20231225

体测单位/天津石化.ipynb

@@ -2251,9 +2251,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 325,
    "id": "3fa6a1a9-63af-4f4e-9d30-b94f4357f7dc",
    "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-12-20T01:58:47.982585Z",
+     "iopub.status.busy": "2023-12-20T01:58:47.982111Z",
+     "iopub.status.idle": "2023-12-20T01:58:48.241957Z",
+     "shell.execute_reply": "2023-12-20T01:58:48.241442Z",
+     "shell.execute_reply.started": "2023-12-20T01:58:47.982530Z"
+    },
     "tags": []
    },
    "outputs": [],
@@ -2263,8 +2270,8 @@
     "import glob\n",
     "from pathlib import Path\n",
     "\n",
-    "fi_path = '/home/songyi/pdf-typescript/134'\n",
-    "new_path = 'file/134'\n",
+    "fi_path = '/home/songyi/pdf-typescript/天津石化问卷'\n",
+    "new_path = 'file/天津石化问卷1'\n",
     "old = []\n",
     "dict2 = {}\n",
     "\n",
@@ -2275,7 +2282,7 @@
     "for fn in fls:\n",
     "    fi_name =Path(fn).stem.split('-')[0]\n",
     "    code = int(fi_name)\n",
-    "    unit_path = Path(new_path,dict1[str(code)]['unit'])\n",
+    "    unit_path = Path(new_path,dict1[str(code)]['unit'],dict1[str(code)]['sub_unit'])\n",
     "    unit_path.mkdir(parents = True, exist_ok = True)\n",
     "    n_name = Path(unit_path,Path(fn).stem+'.pdf')\n",
     "    if not os.path.exists(n_name):\n",
@@ -2491,22 +2498,37 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 324,
    "id": "8397633f-fddb-4cfa-b9bd-e38f3fe6772c",
    "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-12-19T04:46:55.234792Z",
+     "iopub.status.busy": "2023-12-19T04:46:55.234584Z",
+     "iopub.status.idle": "2023-12-19T04:46:55.720872Z",
+     "shell.execute_reply": "2023-12-19T04:46:55.720417Z",
+     "shell.execute_reply.started": "2023-12-19T04:46:55.234777Z"
+    },
     "tags": []
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ok\n"
+     ]
+    }
+   ],
    "source": [
     "import os,sys,shutil\n",
     "import json\n",
     "import glob\n",
     "from pathlib import Path\n",
     "\n",
-    "fi_path = '/home/songyi/pdf-typescript/134'\n",
-    "new_path = 'file/134_1'\n",
+    "fi_path = '/home/songyi/pdf-typescript/天津石化问卷'\n",
+    "new_path = 'file/134_2'\n",
     "old = []\n",
-    "filename = 'data/result_天津231017.json'\n",
+    "filename = 'data/result_天津问卷2.json'\n",
     "with open(filename,'r') as fl:\n",
     "    dict1 = json.load(fl)\n",
     "\n",
@@ -2535,9 +2557,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 323,
    "id": "35d1738a-1ec1-4764-bcbd-c1333fac6bfd",
    "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-12-19T04:45:06.677002Z",
+     "iopub.status.busy": "2023-12-19T04:45:06.676614Z",
+     "iopub.status.idle": "2023-12-19T04:45:06.915694Z",
+     "shell.execute_reply": "2023-12-19T04:45:06.915217Z",
+     "shell.execute_reply.started": "2023-12-19T04:45:06.676971Z"
+    },
     "tags": []
    },
    "outputs": [],
@@ -2612,8 +2641,9 @@
     "    days =  (rq-birth).days          \n",
     "    dict1[str(item[4])]['age'] = int(days/365)\n",
     "    dict1[str(item[4])]['month'] = int(days/365*12)\n",
+    "    dict1[str(item[4])]['rq'] = item[6].replace('/','-').split(' ')[0]\n",
     "#print(dict1)\n",
-    "filename = 'data/result_天津问卷1.json'\n",
+    "filename = 'data/result_天津问卷2.json'\n",
     "\n",
     "with open(filename,'w') as fl:\n",
     "    json.dump(dict1, fl, ensure_ascii=False)   "
@@ -2656,10 +2686,10 @@
     "for k,v in dict1.items():    \n",
     "    list1 = []\n",
     "    mydata = {}    \n",
-    "    id = k.rjust(3,\"0\")\n",
+    "    id = k.rjust(8,\"0\")\n",
     "    mydata['path'] = fiie_path+id+'-'+ v['name']+'.pdf'\n",
     "    mydata['title'] = '中石化(天津)石油化工\\n有限公司'\n",
-    "    mydata['subtitle'] = ''\n",
+    "    mydata['subtitle'] = v['unit']\n",
     "    mydata['id'] = id\n",
     "    mydata['name'] = v['name']\n",
     "    if v['sex'] == '男':\n",
@@ -2703,12 +2733,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 319,
    "id": "ca0780fe-5d74-4d4e-ad1d-38813040c778",
    "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-12-18T11:26:08.026183Z",
+     "iopub.status.busy": "2023-12-18T11:26:08.025794Z",
+     "iopub.status.idle": "2023-12-18T11:26:08.295041Z",
+     "shell.execute_reply": "2023-12-18T11:26:08.294596Z",
+     "shell.execute_reply.started": "2023-12-18T11:26:08.026152Z"
+    },
     "tags": []
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ok\n"
+     ]
+    }
+   ],
    "source": [
     "import json\n",
     "import csv\n",
@@ -2750,10 +2795,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 318,
    "id": "9b469138-1da9-43ca-98e8-8dc6cb3916ce",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-12-18T11:18:59.322901Z",
+     "iopub.status.busy": "2023-12-18T11:18:59.322423Z",
+     "iopub.status.idle": "2023-12-18T11:18:59.414582Z",
+     "shell.execute_reply": "2023-12-18T11:18:59.414174Z",
+     "shell.execute_reply.started": "2023-12-18T11:18:59.322852Z"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1730629\n",
+      "3499711\n",
+      "3145556\n"
+     ]
+    }
+   ],
    "source": [
     "import json\n",
     "import csv\n",