gao
05635b76b9
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）
252 lines
9.6 KiB
Python
252 lines
9.6 KiB
Python
"""同步任务：全市场日 K 线。
|
||
|
||
数据流：
|
||
1. 选主源（按 priority 选第一个 is_available 的源）
|
||
2. 增量判断：读 kline_stock.MAX(trade_date) 决定每只股票 start
|
||
3. **Producer-Consumer 模式**：
|
||
- N 个 fetcher 线程并发拉 K 线，把 (code, rows) 塞到 Queue
|
||
- 1 个 writer 线程攒满 BATCH_SIZE 就 executemany + commit 一次
|
||
4. 更新 stocks.kline_synced_at
|
||
|
||
设计要点：
|
||
- 避免每只股票 commit（5000 只 = 5000 次 commit 太慢）
|
||
- 减少并发数（避免新浪限流 / MySQL 连接数爆）
|
||
- fetcher 间用 Queue 解耦，写库串行避免锁竞争
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import os
|
||
import queue
|
||
import threading
|
||
import time
|
||
from datetime import datetime, timedelta
|
||
from typing import Any
|
||
|
||
import pandas as pd
|
||
|
||
from app.core.db import ops as db_ops
|
||
from app.core.datasource.base import registry as ds_registry
|
||
from app.core.datasource.utils import is_a_share_code, to_code6
|
||
from app.core.sync.base import SyncTask, _effective_sync_end
|
||
from app.core.utils.logging import get_logger
|
||
|
||
logger = get_logger("sync.kline_daily")
|
||
|
||
# 主源优先级：mairui（5 RPS，免费 + 稳定 + 单接口含5min）→ 雪球 → Baostock → 新浪
|
||
# 经验：sina 在单日窗口 (start=end=某天) 会返回空，雪球更可靠
|
||
PRIMARY_PRIORITY = ["datasource_xueqiu", "datasource_mairui", "datasource_xinlang"]
|
||
DEFAULT_START = "2018-01-01"
|
||
# 写库批量：攒够 BATCH_SIZE 行就 executemany 一次 + commit
|
||
BATCH_SIZE = 2000
|
||
# fetcher 并发：实测单线程最稳（5000 只 × 0.2s = 17 分钟，足够）
|
||
# 雪球 token 限速 10 RPS，单线程 0.1s/只 已经打满。多 worker 会触发风控 hang
|
||
DEFAULT_FETCH_WORKERS = 1
|
||
|
||
|
||
class SyncKlineDaily(SyncTask):
|
||
dataset_id = "kline_daily"
|
||
|
||
def _run(
|
||
self,
|
||
*,
|
||
trigger_source: str = "manual",
|
||
start: str | None = None,
|
||
end: str | None = None,
|
||
codes: list[str] | None = None,
|
||
incremental: bool = True,
|
||
max_workers: int = DEFAULT_FETCH_WORKERS,
|
||
**kwargs,
|
||
) -> dict[str, Any]:
|
||
# 1. 选主源
|
||
primary = self._pick_primary()
|
||
if primary is None:
|
||
return {"status": "error", "message": "所有 K 线数据源均不可用"}
|
||
|
||
self._progress(
|
||
message=f"使用 {primary.name} 同步日K线 (fetcher={max_workers}, batch={BATCH_SIZE})...",
|
||
current_step=primary.key,
|
||
)
|
||
|
||
# 2. 拉股票列表
|
||
if codes:
|
||
stock_codes = [to_code6(c) for c in codes]
|
||
else:
|
||
stock_codes = [
|
||
c for c in db_ops.iter_stock_codes(active_only=True)
|
||
if is_a_share_code(c)
|
||
]
|
||
limit_raw = os.environ.get("MARKET_DATA_STOCK_LIMIT", "").strip()
|
||
if limit_raw.isdigit() and int(limit_raw) > 0:
|
||
stock_codes = stock_codes[: int(limit_raw)]
|
||
|
||
if not stock_codes:
|
||
return {"status": "error", "message": "无股票代码（stocks 表为空？）"}
|
||
|
||
# 3. 增量判断
|
||
_end = end or _effective_sync_end()
|
||
end_date_obj = datetime.strptime(_end, "%Y-%m-%d").date()
|
||
jobs: list[tuple[str, str]] = []
|
||
if incremental and not start:
|
||
for c6 in stock_codes:
|
||
last = db_ops.get_stock_kline_max_date(c6)
|
||
if last is None:
|
||
fetch_start = DEFAULT_START
|
||
elif datetime.strptime(last, "%Y-%m-%d").date() >= end_date_obj:
|
||
continue
|
||
else:
|
||
fetch_start = (datetime.strptime(last, "%Y-%m-%d").date() - timedelta(days=5)).strftime("%Y-%m-%d")
|
||
jobs.append((c6, fetch_start))
|
||
else:
|
||
fetch_start = start or DEFAULT_START
|
||
jobs = [(c, fetch_start) for c in stock_codes]
|
||
|
||
total = len(jobs)
|
||
skipped = len(stock_codes) - total
|
||
self._progress(
|
||
message=f"开始同步 {total} 只股票 (跳过 {skipped} 只已最新)",
|
||
current=0, total=total,
|
||
)
|
||
|
||
# 4. 并发 fetch + 攒 batch 写库（线程安全）
|
||
# mairui 等外部 API 无并发问题；DB 写串行加锁
|
||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||
t0 = time.time()
|
||
batch_lock = threading.Lock()
|
||
batch_rows: list[dict] = []
|
||
pending_codes: dict[str, str] = {}
|
||
ok_lock = threading.Lock()
|
||
ok_cnt = [0]
|
||
fail_cnt = [0]
|
||
rows_cnt = [0]
|
||
|
||
def _flush():
|
||
with batch_lock:
|
||
if not batch_rows:
|
||
return
|
||
rows_to_write = list(batch_rows)
|
||
codes_to_update = dict(pending_codes)
|
||
batch_rows.clear()
|
||
pending_codes.clear()
|
||
try:
|
||
db_ops.upsert_kline_stock(rows_to_write)
|
||
except Exception as e:
|
||
logger.error(f"batch upsert 失败 ({len(rows_to_write)} 行): {e}")
|
||
return
|
||
for c6, latest in codes_to_update.items():
|
||
try:
|
||
db_ops.update_stock_kline_synced_at(c6, latest)
|
||
except Exception as e:
|
||
logger.warning(f"update synced_at 失败 {c6}: {e}")
|
||
|
||
def _fetch_one(code6: str, fetch_start: str) -> tuple[str, list[dict] | None, str | None]:
|
||
try:
|
||
df = primary.fetch_kline_daily(code6, fetch_start, _end)
|
||
except Exception as e:
|
||
return (code6, None, str(e)[:120])
|
||
if df is None or df.empty:
|
||
return (code6, None, "no data")
|
||
rows = []
|
||
for _, r in df.iterrows():
|
||
td = r["trade_date"]
|
||
rows.append({
|
||
"stock_code": code6,
|
||
"trade_date": td.strftime("%Y-%m-%d") if hasattr(td, "strftime") else str(td)[:10],
|
||
"open": float(r["open"]),
|
||
"high": float(r["high"]),
|
||
"low": float(r["low"]),
|
||
"close": float(r["close"]),
|
||
"volume": float(r["volume"]),
|
||
})
|
||
latest = df["trade_date"].max()
|
||
latest = latest.strftime("%Y-%m-%d") if hasattr(latest, "strftime") else str(latest)[:10]
|
||
return (code6, rows, latest)
|
||
|
||
total = len(jobs)
|
||
with ThreadPoolExecutor(max_workers=max_workers) as pool:
|
||
futures = {pool.submit(_fetch_one, c6, fs): c6 for c6, fs in jobs}
|
||
done_cnt = 0
|
||
for future in as_completed(futures):
|
||
done_cnt += 1
|
||
code6, rows, latest = future.result()
|
||
if rows is None:
|
||
with ok_lock:
|
||
fail_cnt[0] += 1
|
||
logger.warning(f"[kline {code6}] {latest}")
|
||
continue
|
||
with batch_lock:
|
||
batch_rows.extend(rows)
|
||
pending_codes[code6] = latest
|
||
cur_size = len(batch_rows)
|
||
with ok_lock:
|
||
ok_cnt[0] += 1
|
||
rows_cnt[0] += len(rows)
|
||
|
||
if cur_size >= BATCH_SIZE:
|
||
_flush()
|
||
|
||
if done_cnt % 50 == 0 or done_cnt == total:
|
||
elapsed = time.time() - t0
|
||
rate = done_cnt / elapsed if elapsed > 0 else 0
|
||
self._progress(
|
||
message=f"进度 {done_cnt}/{total} OK:{ok_cnt[0]} FAIL:{fail_cnt[0]} {rate:.1f}只/秒",
|
||
current=done_cnt, total=total, current_step=code6,
|
||
)
|
||
|
||
# 收尾 flush
|
||
_flush()
|
||
|
||
elapsed = round(time.time() - t0, 1)
|
||
msg = f"日K线 {ok_cnt[0]}成 {fail_cnt[0]}败 {skipped}跳 共{rows_cnt[0]}行, {elapsed}s"
|
||
return {
|
||
"status": "ok" if fail_cnt[0] == 0 else "warning",
|
||
"message": msg,
|
||
"ok": ok_cnt[0],
|
||
"fail": fail_cnt[0],
|
||
"skip": skipped,
|
||
"rows": rows_cnt[0],
|
||
"elapsed_sec": elapsed,
|
||
"primary_source": primary.key,
|
||
}
|
||
|
||
def _pick_primary(self):
|
||
from app.core.datasource.registry import is_source_ready, run_health_check, get_health_status
|
||
if not get_health_status():
|
||
run_health_check()
|
||
for key in PRIMARY_PRIORITY:
|
||
ok, _ = is_source_ready(key)
|
||
if ok:
|
||
return ds_registry.get(key)
|
||
return None
|
||
|
||
def _sync_one(self, primary, code6: str, start: str, end: str) -> dict:
|
||
"""保留这个方法以兼容外部调用（已不用，但单只测试可能用到）"""
|
||
try:
|
||
df = primary.fetch_kline_daily(code6, start, end)
|
||
except Exception as e:
|
||
return {"status": "fail", "error": str(e)}
|
||
if df is None or df.empty:
|
||
return {"status": "fail", "error": "no data"}
|
||
rows = []
|
||
for _, r in df.iterrows():
|
||
td = r["trade_date"]
|
||
rows.append({
|
||
"stock_code": code6,
|
||
"trade_date": td.strftime("%Y-%m-%d") if hasattr(td, "strftime") else str(td)[:10],
|
||
"open": float(r["open"]),
|
||
"high": float(r["high"]),
|
||
"low": float(r["low"]),
|
||
"close": float(r["close"]),
|
||
"volume": float(r["volume"]),
|
||
})
|
||
try:
|
||
db_ops.upsert_kline_stock(rows)
|
||
except Exception as e:
|
||
return {"status": "fail", "error": f"db write: {e}"}
|
||
if rows:
|
||
latest = max(r["trade_date"] for r in rows)
|
||
try:
|
||
db_ops.update_stock_kline_synced_at(code6, latest)
|
||
except Exception:
|
||
pass
|
||
return {"status": "ok", "rows": len(rows)}
|