pdf-watermark-remover 0.6.0

A package to remove watermarks from PDF files

PDF Watermark Remover

A Python package to remove watermarks from PDF files.

Installation

pip install pdf_watermark_remover

Usage

from pdf_watermark_remover import process_pdf

process_pdf('input.pdf', 'output.pdf')

Update PyPI Version

1.更新 setup.py 中的版本号
setup(
    name='your-package-name',
    version='0.6.0',  # 更新版本号
    ...
)
2.重新生成分发文件
rm -rf dist
python setup.py sdist bdist_wheel
3.上传新版本
twine upload dist/*

.pypirc 配置

[distutils]
index-servers =
    pypi

[pypi]
  username = __token__
  password = <your-api-token>

setup.py

from setuptools import setup, find_packages

setup(
    name='pdf_watermark_remover',
    version='0.6.0',
    packages=find_packages(),
    install_requires=[
        'numpy',
        'Pillow',
        'PyMuPDF',
        'reportlab',
    ],
    entry_points={
        'console_scripts': [
            'pdf_watermark_remover=pdf_watermark_remover.remover:process_pdf',
        ],
    },
    author='huapohen',
    author_email='[e-mail]',
    description='A package to remove watermarks from PDF files',
    long_description=open('README.md').read(),
    long_description_content_type='text/markdown',
    url='https://github.com/huapohen/pdf_watermark_remover',
    classifiers=[
        'Programming Language :: Python :: 3',
        'License :: OSI Approved :: Apache Software License',
        'Operating System :: OS Independent',
    ],
    python_requires='>=3.6',
)

requirements.txt

# opencv-python-headless
opencv-python
numpy
Pillow
PyMuPDF
reportlabW

准备项目结构

pdf_watermark_remover/
│
├── pdf_watermark_remover/
│   ├── __init__.py
│   ├── remover.py
│
├── setup.py
├── README.md
├── LICENSE
└── requirements.txt

创建项目文件

pdf_watermark_remover/remover.py pdf_watermark_remover/init.py：

from .remover import process_pdf, remove_watermark, pdf_to_images, images_to_pdf

构建和发布包

1.安装必要的工具
pip install setuptools wheel twine
2.构建包
rm -rf dist
python setup.py sdist bdist_wheel
3.发布到PyPI
这里需要配置好.pypirc，填写pypi api token
twine upload dist/*
4.安装
pip install pdf_watermark_remover
5.使用
from pdf_watermark_remover import process_pdf
process_pdf('input.pdf', 'output.pdf')

remover.py

# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.


# pip install pymupdf pillow opencv-python reportlab
import io, os, cv2, fitz, tempfile
import numpy as np
from PIL import Image
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter


def remove_watermark(img):
    # img = cv2.imread("words_watermark.jpg")
    # 从一张图像中去除所有白色内容（或在HSV色彩空间中接近白色的内容）
    # 用的是HSV色彩空间，数组的三个值分别对应Hue（色调），Saturation（饱和度）和Value（亮度）
    lower_hsv = np.array([160, 160, 160])  # 大致对应于白色，偏白
    upper_hsv = np.array([255, 255, 255])  # 最大值，纯白。范围 0~255
    # 根据设定的阈值范围，生成一个二值掩码（mask），其中白色部分表示水印，黑色部分表示非水印区域
    mask = cv2.inRange(img, lower_hsv, upper_hsv)  # 从较亮的灰色（160）到纯白色（255）
    mask = cv2.GaussianBlur(
        mask, (1, 1), 0
    )  # 对生成的掩码进行高斯模糊处理，细节处减少噪点
    mask_indices = mask == 255  # 获取掩码中所有白色像素的索引，160~255以全部重置为255
    img[mask_indices] = [255, 255, 255]  # 使用掩码将原始图片中的水印区域设置为纯白色
    # quality = [int(cv2.IMWRITE_JPEG_QUALITY), 100]  # 保存为最高质量（100）
    # cv2.imwrite('clean.jpg', img, quality)
    return img


def pdf_to_images(pdf_path, dpi=300):
    pdf_document = fitz.open(pdf_path)
    images = []

    for page_num in range(len(pdf_document)):
        page = pdf_document.load_page(page_num)
        zoom = dpi / 72
        mat = fitz.Matrix(zoom, zoom)
        pix = page.get_pixmap(matrix=mat, alpha=False)
        img_bytes = pix.tobytes('png')
        img = Image.open(io.BytesIO(img_bytes))
        images.append(img)

    return images


def images_to_pdf(images, output_pdf_path):
    c = canvas.Canvas(output_pdf_path, pagesize=letter)
    for img in images:
        with tempfile.NamedTemporaryFile(suffix='.png', delete=False) as temp_img_file:
            img.save(temp_img_file, format='PNG')
            temp_img_file_path = temp_img_file.name
        c.drawImage(temp_img_file_path, 0, 0, width=letter[0], height=letter[1])
        c.showPage()
        os.remove(temp_img_file_path)
    c.save()


def process_pdf(pdf_path, output_pdf_path):
    images = pdf_to_images(pdf_path)
    cleaned_images = []

    for img in images:
        img_np = np.array(img)
        cleaned_img_np = remove_watermark(img_np)
        cleaned_img = Image.fromarray(cleaned_img_np)
        cleaned_images.append(cleaned_img)

    images_to_pdf(cleaned_images, output_pdf_path)
    # print(f"处理完成，新的PDF已保存到{output_pdf_path}")


'''
# 示例使用
pdf_path = "example.pdf"  # 你的PDF文件路径
output_pdf_path = "cleaned_example.pdf"  # 保存处理后PDF文件的路径
process_pdf(pdf_path, output_pdf_path)
'''