NewStock/main/data/update/sw_daily.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f74ce078-f7e8-4733-a14c-14d8815a3626",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:35.618124Z",
     "start_time": "2025-04-09T14:57:34.837095Z"
    }
   },
   "outputs": [],
   "source": [
    "import tushare as ts\n",
    "ts.set_token('3a0741c702ee7e5e5f2bf1f0846bafaafe4e320833240b2a7e4a685f')\n",
    "pro = ts.pro_api()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "44dd8d87-e60b-49e5-aed9-efaa7f92d4fe",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:38.089531Z",
     "start_time": "2025-04-09T14:57:35.854308Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        ts_code trade_date\n",
      "0     801001.SI   20250221\n",
      "1     801002.SI   20250221\n",
      "2     801003.SI   20250221\n",
      "3     801005.SI   20250221\n",
      "4     801010.SI   20250221\n",
      "...         ...        ...\n",
      "2190  859811.SI   20260112\n",
      "2191  859821.SI   20260112\n",
      "2192  859822.SI   20260112\n",
      "2193  859852.SI   20260112\n",
      "2194  859951.SI   20260112\n",
      "\n",
      "[1140973 rows x 2 columns]\n",
      "20260116\n",
      "start_date: 20260119\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import time\n",
    "\n",
    "h5_filename = '/mnt/d/PyProject/NewStock/data/sw_daily.h5'\n",
    "key = '/sw_daily'\n",
    "max_date = None\n",
    "with pd.HDFStore(h5_filename, mode='r') as store:\n",
    "    df = store[key][['ts_code', 'trade_date']]\n",
    "    print(df)\n",
    "    max_date = df['trade_date'].max()\n",
    "\n",
    "print(max_date)\n",
    "trade_cal = pro.trade_cal(exchange='', start_date='20170101', end_date='20260201')\n",
    "trade_cal = trade_cal[trade_cal['is_open'] == 1]  # 只保留交易日\n",
    "trade_dates = trade_cal[trade_cal['cal_date'] > max_date]['cal_date'].tolist()\n",
    "start_date = min(trade_dates)\n",
    "print(f'start_date: {start_date}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "747acc47-0884-4f76-90fb-276f6494e31d",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:40.754159Z",
     "start_time": "2025-04-09T14:57:38.104541Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "任务 20260130 完成\n",
      "任务 20260129 完成\n",
      "任务 20260128 完成\n",
      "任务 20260127 完成\n",
      "任务 20260126 完成\n",
      "任务 20260123 完成\n",
      "任务 20260122 完成\n",
      "任务 20260121 完成\n",
      "任务 20260120 完成\n",
      "任务 20260119 完成\n"
     ]
    }
   ],
   "source": [
    "from concurrent.futures import ThreadPoolExecutor, as_completed\n",
    "\n",
    "all_daily_data = []\n",
    "\n",
    "# API 调用计数和时间控制变量\n",
    "api_call_count = 0\n",
    "batch_start_time = time.time()\n",
    "\n",
    "\n",
    "def get_data(trade_date):\n",
    "    time.sleep(0.1)\n",
    "    data = pro.sw_daily(trade_date=trade_date)\n",
    "    if data is not None and not data.empty:\n",
    "        return data\n",
    "\n",
    "\n",
    "with ThreadPoolExecutor(max_workers=2) as executor:\n",
    "    future_to_date = {executor.submit(get_data, td): td for td in trade_dates}\n",
    "\n",
    "    for future in as_completed(future_to_date):\n",
    "        trade_date = future_to_date[future]  # 获取对应的交易日期\n",
    "        try:\n",
    "            result = future.result()  # 获取任务执行的结果\n",
    "            all_daily_data.append(result)\n",
    "            print(f\"任务 {trade_date} 完成\")\n",
    "        except Exception as e:\n",
    "            print(f\"获取 {trade_date} 数据时出错: {e}\")\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c6765638-481f-40d8-a259-2e7b25362618",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:40.994975Z",
     "start_time": "2025-04-09T14:57:40.773783Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "所有每日基础数据获取并保存完毕！\n"
     ]
    }
   ],
   "source": [
    "all_daily_data_df = pd.concat(all_daily_data, ignore_index=True)\n",
    "\n",
    "# 将所有数据合并为一个 DataFrame\n",
    "\n",
    "# 将数据保存为 HDF5 文件（table 格式）\n",
    "all_daily_data_df.to_hdf(h5_filename, key=key, mode='a', format='table', append=True, data_columns=True)\n",
    "\n",
    "print(\"所有每日基础数据获取并保存完毕！\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "stock",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}