{ "cells": [ { "cell_type": "markdown", "id": "ae533fe9-e20e-4e44-b9bb-030c4fa4e714", "metadata": {}, "source": [ "## 体测人员导入" ] }, { "cell_type": "code", "execution_count": null, "id": "1144aaac-92a0-4bcf-aba7-096f7dd3ad3b", "metadata": { "tags": [] }, "outputs": [], "source": [ "import openpyxl\n", "import json\n", "\n", "\n", "wb = openpyxl.load_workbook('data/天津石化员工检测花名册 （20221014）.xlsx')\n", "sheet = wb.active\n", "# sheets = wb.sheetnames\n", "person = {}\n", "\n", "for n in range(2, sheet.max_row+1):\n", " code = int(sheet.cell(n, 6).value)\n", " person.setdefault(code, {})\n", " dict1 = {}\n", " dict1['name'] = sheet.cell(n, 3).value\n", " dict1['sex'] = sheet.cell(n, 4).value\n", " dict1['unit'] = sheet.cell(n, 1).value\n", " dict1['sub_unit'] = sheet.cell(n, 2).value\n", " if sheet.cell(n,5).value is not None:\n", " dict1['id_num'] = sheet.cell(n,5).value\n", " person[code] = dict1\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename, 'w') as fl:\n", " json.dump(person, fl, ensure_ascii=False)\n", "print('ok')" ] }, { "cell_type": "markdown", "id": "5e648b69-40bf-4494-9079-e4e2b6ab8866", "metadata": {}, "source": [ "## 获取人员测试成绩" ] }, { "cell_type": "code", "execution_count": null, "id": "a57ebb22-543c-4804-8d44-89984058ec1d", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import time\n", "import csv\n", "\n", "filename = '../item.json'\n", "item = {}\n", "unit = {}\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl) \n", "for k,v in dict1.items():\n", " item[k] = v\n", "#SQL语句为：\n", "#SELECT a.item_id,a.performance,a.score,a.date AS DATE1,a.avatar_id,b.unit,b.name,a.date_joined FROM places_result AS a,_tianjin AS b WHERE a.place_id=134 AND a.avatar_id=b.id\n", "\n", "re_ta = {}\n", "dict1 = {}\n", "list1 = []\n", "#print(\"\\n运动项目信息：\")\n", "filename = 'data/134_2210.csv'\n", "with open(filename,'r',newline='') as csv_file:\n", " fl = csv.reader(csv_file,delimiter=',')\n", " header = next(fl) \n", " for line in fl:\n", " #line = re.sub('[\\r\\n\\f ]{1,}', '', line)\n", " list1.append(line)\n", "#print(list1)\n", "for result in list1:\n", " user = str(result[4])\n", " m_item = str(result[0]) \n", " re_ta.setdefault(user,{}) \n", " re_ta[user]['name'] = str(result[6])\n", " re_ta[user]['unit'] = str(result[5]) \n", " item_name = item[m_item]['name']\n", " re_ta[user].setdefault(item_name,{}) \n", " score = int(result[1])/item[m_item]['divisor'] \n", " re_ta[user][item_name]['成绩'] = f'{score} {item[m_item][\"unit\"]}'\n", " re_ta[user][item_name]['得分'] =result[2]\n", "filename = 'data/result_天津.json'\n", "with open(filename,'w') as fl:\n", " json.dump(re_ta, fl) \n", "print('ok')" ] }, { "cell_type": "markdown", "id": "55d961e5-a512-44b2-808e-7c55d7000d52", "metadata": {}, "source": [ "## 导出测试成绩" ] }, { "cell_type": "code", "execution_count": null, "id": "38397ad4-2bb3-4b5e-8ece-9ea11e801890", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "items = ['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", "title = ['编号','姓名','性别','单位/部门','车间/科室','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", "filename = 'data/result_天津.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员名单.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(8,'0'))\n", " list2.append(v['name']) \n", " list2.append(dict2[k]['sex'])\n", " list2.append(dict2[k]['unit'])\n", " list2.append(dict2[k]['sub_unit'])\n", " \n", " for item in items:\n", " if item in v.keys():\n", " list2.append(v[item]['成绩'])\n", " \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（截至20221122）.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": "239ceb76-f690-4dae-991c-62c38d617c85", "metadata": {}, "source": [ "## 导出测试成绩(带得分)" ] }, { "cell_type": "code", "execution_count": null, "id": "27529013-f3de-4e23-980d-f62203e4df88", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "items = ['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", "title = ['编号','姓名','性别','单位/部门','车间/科室','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", "filename = 'data/result_天津.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict2 = json.load(fl)\n", " \n", "list1 = []\n", "for k, v in dict1.items():\n", " #print(k,dict2[str(k)]['name'])\n", " list2 = []\n", " list2.append(str(k).rjust(5,'0'))\n", " list2.append(dict2[k]['name']) \n", " list2.append(dict2[k]['sex'])\n", " list2.append(dict2[k]['unit']) \n", " list2.append(dict2[k]['sub_unit']) \n", " for item in items:\n", " if item in dict1[k].keys():\n", " list2.append(dict1[k][item]['成绩'])\n", " list2.append(dict1[k][item]['得分']) \n", " elif item =='name':\n", " list2.append(dict1[k][item])\n", " else:\n", " list2.append('') \n", " list2.append('') \n", " list1.append(list2)\n", "filename = 'data/天津石化体测情况表.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)\n", "print('ok') " ] }, { "cell_type": "markdown", "id": "1c7b219f-43cd-4bf0-971f-2c398f8db8ed", "metadata": {}, "source": [ "## 按照日期进行报告分类" ] }, { "cell_type": "markdown", "id": "3d57ff66-69c3-4c13-811b-f1e13b404077", "metadata": {}, "source": [ "### 按照体测明细分类" ] }, { "cell_type": "code", "execution_count": null, "id": "29c0f15b-1345-4b46-ac1d-b45ddede9641", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import time\n", "import csv\n", "import os,sys,shutil\n", "import glob\n", "\n", "dict1 = {}\n", "list1 = []\n", "filename = 'data/134_2210.csv'\n", "with open(filename,'r',newline='') as csv_file:\n", " fl = csv.reader(csv_file,delimiter=',')\n", " header = next(fl) \n", " for line in fl:\n", " #line = re.sub('[\\r\\n\\f ]{1,}', '', line)\n", " list1.append(line)\n", "for result in list1:\n", " user = str(result[4])\n", " dict1.setdefault(user,'2022-10-01')\n", " m_date = result[7]\n", " if m_date> dict1[user]:\n", " dict1[user] = m_date\n", "\n", "m_path = 'file/134'\n", "\n", "fls = glob.glob(f'file/new/*.pdf')\n", "for fn in fls:\n", " #old = os.path.basename(fn).split('.')[0].rjust(8,'0') \n", " old = os.path.basename(fn).split('.')[0]\n", " mrq = str(dict1[old]).split(' ')[0].replace('-', '', 2)\n", " if not os.path.exists(m_path + '/new/' + mrq):\n", " os.mkdir(m_path + '/new/' + mrq)\n", " n_name = f'{m_path}/new/{mrq}/{str(old).rjust(8,\"0\")}_{mrq}.pdf'\n", " if not os.path.exists(n_name):\n", " shutil.copyfile(fn,n_name)\n", "print('ok!')" ] }, { "cell_type": "markdown", "id": "ae2b17bd-38b9-4809-affb-01441a5581eb", "metadata": {}, "source": [ "### 按照报告生成日期分类" ] }, { "cell_type": "code", "execution_count": null, "id": "eb24c1be-b5d3-4e61-a432-854a887746d4", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import time\n", "import csv\n", "import os,sys,shutil\n", "import glob\n", "\n", "dict1 = {}\n", "list1 = []\n", "\n", "m_path = 'file/134'\n", "mrq = '20221028'\n", "if not os.path.exists(m_path + '/' + mrq):\n", " os.mkdir(m_path + '/' + mrq)\n", "fls = glob.glob(f'file/new/*.pdf')\n", "for fn in fls:\n", " #old = os.path.basename(fn).split('.')[0].rjust(8,'0') \n", " old = os.path.basename(fn).split('.')[0] \n", " n_name = f'{m_path}/{mrq}/{str(old).rjust(8,\"0\")}_{mrq}.pdf'\n", " if not os.path.exists(n_name):\n", " shutil.copyfile(fn,n_name)\n", "print('ok!')" ] }, { "cell_type": "markdown", "id": "d9061d26-b09b-4bff-af24-a14adda3d83f", "metadata": {}, "source": [ "## 按照部门报告分组" ] }, { "cell_type": "code", "execution_count": null, "id": "7ea2541f-461f-4eb5-860d-4b56d6be74ab", "metadata": {}, "outputs": [], "source": [ "import os,sys,shutil\n", "import json\n", "import math\n", "import glob\n", "from pathlib import Path\n", "\n", "fi_path = './file'\n", "old = []\n", "dict2 = {}\n", "\n", "\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "for k, v in dict1.items():\n", " m_name = v['name']\n", " m_depart = v['unit'] \n", " dict2[int(k)] = [m_name,m_depart]\n", "\n", "\n", "\n", "fls = glob.glob(f'./file/*.pdf')\n", "\n", "for fn in fls:\n", " old.append(os.path.basename(fn).split('.')[0])\n", " #print(fn)\n", "\n", "\n", "for n in old: \n", " o_name = f'{fi_path}/{n}.pdf'\n", " if not os.path.exists(f'{fi_path}/new/{dict2[int(n)][1]}'):\n", " os.mkdir(f'{fi_path}/new/{dict2[int(n)][1]}') \n", " n_name = f'{fi_path}/new/{dict2[int(n)][1]}/{str(n).rjust(5,\"0\")}-{dict2[int(n)][0]}.pdf'\n", " if not os.path.exists(n_name):\n", " shutil.copyfile(o_name,n_name)\n", " print(n_name)" ] }, { "cell_type": "code", "execution_count": null, "id": "63eb8a23-4876-4be6-8800-1a67df8773ff", "metadata": { "tags": [] }, "outputs": [], "source": [ "import os,sys,shutil\n", "import json\n", "import math\n", "import glob\n", "from pathlib import Path\n", "\n", "fi_path = './file'\n", "old = []\n", "dict2 = {}\n", "\n", "\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "\n", "for k, v in dict1.items():\n", " m_name = v['name']\n", " m_depart = v['unit'] \n", " dict2[int(k)] = [m_name,m_depart]\n", "\n", "\n", "\n", "fls = glob.glob(f'./file/*.pdf')\n", "\n", "for fn in fls:\n", " old.append(os.path.basename(fn).split('.')[0])\n", "\n", "for n in old: \n", " o_name = f'{fi_path}/{n}.pdf'\n", " new_path = Path('file/new',dict1[n]['unit'],dict1[n]['sub_unit'])\n", " new_path.mkdir(parents = True, exist_ok = True)\n", " n_name = Path(new_path,f'{str(n).rjust(7,\"0\")}-{dict2[int(n)][0]}.pdf')\n", " if not os.path.exists(n_name):\n", " shutil.copyfile(o_name,n_name)\n", " print(n_name)\n", " \n", "print('ok')" ] }, { "cell_type": "markdown", "id": "e4590323-6645-450a-8055-756a5bf35b34", "metadata": {}, "source": [ "## 统计报告人员信息表" ] }, { "cell_type": "code", "execution_count": null, "id": "ed681a0d-4ee8-48ec-ab05-23da7156a44e", "metadata": {}, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "import os\n", "import glob\n", "\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "m_path ='./file'\n", "fls = glob.glob(f'file/*.pdf')\n", "list1 = []\n", "for fn in fls:\n", " list2 = []\n", " code = os.path.basename(fn).split('.')[0]\n", " list2 = [code.rjust(7,\"0\"),dict1[code]['name'],dict1[code]['unit'],dict1[code]['sub_unit']]\n", " list1.append(list2)\n", "title = ['编号','姓名','单位/部门','车间/科室',] \n", "filename = 'data/天津石化体测情况表.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": "838ec7d3-137c-4ccd-9f16-7b6312d1ffa6", "metadata": {}, "source": [ "## PDF文件压缩" ] }, { "cell_type": "code", "execution_count": null, "id": "a6ab0943-b018-4dd6-9176-85a762f9f60c", "metadata": { "tags": [] }, "outputs": [], "source": [ "import fitz\n", "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", "import img2pdf \n", "import glob\n", "import shutil\n", "\n", "def covert2pic(old_fn):\n", " if os.path.exists('.pdf'): # 临时文件，需为空\n", " shutil.rmtree('.pdf')\n", " os.mkdir('.pdf')\n", " with tempfile.TemporaryDirectory() as path:\n", " images_from_path = convert_from_path(old_fn, dpi=100,fmt='jpg', output_folder='.pdf')\n", "\n", "def pic2pdf(new_fn):\n", " fl1=glob.glob('.pdf/*.jpg')\n", " fl1.sort()\n", " a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))\n", " layout_fun = img2pdf.get_layout_fun(a4inpt)\n", " with open(new_fn,\"wb\") as f:\n", " f.write(img2pdf.convert(fl1,layout_fun=layout_fun))\n", " print(f'{new_fn}转换成功！')\n", " \n", "\n", "\n", "def pdfz(sor, obj, zoom): \n", " covert2pic(zoom)\n", " pic2pdf(obj)\n", " \n", "fi_path = 'file/134/20221122/'\n", "fl = glob.glob(f'{fi_path}*.pdf')\n", "\n", "for fn in fl:\n", " new_fn = fi_path+'new/'+os.path.basename(fn)\n", " covert2pic(fn)\n", " pic2pdf(new_fn)\n", " shutil.rmtree('.pdf')\n", "print('ok!')\n", "\n" ] }, { "cell_type": "markdown", "id": "a0cc9662-4171-4c2a-828d-f58c327ec8c1", "metadata": {}, "source": [ "## 统计未测试人员名单" ] }, { "cell_type": "code", "execution_count": null, "id": "daef91be-1b58-4fb1-b182-64f43c07c90f", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "title = ['编号','姓名','性别','单位/部门','车间/科室']\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "filename = 'data/result_天津.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", " if k not in dict2.keys(): \n", " list2 = [k,dict1[k]['name'],dict1[k]['sex'],dict1[k]['unit'],dict1[k]['sub_unit'],] \n", " list1.append(list2)\n", "filename = 'data/天津石化未参加体测人数统计表.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)\n", "print('ok!')" ] }, { "cell_type": "markdown", "id": "72c693e1-dd7c-40fa-8948-4fd6fbea8ddc", "metadata": {}, "source": [ "## 区分新文件" ] }, { "cell_type": "code", "execution_count": null, "id": "9d06d4f0-364b-438c-844b-7d5badaf3496", "metadata": { "tags": [] }, "outputs": [], "source": [ "import os,sys,shutil\n", "import glob\n", "import time\n", "\n", "fi_path = 'file/'\n", "fls = glob.glob(f'{fi_path}*.pdf')\n", "m_date = time.strptime('2022-10-28','%Y-%m-%d')\n", "for fn in fls:\n", " c_time = time.gmtime(os.path.getctime(fn))\n", " if c_time > m_date:\n", " n_name = f'{fi_path}new/{os.path.basename(fn)}'\n", " if not os.path.exists(n_name):\n", " shutil.copyfile(fn,n_name)\n", " print(n_name)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "32b61559-4495-4fbe-8eb6-2614e6225b5c", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "title = ['编号','姓名','性别','单位/部门','车间/科室']\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "filename = 'data/result_天津.json'\n", "with open(filename,'r') as fl:\n", " dict2 = json.load(fl)\n", "print(len(dict2),len(dict1),)" ] }, { "cell_type": "markdown", "id": "47015abe-4cb8-436b-afa5-9ffd78d4a628", "metadata": {}, "source": [ "## 心理测试情况统计" ] }, { "cell_type": "code", "execution_count": null, "id": "c21efc40-2639-4b22-851f-925cd3f12d3a", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "title = ['编号','姓名','性别','单位/部门','车间/科室']\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "filename = 'data/134_xinli.csv'\n", "with open(filename,'r',newline='') as csv_file:\n", " fl = csv.reader(csv_file,delimiter=',')\n", " header = next(fl) \n", " for line in fl:\n", " #line = re.sub('[\\r\\n\\f ]{1,}', '', line)\n", " list1.append(line[4])\n", "list3 = []\n", "for k, v in dict1.items():\n", " list2 = []\n", " if k not in list1: \n", " list2 = [k,dict1[k]['name'],dict1[k]['sex'],dict1[k]['unit'],dict1[k]['sub_unit'],] \n", " list3.append(list2)\n", "filename = 'data/天津石化未参加心理测试人数统计表.xlsx'\n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "sheet.append(title)\n", "for row in list3:\n", " sheet.append(row)\n", " \n", "wb.save(filename)\n", "print('ok!')" ] }, { "cell_type": "code", "execution_count": null, "id": "6b8ae75d-71a3-4cbe-a216-03c28d78156c", "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import openpyxl\n", "\n", "title = ['编号','姓名','性别','单位/部门','车间/科室']\n", "filename = 'data/天津石化人员名单.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "list1 = []\n", "filename = 'data/134_xinli.csv'\n", "with open(filename,'r',newline='') as csv_file:\n", " fl = csv.reader(csv_file,delimiter=',')\n", " header = next(fl) \n", " for line in fl:\n", " print(line[4])" ] }, { "cell_type": "markdown", "id": "20e98f0d-61ea-43a5-8993-9656fed23099", "metadata": {}, "source": [ "## 体检报告统计分析" ] }, { "cell_type": "markdown", "id": "0436a3a2-6230-43b3-beae-bc89e789b285", "metadata": {}, "source": [ "### excel数据导入" ] }, { "cell_type": "code", "execution_count": 113, "id": "7bb2e3aa-591d-4fce-983a-cde5d4c30e56", "metadata": { "execution": { "iopub.execute_input": "2023-01-09T13:24:29.720040Z", "iopub.status.busy": "2023-01-09T13:24:29.719490Z", "iopub.status.idle": "2023-01-09T13:24:30.627490Z", "shell.execute_reply": "2023-01-09T13:24:30.626140Z", "shell.execute_reply.started": "2023-01-09T13:24:29.719971Z" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "ok\n" ] } ], "source": [ "import openpyxl\n", "import json\n", "import re\n", "\n", "wb = openpyxl.load_workbook('data/体检结果(模板)化工.xlsx')\n", "sheet = wb.active\n", "# sheets = wb.sheetnames\n", "dict1 = {}\n", "\n", "for n in range(11, sheet.max_row+1):\n", " code = sheet.cell(n, 1).value\n", " name = sheet.cell(n, 8).value\n", " txt = sheet[f'DT{str(n)}'].value \n", " txt = re.sub(r'\\n', \"\", txt)\n", " txt = re.sub(r'\\t', \"\", txt)\n", " txt = re.sub(r'二、尊敬的顾客您好,您本次体检的建议信息如下：', \"\", txt)\n", " ss = r'三、温馨提示： 鉴于医学技术发展的局限性，个体间可能存在的生物差异性以及您选择的检查项目的局限性，任何一次医学检查的手段和方法都不具备绝对的特异性和灵敏度，对于疾病筛检仍有其盲点，因此，我们建议您对本次检查的异常结果进行随诊复查和其他相关检查，以获得更可靠的医学证据建立准确地医学判断。'\n", " txt1 = re.sub(r'三、温馨提示.*', \"\", txt,re.S)\n", " dict1.setdefault(code, {})\n", " dict1[code]['name'] = name\n", " dict1[code]['xb'] = sheet.cell(n, 9).value\n", " #dict1[code]['birth'] = sheet.cell(n, 10).value\n", " dict1[code]['report'] = txt1\n", "filename = 'data/体检结果.json'\n", "with open(filename,'w') as fl:\n", " json.dump(dict1, fl, ensure_ascii=False) \n", "print('ok')" ] }, { "cell_type": "markdown", "id": "227a1c0b-fc78-4951-97ab-5664b59edd1d", "metadata": {}, "source": [ "### 体检结果分解" ] }, { "cell_type": "code", "execution_count": 118, "id": "b38aef28-5d1b-4762-9c7e-70a531594fa4", "metadata": { "execution": { "iopub.execute_input": "2023-01-09T13:32:31.923948Z", "iopub.status.busy": "2023-01-09T13:32:31.923410Z", "iopub.status.idle": "2023-01-09T13:32:32.253445Z", "shell.execute_reply": "2023-01-09T13:32:32.252452Z", "shell.execute_reply.started": "2023-01-09T13:32:31.923900Z" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "ok!\n" ] } ], "source": [ "import openpyxl\n", "import json\n", "import re\n", "\n", "mo1 = r'[0-9]、'\n", "mo2 = '【.*】'\n", "filename = 'data/体检结果.json'\n", "list3 = []\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "for k, v in dict1.items():\n", " \n", " ss = v['report']\n", " list1 = re.split(mo1,ss)\n", " if len(list1) ==1:\n", " continue\n", " else:\n", " list1.remove('')\n", " #print(list1)\n", " for item in list1:\n", " list2 = re.search( mo2, item)\n", " xm =list2.group()\n", " \n", " txt = item.replace(xm,'').strip()\n", " list3.append([k,v['name'],v['xb'],xm,txt])\n", "filename = 'data/症状表.xlsx'\n", "wb = openpyxl.Workbook()\n", "sheet = wb.active\n", "\n", "for row in list3:\n", " sheet.append(row)\n", " \n", "wb.save(filename)\n", "print('ok!')" ] }, { "cell_type": "code", "execution_count": null, "id": "a4c24e30-f4e0-46e9-a22e-5460a73a14c8", "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": "3.8.10" } }, "nbformat": 4, "nbformat_minor": 5 }