From 707dad11c6a66c0740cb22835c2bffd0563ae009 Mon Sep 17 00:00:00 2001
From: shellway-pc <413209390@qq.com>
Date: Sun, 2 Aug 2026 11:53:14 +0800
Subject: [PATCH] =?UTF-8?q?feat:=E5=A2=9E=E5=8A=A0=E6=89=B9=E9=87=8F?=
 =?UTF-8?q?=E8=8E=B7=E5=8F=96=E6=95=B0=E6=8D=AE=E6=97=B6=E6=A3=80=E6=9F=A5?=
 =?UTF-8?q?=E6=95=B0=E6=8D=AE=E5=BA=93=E6=98=AF=E5=90=A6=E6=9C=89=E9=87=8D?=
 =?UTF-8?q?=E5=A4=8D=E6=95=B0=E6=8D=AE=E5=8A=9F=E8=83=BD=EF=BC=8C=E9=81=BF?=
 =?UTF-8?q?=E5=85=8D=E9=87=8D=E5=A4=8D=E5=AF=BC=E5=85=A5=E3=80=82?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../数据批量导入-checkpoint.ipynb             |  1 -
 quantitative_data/importer.py                 | 47 +++++++++++++++++--
 2 files changed, 44 insertions(+), 4 deletions(-)

diff --git a/quantitative_data/.ipynb_checkpoints/数据批量导入-checkpoint.ipynb b/quantitative_data/.ipynb_checkpoints/数据批量导入-checkpoint.ipynb
index 9d2ff3b..c3142f5 100644
--- a/quantitative_data/.ipynb_checkpoints/数据批量导入-checkpoint.ipynb
+++ b/quantitative_data/.ipynb_checkpoints/数据批量导入-checkpoint.ipynb
@@ -84,7 +84,6 @@
     "    init_database,\n",
     "    import_stock_basic,\n",
     "    import_trade_cal,\n",
-    "    import_daily_batch,\n",
     "    import_daily_by_year,\n",
     "    import_daily_basic,\n",
     "    import_daily_basic_by_date,\n",
diff --git a/quantitative_data/importer.py b/quantitative_data/importer.py
index 1fa5c3d..08f81b9 100644
--- a/quantitative_data/importer.py
+++ b/quantitative_data/importer.py
@@ -367,12 +367,16 @@ def import_daily_by_date(
     end_date: Optional[str] = None,
     conn=None,
     sleep_interval: float = 0.3,
+    skip_existing: bool = True,
 ):
     """
     按交易日批量导入日线行情 (高效模式)
     使用 pro.daily(trade_date='YYYYMMDD') 一次性拉取全市场当日数据
     大幅减少 API 调用次数: 约250交易日/年 × 16年 ≈ 4000次 (原来需要 5000股票 × 16年 = 80000次)
 
+    参数:
+    - skip_existing: 是否跳过数据库中已有数据的交易日 (默认 True，避免重复导入)
+
     返回: 失败的交易日列表
     """
     if start_date is None:
@@ -403,14 +407,51 @@ def import_daily_by_date(
             conn.close()
             conn = get_pg_connection()
 
-    total = len(trade_dates)
-    if total == 0:
+    total_cal = len(trade_dates)
+    if total_cal == 0:
         logger.warning(f"  日期范围 {start_date} ~ {end_date} 内无交易日")
         if own_conn:
             conn.close()
         return []
 
-    logger.info(f"  日期范围 {start_date} ~ {end_date}: 共 {total} 个交易日")
+    # --- 跳过已有数据的交易日 ---
+    skipped_count = 0
+    if skip_existing:
+        try:
+            cursor = conn.cursor()
+            cursor.execute(
+                """
+                SELECT DISTINCT trade_date FROM daily
+                WHERE trade_date >= %s AND trade_date <= %s
+                """,
+                (start_date, end_date),
+            )
+            existing_dates = set(row[0] for row in cursor.fetchall())
+            cursor.close()
+            if existing_dates:
+                # 统一格式为 date 类型再比较
+                trade_dates_filtered = [td for td in trade_dates if td not in existing_dates]
+                skipped_count = len(trade_dates) - len(trade_dates_filtered)
+                trade_dates = trade_dates_filtered
+        except Exception as e:
+            logger.warning(f"  查询已有交易日失败，将导入全部: {e}")
+            # 查询失败时回退到全量导入（安全策略）
+
+    total = len(trade_dates)
+    if total == 0:
+        logger.info(f"  日期范围 {start_date} ~ {end_date}: 所有 {total_cal} 个交易日均已有数据，无需导入")
+        if own_conn:
+            conn.close()
+        return []
+
+    if skipped_count > 0:
+        logger.info(
+            f"  日期范围 {start_date} ~ {end_date}: "
+            f"共 {total_cal} 个交易日，跳过 {skipped_count} 个已有数据，"
+            f"待导入 {total} 个"
+        )
+    else:
+        logger.info(f"  日期范围 {start_date} ~ {end_date}: 共 {total} 个交易日")
 
     pro = get_ts_pro()
     success_count = 0