Comment pouvez-vous extraire des images de PDF à l'aide de Python tout en préservant leur résolution d'origine ?

<code class="python">import fitz

# Open the PDF document
doc = fitz.open("file.pdf")

# Iterate through the pages
for i in range(len(doc)):
    # Extract images from the current page
    for img in doc.getPageImageList(i):
        # Retrieve the image's XREF and create a Pixmap
        xref = img[0]
        pix = fitz.Pixmap(doc, xref)

        # Check if the image is grayscale or RGB
        if pix.n < 5:
            # Save the image in PNG format
            pix.writePNG("p%s-%s.png" % (i, xref))

        # If the image is CMYK, convert it to RGB and save
        else:
            pix1 = fitz.Pixmap(fitz.csRGB, pix)
            pix1.writePNG("p%s-%s.png" % (i, xref))
            pix1 = None

        # Release the Pixmaps
        pix = None</code>

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

# Specify the work directory
workdir = "your_folder"

# Iterate through the PDFs in the directory
for each_path in os.listdir(workdir):
    if ".pdf" in each_path:
        # Open the PDF document
        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"):
                # Extract the image and save as PNG
                xref = img[0]
                image = doc.extract_image(xref)
                pix = fitz.Pixmap(doc, xref)
                pix.save(os.path.join(workdir, "%s_p%s-%s.png" % (each_path[:-4], i, xref)))</code>