Python を使用してリサンプリングせずに PDF から高解像度の画像を抽出する方法

<code class="python">import fitz

doc = fitz.open("input.pdf")
for page_num in range(len(doc)):
    for img in doc.getPageImageList(page_num):
        xref = img[0]
        pix = fitz.Pixmap(doc, xref)
        if pix.n < 5:  # Check if it's grayscale or RGB
            pix.writePNG(f"page_{page_num}_img_{xref}.png")
        else:  # Convert CMYK to RGB before saving
            pix1 = fitz.Pixmap(fitz.csRGB, pix)
            pix1.writePNG(f"page_{page_num}_img_{xref}.png")</code>

<code class="python">import os
import fitz
from tqdm import tqdm

workdir = "path_to_pdf_folder"

for each_path in os.listdir(workdir):
    if ".pdf" in each_path:
        doc = fitz.Document(os.path.join(workdir, each_path))

        for i in tqdm(range(len(doc)), desc="pages"):
            for img in tqdm(doc.get_page_images(i), desc="page_images"):
                xref = img[0]
                image = doc.extract_image(xref)
                pix = fitz.Pixmap(doc, xref)
                pix.save(os.path.join(workdir, f"{each_path[:-4]}_p{i}-{xref}.png"))</code>