public/kcc
1
0
Fork 0
mirror of https://github.com/ciromattia/kcc synced 2025-12-15 18:56:28 +00:00
Code Issues Releases Wiki Activity

extract_image instead of Pixmap if possible 20x faster

Browse Source
This commit is contained in:
Alex Xu
2025-07-20 12:12:02 -07:00
parent cb5f4db5c4
commit 3cd6e09bcb
1 changed files with 8 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
kindlecomicconverter/comic2ebook.py
View File

@@ -754,21 +754,15 @@ def extract_page(vector):
blank_page = Image.new("RGB", (width, height), "white") blank_page = Image.new("RGB", (width, height), "white")
blank_page.save(output_path) blank_page.save(output_path)
xref = image_list[0][0] xref = image_list[0][0]
pix = pymupdf.Pixmap(doc, xref) d = doc.extract_image(xref)
if pix.colorspace is None: if d['cs-name'] == 'DeviceCMYK':
# It's a stencil mask (grayscale image with inverted colors) pix = pymupdf.Pixmap(doc, xref)
mask_array = np.frombuffer(pix.samples, dtype=np.uint8).reshape(pix.height, pix.width)
inverted = 255 - mask_array
img = Image.fromarray(inverted, mode="L")
img.save(output_path)
if pix.colorspace.name.startswith("Colorspace(CS_GRAY)"):
# Make sure that an image is just grayscale and not smth like "Colorspace(CS_GRAY) - Separation(DeviceCMYK,Black)"
pix = pymupdf.Pixmap(pymupdf.csGRAY, pix)
else:
pix = pymupdf.Pixmap(pymupdf.csRGB, pix) pix = pymupdf.Pixmap(pymupdf.csRGB, pix)
if pix.alpha: pix.save(output_path)
pix = pymupdf.Pixmap(pix, alpha=0)
pix.save(output_path) else:
with open(Path(output_path).with_suffix('.' + d['ext']), "wb") as imgout:
imgout.write(d["image"])
print("Processed page numbers %i through %i" % (seg_from, seg_to - 1)) print("Processed page numbers %i through %i" % (seg_from, seg_to - 1))