问基于PyPDF2的PDF水印去除

EN

# This Section imports the necessary classes from the PyPDF2 library

from PyPDF2 import PdfFileReader, PdfFileWriter
from PyPDF2.generic import ContentStream, NameObject, TextStringObject
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
reader = PdfFileReader("input.pdf")
writer = PdfFileWriter()

for page in reader.pages:
    # Get the current page's contents
    content_object = page["/Contents"].getObject()
    content = ContentStream(content_object, reader)

    # 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
    writer.addPage(page)

# Write the stream
with open("output.pdf", "wb") as fh:
    writer.write(fh)