def crop_image_from_pdf_page()

in seed/util/preprocess.py [0:0]

• 9 lines of code
• 2 McCabe index (conditional complexity)

def crop_image_from_pdf_page(pdf_path, page_number, bounding_box):
    """
    Crops a region from a given page in a PDF and returns it as an image.

    :param pdf_path: Path to the PDF file.
    :param page_number: The page number to crop from (0-indexed).
    :param bounding_box: A tuple of (x0, y0, x1, y1) coordinates for the bounding box.
    :return: A PIL Image of the cropped area.
    """
    doc = fitz.open(pdf_path)
    page = doc.load_page(page_number)
    
    # Cropping the page. The rect requires the coordinates in the format (x0, y0, x1, y1).
    bbx = [x * 72 for x in bounding_box]
    rect = fitz.Rect(bbx)
    pix = page.get_pixmap(matrix=fitz.Matrix(300/72, 300/72), clip=rect)
    
    img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
    
    doc.close()

    return img