From c28d35c7fc34da4e27700610f58c57135fea6310 Mon Sep 17 00:00:00 2001 From: Bnyro Date: Sun, 23 Mar 2025 15:44:35 +0100 Subject: [PATCH] [fix] duckduckgo news: unescaped html sequences in description --- searx/engines/duckduckgo_extra.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/searx/engines/duckduckgo_extra.py b/searx/engines/duckduckgo_extra.py index 8c4a0b0d8..9d56a8e68 100644 --- a/searx/engines/duckduckgo_extra.py +++ b/searx/engines/duckduckgo_extra.py @@ -9,7 +9,7 @@ from __future__ import annotations from datetime import datetime from typing import TYPE_CHECKING from urllib.parse import urlencode -from searx.utils import get_embeded_stream_url +from searx.utils import get_embeded_stream_url, html_to_text from searx.engines.duckduckgo import fetch_traits # pylint: disable=unused-import from searx.engines.duckduckgo import get_ddg_lang, get_vqd @@ -126,7 +126,7 @@ def _news_result(result): return { 'url': result['url'], 'title': result['title'], - 'content': result['excerpt'], + 'content': html_to_text(result['excerpt']), 'source': result['source'], 'publishedDate': datetime.fromtimestamp(result['date']), }