remove-pages

#!/usr/bin/env python3
import subprocess
import sys


def print_help():
    print("""
Removes specified pages from a given PDF file.

### Usage

1. Ensure that you have `pip` installed.
2. Run the script with the PDF file to be processed and the page numbers
to be removed (comma separated, no spaces).
```
$ ./remove-pages doc.pdf 1,2,3
```
3. The modified file is saved as `new_doc.pdf`.
    """)


print("Installing requirements...")
subprocess.check_call([sys.executable, "-m", "pip", "install", "PyPDF2"])

from PyPDF2 import PdfFileWriter, PdfFileReader

try:
    if len(sys.argv) > 2:
        # PDF file to be processed
        file = sys.argv[1]
        remove_pages = list(map(int, sys.argv[2].split(',')))
        print(f"File to be processed:\t{file}")
        print(f"Pages to be removed:\t{remove_pages}")

        writer = PdfFileWriter()
        # add selected pages to the PDF file writer
        pdf = PdfFileReader(open(file, 'rb'))
        for page in range(pdf.getNumPages()):
            # Note: PyPDF2 pages start at 0, specified pages start at 1
            if (page + 1) not in remove_pages:
                writer.addPage(pdf.getPage(page))

        # save modified PDF
        writer.write(open("new_doc.pdf", 'wb'))
        print("\nPage removal complete! Saved as: new_doc.pdf")
    else:
        print_help()

except Exception as e:
    print("\nError: File could not be processed!")
    print(e)