jupyter/体测单位/沧州炼化.ipynb

体测人员导入

In [2]:

import openpyxl
import json
from datetime import date

wb = openpyxl.load_workbook('data/沧州炼化人员.xlsx')
sheet = wb.active
# sheets = wb.sheetnames
person = {}

for n in range(2, sheet.max_row+1):
    code = sheet.cell(n, 2).value
    person.setdefault(code, {})
    dict1 = {}
    dict1['name'] = sheet.cell(n, 4).value
    dict1['sex'] = sheet.cell(n, 5).value
    dict1['birth'] = str(sheet.cell(n, 6).value).replace('/','-').split(' ')[0] 
    dict1['unit'] = sheet.cell(n, 3).value
    dict1['phone'] = str(sheet.cell(n, 7).value)
    person[code] = dict1
filename = 'data/沧州炼化人员.json'
with open(filename, 'w') as fl:
    json.dump(person, fl, ensure_ascii=False)
print(len(person),'ok')

1287 ok

In [6]:

import openpyxl
import json
from datetime import date

wb = openpyxl.load_workbook('data/沧州炼化人员.xlsx')
sheet = wb.active
# sheets = wb.sheetnames
person = {}
list1 = []
list2 = []
for n in range(2, sheet.max_row+1):
    code = sheet.cell(n, 2).value
    if code not in list1:
        list1.append(code)
    else:
        list2.append(code)
list3 = []
for n in range(2, sheet.max_row+1):
    code = sheet.cell(n, 2).value
    if code in list2:
        list4 = [code,sheet.cell(n, 4).value,sheet.cell(n, 3).value]
        list3.append(list4)
filename = 'data/沧州炼化编号重复人员.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active

for row in list3:
    sheet.append(row)
    
wb.save(filename)

In [ ]: