Use Python to remove pages from a pdf

pdf_remove_pages.py

#! /usr/bin/python3

import click
import PyPDF2

def parseIntSet(inputString):
    selection = set()
    invalid = set()
    tokens = [x.strip() for x in inputString.split(",")]
    for token in tokens:
        try:
            selection.add(int(token))
        except ValueError:
            #try to parse string
            try:
                subtokens = [int(x) for x in token.split("-")]
                subtokens.sort()
                selection.update(range(subtokens[0], subtokens[-1]+1))
            except:
                invalid.add(token)
    return selection
                
            

@click.command()
@click.argument("src", nargs=1)
@click.argument("dst", nargs=1)
@click.argument("skip", nargs=1)
def merge(skip, src, dst):
    pdf_writer = PyPDF2.PdfFileWriter()
    print(f"Processing {src}")
    pdf_file_object = open(src, "rb")
    pdf_reader = PyPDF2.PdfFileReader(pdf_file_object)
    skipped = parseIntSet(skip)
    for pagenum in range(pdf_reader.numPages):
        if pagenum+1 in skipped:
            continue
        print(f"    Adding page:{pagenum+1} of {pdf_reader.numPages}")
        page = pdf_reader.getPage(pagenum)
        pdf_writer.addPage(page)
    
    pdf_out_file = open(dst, "wb")
    pdf_writer.write(pdf_out_file)
    pdf_out_file.close()
    print("Done")

if __name__ == "__main__":
    merge()