remove all text on pdf

clear_pdf_text.py

# Modify from https://gist.github.com/668/2c8f936697ded94394ff4a6ffa4ae87e

import sys
from pypdf import PdfReader, PdfWriter
from pypdf.generic import ContentStream, TextStringObject, NameObject

# Load PDF into PyPDF2
reader = PdfReader(open(sys.argv[1], "rb"))
writer = PdfWriter()

# Migration from PyPDF2 < 2.0.0
def b_(s):
    if type(s) == bytes:
        return s
    else:
        try:
            r = s.encode("latin-1")
            return r
        except Exception:
            r = s.encode("utf-8")
            return r

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

    # Remove Tj Operator
    condition = lambda tupl: not tupl[1] == b_("Tj")
    content.operations = list(filter(condition, content.operations))

    # Set the modified content as content object on the page
    page.__setitem__(NameObject("/Contents"), content)
    page.compress_content_streams()

    # Add the page to the output
    writer.add_page(page)

# Write the stream
outputStream = open(sys.argv[2], "wb")
writer.write(outputStream)