{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 数字文件名转换为文本文件名"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 数字文件名转换为文本文件名"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os,sys\n",
    "import xlrd\n",
    "import math\n",
    "\n",
    "fi_xls = 'test1.xlsx'\n",
    "fi_name = {}\n",
    "fi_path = os.getcwd()+'/pdf'\n",
    "old = []\n",
    "new = []\n",
    "wb = xlrd.open_workbook(fi_xls)\n",
    "sheet1 = wb.sheet_by_index(0)\n",
    "for r in range(sheet1.nrows):\n",
    "    col = []\n",
    "    m1 = str(sheet1.cell(r,0).value)\n",
    "    m1 = str(math.floor(eval(m1)))\n",
    "    m2 = str(sheet1.cell(r,1).value)\n",
    "    fi_name[m1] = m2\n",
    "old = fi_name.keys()\n",
    "new = fi_name.values()\n",
    "fl=os.listdir(fi_path)\n",
    "n = 0\n",
    "for i in fl:\n",
    "    oldname=fl[n]\n",
    "    name, suffix = os.path.splitext(oldname)\n",
    "    if name in old:\n",
    "        new_name = fi_path+ os.sep + fi_name[name]+suffix\n",
    "        old_name = fi_path+ os.sep + fl[n]\n",
    "        os.rename(old_name,new_name)\n",
    "    n+= 1\n",
    "print(n)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 目录文件按照文件名排序"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "import os,sys\n",
    "\n",
    "\n",
    "fi_xls = 'test1.xlsx'\n",
    "fi_name = {}\n",
    "#fi_path = 'drive/My Drive/Colab Notebooks'+'/data'\n",
    "fi_path = os.getcwd()+'/data'\n",
    "old = []\n",
    "new = []\n",
    "\n",
    "fl=os.listdir(fi_path)\n",
    "fl.sort()\n",
    "n = 0\n",
    "for i in fl:\n",
    "    oldname=fl[n]\n",
    "    name, suffix = os.path.splitext(oldname)\n",
    "    if name in old:\n",
    "        new_name = fi_path+ os.sep + fi_name[name]+suffix\n",
    "        old_name = fi_path+ os.sep + fl[n]\n",
    "        os.rename(old_name,new_name)\n",
    "    n+= 1\n",
    "fl"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "toc-hr-collapsed": true,
    "toc-nb-collapsed": true
   },
   "source": [
    "## 将pdf文件转为图片"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pdf2image import convert_from_path, convert_from_bytes\n",
    "import os,sys\n",
    "import tempfile\n",
    "from pdf2image.exceptions import (\n",
    "    PDFInfoNotInstalledError,\n",
    "    PDFPageCountError,\n",
    "    PDFSyntaxError\n",
    ")\n",
    "#images = convert_from_path('1.pdf',dpi=200,fmt='jpg', output_folder='./sample_data')\n",
    "with tempfile.TemporaryDirectory() as path:\n",
    "    images_from_path = convert_from_path('./data/普通高等学校本科专业目录.pdf', dpi=300,fmt='jpg', output_folder='./data/pic')\n",
    "print(path)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "toc-hr-collapsed": true,
    "toc-nb-collapsed": true
   },
   "source": [
    "## 图像文件夹打包"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import zipfile\n",
    "from pdf2image import convert_from_path, convert_from_bytes\n",
    "import os,sys\n",
    "import tempfile\n",
    "import shutil\n",
    "import time\n",
    "\n",
    "from pdf2image.exceptions import (\n",
    "    PDFInfoNotInstalledError,\n",
    "    PDFPageCountError,\n",
    "    PDFSyntaxError\n",
    ")\n",
    "def compress_file(zipfilename, dirname):      # zipfilename是压缩包名字，dirname是要打包的目录\n",
    "    if os.path.isfile(dirname):\n",
    "        with zipfile.ZipFile(zipfilename, 'w') as z:\n",
    "            z.write(dirname)\n",
    "    else:\n",
    "        with zipfile.ZipFile(zipfilename, 'w') as z:\n",
    "            for root, dirs, files in os.walk(dirname):\n",
    "                for single_file in files:\n",
    "                    if single_file != zipfilename:\n",
    "                        filepath = os.path.join(root, single_file)\n",
    "                        z.write(filepath)\n",
    "\n",
    "def addfile(zipfilename, dirname):\n",
    "    if os.path.isfile(dirname):\n",
    "        with zipfile.ZipFile(zipfilename, 'a') as z:\n",
    "            z.write(dirname)\n",
    "    else:\n",
    "        with zipfile.ZipFile(zipfilename, 'a') as z:\n",
    "            for root, dirs, files in os.walk(dirname):\n",
    "                for single_file in files:\n",
    "                    if single_file != zipfilename:\n",
    "                        filepath = os.path.join(root, single_file)\n",
    "                        z.write(filepath)\n",
    "\n",
    "#images = convert_from_path('1.pdf',dpi=200,fmt='jpg', output_folder='./sample_data')\n",
    "def make_path(p):\n",
    "    if os.path.exists(p):       # 判断文件夹是否存在\n",
    "        shutil.rmtree(p)        # 删除文件夹\n",
    "    os.mkdir(p)    \n",
    "pdf_file = '2.pdf'\n",
    "output_folder='./pic1'\n",
    "zip_file = 'ribenweiqishihua.zip'\n",
    "make_path(output_folder)\n",
    "print (time.strftime(\"%a %b %d %H:%M:%S %Y\", time.localtime()))\n",
    "with tempfile.TemporaryDirectory() as path:\n",
    "    images_from_path = convert_from_path(pdf_file, dpi=300,fmt='jpg', output_folder=output_folder)\n",
    "compress_file(zip_file, output_folder)      # 执行函数\n",
    "print (time.strftime(\"%a %b %d %H:%M:%S %Y\", time.localtime()))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "toc-hr-collapsed": true,
    "toc-nb-collapsed": true
   },
   "source": [
    "## 文本文件操作"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 基本读取"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "file_name = 'data/2012.txt'\n",
    "with open(file_name,'r') as fl,open('new_2012_1.txt','w') as fl1:\n",
    "    for l in fl:\n",
    "        l = re.sub('[\\r\\n\\f ]{1,}', '', l)\n",
    "        if l.split():\n",
    "            print(l)\n",
    "            fl1.write(l)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 读取分隔符分割文件，导入MongoDB"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pymongo\n",
    "import re\n",
    "myclient = pymongo.MongoClient('mongodb://localhost:27017/')\n",
    "mydb = myclient[\"gaokao\"]\n",
    "mycol = mydb[\"city\"]\n",
    "m_mongo = {}\n",
    "m_xx = []\n",
    "fl_name = 'china-city-list.txt'\n",
    "n = 0\n",
    "with open(fl_name,'r') as fl:\n",
    "    for l in fl:\n",
    "        n += 1\n",
    "        if n >6:\n",
    "            m_mongo = {}\n",
    "            m_xx = re.sub('[ ]{1,}', '', l).split('|')\n",
    "            #print(m_xx[1],m_xx[3],m_xx[8],m_xx[10])\n",
    "            m_mongo['name'] = m_xx[3]\n",
    "            m_mongo['code'] = m_xx[1]\n",
    "            m_mongo['sheng'] = m_xx[8]\n",
    "            m_mongo['shi'] = m_xx[10]\n",
    "            m_mongo['jing'] = m_xx[11]\n",
    "            m_mongo['wei'] = m_xx[12]\n",
    "            mycol.insert_one(m_mongo) \n",
    "            #print(m_mongo)\n",
    "print('ok!')\n",
    "\n",
    "\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "toc-hr-collapsed": true,
    "toc-nb-collapsed": true
   },
   "source": [
    "# Twilio使用"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from twilio.rest import Client\n",
    "\n",
    "\n",
    "# Your Account Sid and Auth Token from twilio.com/console\n",
    "# and set the environment variables. See http://twil.io/secure\n",
    "account_sid = 'AC1aac8c18078bf371992fda0f924860c8'\n",
    "auth_token = '956199d0f1b724d00ef8bb934fcaefe9'\n",
    "client = Client(account_sid, auth_token)\n",
    "\n",
    "message = client.messages \\\n",
    "                .create(\n",
    "                     body=\"I'm back.\",\n",
    "                     from_='+12056066931',\n",
    "                     to='+8613793180751'\n",
    "                 )\n",
    "\n",
    "print(message.sid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import time\n",
    "\n",
    "localtime = time.localtime(time.time())\n",
    "#type(localtime)\n",
    "print (\"本地时间为 :\", localtime)\n",
    "jyr = '12345'\n",
    "if time.strftime(\"%w\", time.localtime()) in jyr:\n",
    "    print('ok')\n",
    "else:\n",
    "    print('今日不是交易日！')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from email.mime.text import MIMEText\n",
    "from email.header import Header\n",
    "import smtplib\n",
    "import requests\n",
    "import time\n",
    "import re\n",
    "\n",
    "def sendmail(message):\n",
    "    msg = MIMEText(message,'plain','utf-8')\n",
    "    msg['Subject'] = Header(\"外汇价格已经到达预期价位！\",'utf-8')\n",
    "    msg['From'] = Header('512song@sina.com')\n",
    "    msg['To'] = Header('songyi@yeah.net','utf-8')\n",
    "\n",
    "    from_addr = '512song@sina.com' #发件邮箱\n",
    "    password = '409fe5d8471da663' #邮箱密码\n",
    "    to_addr = 'songyi@yeah.net' #收件邮箱\n",
    "    smtp_server = 'smtp.sina.com' #SMTP服务器，以新浪为例\n",
    "    server = smtplib.SMTP(smtp_server,25) #第二个参数为默认端口为25，有些邮件有特殊端口\n",
    "    server.login(from_addr,password) #登录邮箱\n",
    "    server.sendmail(from_addr,to_addr,msg.as_string())  #将msg转化成string发出\n",
    "    server.quit()    \n",
    "    \n",
    "       \n",
    "\n",
    "pattern = re.compile(r'\\\"(.*)\\\"')\n",
    "url = 'http://hq.sinajs.cn/list=USDCAD'\n",
    "strhtml = requests.get(url)\n",
    "data = strhtml.text\n",
    "if pattern.findall(data):\n",
    "    for data1 in pattern.findall(data):\n",
    "        data2 = data1.split(',')\n",
    "#print(data2)\n",
    "with open('price.txt','r') as fl:\n",
    "    for line in fl:\n",
    "        p_high = line.split(',')[0]\n",
    "        p_low = line.split(',')[1]\n",
    "m_message = '当前美元加元买入价：{}'.format(data2[1])\n",
    "while time.strftime(\"%w\", time.localtime()) in '12345':\n",
    "    \n",
    "    print(p_high,p_low)\n",
    "    time.sleep(10)\n",
    "    strhtml = requests.get(url)\n",
    "    data = strhtml.text\n",
    "    if pattern.findall(data):\n",
    "        for data1 in pattern.findall(data):\n",
    "            data2 = data1.split(',')\n",
    "        if float(data2[1]) > float(p_high):\n",
    "            m_message = '当前美元加元买入价：{}'.format(data2[1])\n",
    "            sendmail(m_message)\n",
    "            p_high = str(float(p_high) + 0.04) \n",
    "        if float(data2[1]) > float(p_high):\n",
    "            m_message = '当前美元加元卖出价：{}'.format(data2[2])\n",
    "            p_low = str(float(p_low) - 0.04)\n",
    "            sendmail(m_message)\n",
    "    time.sleep(900)\n",
    "            "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "toc-hr-collapsed": true,
    "toc-nb-collapsed": true
   },
   "source": [
    "# AWS应用"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## AWS获取sns信息"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import boto3\n",
    "\n",
    "# Create an SNS client\n",
    "sns = boto3.client('sns')\n",
    "\n",
    "# Call SNS to list topics\n",
    "response = sns.list_topics()\n",
    "\n",
    "# Get a list of all topic ARNs from the response\n",
    "topics = [topic['TopicArn'] for topic in response['Topics']]\n",
    "\n",
    "# Print out the topic list\n",
    "print(\"Topic List: %s\" % topics)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## AWS操作DynamoDB"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-17T01:38:23.108908Z",
     "iopub.status.busy": "2020-11-17T01:38:23.107956Z",
     "iopub.status.idle": "2020-11-17T01:38:44.538417Z",
     "shell.execute_reply": "2020-11-17T01:38:44.535587Z",
     "shell.execute_reply.started": "2020-11-17T01:38:23.108799Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n"
     ]
    }
   ],
   "source": [
    "import boto3\n",
    "\n",
    "# Get the service resource.\n",
    "dynamodb = boto3.resource('dynamodb')\n",
    "\n",
    "# Create the DynamoDB table.\n",
    "table = dynamodb.create_table(\n",
    "    TableName='waihui',\n",
    "    \n",
    "    AttributeDefinitions=[        \n",
    "        {\n",
    "            'AttributeName': 'code',\n",
    "            'AttributeType': 'S'\n",
    "        }\n",
    "        \n",
    "        \n",
    "    ],\n",
    "    KeySchema=[\n",
    "        {\n",
    "            'AttributeName': 'code',\n",
    "            'KeyType': 'HASH'\n",
    "        }\n",
    "        \n",
    "    ],\n",
    "    ProvisionedThroughput={\n",
    "        'ReadCapacityUnits': 5,\n",
    "        'WriteCapacityUnits': 5\n",
    "    }\n",
    "    \n",
    ")\n",
    "\n",
    "# Wait until the table exists.\n",
    "table.meta.client.get_waiter('table_exists').wait(TableName='waihui')\n",
    "\n",
    "# Print out some data about the table.\n",
    "print(table.item_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-17T01:43:20.350295Z",
     "iopub.status.busy": "2020-11-17T01:43:20.349393Z",
     "iopub.status.idle": "2020-11-17T01:43:23.386976Z",
     "shell.execute_reply": "2020-11-17T01:43:23.384304Z",
     "shell.execute_reply.started": "2020-11-17T01:43:20.350192Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'ResponseMetadata': {'RequestId': 'C9B2079636H46D3BCM9K0IJJPVVV4KQNSO5AEMVJF66Q9ASUAAJG',\n",
       "  'HTTPStatusCode': 200,\n",
       "  'HTTPHeaders': {'server': 'Server',\n",
       "   'date': 'Tue, 17 Nov 2020 01:43:23 GMT',\n",
       "   'content-type': 'application/x-amz-json-1.0',\n",
       "   'content-length': '2',\n",
       "   'connection': 'keep-alive',\n",
       "   'x-amzn-requestid': 'C9B2079636H46D3BCM9K0IJJPVVV4KQNSO5AEMVJF66Q9ASUAAJG',\n",
       "   'x-amz-crc32': '2745614147'},\n",
       "  'RetryAttempts': 0}}"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import boto3\n",
    "import decimal\n",
    "# Get the service resource.\n",
    "dynamodb = boto3.resource('dynamodb')\n",
    "\n",
    "table = dynamodb.Table('waihui')\n",
    "\n",
    "table.put_item(\n",
    "   Item={\n",
    "        'code': 'USDCAD',\n",
    "        'high': Decimal('1.3200'),\n",
    "        'low': Decimal('1.3000'),\n",
    "    }\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-17T01:58:10.720722Z",
     "iopub.status.busy": "2020-11-17T01:58:10.719781Z",
     "iopub.status.idle": "2020-11-17T01:58:13.750170Z",
     "shell.execute_reply": "2020-11-17T01:58:13.747156Z",
     "shell.execute_reply.started": "2020-11-17T01:58:10.720618Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'high': Decimal('1.32'), 'low': Decimal('1.298'), 'code': 'USDCAD'}\n"
     ]
    }
   ],
   "source": [
    "import boto3\n",
    "# Get the service resource.\n",
    "dynamodb = boto3.resource('dynamodb')\n",
    "\n",
    "table = dynamodb.Table('waihui')\n",
    "\n",
    "response = table.get_item(\n",
    "   Key={\n",
    "        'code': 'USDCAD'        \n",
    "    }\n",
    ")\n",
    "item = response['Item']\n",
    "print(item)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-17T01:43:05.153025Z",
     "iopub.status.busy": "2020-11-17T01:43:05.152079Z",
     "iopub.status.idle": "2020-11-17T01:43:06.138506Z",
     "shell.execute_reply": "2020-11-17T01:43:06.135790Z",
     "shell.execute_reply.started": "2020-11-17T01:43:05.152919Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'ResponseMetadata': {'RequestId': 'HJ7KVGIA4B36S7EAIGBNI8OGMVVV4KQNSO5AEMVJF66Q9ASUAAJG',\n",
       "  'HTTPStatusCode': 200,\n",
       "  'HTTPHeaders': {'server': 'Server',\n",
       "   'date': 'Tue, 17 Nov 2020 01:43:06 GMT',\n",
       "   'content-type': 'application/x-amz-json-1.0',\n",
       "   'content-length': '2',\n",
       "   'connection': 'keep-alive',\n",
       "   'x-amzn-requestid': 'HJ7KVGIA4B36S7EAIGBNI8OGMVVV4KQNSO5AEMVJF66Q9ASUAAJG',\n",
       "   'x-amz-crc32': '2745614147'},\n",
       "  'RetryAttempts': 0}}"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import boto3\n",
    "# Get the service resource.\n",
    "dynamodb = boto3.resource('dynamodb')\n",
    "\n",
    "table = dynamodb.Table('waihui')\n",
    "\n",
    "table.delete_item(\n",
    "   Key={\n",
    "        'code': 'USDCAD'        \n",
    "    }\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-17T01:58:00.482537Z",
     "iopub.status.busy": "2020-11-17T01:58:00.481642Z",
     "iopub.status.idle": "2020-11-17T01:58:01.617227Z",
     "shell.execute_reply": "2020-11-17T01:58:01.614695Z",
     "shell.execute_reply.started": "2020-11-17T01:58:00.482434Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'ResponseMetadata': {'RequestId': 'F9DR02KDF2PKEQ7R1MSAUCKVIBVV4KQNSO5AEMVJF66Q9ASUAAJG',\n",
       "  'HTTPStatusCode': 200,\n",
       "  'HTTPHeaders': {'server': 'Server',\n",
       "   'date': 'Tue, 17 Nov 2020 01:58:01 GMT',\n",
       "   'content-type': 'application/x-amz-json-1.0',\n",
       "   'content-length': '2',\n",
       "   'connection': 'keep-alive',\n",
       "   'x-amzn-requestid': 'F9DR02KDF2PKEQ7R1MSAUCKVIBVV4KQNSO5AEMVJF66Q9ASUAAJG',\n",
       "   'x-amz-crc32': '2745614147'},\n",
       "  'RetryAttempts': 0}}"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import boto3\n",
    "import decimal\n",
    "# Get the service resource.\n",
    "dynamodb = boto3.resource('dynamodb')\n",
    "\n",
    "table = dynamodb.Table('waihui')\n",
    "table.update_item(\n",
    "    Key={\n",
    "        'code': 'USDCAD'\n",
    "    },\n",
    "    UpdateExpression='SET low = :val1',\n",
    "    ExpressionAttributeValues={\n",
    "        ':val1': Decimal('1.2980')\n",
    "    }\n",
    ")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# MongoDB系统GridFS文件管理"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 文件上传"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-26T05:30:36.433098Z",
     "iopub.status.busy": "2020-11-26T05:30:36.432192Z",
     "iopub.status.idle": "2020-11-26T05:30:37.438663Z",
     "shell.execute_reply": "2020-11-26T05:30:37.436233Z",
     "shell.execute_reply.started": "2020-11-26T05:30:36.432996Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5fbf3d7c62452a56d7d16630\n",
      "5fbf3d7d62452a56d7d16635\n",
      "5fbf3d7d62452a56d7d1663a\n",
      "5fbf3d7d62452a56d7d1663f\n",
      "5fbf3d7d62452a56d7d16643\n",
      "5fbf3d7d62452a56d7d16648\n",
      "5fbf3d7d62452a56d7d1664d\n"
     ]
    }
   ],
   "source": [
    "import pymongo\n",
    "from gridfs import GridFS\n",
    "from bson.objectid import ObjectId\n",
    "import os\n",
    "\n",
    "myclient = pymongo.MongoClient('mongodb://localhost:27017/')\n",
    "mydb = myclient[\"gaokao\"]\n",
    "mycol = mydb[\"college\"]\n",
    "\n",
    "UploadCache = \"uploadcache\"\n",
    "dbURL = \"mongodb://localhost:27017\"\n",
    "\n",
    "#上传文件\n",
    "def upLoadFile(file_coll,file_name,data_link):\n",
    "    client = pymongo.MongoClient('mongodb://localhost:27017/')\n",
    "\n",
    "    db = client[\"gaokao\"]\n",
    "\n",
    "    filter_condition = {\"filename\": os.path.basename(file_name), \"url\": data_link}\n",
    "    gridfs_col = GridFS(db, collection=file_coll)\n",
    "    file_ = \"0\"\n",
    "    query = {\"filename\":\"\"}\n",
    "    query[\"filename\"] = file_name\n",
    "\n",
    "    if gridfs_col.exists(query):\n",
    "        print('已经存在该文件')\n",
    "    else:\n",
    "\n",
    "        with open(file_name, 'rb') as file_r:\n",
    "            file_data = file_r.read()\n",
    "            file_ = gridfs_col.put(data=file_data, **filter_condition)  # 上传到gridfs\n",
    "\n",
    "            print(file_)\n",
    "\n",
    "\n",
    "    return file_   \n",
    "# 按文件名获取文档\n",
    "def downLoadFile(self,file_coll,file_name,out_name,ver):\n",
    "    client = pymongo.MongoClient(self.dbURL)\n",
    "\n",
    "    db = client[\"store\"]\n",
    "\n",
    "    gridfs_col = GridFS(db, collection=file_coll)\n",
    "\n",
    "    file_data = gridfs_col.get_version(filename=file_name, version=ver).read()\n",
    "\n",
    "    with open(out_name, 'wb') as file_w:\n",
    "        file_w.write(file_data)\n",
    "\n",
    "# 按文件_Id获取文档       \n",
    "def downLoadFilebyID(self,file_coll,_id,out_name):\n",
    "    client = pymongo.MongoClient(self.dbURL)\n",
    "\n",
    "    db = client[\"store\"]\n",
    "\n",
    "    gridfs_col = GridFS(db, collection=file_coll)\n",
    "\n",
    "    O_Id = ObjectId(_id)\n",
    "\n",
    "    gf = gridfs_col.get(file_id=O_Id)\n",
    "    file_data = gf.read()\n",
    "    with open(out_name, 'wb') as file_w:\n",
    "\n",
    "        file_w.write(file_data)     \n",
    "\n",
    "\n",
    "    return gf.filename    \n",
    "m_dir = './data/tmp'\n",
    "fls=os.listdir(m_dir)\n",
    "n = 0\n",
    "for fl in fls:\n",
    "    #oldname=fl[n]\n",
    "    name, suffix = os.path.splitext(fl)\n",
    "    #if name in old:\n",
    "    #    new_name = fi_path+ os.sep + fi_name[name]+suffix\n",
    "    #    old_name = fi_path+ os.sep + fl[n]\n",
    "     #   os.rename(old_name,new_name)\n",
    "    #print(os.path.basename(fl))\n",
    "    #print(fl,suffix[1:])\n",
    "    full_path = m_dir+ '/' + fl\n",
    "    upLoadFile(\"document\",full_path,\"\")\n",
    "#a = MongoGridFS(\"\")\n",
    "#a.upLoadFile(\"pdf\",\"MongoGridFS.py\",\"\")\n",
    "#a.downLoadFile(\"pdf\",\"MongoGridFS.py\",\"out2.p\",2)\n",
    "#ll = a.downLoadFilebyID(\"pdf\",\"5d70a5b283a3c5104cd39346\",\"out3.p\")\n",
    "#print (ll)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-26T05:10:44.453509Z",
     "iopub.status.busy": "2020-11-26T05:10:44.452576Z",
     "iopub.status.idle": "2020-11-26T05:10:44.517014Z",
     "shell.execute_reply": "2020-11-26T05:10:44.515170Z",
     "shell.execute_reply.started": "2020-11-26T05:10:44.453402Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "./data/tmp/山东大学强基计划招生专业培养方案（2020版）+-+物理学.pdf\n"
     ]
    }
   ],
   "source": [
    "import pymongo\n",
    "from gridfs import GridFS\n",
    "from bson.objectid import ObjectId\n",
    "import os\n",
    "\n",
    "myclient = pymongo.MongoClient('mongodb://localhost:27017/')\n",
    "mydb = myclient[\"gaokao\"]\n",
    "mycol = mydb[\"college\"]\n",
    "\n",
    "UploadCache = \"uploadcache\"\n",
    "dbURL = \"mongodb://localhost:27017\"\n",
    "\n",
    "#上传文件\n",
    "def upLoadFile(file_coll,file_name,data_link):\n",
    "    client = pymongo.MongoClient('mongodb://localhost:27017/')\n",
    "\n",
    "    db = client[\"gaokao\"]\n",
    "\n",
    "    filter_condition = {\"filename\": file_name, \"url\": data_link}\n",
    "    gridfs_col = GridFS(db, collection=file_coll)\n",
    "    file_ = \"0\"\n",
    "    query = {\"filename\":\"\"}\n",
    "    query[\"filename\"] = file_name\n",
    "\n",
    "    if gridfs_col.exists(query):\n",
    "        print('已经存在该文件')\n",
    "    else:\n",
    "\n",
    "        with open(file_name, 'rb') as file_r:\n",
    "            file_data = file_r.read()\n",
    "            file_ = gridfs_col.put(data=file_data, **filter_condition)  # 上传到gridfs\n",
    "\n",
    "            print(file_)\n",
    "\n",
    "\n",
    "    return file_   \n",
    "# 按文件名获取文档\n",
    "def downLoadFile(self,file_coll,file_name,out_name,ver):\n",
    "    client = pymongo.MongoClient(self.dbURL)\n",
    "\n",
    "    db = client[\"store\"]\n",
    "\n",
    "    gridfs_col = GridFS(db, collection=file_coll)\n",
    "\n",
    "    file_data = gridfs_col.get_version(filename=file_name, version=ver).read()\n",
    "\n",
    "    with open(out_name, 'wb') as file_w:\n",
    "        file_w.write(file_data)\n",
    "\n",
    "# 按文件_Id获取文档       \n",
    "def downLoadFilebyID(file_coll,_id,out_name):\n",
    "    client = pymongo.MongoClient('mongodb://localhost:27017/')\n",
    "\n",
    "    db = client[\"gaokao\"]\n",
    "\n",
    "    gridfs_col = GridFS(db, collection=file_coll)\n",
    "\n",
    "    O_Id = ObjectId(_id)\n",
    "\n",
    "    gf = gridfs_col.get(file_id=O_Id)\n",
    "    file_data = gf.read()\n",
    "    with open(out_name, 'wb') as file_w:\n",
    "\n",
    "        file_w.write(file_data)     \n",
    "\n",
    "\n",
    "    return gf.filename    \n",
    "ll = downLoadFilebyID(\"pdf\",\"5fbf351b62452a56d7d16603\",\"out3.pdf\")\n",
    "print (ll)\n",
    "#a = MongoGridFS(\"\")\n",
    "#a.upLoadFile(\"pdf\",\"MongoGridFS.py\",\"\")\n",
    "#a.downLoadFile(\"pdf\",\"MongoGridFS.py\",\"out2.p\",2)\n",
    "#ll = a.downLoadFilebyID(\"pdf\",\"5d70a5b283a3c5104cd39346\",\"out3.pdf\")\n",
    "#print (ll)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}