python清除PDF文件中水印的项目实践

"""
Title: 清除PDF水印（非pdf加的水印而是用word文件头加的然后转成了pdf）
Author: JackieZheng
Date: 2025-05-11 10:31:23
LastEditTime: 2025-05-12 23:43:21
LastEditors: Please set LastEditors
Description:
FilePath: \\pythonCode\\remove_pdf_watermark.py
"""

import os
import fitz  # PyMuPDF


def remove_image_watermark(pdf_path):
    doc = fitz.open(pdf_path)
    for page_num in range(len(doc)):
        page = doc[page_num]
        xref = page.get_contents()[0]  # 获取页面字节流，以xref的形式返回
        cont0 = doc.xref_stream(xref).decode()  # 将流解码为字符串
        page.clean_contents()
        if '/Header>> BDC' in cont0:  # 找到word页眉总分
            start_str = '/Header>> BDC'  # 获取水印起始位置
            end_str = 'c\r\nh\r\nf*\r\nq'  # 获取水印结束位置 （需要自己根据情况找到类似字符）

            cont = remove_between_strings(cont0, start_str, end_str)

            doc.update_stream(xref, cont.encode())  # 更新流
        print('page', page_num, 'processed')

    doc.save(pdf_path[:-4] + '_processed.pdf')
    doc.close()


def remove_between_strings(original_text, start_str, end_str):
    start = original_text.index(start_str) + len(start_str)
    end = original_text.index(end_str, start)
    content = original_text[:start] + original_text[end:]
    # print(content)
    return content


pdf_path = r'C:\Users\JackieZheng\Desktop\满分冲刺练.pdf'

remove_image_watermark(pdf_path)