eulaurarien/adblock_to_domain_list.py

#!/usr/bin/env python3
# pylint: disable=C0103

"""
Extract the domains to block as a whole
from a AdBlock rules list.
"""

import argparse
import sys
import typing

import abp.filters


def get_domains(rule: abp.filters.parser.Filter) -> typing.Iterable[str]:
    if rule.options:
        return
    selector_type = rule.selector['type']
    selector_value = rule.selector['value']
    if selector_type == 'url-pattern' \
            and selector_value.startswith('||') \
            and selector_value.endswith('^'):
        yield selector_value[2:-1]


if __name__ == '__main__':

    # Parsing arguments
    parser = argparse.ArgumentParser(
        description="Extract whole domains from an AdBlock blocking list")
    parser.add_argument(
        '-i', '--input', type=argparse.FileType('r'), default=sys.stdin,
        help="Input file with AdBlock rules")
    parser.add_argument(
        '-o', '--output', type=argparse.FileType('w'), default=sys.stdout,
        help="Outptut file with one rule tracking subdomain per line")
    args = parser.parse_args()

    # Reading rules
    rules = abp.filters.parse_filterlist(args.input)

    # Filtering
    for rule in rules:
        if not isinstance(rule, abp.filters.parser.Filter):
            continue
        for domain in get_domains(rule):
            print(domain, file=args.output)