Takes a pdf file and extracts a range of pages. Useful for batch removing cover pages or editing

split_pdf.py

#!/usr/bin/python
import argparse
import os
from pyPdf import PdfFileWriter, PdfFileReader

def is_valid_file(parser, arg):
    if not os.path.exists(arg):
        parser.error("The file %s does not exist." % arg)
    else:
        return arg
def main():
    parser = argparse.ArgumentParser(description="Split PDFs")

    parser.add_argument('pdf_file', help="input file that you are splitting",
                        metavar="SOURCE-PDF", type=lambda x: is_valid_file(parser, x))
    parser.add_argument('output_file', help="name of output file", metavar="OUTPUT-PDF")
    parser.add_argument('start_page', help="start page", type=int, metavar="START-PAGE")
    parser.add_argument('end_page', help="end page", type=int, metavar="END-PAGE")

    args = parser.parse_args()

    if args.start_page > args.end_page or args.start_page < 0:
        parser.error("Bad page numbers.")

    with open(args.pdf_file, "rb") as pdf_file:
        inputpdf = PdfFileReader(pdf_file)
        outputpdf = PdfFileWriter()
        if inputpdf.numPages < args.end_page:
            parser.error("End page out of range. Only %s pages in document." % inputpdf.numPages)
        for page in xrange(args.start_page, args.end_page+1):
            outputpdf.addPage(inputpdf.getPage(page))
        outputpdf.write(open(args.output_file, "wb"))

if __name__ == '__main__':
    main()