使用 PyPDF2 去除 PDF 上的水印

Question

本节从 PyPDF2 库中导入必要的类

from PyPDF2 import PdfFileReader, PdfFileWriter
from PyPDF2.pdf import ContentStream
from PyPDF2.generic import TextStringObject, NameObject
from PyPDF2.utils import b_

>The watermark says SAMPLE on it so I've tried different capitalization cases 
wm_text = 'Sample'
replace_with = ''
>I'm hoping to just replace the SAMPLE watermark with nothing so a space could suffice

> Load PDF into pyPDF
source = PdfFileReader(open('input.pdf', "rb"))
output = PdfFileWriter()

> For each page
for page in range(source.getNumPages()):
    # Get the current page and it's contents
    page = source.getPage(page)
    content_object = page["/Contents"].getObject()
    content = ContentStream(content_object, source)

> Loop over all pdf elements
    for operands, operator in content.operations:

被告知根据我的 PDF 文件调整这部分

        if operator == b_("TJ"):
            text = operands[0][0]
            if isinstance(text, TextStringObject) and text.startswith(wm_text):
                operands[0] = TextStringObject(replace_with)

将修改后的内容设置为页面上的内容对象

    page.__setitem__(NameObject('/Contents'), content)

将页面添加到输出

    output.addPage(page)

写流 outputStream = open("output.pdf", "wb") output.write(outputStream)

Answer 1

使用此处问题中的代码是一个在 Python 3 中有效的函数。

def remove_watermark(wm_text, inputFile, outputFile):
    from PyPDF4 import PdfFileReader, PdfFileWriter
    from PyPDF4.pdf import ContentStream
    from PyPDF4.generic import TextStringObject, NameObject
    from PyPDF4.utils import b_
    
    with open(inputFile, "rb") as f:
        source = PdfFileReader(f, "rb")
        output = PdfFileWriter()

        for page in range(source.getNumPages()):
            page = source.getPage(page)
            content_object = page["/Contents"].getObject()
            content = ContentStream(content_object, source)

            for operands, operator in content.operations:
                if operator == b_("Tj"):
                    text = operands[0]

                    if isinstance(text, str) and text.startswith(wm_text):
                        operands[0] = TextStringObject('')

            page.__setitem__(NameObject('/Contents'), content)
            output.addPage(page)

        with open(outputFile, "wb") as outputStream:
            output.write(outputStream)
            
wm_text = 'wm_text'
inputFile = r'input.pdf'
outputFile = r"output.pdf"
remove_watermark(wm_text, inputFile, outputFile)