fix: keep baostock session alive across bulk downloads

baostock drops a session after a few hundred queries; every later query
then returned 用户未登录 and the symbol failed. download_daily_batch now
refreshes the session every relogin_every symbols and re-logs in + retries
once on a detected session loss. akshare fallback now defaults off in the
batch path since it is slow/unreliable on this network and the re-login
keeps baostock as the fast primary.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

data/downloader.py

@@ -13,6 +13,10 @@ _BAOSTOCK_FIELDS = "date,open,high,low,close,volume,amount"
 _OHLCV = ["open", "high", "low", "close", "volume", "amount"]
 
 
+class _SessionLost(Exception):
+    """baostock reported the session was dropped (``用户未登录``)."""
+
+
 def _download_akshare(symbol: str, start: str, end: str, adjust: str = "qfq") -> Optional[pd.DataFrame]:
     """Download daily bars from akshare. Returns DataFrame with OHLCV columns."""
     try:
@@ -124,50 +128,80 @@ def download_daily_batch(
     start: str,
     end: str,
     adjust: str = "qfq",
-    akshare_fallback: bool = True,
+    akshare_fallback: bool = False,
+    relogin_every: int = 200,
 ) -> Iterator[Tuple[str, Optional[pd.DataFrame]]]:
-    """Download many symbols under a single baostock session.
+    """Download many symbols, keeping a baostock session alive across the run.
 
-    Logging into baostock once per call (instead of per symbol) is the dominant
+    Logging in once (instead of per symbol) is the dominant speed-up for
-    speed-up when fetching thousands of symbols. Yields ``(symbol, df)`` as each
+    thousands of symbols, but baostock drops a session after a while
-    symbol completes so callers can stream results to disk; ``df`` is ``None``
+    (subsequent queries return ``用户未登录``). So we refresh the session every
-    when both sources fail. Each ``df`` has the same 8 columns as
+    ``relogin_every`` symbols and also re-login + retry once whenever a query
-    :func:`download_daily`.
+    reports the session is gone. Yields ``(symbol, df)`` as each symbol
+    completes; ``df`` is ``None`` when no data is available. Each ``df`` has the
+    same 8 columns as :func:`download_daily`.
 
     Args:
         symbols: Internal-form symbols (``sh600000`` / ``sz000001``).
         start, end: ``YYYY-MM-DD`` bounds.
         adjust: ``qfq`` / ``hfq`` / ``''``.
-        akshare_fallback: Retry a failed symbol through akshare before yielding
+        akshare_fallback: Retry a failed symbol through akshare. Off by default
-            ``None``.
+            because akshare is unreliable on the deployment network and each
+            failed attempt is slow; baostock + re-login is the fast path.
+        relogin_every: Proactively refresh the baostock session every N symbols.
     """
     flag = _BAOSTOCK_ADJUST.get(adjust, "2")
+
+    def _relogin() -> None:
+        try:
+            bs.logout()
+        except Exception:
+            pass
         bs.login()
-    try:
+
-        for symbol in symbols:
+    def _fetch(symbol: str) -> Optional[pd.DataFrame]:
-            df: Optional[pd.DataFrame] = None
+        """One baostock query; returns df, or None (no data), or raises _SessionLost."""
-            try:
         code = f"{symbol[:2]}.{symbol[2:]}"
         rs = bs.query_history_k_data_plus(
             code=code, fields=_BAOSTOCK_FIELDS,
-                    start_date=start, end_date=end,
+            start_date=start, end_date=end, frequency="d", adjustflag=flag,
-                    frequency="d", adjustflag=flag,
         )
-                if rs.error_code == "0":
+        if rs.error_code != "0":
+            if "未登录" in (rs.error_msg or ""):
+                raise _SessionLost(rs.error_msg)
+            logger.warning("baostock error for %s: %s", symbol, rs.error_msg)
+            return None
         rows = []
         while rs.next():
             rows.append(rs.get_row_data())
-                    if rows:
+        if not rows:
+            return None
         df = pd.DataFrame(rows, columns=["date", *_OHLCV])
-                        # Suspended-trading days come back as empty strings;
+        # Suspended-trading days come back as empty strings; coerce to NaN
-                        # coerce to NaN rather than crashing the whole symbol.
+        # rather than crashing the whole symbol.
         df[_OHLCV] = df[_OHLCV].apply(pd.to_numeric, errors="coerce")
         df["symbol"] = symbol
-                        df = df[["symbol", "date", *_OHLCV]]
+        return df[["symbol", "date", *_OHLCV]]
-                else:
+
-                    logger.warning("baostock error for %s: %s", symbol, rs.error_msg)
+    bs.login()
+    try:
+        for i, symbol in enumerate(symbols):
+            if i and relogin_every and i % relogin_every == 0:
+                _relogin()
+
+            df: Optional[pd.DataFrame] = None
+            for attempt in (1, 2):
+                try:
+                    df = _fetch(symbol)
+                    break
+                except _SessionLost:
+                    if attempt == 1:
+                        _relogin()  # session dropped — refresh and retry once
+                        continue
+                    logger.warning("baostock session lost for %s after relogin", symbol)
                 except Exception as e:
                     logger.warning("baostock download failed for %s: %s", symbol, e)
+                    break
 
             if (df is None or df.empty) and akshare_fallback:
                 df = _download_akshare(symbol, start, end, adjust)