[unbload] drop meaningless field `number_of_results_xpath` from results (#6130)

In the result-list, the ``number_of_results`` indicate the number of hits in the
Index, they do not indicate how many results are in the answer.

In the past, search engines such as google or ddg had an indication on the first
page of a search term of how many hits there were for this term in total in
their index.

This info was added up in SearXNG and delivered under ``number_of_results``.
Nowadays the search engines no longer indicate how many hits there are in the
index and so this field in SearXNG is also superfluous.

- https://github.com/searxng/searxng/issues/2457#issuecomment-2566181574
- https://github.com/searxng/searxng/issues/2987
- https://github.com/searxng/searxng/issues/5034

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>

searx/engines/ahmia.py

@@ -39,7 +39,6 @@ url_xpath = './h4/a/@href'
 title_xpath = './h4/a[1]'
 content_xpath = './/p[1]'
 correction_xpath = '//*[@id="didYouMean"]//a'
-number_of_results_xpath = '//*[@id="totalResults"]'
 name_token_xpath = '//form[@id="searchForm"]/input[@type="hidden"]/@name'
 value_token_xpath = '//form[@id="searchForm"]/input[@type="hidden"]/@value'
 
@@ -107,14 +106,6 @@ def response(resp):
     for correction in eval_xpath_list(dom, correction_xpath):
         results.append({'correction': extract_text(correction)})
 
-    # get number of results
-    number_of_results = eval_xpath(dom, number_of_results_xpath)
-    if number_of_results:
-        try:
-            results.append({'number_of_results': int(extract_text(number_of_results))})
-        except:  # pylint: disable=bare-except
-            pass
-
     # Update the tokens to the newest ones
     token_str = _get_tokens(dom)
     CACHE.set('ahmia-tokens', token_str, expire=60 * 60)

searx/engines/bing.py

@@ -13,7 +13,6 @@ implementations are shared by other engines:
 """
 
 import base64
-import re
 import typing as t
 from urllib.parse import parse_qs, urlencode, urlparse
 
@@ -159,12 +158,6 @@ def response(resp: "SXNG_Response") -> list[dict[str, t.Any]]:
 
         results.append({"url": href, "title": title, "content": content})
 
-    if results:
-        result_len_container = "".join(eval_xpath(dom, '//span[@class="sb_count"]//text()'))
-        result_len_container = re.sub(r"[^0-9]", "", result_len_container)
-        if result_len_container:
-            results.append({"number_of_results": int(result_len_container)})
-
     return results
 
 

searx/engines/demo_offline.py

@@ -109,7 +109,6 @@ def search(query: str, params: "RequestParams") -> EngineResults:
                 kvmap=kvmap,
             )
         )
-    res.add(res.types.LegacyResult(number_of_results=count))
 
     # cache counter value for 20sec
     CACHE.set("count", count, expire=20)

searx/engines/discourse.py

@@ -176,6 +176,4 @@ def response(resp):
 
         results.append(result)
 
-    results.append({'number_of_results': len(json_data['topics'])})
-
     return results

searx/engines/duden.py

@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Duden"""
 
-import re
 from urllib.parse import quote, urljoin
 from lxml import html
 from searx.utils import extract_text, eval_xpath, eval_xpath_list, eval_xpath_getindex
@@ -51,13 +50,6 @@ def response(resp):
 
     dom = html.fromstring(resp.text)
 
-    number_of_results_element = eval_xpath_getindex(
-        dom, '//a[@class="active" and contains(@href,"/suchen/dudenonline")]/span/text()', 0, default=None
-    )
-    if number_of_results_element is not None:
-        number_of_results_string = re.sub('[^0-9]', '', number_of_results_element)
-        results.append({'number_of_results': int(number_of_results_string)})
-
     for result in eval_xpath_list(dom, '//section[not(contains(@class, "essay"))]'):
         url = eval_xpath_getindex(result, './/h2/a', 0).get('href')
         url = urljoin(base_url, url)

searx/engines/mongodb.py

@@ -93,7 +93,6 @@ def search(query, params) -> EngineResults:
 
     query = _client.find({key: q}).skip((params['pageno'] - 1) * results_per_page).limit(results_per_page)
 
-    res.add(res.types.LegacyResult(number_of_results=query.count()))
     for row in query:
         del row['_id']
         kvmap = {str(k): str(v) for k, v in row.items()}

searx/engines/searx_engine.py

@@ -54,6 +54,4 @@ def response(resp):
 
     results.extend({'suggestion': s} for s in response_json['suggestions'])
 
-    results.append({'number_of_results': response_json['number_of_results']})
-
     return results

searx/engines/tineye.py

@@ -211,8 +211,4 @@ def response(resp) -> EngineResults:
 
     # append number of results
 
-    number_of_results = json_data.get('num_matches')
-    if number_of_results:
-        results.append({'number_of_results': number_of_results})
-
     return results