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   20250526\n",
      "2191  859821.SI   20250526\n",
      "2192  859822.SI   20250526\n",
      "2193  859852.SI   20250526\n",
      "2194  859951.SI   20250526\n",
      "\n",
      "[1073367 rows x 2 columns]\n",
      "20250530\n",
      "start_date: 20250603\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='20250620')\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 20250620 完成\n",
      "任务 20250619 完成\n",
      "任务 20250618 完成\n",
      "任务 20250617 完成\n",
      "任务 20250616 完成\n",
      "任务 20250613 完成\n",
      "任务 20250611 完成\n",
      "任务 20250612 完成\n",
      "任务 20250610 完成\n",
      "任务 20250609 完成\n",
      "任务 20250606 完成\n",
      "任务 20250605 完成\n",
      "任务 20250604 完成\n",
      "任务 20250603 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": "3.13.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}