def combina_foi_din_diferite_pdf():
"""1. Find all pdf in a folder."""
pdfFiles = []
pdfWriter = PyPDF3.PdfFileWriter()
for filename in os.listdir('.'):
if filename.endswith('.pdf'):
pdfFiles.append(filename)
pdfFiles.sort(key=str.lower)
#print(pdfFiles)
pdfFiles = ['3340063.pdf', 'bus.pdf'] # pentru test
print(pdfFiles) # pentru test
# pdfWriter = PyPDF3.PdfFileWriter()
# """2. Open each pdf."""
# pdfFiles = []
for filename in pdfFiles:
pdfFileObj = open(filename, 'rb')
pdfReader = PyPDF3.PdfFileReader(pdfFileObj)
print(pdfReader)
# """3. Add each page."""
for filename in pdfFiles:
for pageNum in range(1, pdfReader.numPages):
pageObj = pdfReader.getPage(pageNum)
pdfWriter.addPage(pageObj)
print(pdfWriter)
# """4. Save the result."""
for filename in pdfFiles:
for pageNum in range(1, pdfReader.numPages):
pdfOutput = open('rezultat_merging.pdf', 'wb')
pdfWriter.write(pdfOutput)
pdfOutput.close()
def add_barcode(self, barcode, original_path, x_pos=None, y_pos=None):
"""
Adds a barcode to the first page of a document
:param barcode: Barcode to add to the file specified in original_path
:param original_path: Path to the original file.
:param y_pos: Position of the bottom of the barcode measure in mm from the bottom of the page.
:return:
"""
merger = PyPDF3.PdfFileReader(original_path)
barcode_doc = PyPDF3.PdfFileReader(
self.barcode_doc.generate_barcode(barcode)).getPage(0)
first_page = merger.getPage(0)
if y_pos is not None:
barcode_target_y = self.get_y_pos(first_page.mediaBox[3], y_pos)
else:
barcode_target_y = 0
centre_pos = float(first_page.mediaBox[2]) / 2 - float(
barcode_doc.mediaBox[2]) / 2
first_page.mergeTranslatedPage(barcode_doc, centre_pos,
barcode_target_y)
out = PyPDF3.PdfFileWriter()
out.addPage(first_page)
[out.addPage(page) for page in merger.pages[1:]]
filename = original_path[original_path.rfind('/'):original_path.
rfind('.')]
output_filename = f"{self.save_path}/{filename}_{barcode}_coded.pdf"
with open(output_filename, 'wb') as output:
out.write(output)
def decrypt():
pdfName = input('Enter the name of PDF file to decrypt:\n')
pdfName = path.abspath(pdfName)
# Check if entered filename is valid
if not path.exists(pdfName) or pdfName[-4:].lower() != '.pdf':
print(f'The filename {pdfName} is not a PDF.')
sys.exit()
pdfFile = open(pdfName, 'rb')
pdfReader = PyPDF3.PdfFileReader(pdfFile)
# Password for decryption
password = input('Enter the password to decrypt the PDF: \n')
pdfReader.decrypt(password)
pdfWriter = PyPDF3.PdfFileWriter()
# Loop through the pages and add them to pdfWriter
for pageNum in range(pdfReader.numPages):
pdfWriter.addPage(pdfReader.getPage(pageNum))
# Save the resulting PDF to a file
decryptedPdf = open('decrypted' + path.basename(pdfName), 'wb')
pdfWriter.write(decryptedPdf)
decryptedPdf.close()
print(f'File decrypted and saved as decrypted{path.basename(pdfName)}')
def encripteaza(pdf_file):
pdfFile = open(pdf_file, 'rb')
pdfReader = PyPDF3.PdfFileReader(pdfFile)
pdfWriter = PyPDF3.PdfFileWriter()
for pageNum in range(pdfReader.numPages):
pdfWriter.addPage(pdfReader.getPage(pageNum))
pdfWriter.encrypt('swordfish') # parola cu care encripteaza
resultPdf = open('rezultat_encriptare.pdf', 'wb')
pdfWriter.write(resultPdf)
resultPdf.close()
def roteste_pagina(pdf_file): # roteste prima pagina si face din ea un nou pdf
minutesFile = open(pdf_file, 'rb')
pdfReader = PyPDF3.PdfFileReader(minutesFile)
page = pdfReader.getPage(0)
page.rotateClockwise(90)
pdfWriter = PyPDF3.PdfFileWriter()
pdfWriter.addPage(page)
resultPdfFile = open('rezultat_rotire.pdf', 'wb')
pdfWriter.write(resultPdfFile)
resultPdfFile.close()
minutesFile.close()
def overlay(pdf_file):
minutesFile = open(pdf_file, 'rb')
pdfReader = PyPDF3.PdfFileReader(minutesFile)
minutesFirstPage = pdfReader.getPage(0)
pdfWatermarkReader = PyPDF2.PdfFileReader(open('watermark.pdf', 'rb'))
minutesFirstPage.mergePage(pdfWatermarkReader.getPage(0))
pdfWriter = PyPDF3.PdfFileWriter()
pdfWriter.addPage(minutesFirstPage)
for pageNum in range(1, pdfReader.numPages):
pageObj = pdfReader.getPage(pageNum)
pdfWriter.addPage(pageObj)
resultPdfFile = open('rezultat_overlay.pdf', 'wb')
pdfWriter.write(resultPdfFile)
minutesFile.close()
resultPdfFile.close()
def __crop__(self, name):
pagNum = int(input("Enter page number\n"))
upperX = int(input("please enter upper x cordinate\n"))
upperY = int(input("please enter upper y cordinate\n"))
lowerX = int(input("please enter lower x cordinate\n"))
lowerY = int(input("please enter lower y cordinate\n"))
path = self.getPath()
writer = PyPDF3.PdfFileWriter()
page = self.tPdf.getPage(pagNum)
page.cropBox.setLowerLeft((lowerX, lowerY))
page.cropBox.setUpperRight((upperX, upperY))
writer.addPage(page)
path = "Class\pdfFileHere\{0}.pdf".format(name)
outstream = open(path, 'wb')
writer.write((outstream))
outstream.close()
def append_pdf(): # append a pdf to another pdf (merge 2 pdf-uri)
pdf1File = open('meetingminutes.pdf', 'rb')
pdf2File = open('meetingminutes2.pdf', 'rb')
pdf1Reader = PyPDF3.PdfFileReader(pdf1File)
pdf2Reader = PyPDF3.PdfFileReader(pdf2File)
pdfWriter = PyPDF3.PdfFileWriter()
for pageNum in range(pdf1Reader.numPages):
pageObj = pdf1Reader.getPage(pageNum)
pdfWriter.addPage(pageObj)
for pageNum in range(pdf2Reader.numPages):
pageObj = pdf2Reader.getPage(pageNum)
pdfWriter.addPage(pageObj)
pdfOutputFile = open('combinedminutes1.pdf', 'wb')
pdfWriter.write(pdfOutputFile)
pdfOutputFile.close()
pdf1File.close()
pdf2File.close()
def split_pdf(pdffile: str):
"""Split a PDF file in one file per page.
Args:
pdffile (str): The name of the PDF file to split.
"""
with open(pdffile, 'rb') as pdffile_handle:
pdf_in = pypdf.PdfFileReader(pdffile_handle)
num_pages = pdf_in.numPages
pages = []
if 'pdf' in pdffile.lower():
file_first_name = pdffile.lower()[:pdffile.lower().index('.pdf')]
for page in range(num_pages):
pages.append(file_first_name + f'_p_{page}' + '.pdf')
pdf_out = pypdf.PdfFileWriter()
pdf_out.addPage(pdf_in.getPage(page))
with open(pages[-1], 'wb') as stream:
pdf_out.write(stream)
return pages
def simple2():
pdf_file = open('meetingminutes.pdf', 'rb')
pdf_reader = PyPDF3.PdfFileReader(pdf_file)
pdf_file2 = open('meetingminutes2.pdf', 'rb')
pdf_reader2 = PyPDF3.PdfFileReader(pdf_file)
pdf_writer = PyPDF3.PdfFileWriter()
for page_num in range(pdf_reader.numPages):
pdf_obj = pdf_reader.getPage(page_num)
pdf_writer.addPage(pdf_obj)
for page_num in range(pdf_reader2.numPages):
pdf_obj = pdf_reader2.getPage(page_num)
pdf_writer.addPage(pdf_obj)
pdf_file3 = open('combinedminutes.pdf', 'wb')
pdf_writer.write(pdf_file3)
pdf_file3.close()
pdf_file.close()
pdf_file2.close()
import PyPDF3, os
os.chdir('C:\\users\\rahul.goyal\\documents')
pdf1File = open('RBI-GradeB-Prep.pdf', 'rb')
pdf2File = open('Leave Policy ION India.pdf', 'rb')
reader1 = PyPDF3.PdfFileReader(pdf1File)
reader2 = PyPDF3.PdfFileReader(pdf2File)
writer = PyPDF3.PdfFileWriter()
for pageNum in range(reader1.numPages):
page = reader1.getPage(pageNum)
writer.addPage(page)
for pageNum in range(reader2.numPages):
page = reader2.getPage(pageNum)
writer.addPage(page)
outFile = open('Comb_Doc.pdf', 'wb')
writer.write(outFile)
outFile.close()
pdf2File.close()
pdf1File.close()
print("Found Email List File Named: "+file)
emails = [x.replace('\n', '') for x in configStream]
if not emails:
raiseEmailFileError()
os._exit(0)
except:
raiseEmailFileError()
os._exit(0)
ln = pdf.getNumPages()
c = ln/len(emails)
if c % 1 != 0:
raiseEmailCountError(ln, len(emails))
os._exit(0)
c = int(c)
print("Detected "+str(c)+" Report Page(s) Per Student.")
for pg in range(0, ln, c):
output = PyPDF3.PdfFileWriter()
for i in range(0, c):
output.addPage(pdf.getPage(pg+i))
outputStream = BytesIO()
output.write(outputStream)
data = outputStream.getvalue()
outputStream.close()
mailPDF(emails[int(pg/c)], data, "report.pdf")
pdf = PyPDF3.PdfFileReader(inputStream)
inputStream.close()