}"
class SyncIndustrySector(SyncTask):
dataset_id = "industry_sector"
def _run(self, *, trigger_source: str = "manual", **kwargs) -> dict[str, Any]:
bs = ds_registry.get("datasource_baostock")
if bs is None:
return {"status": "error", "message": "Baostock 数据源未注册"}
ok, reason = is_source_ready(bs.key)
if not ok:
mark_sync_blocked(self.dataset_id, message=f"Baostock 未就绪: {reason}")
return {"status": "blocked", "message": f"Baostock 未就绪: {reason}"}
self._progress(message="拉取股票-行业映射...")
t0 = time.time()
try:
raw_rows = bs.fetch_industry_map()
except Exception as e:
return {"status": "error", "message": f"拉取失败: {e}"}
if not raw_rows:
return {"status": "warning", "message": "Baostock 未返回行业数据"}
# 合并:sectors + stock_sector_map + industry
sectors_rows: dict[str, dict] = {}
stock_sector_rows: list[dict] = []
industry_rows: list[dict] = []
for r in raw_rows:
code6 = str(r["code"]).zfill(6)
name = (r.get("industry_name") or "").strip()
if not name:
continue
classification = (r.get("industry_classification") or "").strip()
sector_key = _build_sector_key(classification, name)
sectors_rows[sector_key] = {
"sector_key": sector_key,
"sector_name": name,
"taxonomy": classification,
"level": "",
"source": "baostock_query_stock_industry",
"enabled": 1,
}
stock_sector_rows.append({"stock_code": code6, "sector_key": sector_key})
industry_rows.append({
"code": code6,
"industry_name": name,
"industry_classification": classification,
"update_date": r.get("update_date", ""),
})
# 写库(全量替换)
try:
db_ops.replace_all_sectors(list(sectors_rows.values()))
db_ops.replace_all_stock_sector_map(stock_sector_rows)
db_ops.replace_all_industries(industry_rows)
except Exception as e:
return {"status": "error", "message": f"写库失败: {e}"}
# 回填 stocks.industry 字段(让 stocks 表也能直接看到)
# 使用批量 UPDATE ... CASE WHEN 方式一次性完成
try:
from app.core.db.connection import get_mysql
from app.core.db.schema import ensure_all_tables
ensure_all_tables(get_mysql())
# 按 industry_name 分组,对每组用一个 IN 查询批量更新
by_industry: dict[str, list[str]] = {}
for r in industry_rows:
name = r["industry_name"]
code = r["code"]
if name not in by_industry:
by_industry[name] = []
by_industry[name].append(code)
with get_mysql().cursor() as cur:
for ind_name, codes in by_industry.items():
# 构造 IN 子句:code IN (SHxxx, SZxxx, BJxxx)
placeholders = []
params = [ind_name]
for c in codes:
for prefix in ("SH", "SZ", "BJ"):
placeholders.append("%s")
params.append(f"{prefix}{c}")
in_clause = ", ".join(placeholders)
sql = f"UPDATE stocks SET industry = %s WHERE code IN ({in_clause})"
cur.execute(sql, params)
get_mysql().commit()
except Exception as e:
logger.warning(f"回填 stocks.industry 失败(不影响主任务): {e}")
elapsed = round(time.time() - t0, 1)
msg = f"行业 {len(sectors_rows)}个 映射{len(stock_sector_rows)}条, {elapsed}s"
return {
"status": "ok",
"message": msg,
"sectors": len(sectors_rows),
"stock_sector_map": len(stock_sector_rows),
"elapsed_sec": elapsed,
}