Watermark Removal on PDF with PyPDF2

问题

This Section imports the necessary classes from the PyPDF2 library

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:

Was told to adapt this part dependent on my PDF file

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

Set the modified content as content object on the page

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

Add the page to the output

    output.addPage(page)

Write the stream outputStream = open("output.pdf", "wb") output.write(outputStream)

回答1:

Using the code from the question here is a function that works in Python 3.

def removeWatermark(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"
removeWatermark(wm_text, inputFile, outputFile)

来源：https://stackoverflow.com/questions/37752604/watermark-removal-on-pdf-with-pypdf2

标签

python

pdf

watermark

pypdf2