{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "f74ce078-f7e8-4733-a14c-14d8815a3626",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:34.662465Z",
     "start_time": "2025-04-09T14:57:33.903794Z"
    }
   },
   "outputs": [],
   "source": [
    "import tushare as ts\n",
    "ts.set_token('3a0741c702ee7e5e5f2bf1f0846bafaafe4e320833240b2a7e4a685f')\n",
    "pro = ts.pro_api()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "44dd8d87-e60b-49e5-aed9-efaa7f92d4fe",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:41.818953Z",
     "start_time": "2025-04-09T14:57:34.666469Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "         ts_code trade_date\n",
      "0      000001.SZ   20250312\n",
      "1      000002.SZ   20250312\n",
      "2      000004.SZ   20250312\n",
      "3      000006.SZ   20250312\n",
      "4      000007.SZ   20250312\n",
      "...          ...        ...\n",
      "21755  920978.BJ   20251117\n",
      "21756  920981.BJ   20251117\n",
      "21757  920982.BJ   20251117\n",
      "21758  920985.BJ   20251117\n",
      "21759  920992.BJ   20251117\n",
      "\n",
      "[8385278 rows x 2 columns]\n",
      "20251120\n",
      "start_date: 20251121\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import time\n",
    "\n",
    "h5_filename = '/mnt/d/PyProject/NewStock/data/cyq_perf.h5'\n",
    "key = '/cyq_perf'\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='20251220')\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": 5,
   "id": "747acc47-0884-4f76-90fb-276f6494e31d",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:45.660215Z",
     "start_time": "2025-04-09T14:57:42.232250Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "任务 20251219 完成\n",
      "任务 20251218 完成\n",
      "任务 20251216 完成\n",
      "任务 20251217 完成\n",
      "任务 20251215 完成\n",
      "任务 20251212 完成\n",
      "任务 20251211 完成\n",
      "任务 20251210 完成\n",
      "任务 20251209 完成\n",
      "任务 20251208 完成\n",
      "任务 20251205 完成\n",
      "任务 20251204 完成\n",
      "任务 20251203 完成\n",
      "任务 20251202 完成\n",
      "任务 20251201 完成\n",
      "任务 20251128 完成\n",
      "任务 20251127 完成\n",
      "任务 20251126 完成\n",
      "任务 20251125 完成\n",
      "任务 20251124 完成\n",
      "任务 20251121 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.cyq_perf(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": 6,
   "id": "c6765638-481f-40d8-a259-2e7b25362618",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:48.970445Z",
     "start_time": "2025-04-09T14:57:45.698824Z"
    }
   },
   "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
}