INNER CODE UNIT · Python

_load_document

mindee/doctr · doctr/cli/main.py:95

def _load_document(args: argparse.Namespace) -> list[np.ndarray]:
    """Load every input into a single list of pages

    Args:
        args: the parsed command-line arguments

    Returns:
        the list of pages decoded as numpy ndarray of shape H x W x 3
    """
    pdf_kwargs: dict[str, Any] = {"scale": args.pdf_scale, "password": args.pdf_password}

    pages: list[np.ndarray] = []
    for input_path in args.input_path:
        try:
            if input_path.lower().startswith(("http://", "https://")):
                pages.extend(DocumentFile.from_url(input_path, **pdf_kwargs))
            elif input_path.lower().endswith(".pdf"):
                pages.extend(DocumentFile.from_pdf(input_path, **pdf_kwargs))

View source record →