A script that removes the watermarks from the HTML file generated by MindMaster. It is for study only, you may subscript the paid plan if you want to public the file.

mindmaster_clean.py

#!/usr/bin/python3
"""
A script that removes the watermarks from the HTML file generated by MindMaster. It is for study only, you may subscript the paid plan if you wnat to public the file.
"""

import os
import re
import sys
import argparse

parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("file", type=str, help="the HTML file path")
args = parser.parse_args()


def read_file(file):
    """
    return file content if file exists, otherwise raise exception
    """
    if not os.path.exists(file):
        print(f"{file} doesn't found, exit...")
        sys.exit(-1)

    if not os.path.isfile(file):
        print(f"{file} is not file, exit...")
        sys.exit(-1)

    with open(file, "r", encoding="utf-8") as r_f:
        text = r_f.read()
    return text


html = read_file(args.file)
regexes = [r"<svg\sxmlns=.*?</svg>", r"<div\sid=\"copyright\">.*</div>"]
EMPTY = ""

for regex in regexes:
    html = re.sub(regex, EMPTY, html, 0, re.MULTILINE | re.DOTALL)
STEM, EXT = os.path.splitext(args.file)
NEW_FILE = STEM + ".clean" + EXT

with open(NEW_FILE, "w+", encoding="utf-8") as wf:
    wf.write(html)

print(f"The watermarks were removed, please check the new file {NEW_FILE}")