Python - Split PDF Files

Python - Split PDF Files

CODE

#Import Modules required for the PDF Splitting operation from PyPDF2 import PdfFileReader, PdfFileWriter #Provide the Input and Output Folder and Files inputFolder = "C:\\Test\\Simple Kettle\\Programs\\work\\input" outputFolder = "C:\\Test\\Simple Kettle\\Programs\\work\\output" inputFile = inputFolder + "\\input.pdf" #Function definition: This will take care of splitting the input file. def splitPDFFile(): #Open the input pdf file in the binary format. with open(inputFile, 'rb') as f: #Read the pdf file. r = PdfFileReader(f) #Loop through the different pages of the pdf file. In the below for loop, the i starts from 0 and go up to the maximum pages. for i in range(0, r.getNumPages()): print("Splitting Page_" + str(i+1)) #Start a PDF Writer object. w = PdfFileWriter() #Add the current page to the PDF Writer object. w.addPage(r.getPage(i)) #Open and Write the writer object contents to a new pdf output file. #If 4 pages are there in the input file, it will be splitted into 4 different pdf files. #The iteration variable "i" controls the naming of the pdf output files. with open(outputFolder + "\\output_" + str(i+1) + ".pdf", "wb") as result: w.write(result) #Invoke the function splitPDFFile()