Python去除PDF水印的实现示例

pip install pillow

from PIL import Image

img = Image.open('watermark_pic.png')
width, height = img.size

for i in range(width):
    for j in range(height):
        pos = (i, j)
        print(img.getpixel(pos)[:3])

if sum(img.getpixel(pos)[:3]) >= 651:
    img.putpixel(pos, (255, 255, 255))

from PIL import Image

img = Image.open('watermark_pic.png')
width, height = img.size

for i in range(width):
    for j in range(height):
        pos = (i, j)
        if sum(img.getpixel(pos)[:3]) >= 651:
            img.putpixel(pos, (255, 255, 255))

img.save('watermark_removed_pic.png')

pip install pymupdf

import fitz

doc = fitz.open("数据结构和算法手册@公众号渡码.pdf")
for page in doc:
    pix = page.get_pixmap()

from itertools import product

for pos in product(range(pix.width), range(pix.height)):
    if sum(pix.pixel(pos[0], pos[1])) >= 651:
        pix.set_pixel(pos[0], pos[1], (255, 255, 255))

from itertools import product
import fitz


doc = fitz.open("数据结构和算法手册@公众号渡码.pdf")

page_no = 0
for page in doc:
    pix = page.get_pixmap()

    for pos in product(range(pix.width), range(pix.height)):
        if sum(pix.pixel(pos[0], pos[1])) >= 651:
            pix.set_pixel(pos[0], pos[1], (255, 255, 255))

    pix.pil_save(f"pdf_pics/page_{page_no}.png", dpi=(30000, 30000))

    print(f'第 {page_no} 页去除完成')
    page_no += 1