{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>tag</th>\n",
       "      <th>title</th>\n",
       "      <th>body</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>功能文档</td>\n",
       "      <td>数据表格</td>\n",
       "      <td>数据表格 数据表格是简化版的excel，可以使用【数据表格】相关的指令对其进行操作，支持导...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>问答</td>\n",
       "      <td>数据表格数据处理</td>\n",
       "      <td>数据表格批量获取数据后，然后循环处理数据表格，再循环里面过滤不要的数据，用删除数据表格行删除...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>指令文档</td>\n",
       "      <td>清空数据表格</td>\n",
       "      <td>清空数据表格 清空数据表格 注：【 清空数据表格 】指令一般主要是用于在流程开始前初始化数...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>指令文档</td>\n",
       "      <td>数据表格导入</td>\n",
       "      <td>数据表格导入 导入数据到数据表格 文件路径 目标文件的绝对路径,支持xls、xlsx、cs...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>指令文档</td>\n",
       "      <td>数据表格导出</td>\n",
       "      <td>数据表格导出 将数据表格导出为文件 文件夹 桌面/下载目录/临时目录/自定义目录 文件名称...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    tag     title                                               body\n",
       "0  功能文档      数据表格   数据表格 数据表格是简化版的excel，可以使用【数据表格】相关的指令对其进行操作，支持导...\n",
       "1    问答  数据表格数据处理  数据表格批量获取数据后，然后循环处理数据表格，再循环里面过滤不要的数据，用删除数据表格行删除...\n",
       "2  指令文档    清空数据表格   清空数据表格 清空数据表格 注：【 清空数据表格 】指令一般主要是用于在流程开始前初始化数...\n",
       "3  指令文档    数据表格导入   数据表格导入 导入数据到数据表格 文件路径 目标文件的绝对路径,支持xls、xlsx、cs...\n",
       "4  指令文档    数据表格导出   数据表格导出 将数据表格导出为文件 文件夹 桌面/下载目录/临时目录/自定义目录 文件名称..."
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import requests\n",
    "url = 'https://api.yingdao.com/api/noauth/v1/sns/fullIndex/search'\n",
    "headers = {\n",
    "    'accept': 'application/json',\n",
    "    'authorization': 'Bearer 4e49960a-4d22-4fed-acea-d6faee687c4c',\n",
    "}\n",
    "\n",
    "all_data = []\n",
    "page = 1\n",
    "while True:\n",
    "    params = {\n",
    "        'page': page,\n",
    "        'size': 20,\n",
    "        'key': '数据表格',\n",
    "        'source': ''\n",
    "    }\n",
    "    response = requests.get(url, headers=headers, params=params)\n",
    "    data = response.json()\n",
    "    if not data['data']:\n",
    "        break\n",
    "    all_data.extend(data['data'])\n",
    "    page += 1\n",
    "\n",
    "all_data\n",
    "import re\n",
    "\n",
    "def remove_em_tags(text):\n",
    "    return re.sub(r'<em>(.*?)</em>', r'\\1', text)\n",
    "\n",
    "import pandas as pd\n",
    "# Extract tag, title, and body from the results\n",
    "extracted_data = []\n",
    "for item in all_data:\n",
    "    extracted_data.append({\n",
    "        'tag': item.get('tag'),\n",
    "        'title': remove_em_tags(item.get('title', '')),\n",
    "        'body': remove_em_tags(item.get('body', ''))\n",
    "    })\n",
    "# Create a DataFrame and save to an xlsx file\n",
    "df = pd.DataFrame(extracted_data)\n",
    "df.to_excel('extracted_data.xlsx', index=False)\n",
    "df.head()  # Display the first few rows of the DataFrame to verify\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}