Last active
December 6, 2022 15:35
-
-
Save kokoro-aya/5ef4cc61c243dbe1de71fdcfb965a07b to your computer and use it in GitHub Desktop.
Extract PDF pages from a single PDF file with range
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from argparse import ArgumentParser | |
from PyPDF2 import PdfFileReader, PdfWriter | |
def main(): | |
parser = ArgumentParser( | |
prog="A simple PDF page extractor", | |
description="A simple PDF page extractor", | |
epilog="Text at the bottom for help" | |
) | |
parser.add_argument("input") | |
parser.add_argument("output") | |
parser.add_argument("start") | |
parser.add_argument("to") | |
args = parser.parse_args() | |
input_file = args.input | |
output_file = args.output | |
start = int(args.start) | |
to = int(args.to) | |
if start < 0 or to < 0: | |
raise "Starting and ending page must be a natural number." | |
if start > to: | |
raise "Starting page must be smaller than ending page." | |
with open(input_file, 'rb') as reader: | |
pdf = PdfFileReader(reader) | |
info = pdf.getDocumentInfo() | |
page_num = pdf.getNumPages() | |
if start > page_num or to > page_num: | |
raise f"Either the starting page or ending page is out of range of the file pages. " \ | |
f"The file has {page_num} pages." | |
pdf_out = PdfWriter() | |
for i in range(start, to): | |
pdf_out.addPage(pdf.getPage(i)) | |
pdf_out.write(output_file) | |
print("Extraction finished.") | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment