pypdf로 PDF를 합치고 페이지 범위를 추출하기

from pathlib import Path
from pypdf import PdfWriter

SOURCE_DIR = Path("outputs") / "pdf_merge_split_demo"
PDFS = {
    "alpha.pdf": [(100, 200), (110, 210)],
    "beta.pdf": [(120, 220)],
    "gamma.pdf": [(130, 230), (140, 240), (150, 250)],
}

SOURCE_DIR.parent.mkdir(parents=True, exist_ok=True)
SOURCE_DIR.mkdir()  # Stop if the synthetic source already exists.

for filename, page_sizes in PDFS.items():
    writer = PdfWriter()
    for width, height in page_sizes:
        writer.add_blank_page(width=width, height=height)
    target = SOURCE_DIR / filename
    with target.open("xb") as stream:
        writer.write(stream)

python create_pdf_demo.py

from pathlib import Path
from pypdf import PdfReader, PdfWriter

SOURCE_DIR = Path("outputs") / "pdf_merge_split_demo"
INPUTS = ("alpha.pdf", "beta.pdf", "gamma.pdf")
OUTPUT_DIR = Path("outputs") / "pdf_merge_split_result"
MERGED = OUTPUT_DIR / "merged.pdf"
EXTRACTED = OUTPUT_DIR / "pages_2_to_5.pdf"
START_PAGE = 2
END_PAGE = 5


def page_size(page) -> tuple[int, int]:
    width = int(float(page.mediabox.width))
    height = int(float(page.mediabox.height))
    return width, height


def main() -> None:
    source_root = SOURCE_DIR.resolve(strict=True)
    if not source_root.is_dir():
        raise ValueError("SOURCE_DIR must be a directory.")
    if START_PAGE < 1 or END_PAGE < START_PAGE:
        raise ValueError("Invalid page range.")

    input_paths = [source_root / name for name in INPUTS]
    for path in input_paths:
        if not path.is_file():
            raise FileNotFoundError(f"Missing input PDF: {path}")

    OUTPUT_DIR.parent.mkdir(parents=True, exist_ok=True)
    OUTPUT_DIR.mkdir()  # Refuse to reuse an existing result folder.

    expected_sizes = []
    writer = PdfWriter()
    for path in input_paths:
        reader = PdfReader(path)
        if reader.is_encrypted:
            raise ValueError(f"Encrypted PDF is not supported here: {path.name}")
        for page in reader.pages:
            expected_sizes.append(page_size(page))
            writer.add_page(page)

    with MERGED.open("xb") as stream:
        writer.write(stream)

    merged_reader = PdfReader(MERGED)
    if merged_reader.is_encrypted:
        raise RuntimeError("Unexpected encrypted merged PDF.")
    merged_sizes = [page_size(page) for page in merged_reader.pages]
    if merged_sizes != expected_sizes:
        raise RuntimeError("Merged page count or order does not match the inputs.")

    if END_PAGE > len(merged_reader.pages):
        raise ValueError(
            f"Requested page {END_PAGE}, but merged PDF has only "
            f"{len(merged_reader.pages)} pages."
        )

    selected_pages = merged_reader.pages[START_PAGE - 1:END_PAGE]
    extracted_writer = PdfWriter()
    expected_extract_sizes = []
    for page in selected_pages:
        expected_extract_sizes.append(page_size(page))
        extracted_writer.add_page(page)

    with EXTRACTED.open("xb") as stream:
        extracted_writer.write(stream)

    extracted_reader = PdfReader(EXTRACTED)
    extracted_sizes = [page_size(page) for page in extracted_reader.pages]
    if extracted_sizes != expected_extract_sizes:
        raise RuntimeError("Extracted PDF does not match the selected pages.")

    print(f"Merged {len(INPUTS)} PDFs into {len(merged_reader.pages)} pages.")
    print(
        f"Extracted pages {START_PAGE}-{END_PAGE}: "
        f"{len(extracted_reader.pages)} pages."
    )
    print(f"Merged output: {MERGED.as_posix()}")
    print(f"Extracted output: {EXTRACTED.as_posix()}")


if __name__ == "__main__":
    main()

python pdf_merge_split.py

Merged 3 PDFs into 6 pages.
Extracted pages 2-5: 4 pages.
Merged output: outputs/pdf_merge_split_result/merged.pdf
Extracted output: outputs/pdf_merge_split_result/pages_2_to_5.pdf