searxng/searxng_extra/update/update_ahmia_blacklist.py
Markus Heiser 542f7d0d7b [mod] pylint all files with one profile / drop PYLINT_SEARXNG_DISABLE_OPTION
In the past, some files were tested with the standard profile, others with a
profile in which most of the messages were switched off ... some files were not
checked at all.

- ``PYLINT_SEARXNG_DISABLE_OPTION`` has been abolished
- the distinction ``# lint: pylint`` is no longer necessary
- the pylint tasks have been reduced from three to two

  1. ./searx/engines -> lint engines with additional builtins
  2. ./searx ./searxng_extra ./tests -> lint all other python files

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2024-03-11 14:55:38 +01:00

32 lines
949 B
Python
Executable file

#!/usr/bin/env python
# SPDX-License-Identifier: AGPL-3.0-or-later
"""This script saves `Ahmia's blacklist`_ for onion sites.
Output file: :origin:`searx/data/ahmia_blacklist.txt` (:origin:`CI Update data
... <.github/workflows/data-update.yml>`).
.. _Ahmia's blacklist: https://ahmia.fi/blacklist/
"""
# pylint: disable=use-dict-literal
import requests
from searx.data import data_dir
DATA_FILE = data_dir / 'ahmia_blacklist.txt'
URL = 'https://ahmia.fi/blacklist/banned/'
def fetch_ahmia_blacklist():
resp = requests.get(URL, timeout=3.0)
if resp.status_code != 200:
# pylint: disable=broad-exception-raised
raise Exception("Error fetching Ahmia blacklist, HTTP code " + resp.status_code) # type: ignore
return resp.text.split()
if __name__ == '__main__':
blacklist = fetch_ahmia_blacklist()
blacklist.sort()
with DATA_FILE.open("w", encoding='utf-8') as f:
f.write('\n'.join(blacklist))