20211215

数据处理.ipynb

@@ -174,6 +174,13 @@
     "## 穴位数据导入"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 简单导出简介、内容"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -198,11 +205,476 @@
     "        dict1.setdefault(line1['title'][0],{})\n",
     "        dict1[line1['title'][0]]['简介'] = line1['jj'] \n",
     "        dict1[line1['title'][0]]['内容'] = dict2\n",
-    "filename = './file/穴位.json'\n",
+    "filename = './file/穴位1.json'\n",
     "with open(filename,'w') as fl:\n",
     "    json.dump(dict1, fl)        "
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 数据导入文件中"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import re\n",
+    "\n",
+    "dict1 = {}\n",
+    "filename = 'file/zhongyi/xuewei.json'\n",
+    "with open(filename,'r',encoding='utf-8') as fl:\n",
+    "    for line in fl:\n",
+    "        line1 = json.loads(re.sub(r'\\xa0','',line))\n",
+    "        list1 = line1['tables']\n",
+    "        list2 = line1['contents']\n",
+    "        list3 = line1['jj']\n",
+    "        dict2 = dict(zip(list1, list2))\n",
+    "        dict1.setdefault(line1['title'][0],{})\n",
+    "        if len(list3) > 0:\n",
+    "            \n",
+    "            dict1[line1['title'][0]]['about'] = list3\n",
+    "        dict1[line1['title'][0]].setdefault('content',{})\n",
+    "        for k, v in dict2.items():\n",
+    "            dict1[line1['title'][0]]['content'][k] = v \n",
+    "        #dict1[line1['title'][0]]['内容'] = dict2\n",
+    "filename = './file/穴位1.json'\n",
+    "with open(filename,'w') as fl:\n",
+    "    json.dump(dict1, fl)        "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 穴位数据导入数据库中"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import re\n",
+    "import pymongo\n",
+    "\n",
+    "myclient = pymongo.MongoClient('mongodb://192.168.3.100:27017/')\n",
+    "#dblist = myclient.list_database_names()\n",
+    "mydb = myclient['dayi']\n",
+    "mycol = mydb[\"xuewei\"]\n",
+    "db_list = []\n",
+    "filename = 'file/zhongyi/xuewei.json'\n",
+    "with open(filename,'r',encoding='utf-8') as fl:\n",
+    "    for line in fl:\n",
+    "        dict1 = {}\n",
+    "        line1 = json.loads(re.sub(r'\\xa0','',line))\n",
+    "        list1 = line1['tables']\n",
+    "        list2 = line1['contents']\n",
+    "        list3 = line1['jj']\n",
+    "        dict2 = dict(zip(list1, list2))\n",
+    "        dict1['name'] = line1['title'][0]\n",
+    "        if len(list3) > 0:\n",
+    "            dict1.setdefault('about',{})\n",
+    "            for s in list3:\n",
+    "                item = s.strip().split(':')\n",
+    "                dict1['about'][item[0]] = item[1]\n",
+    "        dict1.setdefault('content',{})\n",
+    "        for k, v in dict2.items():\n",
+    "            dict1['content'][k] = v \n",
+    "        #dict1[line1['title'][0]]['内容'] = dict2\n",
+    "        db_list.append(dict1)\n",
+    "x = mycol.insert_many(db_list)\n",
+    "print('ok!')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 中医症状数据导入数据库中"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import re\n",
+    "import pymongo\n",
+    "\n",
+    "myclient = pymongo.MongoClient('mongodb://192.168.3.100:27017/')\n",
+    "mydb = myclient['dayi']\n",
+    "mycol = mydb[\"zhongyizhengzhuang\"]\n",
+    "db_list = []\n",
+    "filename = 'file/zhongyi/zhongyizhengzhuang.json'\n",
+    "with open(filename,'r',encoding='utf-8') as fl:\n",
+    "    for line in fl:\n",
+    "        dict1 = {}\n",
+    "        line1 = json.loads(re.sub(r'\\xa0','',line))\n",
+    "        list1 = line1['tables']\n",
+    "        list2 = line1['contents']\n",
+    "        list3 = line1['jj']\n",
+    "        dict2 = dict(zip(list1, list2))\n",
+    "        dict1['name'] = line1['title'][0]\n",
+    "        if len(list3) > 0:\n",
+    "            dict1.setdefault('about',{})\n",
+    "            for i in range(0,int(len(list3)/2)):\n",
+    "                dict1['about'][list3[2*i]] = list3[2*i+1]\n",
+    "        dict1.setdefault('content',{})\n",
+    "        for k, v in dict2.items():\n",
+    "            dict1['content'][k] = v \n",
+    "        #dict1[line1['title'][0]]['内容'] = dict2\n",
+    "        db_list.append(dict1)\n",
+    "x = mycol.insert_many(db_list)\n",
+    "print('ok!')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 疾病数据导入数据库中"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import re\n",
+    "import pymongo\n",
+    "\n",
+    "myclient = pymongo.MongoClient('mongodb://192.168.3.100:27017/')\n",
+    "mydb = myclient['dayi']\n",
+    "mycol = mydb[\"jibing\"]\n",
+    "db_list = []\n",
+    "filename = 'file/zhongyi/jibing.json'\n",
+    "with open(filename,'r',encoding='utf-8') as fl:\n",
+    "    for line in fl:\n",
+    "        dict1 = {}\n",
+    "        line1 = json.loads(re.sub(r'\\xa0','',line))\n",
+    "        list1 = line1['tables']\n",
+    "        list2 = line1['contents']\n",
+    "        list3 = line1['jj']\n",
+    "        dict2 = dict(zip(list1, list2))\n",
+    "        dict1['name'] = line1['title'][0]\n",
+    "        if len(list3) > 0:\n",
+    "            dict1.setdefault('about',{})\n",
+    "            for i in range(0,int(len(list3)/2)):\n",
+    "                dict1['about'][list3[2*i]] = list3[2*i+1]\n",
+    "        dict1.setdefault('content',{})\n",
+    "        for k, v in dict2.items():\n",
+    "            dict1['content'][k] = v \n",
+    "        #dict1[line1['title'][0]]['内容'] = dict2\n",
+    "        db_list.append(dict1)\n",
+    "x = mycol.insert_many(db_list)\n",
+    "print('ok!')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 术语数据导入数据库中"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import re\n",
+    "import pymongo\n",
+    "\n",
+    "myclient = pymongo.MongoClient('mongodb://192.168.3.100:27017/')\n",
+    "#dblist = myclient.list_database_names()\n",
+    "mydb = myclient['dayi']\n",
+    "mycol = mydb[\"shuyu\"]\n",
+    "db_list = []\n",
+    "filename = 'file/zhongyi/shuyu.json'\n",
+    "with open(filename,'r',encoding='utf-8') as fl:\n",
+    "    for line in fl:\n",
+    "        dict1 = {}\n",
+    "        line1 = json.loads(re.sub(r'\\xa0','',line))\n",
+    "        list1 = line1['tables']\n",
+    "        list2 = line1['contents']\n",
+    "        list3 = line1['jj']\n",
+    "        dict2 = dict(zip(list1, list2))\n",
+    "        dict1['name'] = line1['title'][0]\n",
+    "        if len(list3) > 0:\n",
+    "            dict1.setdefault('about',{})\n",
+    "            for s in list3:\n",
+    "                item = s.strip().split(':')\n",
+    "                dict1['about'][item[0]] = item[1]\n",
+    "        dict1.setdefault('content',{})\n",
+    "        for k, v in dict2.items():\n",
+    "            dict1['content'][k] = v \n",
+    "        #dict1[line1['title'][0]]['内容'] = dict2\n",
+    "        db_list.append(dict1)\n",
+    "x = mycol.insert_many(db_list)\n",
+    "print('ok!')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-12-15T10:01:32.917184Z",
+     "iopub.status.busy": "2021-12-15T10:01:32.917184Z",
+     "iopub.status.idle": "2021-12-15T10:01:32.921185Z",
+     "shell.execute_reply": "2021-12-15T10:01:32.921185Z",
+     "shell.execute_reply.started": "2021-12-15T10:01:32.917184Z"
+    }
+   },
+   "source": [
+    "### 西医症状数据导入数据库中"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import re\n",
+    "import pymongo\n",
+    "\n",
+    "myclient = pymongo.MongoClient('mongodb://192.168.3.100:27017/')\n",
+    "mydb = myclient['dayi']\n",
+    "mycol = mydb[\"xiyizhengzhuang\"]\n",
+    "db_list = []\n",
+    "filename = 'file/zhongyi/xiyizhengzhuang.json'\n",
+    "with open(filename,'r',encoding='utf-8') as fl:\n",
+    "    for line in fl:\n",
+    "        dict1 = {}\n",
+    "        line1 = json.loads(re.sub(r'\\xa0','',line))\n",
+    "        list1 = line1['tables']\n",
+    "        list2 = line1['contents']\n",
+    "        list3 = line1['jj']\n",
+    "        dict2 = dict(zip(list1, list2))\n",
+    "        dict1['name'] = line1['title'][0]\n",
+    "        if len(list3) > 0:\n",
+    "            dict1.setdefault('about',{})\n",
+    "            for i in range(0,int(len(list3)/2)):\n",
+    "                dict1['about'][list3[2*i]] = list3[2*i+1]\n",
+    "        dict1.setdefault('content',{})\n",
+    "        for k, v in dict2.items():\n",
+    "            dict1['content'][k] = v \n",
+    "        #dict1[line1['title'][0]]['内容'] = dict2\n",
+    "        db_list.append(dict1)\n",
+    "x = mycol.insert_many(db_list)\n",
+    "print('ok!')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 药剂数据导入数据库中"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-12-15T10:13:01.097292Z",
+     "iopub.status.busy": "2021-12-15T10:13:01.097292Z",
+     "iopub.status.idle": "2021-12-15T10:13:04.127788Z",
+     "shell.execute_reply": "2021-12-15T10:13:04.127788Z",
+     "shell.execute_reply.started": "2021-12-15T10:13:01.097292Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ok!\n"
+     ]
+    }
+   ],
+   "source": [
+    "import json\n",
+    "import re\n",
+    "import pymongo\n",
+    "\n",
+    "myclient = pymongo.MongoClient('mongodb://192.168.3.100:27017/')\n",
+    "#dblist = myclient.list_database_names()\n",
+    "mydb = myclient['dayi']\n",
+    "mycol = mydb[\"yaoji\"]\n",
+    "db_list = []\n",
+    "filename = 'file/zhongyi/yaoji.json'\n",
+    "with open(filename,'r',encoding='utf-8') as fl:\n",
+    "    for line in fl:\n",
+    "        dict1 = {}\n",
+    "        line1 = json.loads(re.sub(r'\\xa0','',line))\n",
+    "        list1 = line1['tables']\n",
+    "        list2 = line1['contents']\n",
+    "        list3 = line1['jj']        \n",
+    "        dict2 = dict(zip(list1, list2))        \n",
+    "        if len(list3) > 0: \n",
+    "            jj = {}\n",
+    "            for s in list3:\n",
+    "                item = s.strip().split(':')\n",
+    "                jj[item[0]] = item[1]        \n",
+    "        dict1['name'] = jj['名称']\n",
+    "        dict1['about'] = jj\n",
+    "        dict1.setdefault('content',{})\n",
+    "        for k, v in dict2.items():\n",
+    "            dict1['content'][k] = v \n",
+    "        #dict1[line1['title'][0]]['内容'] = dict2\n",
+    "        db_list.append(dict1)\n",
+    "x = mycol.insert_many(db_list)\n",
+    "print('ok!')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 药膳数据导入数据库中"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-12-15T10:15:38.181411Z",
+     "iopub.status.busy": "2021-12-15T10:15:38.181411Z",
+     "iopub.status.idle": "2021-12-15T10:15:38.468083Z",
+     "shell.execute_reply": "2021-12-15T10:15:38.467083Z",
+     "shell.execute_reply.started": "2021-12-15T10:15:38.181411Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ok!\n"
+     ]
+    }
+   ],
+   "source": [
+    "import json\n",
+    "import re\n",
+    "import pymongo\n",
+    "\n",
+    "myclient = pymongo.MongoClient('mongodb://192.168.3.100:27017/')\n",
+    "#dblist = myclient.list_database_names()\n",
+    "mydb = myclient['dayi']\n",
+    "mycol = mydb[\"yaoshan\"]\n",
+    "db_list = []\n",
+    "filename = 'file/zhongyi/yaoshan.json'\n",
+    "with open(filename,'r',encoding='utf-8') as fl:\n",
+    "    for line in fl:\n",
+    "        dict1 = {}\n",
+    "        line1 = json.loads(re.sub(r'\\xa0','',line))\n",
+    "        list1 = line1['tables']\n",
+    "        list2 = line1['contents']\n",
+    "        list3 = line1['jj']\n",
+    "        dict2 = dict(zip(list1, list2))\n",
+    "        dict1['name'] = line1['title'][0]\n",
+    "        if len(list3) > 0:\n",
+    "            dict1.setdefault('about',{})\n",
+    "            for s in list3:\n",
+    "                item = s.strip().split(':')\n",
+    "                dict1['about'][item[0]] = item[1]\n",
+    "        dict1.setdefault('content',{})\n",
+    "        for k, v in dict2.items():\n",
+    "            dict1['content'][k] = v \n",
+    "        #dict1[line1['title'][0]]['内容'] = dict2\n",
+    "        db_list.append(dict1)\n",
+    "x = mycol.insert_many(db_list)\n",
+    "print('ok!')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 中草药数据导入数据库中"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-12-15T10:17:41.510430Z",
+     "iopub.status.busy": "2021-12-15T10:17:41.510430Z",
+     "iopub.status.idle": "2021-12-15T10:17:44.974610Z",
+     "shell.execute_reply": "2021-12-15T10:17:44.973618Z",
+     "shell.execute_reply.started": "2021-12-15T10:17:41.510430Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ok!\n"
+     ]
+    }
+   ],
+   "source": [
+    "import json\n",
+    "import re\n",
+    "import pymongo\n",
+    "\n",
+    "myclient = pymongo.MongoClient('mongodb://192.168.3.100:27017/')\n",
+    "mydb = myclient['dayi']\n",
+    "mycol = mydb[\"zhongcaoyao\"]\n",
+    "db_list = []\n",
+    "filename = 'file/zhongyi/zhongcaoyao.json'\n",
+    "with open(filename,'r',encoding='utf-8') as fl:\n",
+    "    for line in fl:\n",
+    "        dict1 = {}\n",
+    "        line1 = json.loads(re.sub(r'\\xa0','',line))\n",
+    "        list1 = line1['tables']\n",
+    "        list2 = line1['contents']\n",
+    "        list3 = line1['jj']\n",
+    "        dict2 = dict(zip(list1, list2))\n",
+    "        dict1['name'] = line1['title'][0]\n",
+    "        if len(list3) > 0:\n",
+    "            dict1.setdefault('about',{})\n",
+    "            for i in range(0,int(len(list3)/2)):\n",
+    "                dict1['about'][list3[2*i]] = list3[2*i+1]\n",
+    "        dict1.setdefault('content',{})\n",
+    "        for k, v in dict2.items():\n",
+    "            dict1['content'][k] = v \n",
+    "        #dict1[line1['title'][0]]['内容'] = dict2\n",
+    "        db_list.append(dict1)\n",
+    "x = mycol.insert_many(db_list)\n",
+    "print('ok!')"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -355,15 +827,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 78,
+   "execution_count": null,
    "metadata": {
-    "execution": {
-     "iopub.execute_input": "2021-11-24T11:15:33.859507Z",
-     "iopub.status.busy": "2021-11-24T11:15:33.858508Z",
-     "iopub.status.idle": "2021-11-24T11:15:33.864520Z",
-     "shell.execute_reply": "2021-11-24T11:15:33.864520Z",
-     "shell.execute_reply.started": "2021-11-24T11:15:33.859507Z"
-    },
     "tags": []
    },
    "outputs": [],