512song/jupyter
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

20251203

Browse Source
This commit is contained in:
512song committed 2025-12-03 22:24:07 +08:00
1 parent 7b02657d6d
commit 1036605b50
6 files changed
+761 -281
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

体测单位/天津石化.ipynb
+483 -164
View File
@@ -2793,9 +2793,7 @@
{
"cell_type": "markdown",
"id": "08bcbf58-4356-4f30-850f-0d0ff0e2528b",
"metadata": {
"jp-MarkdownHeadingCollapsed": true
},
"metadata": {},
"source": [
"# 第三次体测（2024年10月）"
]
@@ -3205,26 +3203,10 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": null,
"id": "98d2da23-cfd4-461a-890a-4533f0409712",
"metadata": {
"execution": {
"iopub.execute_input": "2024-11-12T03:00:45.476616Z",
"iopub.status.busy": "2024-11-12T03:00:45.475867Z",
"iopub.status.idle": "2024-11-12T03:00:48.668118Z",
"shell.execute_reply": "2024-11-12T03:00:48.667607Z",
"shell.execute_reply.started": "2024-11-12T03:00:45.476543Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ok\n"
]
}
],
"metadata": {},
"outputs": [],
"source": [
"import os,sys,shutil\n",
"import json\n",
@@ -3265,12 +3247,27 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 48,
"id": "9dcbc866-2481-4cf6-a563-df4bb6596dfd",
"metadata": {
"execution": {
"iopub.execute_input": "2025-12-03T13:04:55.617841Z",
"iopub.status.busy": "2025-12-03T13:04:55.617249Z",
"iopub.status.idle": "2025-12-03T13:04:56.054475Z",
"shell.execute_reply": "2025-12-03T13:04:56.053478Z",
"shell.execute_reply.started": "2025-12-03T13:04:55.617812Z"
},
"tags": []
},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ok\n"
]
}
],
"source": [
"import os,sys,shutil\n",
"import json\n",
@@ -3318,26 +3315,10 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "e92d76a8-6841-4a1b-8529-caa5e37d624a",
"metadata": {
"execution": {
"iopub.execute_input": "2024-11-22T02:08:10.643448Z",
"iopub.status.busy": "2024-11-22T02:08:10.642748Z",
"iopub.status.idle": "2024-11-22T02:08:12.178978Z",
"shell.execute_reply": "2024-11-22T02:08:12.178427Z",
"shell.execute_reply.started": "2024-11-22T02:08:10.643386Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ok\n"
]
}
],
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import openpyxl\n",
@@ -3415,26 +3396,10 @@
},
{
"cell_type": "code",
"execution_count": 24,
"execution_count": null,
"id": "c101eccb-a2f3-4404-9583-682cec049160",
"metadata": {
"execution": {
"iopub.execute_input": "2025-11-21T13:09:40.491935Z",
"iopub.status.busy": "2025-11-21T13:09:40.491689Z",
"iopub.status.idle": "2025-11-21T13:09:41.068111Z",
"shell.execute_reply": "2025-11-21T13:09:41.067547Z",
"shell.execute_reply.started": "2025-11-21T13:09:40.491915Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"5057 ok\n"
]
}
],
"metadata": {},
"outputs": [],
"source": [
"import openpyxl\n",
"import json\n",
@@ -3471,26 +3436,10 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": null,
"id": "85bae94e-f480-4c0b-a120-e516e6a5c14d",
"metadata": {
"execution": {
"iopub.execute_input": "2025-11-10T10:34:12.756830Z",
"iopub.status.busy": "2025-11-10T10:34:12.756579Z",
"iopub.status.idle": "2025-11-10T10:34:12.798482Z",
"shell.execute_reply": "2025-11-10T10:34:12.797837Z",
"shell.execute_reply.started": "2025-11-10T10:34:12.756807Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"5053 ok\n"
]
}
],
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"\n",
@@ -3523,28 +3472,10 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "0bebc944-ffa0-4bc9-8ae5-5643fe1015dd",
"metadata": {
"execution": {
"iopub.execute_input": "2025-11-25T09:08:42.753636Z",
"iopub.status.busy": "2025-11-25T09:08:42.752981Z",
"iopub.status.idle": "2025-11-25T09:08:42.813419Z",
"shell.execute_reply": "2025-11-25T09:08:42.812811Z",
"shell.execute_reply.started": "2025-11-25T09:08:42.753578Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"03603055 赵文远 电仪部-电气作业一区\n",
"03603051 李英豪 电仪部-电气作业一区\n",
"5060 ok\n"
]
}
],
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"\n",
@@ -3584,26 +3515,10 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "52de3ba0-f430-444b-87e9-1f13c3e2dcc2",
"metadata": {
"execution": {
"iopub.execute_input": "2025-11-29T12:48:41.369858Z",
"iopub.status.busy": "2025-11-29T12:48:41.369285Z",
"iopub.status.idle": "2025-11-29T12:48:41.616095Z",
"shell.execute_reply": "2025-11-29T12:48:41.615602Z",
"shell.execute_reply.started": "2025-11-29T12:48:41.369808Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"3749\n"
]
}
],
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import datetime\n",
@@ -3615,7 +3530,7 @@
"with open(filename,'r') as fl:\n",
" dict1 = json.load(fl) \n",
"filename = 'data/marks_20251129.csv'\n",
"re_ta = My.get_result(filename,dict1)\n",
"re_ta = My.get_result_2023(filename,dict1)\n",
"\n",
"\n",
"filename = 'data/result_天津石化2025.json'\n",
@@ -3634,17 +3549,9 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": null,
"id": "04990b9f-a8f9-4442-935e-d223fde24e72",
"metadata": {
"execution": {
"iopub.execute_input": "2025-11-30T09:11:15.004533Z",
"iopub.status.busy": "2025-11-30T09:11:15.003858Z",
"iopub.status.idle": "2025-11-30T09:11:15.536091Z",
"shell.execute_reply": "2025-11-30T09:11:15.535622Z",
"shell.execute_reply.started": "2025-11-30T09:11:15.004455Z"
}
},
"metadata": {},
"outputs": [],
"source": [
"import json\n",
@@ -3686,23 +3593,15 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": null,
"id": "fcb3c816-5260-4807-9536-b8203680ed1c",
"metadata": {
"execution": {
"iopub.execute_input": "2025-11-26T12:46:57.881794Z",
"iopub.status.busy": "2025-11-26T12:46:57.881481Z",
"iopub.status.idle": "2025-11-26T12:46:57.922877Z",
"shell.execute_reply": "2025-11-26T12:46:57.922323Z",
"shell.execute_reply.started": "2025-11-26T12:46:57.881771Z"
}
},
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import openpyxl\n",
"\n",
"filename = 'data/result_天津石化2025.json'\n",
"filename = 'data/result_天津石化2025-2.json'\n",
"with open(filename,'r') as fl:\n",
" dict1 = json.load(fl)\n",
"\n",
@@ -3733,7 +3632,7 @@
" list2 = [k,v['人数'],v['体测人数']]\n",
" list1.append(list2)\n",
"\n",
"filename = 'data/天津石化部门测试情况（截至20241126）.xlsx'\n",
"filename = 'data/天津石化部门测试情况（截至20241130）.xlsx'\n",
"wb = openpyxl.Workbook()\n",
"sheet = wb.active\n",
"sheet.append(title)\n",
@@ -3753,17 +3652,9 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": null,
"id": "df8b9405-a2d9-413d-bcf4-205704b0243a",
"metadata": {
"execution": {
"iopub.execute_input": "2025-11-26T12:47:05.652854Z",
"iopub.status.busy": "2025-11-26T12:47:05.652259Z",
"iopub.status.idle": "2025-11-26T12:47:05.810426Z",
"shell.execute_reply": "2025-11-26T12:47:05.809906Z",
"shell.execute_reply.started": "2025-11-26T12:47:05.652799Z"
}
},
"metadata": {},
"outputs": [],
"source": [
"import json\n",
@@ -3806,17 +3697,9 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": null,
"id": "06979464-2285-4862-94de-84e772f44bbf",
"metadata": {
"execution": {
"iopub.execute_input": "2025-11-29T13:28:01.451927Z",
"iopub.status.busy": "2025-11-29T13:28:01.451274Z",
"iopub.status.idle": "2025-11-29T13:28:02.297890Z",
"shell.execute_reply": "2025-11-29T13:28:02.297407Z",
"shell.execute_reply.started": "2025-11-29T13:28:01.451868Z"
}
},
"metadata": {},
"outputs": [],
"source": [
"import openpyxl\n",
@@ -3856,6 +3739,442 @@
"wb.save(filename)"
]
},
{
"cell_type": "markdown",
"id": "d4bd8a8f-6326-4568-8417-abb62e35fe00",
"metadata": {},
"source": [
"## 导入手工数据"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "97150a5f-9fcd-4b0a-aed9-61b10b26f2da",
"metadata": {},
"outputs": [],
"source": [
"import openpyxl\n",
"import json\n",
"from datetime import date\n",
"\n",
"wb = openpyxl.load_workbook('data/天津石化手工数据2025.xlsx')\n",
"sheet = wb.active\n",
"filename = 'data/result_天津石化2025.json'\n",
"with open(filename,'r') as fl:\n",
" dict2 = json.load(fl) \n",
"\n",
"for n in range(2, sheet.max_row+1):\n",
" code = str(sheet.cell(n, 1).value)\n",
" item = sheet.cell(n, 2).value\n",
" mark = str(sheet.cell(n, 3).value)\n",
" rq = str(sheet.cell(n, 3).value)\n",
" if code in dict2.keys():\n",
" dict2[code].setdefault(item,{})\n",
" dict2[code][item]['成绩'] = mark\n",
" else:\n",
" print(code)\n",
" \n",
"filename = 'data/result_天津石化2025-1.json'\n",
"with open(filename,'w') as fl:\n",
" json.dump(dict2, fl, ensure_ascii=False) \n",
"print(len(re_ta)) "
]
},
{
"cell_type": "markdown",
"id": "58336a12-561b-4af7-be00-71c6d0a8ef75",
"metadata": {},
"source": [
"## 导入腰臀数据"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f50b8f39-0311-4537-8eae-9a84af01702d",
"metadata": {},
"outputs": [],
"source": [
"import openpyxl\n",
"import json\n",
"from datetime import date\n",
"\n",
"wb = openpyxl.load_workbook('data/天津石化腰围臀围数据.xlsx')\n",
"sheet = wb.active\n",
"filename = 'data/result_天津石化2025-1.json'\n",
"with open(filename,'r') as fl:\n",
" dict2 = json.load(fl) \n",
"\n",
"for n in range(2, sheet.max_row+1):\n",
" code = str(sheet.cell(n, 1).value)\n",
" item = 'wh'\n",
" mark = str(sheet.cell(n, 2).value)+','+str(sheet.cell(n, 3).value)\n",
" if code in dict2.keys():\n",
" dict2[code].setdefault(item,{})\n",
" dict2[code][item]['成绩'] = mark\n",
" else:\n",
" print(code)\n",
" \n",
"filename = 'data/result_天津石化2025-2.json'\n",
"with open(filename,'w') as fl:\n",
" json.dump(dict2, fl, ensure_ascii=False) \n",
"print(len(dict2)) "
]
},
{
"cell_type": "markdown",
"id": "43d2d7dd-b747-4177-80df-5ca36bea8541",
"metadata": {},
"source": [
"## 统计体测人员项目数"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "227b2b23-1eb4-4da9-896f-5db070228f5b",
"metadata": {
"execution": {
"iopub.execute_input": "2025-12-03T11:08:04.377758Z",
"iopub.status.busy": "2025-12-03T11:08:04.377114Z",
"iopub.status.idle": "2025-12-03T11:08:04.744096Z",
"shell.execute_reply": "2025-12-03T11:08:04.743518Z",
"shell.execute_reply.started": "2025-12-03T11:08:04.377699Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"01738573 曹志玲 研究院 2\n",
"01730621 张敬东 电仪部 2\n",
"01733160 王金江 烯烃部 2\n",
"01736847 章洪 热电部 2\n",
"01736378 杨桂强 热电部 1\n",
"01737731 徐欣 运输销售部 1\n",
"01736804 李振江 热电部 2\n",
"01737858 于学宁 运输销售部 2\n",
"01737542 刘呈健 水务部 1\n"
]
}
],
"source": [
"import json\n",
"\n",
"filename = 'data/result_天津石化2025-2.json'\n",
"with open(filename,'r') as fl:\n",
" dict1 = json.load(fl)\n",
"xm = ['bmi','lung','grip','flexion','jump','pushup','balance','reaction','step','situp']\n",
"list3 = []\n",
"for k,v in dict1.items():\n",
" list1 = []\n",
" for item in v.keys():\n",
" if item in xm:\n",
" list1.append(item)\n",
" if len(list1) <3:\n",
" print(k,v['name'],v['unit'],len(list1))\n",
" list3.append(k)\n",
"filename = 'data/天津石化人员2025.json'\n",
"with open(filename,'r') as fl:\n",
" dict2 = json.load(fl)\n",
"\n",
"list1 = []\n",
"\n",
"i = 1\n",
"for k, v in dict1.items():\n",
" if k not in list3:\n",
" list2 = [i,k,v['name'],v['unit'],dict2[k]['sub_unit'],v['rq'],]\n",
" i+=1\n",
" list1.append(list2)\n",
"#print(list1)\n",
"filename = f'data/天津石化体测人员名单（可出报告）.xlsx'\n",
"title = ['序号','员工编号','姓名','部门','车间','体测日期']\n",
"wb = openpyxl.Workbook()\n",
"sheet = wb.active\n",
"sheet.append(title)\n",
"for row in list1:\n",
" sheet.append(row) \n",
"wb.save(filename)"
]
},
{
"cell_type": "markdown",
"id": "620b0be5-0651-4f62-9b4d-8cc590168a61",
"metadata": {},
"source": [
"## 导出测试人员信息"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d2900f9b-573e-41b1-aeae-8cec37a52826",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import openpyxl\n",
"\n",
"items = ['lung','grip','flexion','jump','pushup','situp','balance','reaction','step']\n",
"title = ['编号','姓名','性别','单位','部门','身高','体重','肺活量','握力','坐位体前屈','纵跳','俯卧撑','一分钟仰卧起坐','单脚站立','选择反应时','台阶指数']\n",
"\n",
"filename = 'data/result_天津石化2025-1.json'\n",
"with open(filename,'r') as fl:\n",
" dict1 = json.load(fl)\n",
"\n",
"filename = 'data/天津石化人员2025.json'\n",
"with open(filename,'r') as fl:\n",
" dict2 = json.load(fl)\n",
" \n",
"list1 = []\n",
"for k, v in dict1.items():\n",
" list2 = []\n",
" list2.append(str(k).rjust(5,'0'))\n",
" list2.append(v['name']) \n",
" list2.append(dict2[k]['sex'])\n",
" list2.append(dict2[k]['unit'])\n",
" list2.append(dict2[k]['birth'])\n",
" if 'phone' in v.keys():\n",
" list2.append(dict2[k]['phone'])\n",
" else:\n",
" list2.append('')\n",
" \n",
" if 'bmi' in v.keys():\n",
" height = v['bmi']['成绩'].split(',')[0]\n",
" weight = v['bmi']['成绩'].split(',')[1]\n",
" list2.append(height)\n",
" list2.append(weight)\n",
" else:\n",
" list2.append('')\n",
" list2.append('')\n",
" for item in items:\n",
" if item in v.keys():\n",
" list2.append(v[item]['成绩']) \n",
" elif item =='name':\n",
" list2.append(v[item])\n",
" else:\n",
" list2.append('')\n",
" \n",
" list1.append(list2)\n",
"filename = 'data/天津石化体测情况表(2025年）.xlsx'\n",
"wb = openpyxl.Workbook()\n",
"sheet = wb.active\n",
"sheet.append(title)\n",
"for row in list1:\n",
" sheet.append(row)\n",
" \n",
"wb.save(filename)"
]
},
{
"cell_type": "markdown",
"id": "3df27e2f-55c0-446a-af01-074e85461bab",
"metadata": {},
"source": [
"### 生成报告（按照编号）"
]
},
{
"cell_type": "code",
"execution_count": 44,
"id": "d0368e0f-270b-47fd-aec0-cae3cadd68b2",
"metadata": {
"execution": {
"iopub.execute_input": "2025-12-03T11:31:43.458591Z",
"iopub.status.busy": "2025-12-03T11:31:43.458312Z",
"iopub.status.idle": "2025-12-03T11:31:44.427029Z",
"shell.execute_reply": "2025-12-03T11:31:44.426528Z",
"shell.execute_reply.started": "2025-12-03T11:31:43.458563Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1\n"
]
}
],
"source": [
"import requests\n",
"import json\n",
"import openpyxl\n",
"\n",
"\n",
"headers = {\n",
" \"Content-Type\": \"application/json; charset=UTF-8\"\n",
" }\n",
"filename = 'data/result_天津石化2025-2.json'\n",
"with open(filename,'r') as fl:\n",
" dict1 = json.load(fl)\n",
"filename = 'data/天津石化人员2025.json'\n",
"with open(filename,'r') as fl:\n",
" dict2 = json.load(fl)\n",
"list1 = []\n",
"file_path ='./天津石化2025/'\n",
"list_item = ['lung','grip','flexion','jump','pushup','balance','reaction','step','situp','bmi','wh']\n",
"i=0\n",
"list2 = []\n",
"person = ['03603316']\n",
"bumen =['南港乙烯项目管理部']\n",
"for k, v in dict1.items():\n",
" list1 = []\n",
" mydata = {}\n",
" \n",
" #id = str(k).rjust(8,\"0\")\n",
" id = str(k)\n",
" #if v['unit'] in bumen:\n",
" if id in person:\n",
" mydata['path'] = file_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'] = v['unit'] + ' '+dict2[k]['sub_unit']\n",
" mydata['id'] = id\n",
" mydata['name'] = v['name']\n",
" if v['sex'] == '男':\n",
" mydata['gender'] = 'male'\n",
" else:\n",
" mydata['gender'] = 'female'\n",
" \n",
" mydata['month'] = v['month']\n",
" mydata['fits'] = {}\n",
" \n",
" for item in list_item:\n",
" if item in v.keys():\n",
" mydata.setdefault('fits',{})\n",
" if item in ['lung','pushup','step','situp']:\n",
" mark = v[item]['成绩'].split()[0].split('.')[0]\n",
" else:\n",
" mark = v[item]['成绩'].split()[0]\n",
" if item == 'bmi':\n",
" mydata['fits']['heightWeight'] = {'mark':mark,'score':-1}\n",
" else:\n",
" mydata['fits'][item] = {'mark':mark,'score':-1}\n",
" #if len(mydata['fits']) >2 or len(mydata['surveys']) >0:\n",
" if len(mydata['fits']) >2 : \n",
" list1.append(mydata)\n",
" list2.append([k,v['name']])\n",
" i+=1\n",
" x = requests.post('http://localhost:3003', data = json.dumps(list1), headers=headers)\n",
" #print(id,v['name'],x.text)\n",
" #print(mydata)\n",
" x.close()\n",
"print(i)"
]
},
{
"cell_type": "markdown",
"id": "428ff4de-5c44-4f13-bfd0-3ccca2d2aff4",
"metadata": {},
"source": [
"## 核对报告人员"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "8467b539-c5ca-4db3-8231-f634b70dff88",
"metadata": {
"execution": {
"iopub.execute_input": "2025-12-03T11:13:39.490227Z",
"iopub.status.busy": "2025-12-03T11:13:39.489101Z",
"iopub.status.idle": "2025-12-03T11:13:39.648115Z",
"shell.execute_reply": "2025-12-03T11:13:39.647529Z",
"shell.execute_reply.started": "2025-12-03T11:13:39.490158Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"03603316 马新淼 炼油部\n",
"01738573 曹志玲 研究院\n",
"01730621 张敬东 电仪部\n",
"01733160 王金江 烯烃部\n",
"01736847 章洪 热电部\n",
"01736378 杨桂强 热电部\n",
"01737731 徐欣 运输销售部\n",
"01736804 李振江 热电部\n",
"01737858 于学宁 运输销售部\n",
"01737542 刘呈健 水务部\n"
]
}
],
"source": [
"import os,sys,shutil\n",
"import json\n",
"import glob\n",
"from pathlib import Path\n",
"import openpyxl\n",
"\n",
"filename = 'data/result_天津石化2025-2.json'\n",
"with open(filename,'r') as fl:\n",
" dict1 = json.load(fl)\n",
"\n",
"fi_path = '/home/songyi/pdf-typescript-fit2023/天津石化2025'\n",
"\n",
"fls = glob.glob(f'{fi_path}/*.pdf')\n",
"list1 = []\n",
"title = ['测试编号','姓名','性别','部门']\n",
"for fn in fls:\n",
" list2 = []\n",
" fi_name =Path(fn).stem.split('-')[0] \n",
" list1.append(fi_name)\n",
"for k, v in dict1.items():\n",
" if k not in list1:\n",
" print(k,v['name'],v['unit'])"
]
},
{
"cell_type": "markdown",
"id": "1620d417-e80c-473a-81f8-f4e705ae6982",
"metadata": {},
"source": [
"## 体测报告按部门、车间分类"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "b9f88d36-e72a-4f26-8357-62c7b0e2128d",
"metadata": {
"execution": {
"iopub.execute_input": "2025-12-03T12:03:30.161578Z",
"iopub.status.busy": "2025-12-03T12:03:30.161039Z",
"iopub.status.idle": "2025-12-03T12:03:31.205217Z",
"shell.execute_reply": "2025-12-03T12:03:31.204754Z",
"shell.execute_reply.started": "2025-12-03T12:03:30.161525Z"
}
},
"outputs": [],
"source": [
"import os,sys,shutil\n",
"import json\n",
"import glob\n",
"from pathlib import Path\n",
"\n",
"fi_path = '/home/songyi/pdf-typescript-fit2023/天津石化2025'\n",
"new_path = 'file/天津石化2025'\n",
"old = []\n",
"dict2 = {}\n",
"\n",
"filename = 'data/天津石化人员2025.json'\n",
"with open(filename,'r') as fl:\n",
" dict1 = json.load(fl)\n",
"fls = glob.glob(f'{fi_path}/*.pdf')\n",
"for fn in fls:\n",
" fi_name =Path(fn).stem.split('-')[0]\n",
" code = fi_name\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",
" shutil.copyfile(fn,n_name)"
]
},
{
"cell_type": "markdown",
"id": "85a03b00-9624-4ae9-aa6d-386798d457df",