import docx
import os
className = '16计算机1'
name = "周易"
num = '16211160127'
# filename = input()
doc = docx.Document('tres.docx')
for table in doc.tables:
cell = table.rows[1].cells
cell[1].text = className
cell[3].text = name
cell[5].text = num
doc.save('tres.docx')
##----- CONFIGURATION END -----##
strPath = os.getcwd()
# strPath = 'Z:\\1. Micro Evaluation\\VELOCITY\\paragraph_predict\\XPSR\\test\\test2\\wrong'
# doc = docx.AdvSearch()
translist = list()
### --- Directory Crawl --- ###
for file in os.listdir(strPath):
if file.endswith('.docx'):
doc_id = re.split('_|\s', os.path.splitext(file)[0])[0]
print("_________\ncreated document_id: {} for: \n{}".format(
doc_id, file))
doc = docx.Document(file)
sublesscounter = 0
# paralist = []
for i in range(len(doc.paragraphs)):
headline = ''
lesson_id = None
what = ''
based = ''
lesson = ''
if re.match(
r'^%s\b' % init_word_1,
doc.paragraphs[i].text): #.startswith('Headline') == True:
sublesscounter += 1
lesson_id = str(doc_id + '-' + str(sublesscounter))
print('_________\ninit.DEBUG:----> ', i)
# importing libraries
import re
import requests
import bs4
import docx
#import pandas as pd
import oxford as ox
# importing text
doc = docx.Document('test.docx')
a = doc.paragraphs[0].text
# extracting words
pattern = '([A-Za-z]{4,})'
w_dict = re.findall(pattern, a)
# formatting
c = 0
r_dict = {}
for i in w_dict:
if len(r_dict) < 40:
try:
ox.Word.get(i)
except:
continue
wordform = ox.Word.wordform()
try:
definition = ox.Word.definitions()[0]
r_dict.update({i: [wordform, definition]})
except:
continue
def meaning(self):
if os.path.isfile(self.path):
doc = docx.Document(self.path)
else:
doc = docx.Document()
doc.add_heading("Defination's", 0)
sections = doc.sections
for section in sections:
section.top_margin = Cm(1.5)
section.bottom_margin = Cm(1)
section.left_margin = Cm(1.5)
section.right_margin = Cm(1.5)
url = 'https://www.lexico.com/en/definition/' + self.word
page = requests.get(url)
data = page.content
if (page.status_code == 200):
soup = BeautifulSoup(data, 'html.parser')
sect = soup.find_all("section", "gramb")
for i in range(len(sect)):
typeOfWord = sect[i].find("span", "pos")
typeOfWord = typeOfWord.text.title()
mean = sect[i].find("span", "ind")
try:
example = sect[i].find("div", "ex")
example = example.text
except:
example = 'N.A'
try:
syn1 = sect[i].find("strong", "syn")
synonyms = syn1.text
syn2 = sect[i].find("span", "syn")
synonyms = synonyms + syn2.text
synonymList = synonyms.split(',')
syno = ''
for i in range(5):
if i != 0:
syno = syno + ', ' + synonymList[i]
else:
syno = synonymList[i]
except AttributeError:
syno = 'N.A'
para = self.word.capitalize(
) + ' : ' + mean.text + '\n' + 'Example : ' + example + '\n' + 'Synonyms : ' + syno
font = doc.styles['Normal'].font
font.name = 'Calibri'
font.size = Pt(14)
doc.add_paragraph(para)
doc.save(self.path)
return 0
else:
print(
'Ooops!! The Website may be under maintenance or shifted to new address (URL).'
)
#! /usr/bin/python3
import docx
file_path = "./text_files/python_word_letter.docx"
word_document = docx.Document(file_path)
print(word_document.paragraphs)
title = word_document.paragraphs[0]
title.style = word_document.styles["Heading 1"]
for p in word_document.paragraphs:
print(p.text)
word_document.save(file_path)
def post(self, request, *args, **kwargs):
user_id = request.headers.get('userid')
try:
user_obj = CustomUser.objects.get(id=user_id)
except CustomUser.DoesNotExist:
return Response({
"status": "401",
"message": messages.UNAUTHORIZED
},
status=status.HTTP_401_UNAUTHORIZED)
permission_object = Permission.objects.get(name="Import Questions")
permission_list = [
permission.id for permission in user_obj.permission.all()
]
is_permission = True if permission_object.id in permission_list else False
if is_permission:
try:
serializer = ImportQuestionSerializer(data=request.data)
if serializer.is_valid():
dataset = Dataset()
uploaded_file = request.FILES['question_file']
if uploaded_file.name.endswith('docx'):
print('if up')
import docx
doc = docx.Document(uploaded_file)
paras = [p.text for p in doc.paragraphs if p.text]
print("paras", paras, type(paras))
# imported_data = dataset.load(uploaded_file.read(), format='docx')
# for data in imported_data:
# print("data",data)
if uploaded_file.name.endswith('xlsx'):
print('if up')
imported_data = dataset.load(uploaded_file.read(),
format='xlsx')
for data in imported_data:
print("data", data)
tmpOptionsList = ['A', 'B', 'C', 'D', 'E']
# tmpOptionsList.append(data[5])
# tmpOptionsList.append(data[6])
# tmpOptionsList.append(data[7])
# tmpOptionsList.append(data[8])
# tmpOptionsList.append(data[9])
# print("tmpOptionsList",tmpOptionsList)
if data[11] not in tmpOptionsList:
print("if 1")
return Response(
{
"status": "400",
"message":
messages.MISMATCHOPTIONANSWER
},
status=status.HTTP_400_BAD_REQUEST)
if Question.objects.filter(
question_type__name=data[0],
subject__name=data[2],
topic__name=data[3],
sub_group__sub_group=data[1],
question=data[4],
created_by=user_obj.id).exists():
print("already added question")
topic_obj = Topic.objects.get(name=data[3])
exam_type_obj = ExamType.objects.get(
name=data[0])
if data[1] != None:
sub_group_obj = SubGroup.objects.get(
sub_group=data[1],
created_by=user_obj.id)
subject_obj = Subject.objects.get(
sub_group_id=sub_group_obj,
name=data[2])
Question.objects.filter(
question=data[4],
created_by=user_obj.id).update(
created_by=user_obj.id,
question_type=exam_type_obj.id,
subject=subject_obj,
topic=topic_obj,
sub_group=sub_group_obj,
option_A=data[5],
option_B=data[6],
option_C=data[7],
option_D=data[8],
option_E=data[9],
marks=data[10],
answer=data[11])
else:
subject_obj = Subject.objects.get(
name=data[2])
Question.objects.filter(
question=data[4],
created_by=user_obj.id).update(
created_by=user_obj.id,
question_type=exam_type_obj.id,
subject=subject_obj,
topic=topic_obj,
option_A=data[5],
option_B=data[6],
option_C=data[7],
option_D=data[8],
option_E=data[9],
marks=data[10],
answer=data[11])
else:
print('else')
topic_obj = Topic.objects.get(name=data[3])
exam_type_obj = ExamType.objects.get(
name=data[0])
if data[1] != None:
print("sub_group", data[1], user_obj.id)
sub_group_obj = SubGroup.objects.get(
sub_group=data[1],
created_by=user_obj.id)
print("sub_group_obj", sub_group_obj)
subject_obj = Subject.objects.get(
sub_group_id=sub_group_obj,
name=data[2])
data1 = {
'created_by': user_obj.id,
'question_type': exam_type_obj.id,
'subject': subject_obj.id,
'topic': topic_obj.id,
'sub_group': sub_group_obj.id,
'question': data[4],
'option_A': data[5],
'option_B': data[6],
'option_C': data[7],
'option_D': data[8],
'option_E': data[9],
'marks': data[10],
'answer': data[11]
}
else:
subject_obj = Subject.objects.get(
name=data[2])
data1 = {
'created_by': user_obj.id,
'question_type': exam_type_obj.id,
'subject': subject_obj.id,
'topic': topic_obj.id,
'question': data[4],
'option_A': data[5],
'option_B': data[6],
'option_C': data[7],
'option_D': data[8],
'option_E': data[9],
'marks': data[10],
'answer': data[11]
}
serializer1 = QuestionSerializer(data=data1)
if serializer1.is_valid():
serializer1.save()
else:
return Response(
{
"status": "400",
"message": serializer1.errors
},
status=status.HTTP_400_BAD_REQUEST)
return Response(
{
"status": "200",
"message": messages.CREATED,
"data": {
"file_path":
"/media/excel_files/questions_import.xlsx",
"file_name": "questions_import.xlsx"
}
},
status=status.HTTP_200_OK)
return Response(
{
"status": "400",
"message": "unsupported file type"
},
status=status.HTTP_400_BAD_REQUEST)
return Response({
"status": "400",
"message": serializer.errors
},
status=status.HTTP_400_BAD_REQUEST)
except Exception as error:
return Response({
"status": "400",
"message": str(error)
},
status=status.HTTP_400_BAD_REQUEST)
return Response({
"status": "401",
"message": messages.UNAUTHORIZED
},
status=status.HTTP_401_UNAUTHORIZED)
def getText(filename):
doc = docx.Document(filename)
fullText = []
for p in doc.paragraphs:
fullText.append(p.text)
return '\n'.join(fullText)
import docx
import save_data
import os
path = '.\data_all'
save_path = '.\save_data'
files = os.listdir(path)
if not os.path.exists(save_path):
os.makedirs(save_path)
save_data.delete(save_path)
for file in files:
if not os.path.isdir(file):
doc = docx.Document(path + '/' + file)
for para in doc.paragraphs:
data = para.text
if len(data) > 20:
r1, r2, r3 = save_data.match(data)
file_new = file.replace('.docx', '.csv')
save_data.save(r1, r2, r3, save_path + '/' + file_new)
def generar_informe(request, informe_de, parametros, tipo):
"""Generar informes sobre algun/a persona/objeto.
informe_de -> Tipo de informe,
puede ser: empleado, cliente,
administrador, vehículo, etc.
parametros -> Valores/restricciones del informe,
puede ser: Todo, último mes,
última semana, último año,
o incluso descartados.
tipo -> formato de salida del informe,
puede ser: excel, pdf, csv, word.
El flujo de datos va de CSV a XLSX,
luego pasa a Docx y finalmente se
convierte en PDF, previo es obligado.
"""
tablas_db = apps.all_models['Mantenedor']
informes = {
# 'NOMBRE_EN_FORM_DE_HTML' : tablas_db['NOMBRE_TABLA_ORACLE'],
'empleado': tablas_db['empleado'],
'cliente': tablas_db['cliente'],
'proveedor': tablas_db['proveedor'],
'administrador': tablas_db['perfil'],
'vehiculo': tablas_db['infoauto'],
}
# Abreviación, extensión y 'content-type' de archivos y sus formatos.
tipos_admitidos = {
'csv': ['csv', 'text/csv'],
'excel': [
'xlsx',
'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'
],
'word': [
'docx',
' application/vnd.openxmlformats-officedocument.wordprocessingml.document'
],
'pdf': ['pdf', 'application/pdf'],
}
# Se activa la traducción de fechas a español.
activate('es')
# Obtenemos el nombre del mes en español.
today = datetime.date.today()
mes = date(today, 'F')
# Se asigna la fecha actual de dos maneras,
# Una para ser escrita en los nombres de archivos,
# La otra para ser escrita dentro de los informes.
now = datetime.datetime.now().strftime('%Y-%m-%d__%H_%M_%S')
now_ = datetime.datetime.now().strftime(f'%d de {mes} de %Y, %H:%M %p')
# Se normaliza el dato.
tipo = tipo.lower()
# Validación de formato.
if tipo not in ['csv', 'excel', 'word', 'pdf']:
return HttpResponse('ERROR, el tipo de formato no es válido!')
# Se define el nombre del archivo.
nombre_archivo = f'informe_{informe_de}_{now}'
nombre_archivo_con_extension = f'informe_{informe_de}_{now}.{tipos_admitidos[tipo][0]}'
# Se define el tipo de respuesta y la cabecera.
response = HttpResponse(
content_type=f'{tipos_admitidos[tipo][1]}',
headers={
'Content-Disposition':
f'attachment; filename="{nombre_archivo_con_extension}"'
},
)
# Obtener los títulos de una tabla.
fields = informes[informe_de]._meta.get_fields()
titulos = list()
for titulo in fields:
try:
titulo.field
except AttributeError:
titulos.append(titulo.name)
writer = csv.writer(response)
writer.writerow(titulos)
# Se obtiene la info de la base de datos.
nombre_campos = informes[informe_de]._meta.get_fields()
for fila in informes[informe_de].objects.all():
temp = list()
for columna in nombre_campos:
try:
temp.append(fila.serializable_value(columna.name))
except AttributeError:
pass
writer.writerow(temp)
# Devuelve un archivo CSV.
if tipo == 'csv':
return response
# Se define la ubicación de los archivos temporales.
temp_folder = f'{os.path.realpath(".")}\\__temp\\'
temp_csv = f'{temp_folder}__temp.csv'
# Se corrobora que exista la carpeta temporal.
if not os.path.exists(temp_folder):
os.mkdir(temp_folder)
# Se escribe el CSV en físico.
temp = open(temp_csv, 'wb')
temp.write(response.content)
temp.close()
# Devuelve un archivo XLSX.
if tipo == 'excel':
# Pandas lee el CSV desde un archivo.
archivo_leido = pandas.read_csv(temp_csv)
# Se convierte a excel y se almacena como archivo XLSX.
archivo_leido.to_excel(f'{temp_folder}{nombre_archivo_con_extension}',
index=None,
header=True,
sheet_name=f'{informe_de}')
# Devuelve un archivo XLSX.
return FileResponse(
open(f'{temp_folder}{nombre_archivo_con_extension}', 'rb'))
# Se crea y se rellena un archivo DOCX.
document = docx.Document()
document.add_heading(f'Informe de {informe_de}', 0)
document.add_paragraph(f'Con fecha {now_}.')
with open(temp_csv, newline='') as f:
csv_reader = csv.reader(f)
csv_headers = next(csv_reader)
csv_cols = len(csv_headers)
table = document.add_table(rows=2, cols=csv_cols)
hdr_cells = table.rows[0].cells
for i in range(csv_cols):
hdr_cells[i].text = csv_headers[i]
for row in csv_reader:
row_cells = table.add_row().cells
for i in range(csv_cols):
try:
row_cells[i].text = row[i]
except IndexError:
pass
document.add_page_break()
document.save(f'{temp_folder}{nombre_archivo}.docx')
# Devuelve un archivo DOCX.
if tipo == 'word':
return FileResponse(open(f'{temp_folder}{nombre_archivo}.docx', 'rb'))
if tipo == 'pdf':
try:
# Solución 1.
# Usando MS-Office 365
print('\nUsando Office 365\n')
docx2pdf.convert(f'__temp\{nombre_archivo}.docx')
except:
import subprocess
# Solución 2.
# Usando LibreOffice.
print('\nUsando LibreOffice\n')
path_to_soffice_exe = '"C:\Program Files\LibreOffice\program\soffice.exe"'
to_pdf = '-headless -convert-to pdf'
outdir = '-outdir .\__temp'
res = subprocess.run(
f'{path_to_soffice_exe} {to_pdf} {outdir} "__temp\{nombre_archivo}.docx"'
)
print(f'\n\n{res}\n\n')
return FileResponse(open(f'{temp_folder}{nombre_archivo}.pdf', 'rb'))
else:
return HttpResponse('Error con el servidor...')
def extract_keywords():
f_raw = docx.Document(FilePool.raw_docx2)
for para in f_raw.paragraphs:
if len(para.runs) != 0 and para.runs[-1].bold:
keyword = para.text.strip()
print(keyword)
import docx
docFileObj = docx.Document('Pen.docx')
def run(self):
new_files = []
files_detection_error_encoding = []
files_detection_error_text_type = []
files_detection_error_lang = []
if self.file_paths:
len_file_paths = len(self.file_paths)
for i, file_path in enumerate(self.file_paths):
self.progress_updated.emit(
self.tr(f'Opening files ... ({i + 1}/{len_file_paths})'))
default_dir = wl_checking_misc.check_dir(
self.main.settings_custom['import']['temp_files']
['default_path'])
default_encoding = self.main.settings_custom['import'][
'temp_files']['default_encoding']
file_path = wl_misc.get_normalized_path(file_path)
file_name, file_ext = os.path.splitext(
os.path.basename(file_path))
file_ext = file_ext.lower()
# Text files
if file_ext == '.txt':
(new_file, detection_success_encoding,
detection_success_text_type, detection_success_lang
) = self.main.wl_files._new_file(file_path)
new_files.append(new_file)
if not detection_success_encoding:
files_detection_error_encoding.append(new_file['path'])
if not detection_success_text_type:
files_detection_error_text_type.append(
new_file['path'])
if not detection_success_lang:
files_detection_error_lang.append(new_file['path'])
else:
if file_ext in ['.docx', '.xlsx', '.xls']:
new_path = wl_checking_misc.check_new_path(
os.path.join(default_dir, f'{file_name}.txt'))
# Word documents
if file_ext == '.docx':
lines = []
with open(new_path, 'w',
encoding=default_encoding) as f:
doc = docx.Document(file_path)
for block in self.iter_block_items(doc):
if type(block
) == docx.text.paragraph.Paragraph:
f.write(f'{block.text}\n')
elif type(block) == docx.table.Table:
for row in self.iter_visual_cells(
block):
cells = []
for cell in row:
cells.append(' '.join([
item.text for item in
self.iter_cell_items(cell)
]))
f.write('\t'.join(cells) + '\n')
# Excel workbooks
elif file_ext == '.xlsx':
with open(new_path, 'w',
encoding=default_encoding) as f:
workbook = openpyxl.load_workbook(
file_path, data_only=True)
for worksheet_name in workbook.sheetnames:
worksheet = workbook[worksheet_name]
for row in worksheet.rows:
f.write('\t'.join([(
cell.value if cell.value != None
else '') for cell in row]) + '\n')
elif file_ext == '.xls':
with open(new_path, 'w',
encoding=default_encoding) as f:
workbook = xlrd.open_workbook(file_path)
for i_sheet in range(workbook.nsheets):
worksheet = workbook.sheet_by_index(
i_sheet)
for row in range(worksheet.nrows):
f.write('\t'.join([
worksheet.cell_value(row, col)
for col in range(worksheet.ncols)
]) + '\n')
new_paths = [new_path]
else:
# Detect encoding
if self.main.settings_custom['files'][
'auto_detection_settings']['detect_encodings']:
encoding_code, _ = wl_detection.detect_encoding(
self.main, file_path)
else:
encoding_code = self.main.settings_custom[
'auto_detection']['default_settings'][
'default_encoding']
# CSV files
if file_ext == '.csv':
new_path = wl_checking_misc.check_new_path(
os.path.join(default_dir, f'{file_name}.txt'))
with open(new_path, 'w',
encoding=default_encoding) as f:
with open(file_path,
'r',
newline='',
encoding=encoding_code) as f_csv:
csv_reader = csv.reader(f_csv)
for row in csv_reader:
f.write('\t'.join(row) + '\n')
new_paths = [new_path]
# HTML files
elif file_ext in ['.htm', '.html']:
with open(file_path, 'r',
encoding=encoding_code) as f:
soup = bs4.BeautifulSoup(f.read(), 'lxml')
new_path = wl_checking_misc.check_new_path(
os.path.join(default_dir, f'{file_name}.txt'))
with open(new_path, 'w',
encoding=default_encoding) as f:
f.write(soup.get_text())
new_paths = [new_path]
# XML files
elif file_ext == '.xml':
with open(file_path, 'r',
encoding=encoding_code) as f:
xml_text = f.read()
new_path = wl_checking_misc.check_new_path(
os.path.join(default_dir, f'{file_name}.txt'))
with open(new_path, 'w',
encoding=default_encoding) as f:
f.write(xml_text)
new_paths = [new_path]
# Translation memory files
elif file_ext == '.tmx':
lines_src = []
lines_target = []
with open(file_path, 'r',
encoding=encoding_code) as f:
soup = bs4.BeautifulSoup(f.read(), 'lxml-xml')
for tu in soup.find_all('tu'):
seg_src, seg_target = tu.find_all('seg')
lines_src.append(seg_src.get_text())
lines_target.append(seg_target.get_text())
path_src = wl_checking_misc.check_new_path(
os.path.join(default_dir,
f'{file_name}_source.txt'))
path_target = wl_checking_misc.check_new_path(
os.path.join(default_dir,
f'{file_name}_target.txt'))
with open(path_src, 'w',
encoding=default_encoding) as f:
f.write('\n'.join(lines_src))
f.write('\n')
with open(path_target,
'w',
encoding=default_encoding) as f:
f.write('\n'.join(lines_target))
f.write('\n')
new_paths = [path_src, path_target]
# Lyrics files
elif file_ext == '.lrc':
lyrics = {}
with open(file_path, 'r',
encoding=encoding_code) as f:
for line in f:
time_tags = []
line = line.strip()
# Strip time tags
while re.search(r'^\[[^\]]+?\]', line):
time_tags.append(
re.search(r'^\[[^\]]+?\]',
line).group())
line = line[len(time_tags[-1]):].strip(
)
# Strip word time tags
line = re.sub(r'<[^>]+?>', r'', line)
line = re.sub(r'\s{2,}', r' ',
line).strip()
for time_tag in time_tags:
if re.search(
r'^\[[0-9]{2}:[0-5][0-9]\.[0-9]{2}\]$',
time_tag):
lyrics[time_tag] = line
new_path = wl_checking_misc.check_new_path(
os.path.join(default_dir, f'{file_name}.txt'))
with open(new_path, 'w',
encoding=default_encoding) as f:
for _, lyrics in sorted(lyrics.items()):
f.write(f'{lyrics}\n')
new_paths = [new_path]
for new_path in new_paths:
(new_file, detection_success_encoding,
detection_success_text_type, detection_success_lang
) = self.main.wl_files._new_file(new_path, txt=False)
new_files.append(new_file)
if not detection_success_encoding:
files_detection_error_encoding.append(
new_file['path'])
if not detection_success_text_type:
files_detection_error_text_type.append(
new_file['path'])
if not detection_success_lang:
files_detection_error_lang.append(new_file['path'])
self.main.settings_custom['import']['files'][
'default_path'] = wl_misc.get_normalized_dir(
self.file_paths[0])
self.progress_updated.emit(self.tr('Updating table ...'))
time.sleep(0.1)
self.worker_done.emit(new_files, files_detection_error_encoding,
files_detection_error_text_type,
files_detection_error_lang)
def Save_File_Docx(content, file_name):
doc = docx.Document()
doc.add_paragraph(content)
doc.save(file_name + ' Standard.docx')
def read_doc(self,path):#path or io
x = docx.Document(path)
return x
# print(i)
# xml_string = source_document._body._element.xml
# xml = parseString(xml_string)
# contents = xml.getElementsByTagName('w:bookmarkStart')
# # for i in xml:
# # print(i)
# for i in contents:
# print(i)
import docx
file_name = r'C:\Users\thameem.sakkarai\Desktop\check\AOF edited document.docx'
document = docx.Document(docx = file_name)
section = document.sections
header = section.header
print(header)
print(dir(document))
print(help(document))
core_properties = document.core_properties
print(core_properties.author)
print(core_properties.created)
print(core_properties.last_modified_by)
print(core_properties.last_printed)
print(core_properties.modified)
print(core_properties.revision)
print(core_properties.title)
print(core_properties.category)
import docx
from docx.shared import RGBColor, Pt
# Get message from fake message
fake_text = docx.Document('fakeMessage.docx')
fake_list = []
for paragraph in fake_text.paragraphs:
fake_list.append(paragraph.text)
# Get text from real message
real_text = docx.Document('realMessage.docx')
real_list = []
for paragraph in real_text.paragraphs:
if len(paragraph.text) != 0:
real_list.append(paragraph.text)
# Get template form style, font and etc.
doc = docx.Document('template.docx')
doc.add_heading('Ilsaf Nabiullin', 0)
subtitle = doc.add_heading('Nks1ckk & co', 1)
subtitle.alignment = 1
doc.add_heading('', 1)
doc.add_paragraph('2 Jan 2021')
doc.add_paragraph('')
def set_spacing(paragraph):
"""set space between paragraphs"""
def classify(file_name):
file = docx.Document(file_name)
print("段落数:" + str(len(file.paragraphs))) # 输出段落数
file_word = docx.Document()
information = ''
for para in file.paragraphs:
information = information + para.text
# print(information)
# information = docx.Document("E:/DMY important/段铭杨毕业设计/A-GCNN/测试文档.docx")
# information = "项目经验人力资源000000管理系统项目时间：2019年01月-2019年02月项目简介： 使用技术及语言：SSM框架/Java 开发工具：Eclipse/STS 开发人员： 独立完成 项目描述：管理员对部门、员工、职位、培训、招聘、奖惩、考勤的CRUD；游客浏览招聘，对自己简历的CRUD，投递；员工查看自己的信息、培训、公司通讯录、奖惩、薪资和打卡。本项目结构上分为表现层、业务层和数据访问层，层次间的依赖关系自下到上。业务层封装业务流程，为适应业务的变更，每一业务模块均有专门的接口及实现类。 项目业绩： 项目收获：只是离现在最近的小项目，花费半个多月的时间完成。功能繁琐，但我没有放弃，虚心请教一些大佬，在此我也由衷感谢他们。对于代码的编写，一定要字斟句酌，一个不起眼的问题，就会导致系统BUG。程序员也是在代码的海洋里磨炼起来的！"
a_cut = jieba.cut(information)
a = '/'.join(a_cut)
after_cut = a.split('/')
# print(after_cut)
for i in range(3):
for i in after_cut:
if len(i) > 2:
after_cut.remove(i)
# print(after_cut)
final_cut = []
for item in after_cut:
if item != ' ' and item != ' ' and item != '':
final_cut.append(item)
# print(final_cut)
# 去噪，导入中文停用词表
file_stop = r'./简历分类测试/dmy_stopwords.txt'
stop = []
standard_stop = []
final_information = []
with open(file_stop, 'r', encoding='utf-8-sig') as f:
lines = f.readlines()
for line in lines:
lline = line.strip()
stop.append(lline)
for i in range(0, len(stop)):
for word in stop[i].split():
standard_stop.append(word)
for i in final_cut:
if i not in standard_stop:
final_information.append(i)
# print(final_information)
# 将得到的文本向量化
model_1 = gensim.models.Word2Vec.load(path)
X = []
sentence = []
word_vec = []
zero_array = [0] * 256
word_vec = np.zeros([256, ], dtype=np.float64)
for j in range(len(final_information)):
word_vec = list(model_1[final_information[j]])
sentence.append(word_vec)
for j in range(128 - len(final_information)):
sentence.append(zero_array)
X.append(sentence)
X = np.array(X)
predict = model.predict(X)
print(predict)
# 上面的predict就是最终的分类结果，是一个数组，其中分值最大对应的类别标签就为判定的类别
if predict[0][0] > predict[0][1] and predict[0][0] > predict[0][2] and predict[0][0] > predict[0][3] and predict[0][
0] > predict[0][4]:
return 'JAVA工程师'
if predict[0][1] > predict[0][2] and predict[0][1] > predict[0][3] and predict[0][1] > predict[0][4] and predict[0][
1] > predict[0][0]:
return '技术总监'
if predict[0][2] > predict[0][3] and predict[0][2] > predict[0][4] and predict[0][2] > predict[0][1] and predict[0][
2] > predict[0][0]:
return 'Web工程师'
if [0][3] > predict[0][4] and predict[0][3] > predict[0][2] and predict[0][3] > predict[0][1] and predict[0][3] > \
predict[0][0]:
return '大数据工程师'
if predict[0][4] > predict[0][3] and predict[0][4] > predict[0][2] and predict[0][4] > predict[0][0] and predict[0][
4] > predict[0][1]:
return '算法工程师'
def gerarRecomendacao():
# Dentro da função criamos um arquivo .docx vazio que receberá os dados de recomendação das amostras
# Sendo que, para cada amostra será gerado um arquivo diferente.docx, ao final de cada looping
doc = docx.Document()
# O looping for irá verificar linha por linha da nossa planilha de dados
for row in dadosData:
# Uma instrução if que faz com que o laço ignore
# a primeira linha da planilha de dados (o cabeçalho)
# mas que a partir da segunda linha passe a fazer a leitura de dados de cada amostra
if str(row[0]) != str('Amostra'):
# Buscamos os dados de acordo com seu indice em cada linha da planilha
# Convertemos os dados para o tipo de dados que cada um represente
# Armazenamos os dados em variáveis com nomes mais familiares
# Os três passos acima são feitos para cada linha da planilha
# Onde cada linha representa uma amostra de solo diferente
# amx refere-se ao nome em que o que arquivo de recomendação será salvo utilizando a função
# doc.save() dentro do loop
amx = str(row[1]) + '.docx'
am = str(row[1])
pro = str(row[2])
k = float(row[5])
na = float(row[6])
ca = float(row[7])
mg = float(row[8])
al = float(row[9])
alh = float(row[10])
v1 = float(row[11])
x = float(row[12])
ta = str(row[13])
pf = float(row[14])
li = float(row[15])
el = float(row[16])
fc = float(row[17])
lbc = float(row[18])
cbc = float(row[19])
base_menor = float(row[20])
base_maior = float(row[21])
# à seguir são realizados alguns calculos para conversão e ajuste dos dados obtidos da planilha
# Tranformação do K e o Na de mg/dm³ para cmolc/dm³
k = k / 390
na = na / 230
# CTC potencial
ctctotal = ca + mg + k + na + alh
# CTC efetiva
ctcef = ca + mg + k + na + al
# Soma de Bases
sb = ca + mg + k + na
# Saturação por bases
v2 = sb / ctctotal * 100
# Saturação por aluminio
m = al / ctcef * 100
# Número de plantas por hectare
numplant = 10000 / (el * li)
# Calculos para aplicação de calcário em sulco
vol_de_sulco = ((((base_maior + base_menor) * (pf / 100) / 2) *
(100 / el * 100)) * 1000)
perc_vol_de_sulco = vol_de_sulco / (1000 * 1000 * pf / 10)
# Calculamos também a Necessidade de calagem por 3 diferentes métodos
# Metódo 1 - Soma de bases
ncm1 = ((ctctotal * (v1 - v2)) / 100)
# Metódo 2 - Soma de cálcio e mágnesio ideal para a cultura
ncm2 = (x - (ca + mg))
# Metódo 3 - Teor de H + Al
ncm3 = alh
# A condicional If faz a decisão de qual metódo apresenta valor adequado como necessidade de calagem
# com base nas recomendações de ..... et al ()
if ncm1 >= ncm2:
nc = ncm1
elif ncm2 <= ncm3:
nc = ncm2
else:
nc = ncm3
# qc representa a quantidade de calcário segundo a profundidade a ser aplicado em caso de área total
qc = nc * pf / 20
# A Condicional if elseif else fará a converção de necessidade de calagem (agora chamada de qc) para
# a quantidade de calcário necessário para diferentes métodos de aplicação (faixa, sulco, em cova e área total)
# E geramos uma recomendação para cada amostra
# Instruções para a recomendação para aplicação em faixa
if ta == 'fx':
# Conversão de qc para valores a serem aplicado no sulco em g de calcário/planta
qc = qc * (1000000 / numplant) * fc / 100
# Texto da recomendação
doc.add_paragraph('Prognóstico Para Calagem', 'Title')
doc.add_paragraph('Amostra ' + am)
doc.add_paragraph('Produtor: ' + pro)
doc.add_heading('Quantidade de calcário', 1)
p = doc.add_paragraph(
'Para a corrigir o pH do solo e elevar os teores de Ca e Mg indica-se preparar e '
'aplicar %.2f g de calcário/planta' % qc)
p.alignment = 3
doc.save(amx)
# Após o relatório ser salvo (linha acima),
# a linha abaixo é introduzida para que um novo arquivo .docx vazio seja criado
# e utilizado para criação da próxima recomendação
doc = docx.Document()
# Instruções para a recomendação para aplicação em sulco
elif ta == 'sc':
# Conversão de qc para valores a serem aplicado no sulco em g de calcário/metro de sulco
qc = (qc * perc_vol_de_sulco) / (100 / el * 100) * 1000000
# Texto da recomendação
doc.add_paragraph('Prognóstico Para Calagem', 'Title')
doc.add_paragraph('Amostra ' + am)
doc.add_paragraph('Produtor - ' + pro)
doc.add_heading('Quantidade de calcário', 1)
p = doc.add_paragraph(
'Para a corrigir o pH do solo e elevar os teores de Ca e Mg indica-se preparar e '
'aplicar %.2f g de calcário/metro de suco' % qc)
p.alignment = 3
doc.save(amx)
# Após o relatório ser salvo (linha acima),
# a linha abaixo é introduzida para que um novo arquivo .docx vazio seja criado
# e utilizado para criação da próxima recomendação
doc = docx.Document()
# Instruções para a recomendação para aplicação em cova/berço
elif ta == 'cv':
# Conversão de qc para valores a serem aplicado no sulco em g de calcário/metro de sulco
qc = qc * 100 * lbc * cbc
# Texto da recomendação
doc.add_paragraph('Prognóstico Para Calagem', 'Title')
doc.add_paragraph('Amostra ' + am)
doc.add_paragraph('Produtor - ' + pro)
doc.add_heading('Quantidade de calcário', 1)
p = doc.add_paragraph(
'Para a corrigir o pH do solo e elevar os teores de Ca e Mg indica-se '
'aplicar %.2f g de calcário/cova' % qc)
p.alignment = 3
doc.save(amx)
# Após o relatório ser salvo (linha acima),
# a linha abaixo é introduzida para que um novo arquivo .docx vazio seja criado
# e utilizado para criação da próxima recomendação
doc = docx.Document()
# Instruções para a recomendação para aplicação em área total
else:
qc = nc
doc.add_paragraph('Prognóstico Para Calagem', 'Title')
doc.add_paragraph('Amostra ' + am)
doc.add_paragraph('Produtor - ' + pro)
doc.add_heading('Quantidade de calcário', 1)
p = doc.add_paragraph(
'Para a corrigir o pH do solo e elevar os teores de Ca e Mg indica-se '
'aplicar %.2f t de calcário/ha' % qc)
p.alignment = 3
doc.save(amx)
# Após o relatório ser salvo (linha acima),
# a linha abaixo é introduzida para que um novo arquivo .docx vazio seja criado
# e utilizado para criação da próxima recomendação
doc = docx.Document()
if ca >= 0.4 or al > 0.5 or m > 30:
print('Essa amostra precisa de Gessagem')
def get_text(filename):
doc = docx.Document(filename)
fullText = [para.text for para in doc.paragraphs]
return '\n'.join(fullText)
def read_docx(file_name):
doc = docx.Document(file_name)
content = '\n'.join([para.text for para in doc.paragraphs])
return (content)
def creator():
try:
inv_num = input("Enter Invoice Number: ")
location = input("Enter Location: ")
lot_num = 0
window_amt = input("Enter amt of windows: ")
window_price_per = 22
sliders = input("Enter amt of sliders: ")
slider_price_per = 40
doors = input("Enter amt of doors: ")
doors_price_per = 35
lgDoors = input("Enter amt of large sliders: ")
lgDoor_price_per = 20
lgWin = input("Enter amt of large windows: ")
lgWin_price_per = 11
price_of_trip = input("Enter Price of Trip: ")
desc = input("Enter description of services if applicable: ")
total = ((int(window_amt) * int(window_price_per)) +
(int(lgDoors) * int(lgDoor_price_per)) +
(int(sliders) * int(slider_price_per)) +
(int(doors) * int(doors_price_per)) +
(int(lgWin) * int(lgWin_price_per)) + int(price_of_trip))
document = docx.Document()
document.add_heading(f' Invoice #{inv_num}', 0)
p = document.add_paragraph("""
Chad J Willes Construction
371 west 500 south
Lehi UT, 84043
801-706-8523
""")
document.add_paragraph("""
To:
Alside Exterior Building Products
915 West 2610 South
Salt Lake City Ut 84119
Att: Andrew Germaine
""")
main_p = document.add_paragraph("")
main_p.add_run(
'This invoice is for all the work needed to install windows to the Alside Standard'
).bold = True
main_p.add_run(f"\n {location}")
main_p.add_run(f"\nLot: {lot_num}")
main_p.add_run(
f"\nWindows @${window_price_per} per x{window_amt}"
)
main_p.add_run(
f"\nSliders @${slider_price_per} per x{sliders}"
)
main_p.add_run(
f"\nDoors @${doors_price_per} per x{doors}"
)
main_p.add_run(
f"\nLarge Windows @${lgWin_price_per} per x{lgWin}")
main_p.add_run(
f"\nLarge Sliders @${lgDoor_price_per} per x{lgDoors}")
main_p.add_run(f"\nTrip Price: ${price_of_trip}")
main_p.add_run(f"\n{desc}")
main_p.add_run(
f"\nTOTAL ${total}"
).underline = True
try:
document.save('C:/Users/Owner/Documents/Invoices/' +
f'Invoice for Alside {inv_num} {location}.docx')
print("\n Invoice Created!")
# message = MIMEMultipart()
# mail_content = '''
# Invoice For Windows
# '''
# message.attach(MIMEText(mail_content, 'plain'))
# message['Subject'] = "Invoice"
# attach_file_name = f'C:/Users/terra/Documents/Invoices/Invoice for Alside {inv_num} {location}.docx'
# attach_file = open(attach_file_name, 'rb') # Open the file as binary mode
# payload = MIMEBase('application', 'octate-stream')
# payload.set_payload((attach_file).read())
# encoders.encode_base64(payload) #encode the attachment
# #add payload header with filename
# payload.add_header('Content-Decomposition', 'attachment', filename='Invoice1.docx')
# message.attach(payload)
# r = requests.post(
# "https://api.mailgun.net/v3/sandbox2a89baf534dc4c6a88ecc092c09a65e8.mailgun.org/messages.mime",
# auth=("api", "9077b561bf5dbb09635c5372373e3182-f696beb4-2fb9e654"),
# data={"from": "*****@*****.**","to": "*****@*****.**"},
# files={"message": bytes(str(message), "utf-8")})
creator()
except Exception as e:
print(f"\nInvoice Already Exists, Try Again. Error: {e}")
creator()
except Exception as e:
print(
f"\n Program Broke for some reason. Try Again. \n Error Code for Ethon: {e}"
)
creator()
['LDAP 인젝션', 'LI', 'X'], ['운영체제 명령 실행', 'OC', 'X'],
['SQL 인젝션', 'SI', 'X'], ['SSI 인젝션', 'SS', 'X'],
['Xpath 인젝션', 'XI', 'X'], ['디렉터리 인덱싱', 'DI', 'O'],
['정보 누출', 'IL', 'O'], ['악성 콘텐츠', 'CS', 'X'],
['크로스사이트 스크립팅', 'XS', 'O'], ['약한 문자열 강도', 'BF', 'X'],
['불충분한 인증', 'IA', 'X'], ['취약한 패스워드 복구', 'PR', 'X'],
['크로스사이트 리퀘스트 변조(CSRF)', 'CF', 'X'], ['세션 예측', 'SE', 'X'],
['불충분한 인가', 'IN', 'X'], ['불충분한 세션 만료', 'SC', 'X'],
['세션 고정', 'SF', 'X'], ['자동화 공격', 'AU', 'X'],
['프로세스 검증 누락', 'PV', 'O'], ['파일 업로드', 'FU', 'X'],
['관리자 페이지 노출', 'AE', 'O'], ['경로 추적', 'PT', 'X'],
['위치 공개', 'PL', 'O'], ['데이터 평문 전송', 'SN', 'X'],
['쿠키변조', 'CC', 'O']]
try:
doc = docx.Document('test3.docx')
except Exception as e:
print("파일이 존재하지 않는듯? -> " + str(e))
# 테스트용 함수들..
def table_info(table_num, row_num):
# 실구동때는 사용하지 않음 특정 테이블의 정보를 보고싶을때 사용하면 됨.
# talbe_name = 테이블의 인덱스 / row_num 줄번호
print("*" * 30)
print('줄수 : ' + str(len(doc.tables[table_num].rows)))
print('칸수 : ' + str(len(doc.tables[table_num].columns)))
print("*" * 30)
for num in range(len(doc.tables[table_num].row_cells(row_num))):
print(doc.tables[table_num].row_cells(row_num)[num].text.replace(
def renumber_refs(inp,
output,
refs_input=None,
refs_output='new_refs.xlsx',
start=1):
if refs_input == None:
if exists(inp[:-4] + 'xlsx'):
refs_input = inp[:-4] + 'xlsx'
if refs_input:
lit = pd.read_excel(refs_input)
lit.n = lit.n.astype(dtype=np.dtype(int))
lit.set_index(keys='n', inplace=True)
doc = docx.Document(inp)
new_n = {}
do_analysis = True
for p in paragraph_iterator(doc): # doc.paragraphs:
if stop_tag.search(p.text):
do_analysis = False
if continue_tag.search(p.text):
do_analysis = True
if not do_analysis:
continue
for ss in t.findall(p.text):
for sss in unpack_ref(ss)[1]:
if refs_input and (not (int(sss) in lit.index)):
new_n[sss] = 0
lit.loc[int(sss)] = 'Not found'
continue
if not sss in new_n:
new_n[sss] = start
start += 1
r = list(map(int, new_n.keys()))
if refs_input:
# for rr in r:
# if not rr in lit:
# lit.loc[rr] = str(rr)
lit = lit.loc[r]
lit['new_n'] = list(new_n.values())
lit = fix_dublicates(lit)
else:
lit = pd.DataFrame(
data={
'n': list(new_n.keys()),
'new_n': list(new_n.values()),
'title': list(new_n.keys())
})
lit.set_index(keys='n', inplace=True)
print(lit)
doc = docx.Document(inp)
do_replacement = True
for p in paragraph_iterator(doc): # doc.paragraphs:
if stop_tag.search(p.text):
do_replacement = False
if continue_tag.search(p.text):
do_replacement = True
if not do_replacement:
continue
ss = t.search(p.text)
while ss:
l = ss[1]
new_text = pack_ref(lit.loc[map(int, unpack_ref(l)[1])]['new_n'])
if new_text == '':
print(ss[1], '-> removing')
replace_text_in_runs(p.runs, ss.start(), ss.end(), new_text)
else:
print(ss[1], '->', new_text)
replace_text_in_runs(p.runs,
ss.span(1)[0],
ss.span(1)[1], new_text)
ss = t.search(p.text, pos=ss.span(1)[1] + 1)
doc.save(output)
lit.drop_duplicates(subset='new_n', inplace=True)
lit['n'] = lit['new_n']
lit = lit.loc[lit.title != 'Not found']
lit.to_excel(refs_output, columns=['n', 'title'], index=False)
import xlwt
docxPath2 = r'D:\act选房namecn.docx'
# docxPath='D:\hjzb数据库字典_简化.docx'
#docxPath=r'D:\act选房.docx' # r代表非转义
docxPath = r'D:\act在线选房全.docx'
#docxPath=r'D:\华发在线售楼处.doc'
row = 0 # 记录行数
tableSum = 0 # 记录表个数
workbook = xlwt.Workbook(encoding='utf-8')
worksheet = workbook.add_sheet("sheet1")
style = xlwt.easyxf('pattern: pattern solid, fore_colour ice_blue')
# 创建一个已存在的 word 文档的对象
file2 = docx.Document(docxPath2)
# 创建一个已存在的 word 文档的对象
file = docx.Document(docxPath)
# 读取每个段落的内容并输出
# for it in file.paragraphs:
# print( it.text )
paragraphsList = [it.text for it in file.paragraphs if len(it.text) > 0]
print("段落数量:" + str(len(file.paragraphs)))
print("表格数量:" + str(len(file.tables))) #480
print("paragraphsList数量:" + str(len(paragraphsList)))
dist_table = {}
# 读取表格中的内容并输出
def data(self):
doc = docx.Document(self.doc_path)
raw_data = []
for para in doc.paragraphs:
raw_data.append(para.text.strip())
return raw_data
help='Style for text')
parser.add_argument('--code_style',
default='Normal',
help='Style for code')
parser.add_argument('--print_styles',
action='store_true',
help='Print styles available in template')
parser.add_argument('--verbose',
'-v',
action='store_true',
help='Print various information')
args = parser.parse_args()
if args.template is not None:
d = docx.Document(args.template)
else:
d = docx.Document()
if args.print_styles:
print('=================')
print('Styles available:')
for s in d.styles:
print(s.name)
print('=================')
exit(0)
d = modify_document(d, args.input, args)
d.save(args.output)
rev = Review(reviewAuthor, reviewPosition, reviewCompany, reviewRating, reviewDict, days)
print "Review created for %s..." % rev.name[0]
sys.stdout.flush()
return rev
# Create array of Review objects and populate with our reviews
reviewGuide = []
for num in range(reviewNum):
reviewGuide.append(findMaterials(links[num]))
# Sort our list based on date posted
#reviewGuideSorted = sorted(reviewGuide, key=attrgetter('day'), reverse=True)
# Create document and insert main heading
doc = docx.Document()
doc.add_heading('Trust Radius Weekly Report', 0)
# Func createPage: page (param): an instance of a Review object
def createPage(page):
# Insert Review Info
doc.add_heading(page.name, 1)
doc.add_heading("%s at %s" % (page.position[0], page.company[0]), 3)
doc.add_heading(page.day.strftime('%B %d, %Y'), 3)
doc.add_heading(page.rating + ' out of 10 stars', 3)
# Insert Review Text
for x, y in page.goodies.items():
doc.add_heading(x, 4)
doc.add_paragraph(y)
# Read and write word document
import docx
# New document object.
d = docx.Document('docx_files/demo.docx')
# List of paragraph objects.
print(d.paragraphs)
# One paragraph object.
print(d.paragraphs[0])
# Text of the one paragraph object.
print(d.paragraphs[0].text)
print(d.paragraphs[1].text)
# Save the second paragraph object to a variable.
p = d.paragraphs[1]
# List of run objects (Runs = whenever there is a change in style.)
# p should have 4.
print(p.runs)
# Run objects also have a text member.
print(p.runs[0].text)
print(p.runs[1].text)
print(p.runs[2].text)
print(p.runs[3].text)
# Can also check it
def addruns(filename, runs):
# Add runs to a paragraph.
doc = docx.Document(filename)
for r in runs:
doc.add_paragraph(' ').add_run(r)
doc.save(filename)
Al Sweigart
Robocop
Write a program that would generate a Word document with custom
invitations that look like Figure 13-11.
You can download
a sample guests.txt file from http://nostarch.com/automatestuff/.
'''
import docx
guestFile = open('guests.txt', 'r')
guestStr = guestFile.read()
guestLst = guestStr.split('\n')
guestFile.close()
doc = docx.Document('invitations_empty.docx')
for guest in guestLst:
doc.add_paragraph('It would be a pleasure to have the company of',\
style='InvText')
doc.add_paragraph(guest, style='InvName')
doc.add_paragraph('At 111010 Memory Lane on the Evening of',\
style='InvText')
doc.add_paragraph('April 1st', style='InvDate')
doc.add_paragraph('at 7 o\'clock', style='InvText')
doc.add_page_break()
doc.save('invitations.docx')
