[chore] settings.yml: set broken engines yahoo and karmasearch to inactive

Source: https://www.ask.com/

searx/engines/ask.py

@@ -1,75 +0,0 @@
-# SPDX-License-Identifier: AGPL-3.0-or-later
-"""Ask.com"""
-
-from urllib.parse import urlencode
-import dateutil
-from lxml import html
-from searx import utils
-
-# Metadata
-about = {
-    "website": "https://www.ask.com/",
-    "wikidata_id": 'Q847564',
-    "official_api_documentation": None,
-    "use_official_api": False,
-    "require_api_key": False,
-    "results": "HTML",
-}
-
-# Engine Configuration
-categories = ['general']
-paging = True
-max_page = 5
-"""Ask.com has at max 5 pages."""
-
-# Base URL
-base_url = "https://www.ask.com/web"
-
-
-def request(query, params):
-
-    query_params = {
-        "q": query,
-        "page": params["pageno"],
-    }
-
-    params["url"] = f"{base_url}?{urlencode(query_params)}"
-    return params
-
-
-def response(resp):
-
-    start_tag = 'window.MESON.initialState = {'
-    end_tag = '}};'
-
-    dom = html.fromstring(resp.text)
-    script = utils.eval_xpath_getindex(dom, '//script', 0, default=None).text
-
-    pos = script.index(start_tag) + len(start_tag) - 1
-    script = script[pos:]
-    pos = script.index(end_tag) + len(end_tag) - 1
-    script = script[:pos]
-
-    json_resp = utils.js_obj_str_to_python(script)
-
-    results = []
-
-    for item in json_resp['search']['webResults']['results']:
-
-        pubdate_original = item.get('pubdate_original')
-        if pubdate_original:
-            pubdate_original = dateutil.parser.parse(pubdate_original)
-        metadata = [item.get(field) for field in ['category_l1', 'catsy'] if item.get(field)]
-
-        results.append(
-            {
-                "url": item['url'].split('&ueid')[0],
-                "title": item['title'],
-                "content": item['abstract'],
-                "publishedDate": pubdate_original,
-                # "thumbnail": item.get('image_url') or None, # these are not thumbs / to large
-                "metadata": ' | '.join(metadata),
-            }
-        )
-
-    return results

searx/engines/yandex.py

@@ -87,7 +87,6 @@ def request(query, params):
 
 def response(resp):
     if search_type == 'web':
-
         catch_bad_response(resp)
 
         dom = html.fromstring(resp.text)
@@ -106,7 +105,6 @@ def response(resp):
         return results
 
     if search_type == 'images':
-
         catch_bad_response(resp)
 
         html_data = html.fromstring(resp.text)
@@ -127,22 +125,25 @@ def response(resp):
         for _, item_data in json_resp['initialState']['serpList']['items']['entities'].items():
             title = item_data['snippet']['title']
             source = item_data['snippet']['url']
-            thumb = item_data['image']
-            fullsize_image = item_data['viewerData']['dups'][0]['url']
-            height = item_data['viewerData']['dups'][0]['h']
-            width = item_data['viewerData']['dups'][0]['w']
-            filesize = item_data['viewerData']['dups'][0]['fileSizeInBytes']
-            humanized_filesize = humanize_bytes(filesize)
+
+            image_source = item_data["viewerData"]["thumb"]
+            for i in item_data['viewerData']['dups'] + item_data['viewerData']['preview']:
+                if i["h"] > image_source["h"]:
+                    image_source = i
+
+            humanized_filesize = None
+            if image_source.get("fileSizeInBytes"):
+                humanized_filesize = humanize_bytes(image_source["fileSizeInBytes"])
 
             results.append(
                 {
                     'title': title,
                     'url': source,
-                    'img_src': fullsize_image,
+                    'img_src': image_source["url"],
                     'filesize': humanized_filesize,
-                    'thumbnail_src': thumb,
+                    'thumbnail_src': item_data["image"],
                     'template': 'images.html',
-                    'resolution': f'{width} x {height}',
+                    'resolution': f'{image_source["w"]} x {image_source["h"]}',
                 }
             )
 

searx/settings.yml

@@ -469,11 +469,6 @@ engines:
     engine: arxiv
     shortcut: arx
 
-  - name: ask
-    engine: ask
-    shortcut: ask
-    disabled: true
-
   - name: azure
     engine: azure
     shortcut: az
@@ -1203,6 +1198,7 @@ engines:
     categories: [general, web]
     search_type: web
     shortcut: ka
+    inactive: true
 
   - name: karmasearch images
     engine: karmasearch
@@ -1210,18 +1206,21 @@ engines:
     search_type: images
     shortcut: kai
     paging: false
+    inactive: true
 
   - name: karmasearch videos
     engine: karmasearch
     categories: [videos, web]
     search_type: videos
     shortcut: kav
+    inactive: true
 
   - name: karmasearch news
     engine: karmasearch
     categories: [news, web]
     search_type: news
     shortcut: kan
+    inactive: true
 
   - name: kickass
     engine: kickass
@@ -2149,6 +2148,7 @@ engines:
   - name: yahoo news
     engine: yahoo_news
     shortcut: yhn
+    inactive: true
 
   - name: youtube
     shortcut: yt