PDF file split and copy

[rob101]

Mostly in the interests of learning, but also for a practical application, I've been looking for a way to copy pages from a PDF file and write said pages to a new PDF file. Having done that, I've further developed the idea so that pages from different PDF files can be combined into a new PDF file.

I used the pdfrw 0.4 project, for no other reason than it's the first project I came to. I may (if I find the time and motivation) at some point look at other ways to do this, but right now, this does what I need it to do.

I hope you find it of use. If you find any bugs, please report back (maybe with a fix?) and I'll update the code.

Of note: This code does not traverse directories; simply run from a location in which you have a copy of your PDF files: I take no responsibility for any loss of your files, so please work with copies, so that you know that you have a back-up.

Thanks.

#!/usr/bin/python3

# Install with: pip3 install pdfrw

from pdfrw import PdfReader, PdfWriter

import os


def read_file(opp):
    head = "PDF File List"
    print(head.center(2 * len(head)))
    print(f"{'-'*len(head)}".center(2 * len(head)))
    files = os.listdir()
    file_number = 0
    file_list = []
    for file in files:
        file_name = file.split(".")
        if len(file_name) > 1 and file_name[1].lower() == 'pdf':
            file_number += 1
            file_list.append((file_number, file))
    for index, file in enumerate(file_list):
        print("{:2d}: {}".format(file_list[index][0], file_list[index][1]))
    file_name = False
    while not file_name:
        try:
            file_name = int(input(f"\n{opp}: "))
        except:
            print("Pick a file by its number.")
        if file_name > len(file_list) or file_name == 0:
            file_name = False
        else:
            file_name = file_list[file_name - 1]
    print(f"Reading from {file_name[1]}")
    return file_name[1]
#==============<end of read file>=============#


def page_select(file_name):
    # pages are zero indexed for the file read
    read_from = PdfReader(file_name)
    page_list = []
    process_list = []
    copy_list = []
    pages = len(read_from.pages)  # returns the total number of pages, starting at one
    print(f"\nNumber of pages in {file_name}: {pages}")
    for page in range(pages):
        page_list.append(page)
    if pages == 1:
        process_list.append(file_name)
        process_list.append(0)
    else:
        process_list.append(file_name)
        print()
        print("For each page you want to copy, enter the page")
        print("number and press enter.\n")
        print("To finish, simply press enter.")
        print()
        copy_page = True
        while copy_page:
            copy_page = input("Page number to copy: ")
            if copy_page:
                copy_page = int(copy_page) - 1
                if copy_page not in page_list:
                    print(
                        f"Page {copy_page+1} does not exist.\nPlease check your PDF file and page number.")
                else:
                    process_list.append(copy_page)
                    copy_page = True
        if copy_list:
            print("\nPages to copy:")
            for page in copy_list:
                print(page + 1, end=' ')
            print("\n")
    return process_list
#=============<end of page select>============#


def file_select():
    response = ("yes", "no")
    pdf_select = True
    while pdf_select:
        pdf_select = input("Select another pdf file? ")
        if pdf_select not in response:
            print("Please answer yes or no")
            pdf_select = True
        elif pdf_select == 'yes':
            return True
        else:
            return False
#=============<end of file select>============#


def write_file(process_list):
    files = os.listdir()
    file_name = False
    overwrite = True
    while not file_name:
        file_name = input("Write to: ")
    if file_name in files:
        print(f"\nWARNING!\n{file_name} already exists.")
        print("Do you want to overwrite that file?")
        overwrite = input("(y)es or (n)o: ") in ("y",)
    if overwrite:
        print(f"Writing to file: {file_name}")
        write_to = PdfWriter()
        for file in process_list:
            read_from = PdfReader(file[0])
            for page in range(1, len(file)):
                print(f"Adding page {file[page]+1} from file {file[0]}")
                write_to.addpage(read_from.pages[file[page]])
        write_to.write(file_name)
    else:
        return False
    return True
#============<end of write file>=============#


process_list = []
pdf_select = True
while pdf_select:
    read_from = read_file("Read from")
    process_list.append(page_select(read_from))
    pdf_select = file_select()

opp = write_file(process_list)
if opp:
    input("\nFile successfully written.\nPress the enter key to exit.")
else:
    input("\nOperation aborted.\nPress the enter key to exit.")

As a foot note: I've not done any extensive testing, but I have found one PDF file that this will not read, but as it's a bank account statement, there could be some kind of security issue, but I can't say for sure, as I don't know enough about the topic.