Convert AdBlock - filter list - formated file into hosts file using PyFunceble.

README.md

Note

This is a quick and dirty solution for StevenBlack/hosts#1012. Let me know if you want it as a PyPi package from it.

Requirements

$ pip3 install --user PyFunceble

More info about PyFunceble

• https://pyfunceble.github.io/
• https://pyfunceble.readthedocs.io/en/latest/

More info about the AdBlock decoder

• https://pyfunceble.readthedocs.io/en/latest/code/adblock.html#PyFunceble.adblock.AdBlock

How to run ?

$ chmod +x convert_adblock_to_hosts.py
$ ./convert_adblock_to_hosts.py -f my_awesome_filter_list -o my_new_and_awesome_hosts_file

convert_adblock_to_hosts.py

#!/usr/bin/env python3

import argparse

from PyFunceble import is_domain
from PyFunceble.adblock import AdBlock

HOSTS_IP = "0.0.0.0"
FILE_ENCODING = "utf-8"


def convert_to_hosts_format(
    file_to_convert, destination=None, print_to_stdout=True, aggressive=False
):
    """
    Convert the given file into the hosts file format.

    :param open file_to_convert: The file we have to convert.
    :param str destination:
        The destination.

        .. note::
            If :code:`None` is given we output to :code:`stdout`.
    :param bool print_to_stdout:
        Use this if you only want the output of this function.

    :param bool aggressive:
        An experimental argument of PyFunceble which extract
        every domain of the given file without interpretation
        of what is really blocked by the filter list.

        .. warning::
            Use at your own risk.

    :return: The converted content.
    :rtype: list
    """

    converted = []

    if isinstance(file_to_convert, list):
        for file in file_to_convert:
            converted.extend(
                [
                    f"{HOSTS_IP} {x}"
                    for x in AdBlock(file, aggressive=aggressive).decode()
                    if is_domain(x)
                ]
            )
    else:
        converted = [
            f"{HOSTS_IP} {x}"
            for x in AdBlock(file_to_convert, aggressive=aggressive).decode()
            if is_domain(x)
        ]

    if destination:
        with open(destination, "w", encoding=FILE_ENCODING) as file_stream:
            file_stream.write(
                "# Hosts File generated with the help of the AdBlock decoder of PyFunceble - https://github.com/funilrys/PyFunceble\n\n"
            )
            file_stream.write("\n".join(converted))
    elif print_to_stdout:
        print("\n".join(converted))

    return converted


if __name__ == "__main__":
    PARSER = argparse.ArgumentParser(
        description="A simple tool to convert AdBlock formatted files into hosts file.",  # pylint: disable=line-too-long
        epilog="Crafted with ♥ by Nissar Chababy (Funilrys)",
        add_help=True,
    )

    PARSER.add_argument(
        "--aggressive",
        action="store_true",
        help="[USE AT YOUR OWN RISK AS IT IS EXPERIMENTAL] Activate "
        "the extraction of everything regardless of the interpretation of AdBlock/UBlock.",
    )

    PARSER.add_argument(
        "-f",
        "--file",
        type=argparse.FileType("r", encoding=FILE_ENCODING),
        nargs="+",
        help="Give us the file to convert.",
    )

    PARSER.add_argument(
        "-o", "--output", type=str, help="Tell us where we save the converted data."
    )

    ARGS = PARSER.parse_args()

    convert_to_hosts_format(ARGS.file, ARGS.output, print_to_stdout=True, aggressive=ARGS.aggressive)