Watermark Removal on PDF with PyPDF2
Asked Answered
A

2

8
# 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)
Aucoin answered 10/6, 2016 at 16:1 Comment(0)
U
7

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

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)
Ulna answered 8/8, 2019 at 10:12 Comment(5)
don't support CJK characterRaffo
i tried to use the code to remove logo image, by setting operands[0] = NullObject(), but output pdf gets corrupted.Horehound
The code above worked for me for removing a particular text on each page, I haven't considered other cases.Ulna
I'd recommend to use PyPDF2 instead of PyPDF4. Despite the name, PyPDF2 is the more up-to-date project (in 2022). I'm the new maintainer of PyPDF2.Gupta
Interesting, thank you. I'm going to leave the answer as is as I don't work on this at the moment, but others can see your comment.Ulna
S
0

As of March 2023

from PyPDF2 import PdfReader, PdfWriter
from PyPDF2.generic import ContentStream, NameObject, TextStringObject

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

# Load PDF into pyPDF
reader = PdfReader("INPUT FILE")
writer = PdfWriter()

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

# Write the stream
with open("OUTPUT FILE", "wb") as fh:
    writer.write(fh)
Sacculate answered 19/3, 2023 at 18:22 Comment(3)
PyPDF2 is deprecated. Use pypdf.Gupta
This solution does not work for me, unlike the solution using PyPDF4.Pleasantry
@Pleasantry for PyPDF2?Sacculate

© 2022 - 2025 — McMap. All rights reserved.