edit_pdf_text.py

#!/usr/bin/python3
# Edits minor text in a PDF while preserving original metadata

# Thanks to https://stackoverflow.com/a/69439785/2689986 & https://stackoverflow.com/a/49053629/2689986

from PyPDF2 import PdfFileReader, PdfFileWriter
from PyPDF2.generic import DecodedStreamObject, EncodedStreamObject, NameObject

source_fp = "original.pdf"
destination_fp = "modified.pdf"
replacements = {"original text": "modified text"}


def replace_text(content, replacements=dict()):
    lines = content.splitlines()
    result = ""
    in_text = False
    for line in lines:
        if line == "BT":
            in_text = True
        elif line == "ET":
            in_text = False
        elif in_text:
            cmd = line[-2:]
            if cmd.lower() == "tj":
                replaced_line = line
                for k, v in replacements.items():
                    replaced_line = replaced_line.replace(k, v)
                result += replaced_line + "\n"
            else:
                result += line + "\n"
            continue
        result += line + "\n"
    return result


def process_data(object, replacements):
    data = object.getData()
    decoded_data = data.decode("utf-8")
    replaced_data = replace_text(decoded_data, replacements)
    encoded_data = replaced_data.encode("utf-8")
    if object.decodedSelf is not None:
        object.decodedSelf.setData(encoded_data)
    else:
        object.setData(encoded_data)


reader = PdfFileReader(source_fp)
writer = PdfFileWriter()

# copy (& replace as necessary) from original
for page_number in range(0, reader.getNumPages()):
    page = reader.getPage(page_number)
    contents = page.getContents()
    if isinstance(contents, DecodedStreamObject) or isinstance(
        contents, EncodedStreamObject
    ):
        process_data(contents, replacements)
    elif len(contents) > 0:
        for obj in contents:
            if isinstance(obj, DecodedStreamObject) or isinstance(
                obj, EncodedStreamObject
            ):
                streamObj = obj.getObject()
                process_data(streamObj, replacements)
    # Force content replacement
    page[NameObject("/Contents")] = contents.decodedSelf
    writer.addPage(page)

# copy metadata from original
writer.addMetadata(reader.getDocumentInfo())


with open(destination_fp, "wb") as f:
    writer.write(f)