继续在线求去水印两个pdf

开发调优
1

https://f.ws28.cn/f/eorbtcohs31 复制链接到浏览器打开

1 个赞
2

可以尝试将PDF转换为Word文档

3

从 搞七捻三 到 快问快答

4

https://tmp.link/f/66a35e845eaeb
https://tmp.link/f/66a35e1ad11cf

备用链接

https://pan.huang1111.cn/s/y558Gh6
https://pan.huang1111.cn/s/jRRo7Uy
1 个赞
5

怎么做到的

6
7

他这个pdf全是图片，每一页都有水印。没办法写了个python为他这种文档定制一下。

pip install PyMuPDF Pillow numpy

import fitz
import os
from PIL import Image
import numpy as np
import concurrent.futures

def is_green(color):
    g = color[:, :, 1]
    r = color[:, :, 0]
    b = color[:, :, 2]
    return (g > np.maximum(r, b)) & (g > 180)

def process_image(pix):
    image_np = np.array(pix)
    # 裁剪底部2%的高度
    cropped_image_np = image_np[:-int(image_np.shape[0] * 0.02), :]
    mask = is_green(cropped_image_np)
    cropped_image_np[mask] = [254, 254, 254]
    return Image.fromarray(cropped_image_np)

def process_pdf(input_file, output_file):
    doc = fitz.open(input_file)
    output_doc = fitz.open()
    temp_dir = "temp_images"
    os.makedirs(temp_dir, exist_ok=True)

    page_numbers = range(len(doc))
    with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor:
        futures = []
        for page_num in page_numbers:
            futures.append(executor.submit(process_page, page_num, doc, temp_dir))

        for future in concurrent.futures.as_completed(futures):
            page_num, img_path = future.result()
            output_page = output_doc.new_page(width=doc[page_num].rect.width, height=doc[page_num].rect.height * 0.98)
            output_pix = fitz.Pixmap(img_path)
            output_page.insert_image(output_page.rect, pixmap=output_pix, overlay=False)
            output_pix = None

    output_doc.save(output_file, garbage=4, deflate=True, clean=True)  # Optimize PDF saving
    doc.close()
    output_doc.close()
    for file in os.listdir(temp_dir):
        os.remove(os.path.join(temp_dir, file))
    os.rmdir(temp_dir)

def process_page(page_num, doc, temp_dir):
    page = doc[page_num]
    pix = page.get_pixmap(matrix=fitz.Matrix(150/72, 150/72))  # Reduce image resolution
    temp_png = os.path.join(temp_dir, f"page_{page_num+1}.png")
    pix.save(temp_png)
    img = Image.open(temp_png)
    processed_img = process_image(img)
    temp_jpg = temp_png.replace('.png', '.jpg')
    processed_img.save(temp_jpg, "JPEG", quality=90)
    return page_num, temp_jpg

if __name__ == "__main__":
    process_pdf("input.pdf", "output.pdf")

随便糊的，能力有限

8 个赞
8

牛逼 啊佬

9

多谢大佬

10

马老师助人为乐

11

牛啊 佬

12

这个怎么用啊 大佬

13

mark一下，感谢分享

1 个赞
14

From 快问快答 to 开发调优

15

@pengzhile 可以帮忙在线去下水印嘛，大佬