[PyMemos - Excel, PDF, docs] #python #memo #excel #pdf #doc

doc_manipulation.py

import docx

d = docx.Document('demo.docx')
p = d.paragraphs[1]
print(p.text)
print(p.runs[1].bold)
print(p.runs[3].italic)
p.runs[3].underline = True
p.runs[3].text = 'italic and underlined'
p.style = "Title"
d.save('demo2.docx')

d = docx.Document()
d.add_paragraph('Hello, this is paragraph.')
d.add_paragraph('Andthis is another paragraph.')
d.save('demo3.docx')

def getDocText(filename):
    d = docx.Document(filename)
    fullText = []
    for par in d.paragraphs:
        fullText.append(par.text)
    return '\n'.join(fullText)
print(getDocText('demo.docx'))

excel_manipulation.py

import openpyxl

# open and work with an existing excel workbook
os.chdir(r'C:\Users\woj.wojciechowski\Desktop\py')
workbook = openpyxl.load_workbook('exampleABS.xlsx')
print(workbook.sheetnames)
sheet = workbook['Sheet1']
cell = sheet['A1']
print(cell.value)
print(sheet.cell(row=1, column=3).value)

# open and work new workbook
wb = openpyxl.Workbook()
print(wb.sheetnames)
sheet = wb['Sheet']
sheet['A1'].value = 6
sheet['A2'].value = 12

sheet2 = wb.create_sheet(index=0, title='New_sheet')
print(wb.sheetnames)
sheet2.title = 'Sheet2'
print(wb.sheetnames)
os.chdir(r'C:\Users\woj.wojciechowski\Desktop\py')
wb.save('exampleABS2.xlsx')

pdf_manipulation.py

import PyPDF2

os.chdir(r'C:\Users\woj.wojciechowski\Desktop\py')
pdfFile = open('meetingminutes1.pdf', 'rb')

reader = PyPDF2.PdfFileReader(pdfFile)

print(reader.numPages)
page = reader.getPage(0)
print(page.extractText())

for pageNum in range(reader.numPages):
    print(reader.getPage(pageNum).extractText())

writer = PyPDF2.PdfFileWriter()

for pageNum in range(reader.numPages):
    page = reader.getPage(pageNum)
    writer.addPage(page)
    writer.addPage(page) # duplikuje sobie bo tak

outputFile = open('duplicatedPdf.pdf', 'wb')
writer.write(outputFile)
outputFile.close()
pdfFile.close()