diff options
| author | Markus Heiser <markus.heiser@darmarIT.de> | 2026-07-05 12:07:23 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2026-07-05 12:07:23 +0200 |
| commit | fd5eb84a378e30f90e363ace0223ca9e609f12f3 (patch) | |
| tree | 1e782aeb33f123ed9a217736d6b1e262bbb3e8c4 /searxng_extra | |
| parent | 888364c1ce1f342d32ceedc364d1152457ad831a (diff) | |
[chore] Google (HTML) engine: remove obsolete GSA User-Agents (#6366)
The GSA headers that were introduced in PR #5644 unfortunately no longer
work (#6359).
The Google engines
- google.py
- google_videos.py
do not work anymore either, but we'll leave it in the code for now:
- In google.py, central functions like get_google_info(..) are provided, which
are also used by other modules.
- We will probably need a Google HTML (and video) engine again very soon.
Related:
- https://github.com/searxng/searxng/issues/6359
- https://github.com/searxng/searxng/pull/6364
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
Diffstat (limited to 'searxng_extra')
| -rw-r--r-- | searxng_extra/update/update_gsa_useragents.py | 46 |
1 files changed, 0 insertions, 46 deletions
diff --git a/searxng_extra/update/update_gsa_useragents.py b/searxng_extra/update/update_gsa_useragents.py deleted file mode 100644 index 5cbf0005c..000000000 --- a/searxng_extra/update/update_gsa_useragents.py +++ /dev/null @@ -1,46 +0,0 @@ -#!/usr/bin/env python -# SPDX-License-Identifier: AGPL-3.0-or-later -"""This script fetches user agents suitable for Google. - -Output file: :origin:`searx/data/gsa_useragents.txt` (:origin:`CI Update data -... <.github/workflows/data-update.yml>`). - -.. Source for user agents: https://github.com/intoli/user-agents/ - -""" - -from gzip import decompress -from json import loads - -from searx.data import data_dir -from searx.network import get as http_get -from searx.utils import searxng_useragent - -DATA_FILE = data_dir / "gsa_useragents.txt" -URL = "https://raw.githubusercontent.com/intoli/user-agents/main/src/user-agents.json.gz" - - -def fetch_gsa_useragents() -> list[str]: - response = http_get(URL, timeout=3.0, headers={"User-Agent": searxng_useragent()}) - response.raise_for_status() - - suas: set[str] = set() - for ua in loads(decompress(response.content)): - if ( - "Android" in ua["userAgent"] - and "Chrome" in ua["userAgent"] - and "Samsung" not in ua["userAgent"] - and "Android 10; K" not in ua["userAgent"] - ): - suas.add(ua["userAgent"]) - - luas = list(suas) - luas.sort() - - return luas - - -if __name__ == "__main__": - useragents = fetch_gsa_useragents() - with DATA_FILE.open("w", encoding="utf-8") as f: - f.write("\n".join(useragents)) |