[fix] kagi: safely access unpromised result properties

I was testing the new Kagi engine and found for some queries I was getting a
`KeyError` exception from the result parsing.

This PR ensures we only assumes the `url` key exists, and we use `.get()` to
retrieve values for keys that may not be present.

Their API documentation [1] clarifies that only the `url` and `title` properties
are required/guaranteed in the search result object, but this is not correct:

    File "/home/patrick/code/searxng/searx/engines/kagi.py", line 161, in response
        title=html.unescape(result["title"]),
                            ~~~~~~^^^^^^^^^
    KeyError: 'title

Heard back from Kagi support:

> The image results "title' should be marked as optional, as many images likely
> don't have titles - as you've noticed.  The only required field there should be
> the "url" field.

[1] https://kagi.redocly.app/api/docs/openapi/search/search#search/search/t=response&c=200&path=data/search
[2] https://github.com/searxng/searxng/issues/2247#issuecomment-4692976877
This commit is contained in:
Patrick Evans
2026-06-12 16:25:13 -05:00
committed by Bnyro
parent d58ced8f71
commit f930443726

View File

@@ -42,11 +42,11 @@ To enable Kagi, add the following to the ``engines`` seciton of
.. _Api Portal: https://help.kagi.com/kagi/api/overview.html
"""
from datetime import datetime, timedelta
import typing as t
from searx.extended_types import SXNG_Response
from searx.result_types import EngineResults
from searx.utils import html_to_text, parse_duration_string
@@ -76,7 +76,12 @@ kagi_categ: t.Literal["search", "images", "news", "videos"] = "search"
base_url = "https://kagi.com"
safe_search_map = {0: False, 1: True, 2: True}
time_range_to_days_map: dict[TimeRangeType, int] = {"day": 1, "week": 7, "month": 30, "year": 365}
time_range_to_days_map: dict[TimeRangeType, int] = {
"day": 1,
"week": 7,
"month": 30,
"year": 365,
}
api_key = ""
"""Kagi API key. Required for using this engine."""
@@ -147,8 +152,8 @@ def response(resp: "SXNG_Response") -> EngineResults:
res.add(
res.types.MainResult(
url=result["url"],
title=html_to_text(result["title"]),
content=html_to_text(result["snippet"]),
title=html_to_text(result.get("title", "no title available")),
content=html_to_text(result.get("snippet", "")),
thumbnail=result.get("image", {}).get("url") or "",
publishedDate=published_date,
)
@@ -157,15 +162,15 @@ def response(resp: "SXNG_Response") -> EngineResults:
res.add(
res.types.Image(
url=result["url"],
title=html_to_text(result.get("title")),
title=html_to_text(result.get("title", "no title available")),
img_src=result.get("image", {}).get("url"),
resolution=f"{result['image']['width']}x{result['image']['height']}",
resolution=f"{result.get('image', {}).get('width')}x{result.get('image', {}).get('height')}",
thumbnail_src=result.get("props", {}).get("thumbnail", {}).get("url"),
)
)
elif kagi_categ == "videos":
length: timedelta | None = None
if result["props"].get("duration"):
if result.get("props", {}).get("duration"):
length = parse_duration_string(result["props"]["duration"])
res.add(
@@ -173,11 +178,11 @@ def response(resp: "SXNG_Response") -> EngineResults:
{
"template": "videos.html",
"url": result["url"],
"title": html_to_text(result["title"]),
"content": html_to_text(result["snippet"]),
"title": html_to_text(result.get("title", "no title available")),
"content": html_to_text(result.get("snippet", "")),
"thumbnail": result.get("image", {}).get("url"),
"publishedDate": published_date,
"author": result["props"].get("creator_name"),
"author": result.get("props", {}).get("creator_name"),
"length": length,
}
)