jupyter/体测单位/天津石化.ipynb

体测人员导入

In [ ]:

import openpyxl
import json


wb = openpyxl.load_workbook('data/天津石化员工检测花名册 （20221014）.xlsx')
sheet = wb.active
# sheets = wb.sheetnames
person = {}

for n in range(2, sheet.max_row+1):
    code = int(sheet.cell(n, 6).value)
    person.setdefault(code, {})
    dict1 = {}
    dict1['name'] = sheet.cell(n, 3).value
    dict1['sex'] = sheet.cell(n, 4).value
    dict1['unit'] = sheet.cell(n, 1).value
    dict1['sub_unit'] = sheet.cell(n, 2).value
    if sheet.cell(n,5).value is not None:
        dict1['id_num'] = sheet.cell(n,5).value
    person[code] = dict1
filename = 'data/天津石化人员名单.json'
with open(filename, 'w') as fl:
    json.dump(person, fl, ensure_ascii=False)
print('ok')

获取人员测试成绩

In [5]:

import json
import time
import csv

filename = '../item.json'
item = {}
unit = {}
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
for k,v in dict1.items():
    item[k] = v
#SQL语句为：
# SELECT a.item_id,a.performance,a.score,a.date AS DATE1,a.avatar_id,b.unit,b.name FROM places_result AS a,_zgshhgxs AS b WHERE a.place_id=135 AND a.avatar_id=b.id AND a.avatar_id < 4999

re_ta = {}
dict1 = {}
list1 = []
#print("\n运动项目信息：")
filename = 'data/134_2210.csv'
with open(filename,'r',newline='') as csv_file:
    fl = csv.reader(csv_file,delimiter=',')
    header = next(fl)    
    for line in fl:
        #line = re.sub('[\r\n\f ]{1,}', '', line)
        list1.append(line)
#print(list1)
for result in list1:
    user = str(result[4])
    m_item = str(result[0])    
    re_ta.setdefault(user,{})    
    re_ta[user]['name'] = str(result[6])
    re_ta[user]['unit'] = str(result[5])    
    item_name = item[m_item]['name']
    re_ta[user].setdefault(item_name,{})  
    score = int(result[1])/item[m_item]['divisor']    
    re_ta[user][item_name]['成绩'] = f'{score} {item[m_item]["unit"]}'
    re_ta[user][item_name]['得分'] =result[2]
filename = 'data/result_天津.json'
with open(filename,'w') as fl:
    json.dump(re_ta, fl) 
print('ok')

ok

导出测试成绩

In [7]:

import json
import openpyxl

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']
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']
filename = 'data/result_天津.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

filename = 'data/天津石化人员名单.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
    
list1 = []
for k, v in dict1.items():
    list2 = []
    list2.append(str(k).rjust(8,'0'))
    list2.append(v['name'])    
    list2.append(dict2[k]['sex'])
    list2.append(dict2[k]['unit'])
    list2.append(dict2[k]['sub_unit'])
    if len(v.keys())>5:
        for item in items:
            if item in v.keys():
                list2.append(v[item]['成绩'])

            elif item =='name':
                list2.append(v[item])
            else:
                list2.append('') 

        list1.append(list2)
filename = 'data/天津石化体测情况表（20221116）.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)

导出测试成绩（带得分）

In [6]:

import json
import openpyxl

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']
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']
filename = 'data/result_天津.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
filename = 'data/天津石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
list1 = []

for k, v in dict2.items():
    #print(k,dict2[str(k)]['name'])
    list2 = []
    list2.append(str(k).rjust(5,'0'))
    list2.append(v['name'])    
    list2.append(dict1[k]['sex'])
    list2.append(dict1[k]['unit'])  
    list2.append(dict2[k]['sub_unit'])
    if len(v.keys())>5:  
        for item in items:
            if item in v.keys():
                list2.append(v[item]['成绩'])
                list2.append(v[item]['得分'])   
            elif item =='name':
                list2.append(v[item])
            else:
                list2.append('') 
                list2.append('') 
        list1.append(list2)
filename = 'data/天津石化人员体测情况表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)
print('ok')    

ok

按照日期进行报告分类

按照体测明细分类

In [ ]:

import json
import time
import csv
import os,sys,shutil
import glob

dict1 = {}
list1 = []
filename = 'data/134_2210.csv'
with open(filename,'r',newline='') as csv_file:
    fl = csv.reader(csv_file,delimiter=',')
    header = next(fl)    
    for line in fl:
        #line = re.sub('[\r\n\f ]{1,}', '', line)
        list1.append(line)
for result in list1:
    user = str(result[4])
    dict1.setdefault(user,'2022-10-01')
    m_date = result[7]
    if m_date> dict1[user]:
        dict1[user] = m_date

m_path = 'file/134'

fls = glob.glob(f'file/new/*.pdf')
for fn in fls:
    #old = os.path.basename(fn).split('.')[0].rjust(8,'0') 
    old = os.path.basename(fn).split('.')[0]
    mrq = str(dict1[old]).split(' ')[0].replace('-', '', 2)
    if not os.path.exists(m_path + '/new/' + mrq):
        os.mkdir(m_path + '/new/' + mrq)
    n_name = f'{m_path}/new/{mrq}/{str(old).rjust(8,"0")}_{mrq}.pdf'
    if not os.path.exists(n_name):
        shutil.copyfile(fn,n_name)
print('ok!')

按照报告生成日期分类

In [ ]:

import json
import time
import csv
import os,sys,shutil
import glob

dict1 = {}
list1 = []

m_path = 'file/134'
mrq = '20221028'
if not os.path.exists(m_path + '/' + mrq):
    os.mkdir(m_path + '/' + mrq)
fls = glob.glob(f'file/new/*.pdf')
for fn in fls:
    #old = os.path.basename(fn).split('.')[0].rjust(8,'0') 
    old = os.path.basename(fn).split('.')[0]    
    n_name = f'{m_path}/{mrq}/{str(old).rjust(8,"0")}_{mrq}.pdf'
    if not os.path.exists(n_name):
        shutil.copyfile(fn,n_name)
print('ok!')

PDF文件压缩

In [ ]:

import fitz
from pdf2image import convert_from_path, convert_from_bytes
import os,sys
import tempfile
from pdf2image.exceptions import (
    PDFInfoNotInstalledError,
    PDFPageCountError,
    PDFSyntaxError
)
import img2pdf  
import glob
import shutil

def covert2pic(old_fn):
    if os.path.exists('.pdf'):       # 临时文件，需为空
         shutil.rmtree('.pdf')
    os.mkdir('.pdf')
    with tempfile.TemporaryDirectory() as path:
        images_from_path = convert_from_path(old_fn, dpi=100,fmt='jpg', output_folder='.pdf')

def pic2pdf(new_fn):
    fl1=glob.glob('.pdf/*.jpg')
    fl1.sort()
    a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))
    layout_fun = img2pdf.get_layout_fun(a4inpt)
    with open(new_fn,"wb") as f:
        f.write(img2pdf.convert(fl1,layout_fun=layout_fun))
    print(f'{new_fn}转换成功！')
    


def pdfz(sor, obj, zoom):    
    covert2pic(zoom)
    pic2pdf(obj)
    
fi_path = 'file/134/20221111/'
fl = glob.glob(f'{fi_path}*.pdf')

for fn in fl:
    new_fn = fi_path+'new/'+os.path.basename(fn)
    covert2pic(fn)
    pic2pdf(new_fn)
    shutil.rmtree('.pdf')
print('ok!')

区分新文件

In [ ]:

import os,sys,shutil
import glob
import time

fi_path = 'file/'
fls = glob.glob(f'{fi_path}*.pdf')
m_date = time.strptime('2022-10-28','%Y-%m-%d')
for fn in fls:
    c_time = time.gmtime(os.path.getctime(fn))
    if c_time > m_date:
        n_name = f'{fi_path}new/{os.path.basename(fn)}'
        if not os.path.exists(n_name):
            shutil.copyfile(fn,n_name)
        print(n_name)

In [ ]: