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 [ ]:

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,a.date_joined FROM places_result AS a,_tianjin AS b WHERE a.place_id=134 AND a.avatar_id=b.id

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')

导出测试成绩

In [ ]:

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'])
    
    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（截至20221122）.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 [19]:

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():
    #print(k,dict2[str(k)]['name'])
    list2 = []
    list2.append(str(k).rjust(5,'0'))
    list2.append(dict2[k]['name'])    
    list2.append(dict2[k]['sex'])
    list2.append(dict2[k]['unit'])    
    list2.append(dict2[k]['sub_unit']) 
    for item in items:
        if item in dict1[k].keys():
            list2.append(dict1[k][item]['成绩'])
            list2.append(dict1[k][item]['得分'])   
        elif item =='name':
            list2.append(dict1[k][item])
        else:
            list2.append('') 
            list2.append('') 
    list1.append(list2)
filename = 'data/天津石化体测情况表.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!')

按照部门报告分组

In [ ]:

import os,sys,shutil
import json
import math
import glob
from pathlib import Path

fi_path = './file'
old = []
dict2 = {}


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

for k, v in dict1.items():
    m_name = v['name']
    m_depart = v['unit']    
    dict2[int(k)] = [m_name,m_depart]



fls = glob.glob(f'./file/*.pdf')

for fn in fls:
    old.append(os.path.basename(fn).split('.')[0])
    #print(fn)


for n in old:    
    o_name = f'{fi_path}/{n}.pdf'
    if not os.path.exists(f'{fi_path}/new/{dict2[int(n)][1]}'):
        os.mkdir(f'{fi_path}/new/{dict2[int(n)][1]}') 
    n_name = f'{fi_path}/new/{dict2[int(n)][1]}/{str(n).rjust(5,"0")}-{dict2[int(n)][0]}.pdf'
    if not os.path.exists(n_name):
        shutil.copyfile(o_name,n_name)
        print(n_name)

In [ ]:

import os,sys,shutil
import json
import math
import glob
from pathlib import Path

fi_path = './file'
old = []
dict2 = {}


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

for k, v in dict1.items():
    m_name = v['name']
    m_depart = v['unit']    
    dict2[int(k)] = [m_name,m_depart]



fls = glob.glob(f'./file/*.pdf')

for fn in fls:
    old.append(os.path.basename(fn).split('.')[0])

for n in old:    
    o_name = f'{fi_path}/{n}.pdf'
    new_path = Path('file/new',dict1[n]['unit'],dict1[n]['sub_unit'])
    new_path.mkdir(parents = True, exist_ok = True)
    n_name = Path(new_path,f'{str(n).rjust(7,"0")}-{dict2[int(n)][0]}.pdf')
    if not os.path.exists(n_name):
        shutil.copyfile(o_name,n_name)
        print(n_name)
    
print('ok')

统计报告人员信息表

In [18]:

import json
import openpyxl
import os
import glob

filename = 'data/天津石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
m_path ='./file'
fls = glob.glob(f'file/*.pdf')
list1 = []
for fn in fls:
    list2 = []
    code = os.path.basename(fn).split('.')[0]
    list2 = [code.rjust(7,"0"),dict1[code]['name'],dict1[code]['unit'],dict1[code]['sub_unit']]
    list1.append(list2)
title = ['编号','姓名','单位/部门','车间/科室',]    
filename = 'data/天津石化体测情况表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)

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/134/20221122/'
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!')

统计未测试人员名单

In [ ]:

import json
import openpyxl

title = ['编号','姓名','性别','单位/部门','车间/科室']
filename = 'data/天津石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
filename = 'data/result_天津.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)

list1 = []
for k, v in dict1.items():
    list2 = []
    if k not in dict2.keys():        
        list2 = [k,dict1[k]['name'],dict1[k]['sex'],dict1[k]['unit'],dict1[k]['sub_unit'],] 
        list1.append(list2)
filename = 'data/天津石化未参加体测人数统计表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)
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 [ ]:

import json
import openpyxl

title = ['编号','姓名','性别','单位/部门','车间/科室']
filename = 'data/天津石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
filename = 'data/result_天津.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
print(len(dict2),len(dict1),)

心理测试情况统计

In [22]:

import json
import openpyxl

title = ['编号','姓名','性别','单位/部门','车间/科室']
filename = 'data/天津石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
filename = 'data/134_xinli.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[4])
list3 = []
for k, v in dict1.items():
    list2 = []
    if k not in list1:        
        list2 = [k,dict1[k]['name'],dict1[k]['sex'],dict1[k]['unit'],dict1[k]['sub_unit'],] 
        list3.append(list2)
filename = 'data/天津石化未参加心理测试人数统计表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list3:
    sheet.append(row)
    
wb.save(filename)
print('ok!')

ok!

In [20]:

import json
import openpyxl

title = ['编号','姓名','性别','单位/部门','车间/科室']
filename = 'data/天津石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
list1 = []
filename = 'data/134_xinli.csv'
with open(filename,'r',newline='') as csv_file:
    fl = csv.reader(csv_file,delimiter=',')
    header = next(fl)    
    for line in fl:
        print(line[4])

1731990
1730445
1733543
3402384
1732997
1737697
1730575
1730370
1739948
3442741
1730359
3362198
3417263
1730439
1733749
3440898
1730989
1730356
1735371
1732814
1730913
1736882
1733497
3362212
1731589
1739001
1731819
1732459
3125774
1730902
3362662
1731856
1737990
3125699
3317857
1730219
1732471
3317863
1734383
3499245
1739589
1733813
3499240
1734246
3125710
3499237
3499243
3499253
1739362
3428692
1739050
1737160
1732665
3287806
1731058
1733868
1733867
1731561
3374924
3167516
3287818
3422008
1734221
1733715
3428694
1734188
1536861
3125698
1730538
3428695
3499244
1732461
1739419
3499257
1735528
3252962
1534670
3125708
1736685
3317910
3287811
3499250
3499252
1733962
1732064
1532672
1735489
1732061
1736599
1736711
1738767
1739302
1733200
1733921
1739427
1730169
1739308
1535224
3145487
3452129
3391160
1532563
1730119
1732176
3362572
3394990
1739239
1730527
3145535
3362148
3417105
1735004
1730099
1738145
3417344
3391150
1735011
1739366
1733562
1736119
3468164
1735730
3286619
1738273
3440494
1736766
1738693
3440490
1738688
1736104
1730461
3499700
1739760
1121028
1731513
1732257
1731552
1122144
1738750
1737455
3499719
1736319
1736146
1736909
3499696
1731467
1732266
1732170
1731539
3362183
3499712
1731534
1731510
1731532
1731442
1739826
1731524
3318695
1731469
1736750
3499705
1731444
3468014
3499693
1731476
3499702
3440472
1731514
3499691
1730766
1731487
1733004
1732263
1732815
1088006
1731509
1734184
1731511
1731443
3499708
1730580
1731540
1731449
3286600
3468152
3468033
1731535
1731520
3145577
1731545
1732809
3440496
1733354
1731461
1733157
3442666
3499720
1731472
1732805
1737993
1731500
1739223
3499710
3499718
1731496
1732808
1730648
1731459
3499689
1731529
1731956
1731457
1731471
1738961
1731502
1739835
1732803
1736917
1731386
1731935
1738682
3468160
1732253
3168143
3318687
1737044
1731489
1730524
1739289
1730599
1731477
3468147
3468012
1736728
1731497
1731773
1731468
3287821
1732921
1731463
1736129
1121117
1730586
1730522
1736757
1730550
3499711
3468183
1731486
1738690
1730470
1730593
1731464
1738669
1736743
3499715
1738641
1732807
1736794
1736798
1731465
1738668
1732269
1730468
3145776
1730649
1730612
1739417
1732802
1736729
3468010
1736755
1730639
1731479
1738245
1731538
3499695
1731491
1739006
1730962
3440495
1730616
1731537
1730430
1730163
1732804
1731518
1733541
1731221
1731478
1731840
1737054
1738505
1730052
3391167
3440899
1088010
1730578
3468015
1731482
1732252
1738654
1730230
1730267
1732164
1731875
1730519
1733549
1739010
1739125
1738942
1737065
1732810
3468042
1730244
1730256
1736505
3145483
1731951
1739918
1733503
1738877
1738999
1731536
1739924
1732784
1738890
1738673
1736841
1732682
1738542
1739011
1733733
1740092
1734764
1739014
1739812
1735318
1730650
1738495
1740086
1730656
1738891
3499698
1730657
1739242
1730584
1730651
1730581
1731525
3499703
1730592
1739005
1738876
1730630
1730108
3145594
1730589
1730611
1733725
1736884
3468184
3362172
3362657
1737052
1738861
1735247
3362161
1738700
1733559
1730239
1739007
3442721
1738885
1857524
1731662
1733782
1736720
1738998
1730658
1731475
1738888
1738889
1730266
3145554
1732778
1730467
3499706
3499694
1737420
1731904
1740109
1739647
1739761
1738835
3468162
1738865
1738902
1738915
1735380
1738867
1730306
1739810
3145529
1736754
1121100
1731531
1738911
1731473
1731553
1738538
1730628
1738991
1732206
1733427
3499249
1730582
1737562
1737618
1738958
1737345
1736762
1738968
1739198
1738884
1739763
1739161
1738643
1735007
3145482
3068728
3499688
1738684
1738646
1736320
1738680
1730771
3499704
1733518
1738631
1738914
1735375
3362186
1738857
3499251
1730005
1739121
1730585
3452130
3362163
3417166
3467827
1730383
1738519
1737605
3417279
1732991
3468100
1732698
3442764
1730167
1732265
1738869
1737176
1121078
3145495
1737454
1738834
3442659
1738938
1738937
3145484
3442703
1738969
1731523
1738527
3467917
1733724
1732002
1731076
1739002
1731235
1732144
3318680
1738517
1730394
1738903
1731111
1739128
1732850
1733502
1733498
1738677
1739235
3417267
1732864
1732169
1733703
1738882
1732889
1735641
1733380
1739944
1731422
1732254
3449693
1736753
1733740
1730406
1737424
1730621
1737364
1736723
3468166
1731289
1738841
1733756
1730405
1731501
1739855
1730254
1739806
3286601
1733257
1733699
3145498
1735003
1733721
31215
1732156
1733256
3467834
1731665
3145605
1739061
1733146
1055173
1731680
1736134
1736160
3442807
1732873
1730788
1732871
3442791
3442753
3145569
1733493
1732166
1739015
1088005
1739220
3145488
3145556
3442762
1732904
1088001
1733531
1305017
1730653
3468804
3499669
1732267
1735436
1736588
1103009
1529378
52781
3145452
1730080
3505717
1736872
1733742
1736764
1735650
1736721
1736585
3499690
3499607
1735299
53058
1730386
1738943
3467868
1739915
3452127
1736565
1736551

In [ ]: