How to Remove Pages from a PDF with Python (Tested pypdf Guide)

from pypdf import PdfReader, PdfWriter

def remove_pages(input_path: str, output_path: str, pages_to_remove: list[int]):
    """
    Removes specified 0-based page indices from a PDF file.
    Example: remove_pages('contract.pdf', 'cleaned.pdf', [0, 2])
    """
    reader = PdfReader(input_path)
    writer = PdfWriter()

    # Create a set for O(1) lookup
    exclude_indices = set(pages_to_remove)

    for idx, page in enumerate(reader.pages):
        if idx not in exclude_indices:
            writer.add_page(page)

    with open(output_path, "wb") as output_file:
        writer.write(output_file)

    print(f"Successfully pruned {len(exclude_indices)} pages into {output_path}")

# Example execution: prune page 1 (idx 0) and page 4 (idx 3)
if __name__ == "__main__":
    remove_pages("input.pdf", "output.pdf", [0, 3])

import io
from pypdf import PdfReader, PdfWriter

def remove_pages_in_memory(pdf_bytes: bytes, pages_to_remove: list[int]) -> bytes:
    """
    In-memory PDF page removal for web frameworks (FastAPI, Flask, AWS Lambda).
    Accepts raw binary bytes, returns modified PDF bytes without disk I/O.
    """
    reader = PdfReader(io.BytesIO(pdf_bytes))
    writer = PdfWriter()
    exclude = set(pages_to_remove)

    for idx, page in enumerate(reader.pages):
        if idx not in exclude:
            writer.add_page(page)

    output_stream = io.BytesIO()
    writer.write(output_stream)
    return output_stream.getvalue()