Simple utility to put all <wp:author> tag child on the same line of a WordPress WXR/XML export

cleanser.py

import os


def main():
    export_file_names: list = [
        f for f in os.listdir(".") if f.endswith(".xml") and not f.endswith(".correct.xml")]

    for export_file_name in export_file_names:
        print(f"Going with: {export_file_name}")

        export_file = open(export_file_name, "r")
        export_file_lines = export_file.readlines()
        edited_file = open("./trimmed/" + export_file_name.replace(
            ".xml", ".correct.xml"), "w")

        buffer: str = None
        for export_file_line in export_file_lines:
            if "<wp:author>" in export_file_line:
                buffer = export_file_line.replace("\n", "").strip()
                continue
            elif "</wp:author>" in export_file_line:
                buffer += export_file_line.strip()
                edited_file.write(buffer + "\n")
                buffer = None
                continue

            if buffer is not None:
                buffer += export_file_line.replace("\n", "").strip()
            else:
                edited_file.write(export_file_line)


main()