{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "import zipfile,os,re,time\n",
    "import pandas as pd\n",
    "from pathlib import Path\n",
    "\n",
    "#设置工作目录, 要求工作目录中恰有一个.tex文件和一个.zip文件，其余不论\n",
    "filepath = \"数据导入作业文件\"\n",
    "\n",
    "#生成文件名tex_file和zip_file\n",
    "files = [os.path.join(filepath,f) for f in os.listdir(filepath)]\n",
    "tex_file = [f for f in files if \".tex\" in f][0]\n",
    "zip_file = [f for f in files if \".zip\" in f][0]\n",
    "\n",
    "#获得题号数据，保存在problems_list中\n",
    "with open(tex_file,\"r\",encoding = \"utf8\") as f:\n",
    "    tex_data = f.read()\n",
    "problems_list = re.findall(r\"\\(([\\d]{6})\\)\",tex_data)\n",
    "\n",
    "#在zip文件中找到包含正确率数据的文件\n",
    "zf = zipfile.ZipFile(zip_file)\n",
    "statfiles = [f.filename for f in zf.filelist if \"试题分析\" in f.filename]\n",
    "\n",
    "#生成答题纸区域编号与题目ID的对应\n",
    "correspondence_dict = {}\n",
    "if \"statsfile.xlsx\" in os.listdir(\"临时文件\"):\n",
    "    os.remove(\"临时文件/statsfile.xlsx\")\n",
    "extractedpath = Path(zf.extract(statfiles[0]))\n",
    "extractedpath.rename(\"临时文件/statsfile.xlsx\")\n",
    "df = pd.read_excel(\"临时文件/statsfile.xlsx\")\n",
    "problems_indexes = list(df[df.columns[0]][2:])\n",
    "for p in problems_indexes:\n",
    "    t = input(\"答题纸区域\"+p+\"的题号为(1-\"+str(len(problems_list))+\"):\")\n",
    "    if not (int(t)<1 or int(t)>len(problems_list)):\n",
    "        correspondence_dict[p] = problems_list[int(t)-1] \n",
    "\n",
    "outputstr = \"usages\\n\\n\"\n",
    "\n",
    "for sf in statfiles:\n",
    "    #读取文件生成区域列表与难度列表\n",
    "    classname = re.findall(r\"高三[\\d]*?班\",sf)[0]\n",
    "    date = str(time.localtime().tm_year)+str(time.localtime().tm_mon).zfill(2)+str(time.localtime().tm_mday).zfill(2)\n",
    "    if \"statsfile.xlsx\" in os.listdir(\"临时文件\"):\n",
    "        os.remove(\"临时文件/statsfile.xlsx\")\n",
    "    extractedpath = Path(zf.extract(sf))\n",
    "    extractedpath.rename(\"临时文件/statsfile.xlsx\")\n",
    "    df = pd.read_excel(\"临时文件/statsfile.xlsx\")\n",
    "    difficulties = list(df[df.columns[9]][2:])\n",
    "    problems_indexes = list(df[df.columns[0]][2:])\n",
    "    #生成该班级题目ID对应难度列表组成的字典\n",
    "    class_difficulty = {}\n",
    "    for i in range(len(difficulties)):\n",
    "        if problems_indexes[i] in correspondence_dict:\n",
    "            if not correspondence_dict[problems_indexes[i]] in class_difficulty:\n",
    "                class_difficulty[correspondence_dict[problems_indexes[i]]] = [difficulties[i]]\n",
    "            else:\n",
    "                class_difficulty[correspondence_dict[problems_indexes[i]]].append(difficulties[i])\n",
    "    #添加到输出字符串中\n",
    "    for id in class_difficulty:\n",
    "        outputstr += id + \"\\n\" + date + \"\\t\" + classname + \"\\t\" + \"\\t\".join([str(v) for v in class_difficulty[id]]) + \"\\n\\n\"\n",
    "\n",
    "with open(\"临时文件/自动转换结果.txt\",\"w\",encoding = \"utf8\") as f:\n",
    "    f.write(outputstr)\n",
    "            \n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0.9032,\n",
       " 1,\n",
       " 0.9355,\n",
       " 0.9677,\n",
       " 1,\n",
       " 0.9032,\n",
       " 0.7097,\n",
       " 0.9677,\n",
       " 0.4194,\n",
       " 0.9032,\n",
       " 0.0645,\n",
       " 0.7419,\n",
       " 0.8387,\n",
       " 0.8065,\n",
       " 1,\n",
       " 0.6129,\n",
       " 0.9032,\n",
       " 0.7419,\n",
       " 0.9301,\n",
       " 0.6452,\n",
       " 1,\n",
       " 0.6855,\n",
       " 0.9677,\n",
       " 0.5108,\n",
       " 1,\n",
       " 0.4919,\n",
       " 0.5914,\n",
       " 0.3871]"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "difficulties"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'010923'"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "problems_list[int(t)-1]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'临时文件\\\\班级报表\\\\高三10班\\\\数学\\\\试题分析（数学）.xlsx'"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "zf.extract(sf,"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.8.8 ('base')",
   "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": "3.8.8"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "d311ffef239beb3b8f3764271728f3972d7b090c974f8e972fcdeedf230299ac"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}