使用PyPDF2删除PDF水印的探索

• PDF文件分析

image

通过DC的分析，发现水印是通过/Artifact容器的形式添加，通过PyPDF2打印PDF的结构，对比5468发现位置。编写代码

from PyPDF2 import PdfFileReader, PdfFileWriter

def remove_watermark(input_file, output_file):

    with open(input_file, "rb") as f:

        source = PdfFileReader(f, "rb")

        output = PdfFileWriter()

        for page in range(source.getNumPages()):

            page = source.getPage(page)

            #print(type(page))

            #print(type(page['/Resources']['/XObject']['/Fm0']))

            page['/Resources']['/XObject']['/Fm0'].setData(b'')

            output.addPage(page)

        # 输入新的pdf文件

     with open(output_file, "wb") as outputStream:

            output.write(outputStream)