splitting pdf file into several files

split_pdf.py

# pip install pypdf
from __future__ import annotations

import argparse
from pathlib import Path
from typing import List, Tuple
from pypdf import PdfReader, PdfWriter


def parse_ranges(ranges_str: str, total_pages: int) -> List[Tuple[int, int]]:
    """
    Parse page ranges like: "1-62,63-116" (1-based, inclusive).
    Supports open-ended like "63-" meaning 63..total_pages.
    Returns list of (start, end) as 1-based inclusive ints.
    """
    out: List[Tuple[int, int]] = []
    for part in ranges_str.split(","):
        part = part.strip()
        if not part:
            continue
        if "-" not in part:
            raise ValueError(f"Bad range '{part}'. Use like 1-62.")
        a, b = (x.strip() for x in part.split("-", 1))
        if a == "":
            raise ValueError(f"Bad range '{part}': start page missing.")
        start = int(a)
        end = total_pages if b == "" else int(b)

        if start < 1:
            raise ValueError(f"Bad range '{part}': start must be >= 1.")
        if end < start:
            raise ValueError(f"Bad range '{part}': end must be >= start.")
        if end > total_pages:
            raise ValueError(f"Bad range '{part}': end ({end}) > total pages ({total_pages}).")

        out.append((start, end))

    # optional sanity: detect overlaps
    used = set()
    for s, e in out:
        for p in range(s, e + 1):
            if p in used:
                raise ValueError(f"Overlapping ranges: page {p} appears more than once.")
            used.add(p)

    return out


def split_pdf_ranges(input_pdf: str | Path, ranges: List[Tuple[int, int]], output_dir: str | Path) -> List[Path]:
    input_pdf = Path(input_pdf)
    output_dir = Path(output_dir)
    output_dir.mkdir(parents=True, exist_ok=True)

    reader = PdfReader(str(input_pdf))
    total_pages = len(reader.pages)

    outputs: List[Path] = []
    for start, end in ranges:
        writer = PdfWriter()
        for i in range(start - 1, end):  # to 0-based, end is inclusive
            writer.add_page(reader.pages[i])

        out_path = output_dir / f"{input_pdf.stem}_{start:03d}-{end:03d}.pdf"
        with out_path.open("wb") as f:
            writer.write(f)
        outputs.append(out_path)

    return outputs


def main():
    ap = argparse.ArgumentParser(description="Split a PDF into multiple PDFs by page ranges.")
    ap.add_argument("input_pdf", help="Path to input PDF")
    ap.add_argument("--ranges", required=True, help='Ranges like "1-62,63-116" (1-based, inclusive)')
    ap.add_argument("--out", default="splits", help="Output directory (default: splits)")
    args = ap.parse_args()

    reader = PdfReader(args.input_pdf)
    total_pages = len(reader.pages)
    ranges = parse_ranges(args.ranges, total_pages)

    outputs = split_pdf_ranges(args.input_pdf, ranges, args.out)
    for p in outputs:
        print(p)


if __name__ == "__main__":
    main()

python split_pdf.py main.pdf --ranges "1-78,79-117" --out out_pdfs