From dd27fce3b7b5a14e4855474ead81447adbf73d7d Mon Sep 17 00:00:00 2001 From: Markus Heiser Date: Mon, 25 May 2026 12:43:02 +0200 Subject: [PATCH] [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 --- searx/engines/ahmia.py | 9 ------- searx/engines/bing.py | 7 ------ searx/engines/demo_offline.py | 1 - searx/engines/discourse.py | 2 -- searx/engines/duden.py | 8 ------ searx/engines/mongodb.py | 1 - searx/engines/searx_engine.py | 2 -- searx/engines/tineye.py | 4 --- searx/result_types/_base.py | 2 +- searx/results.py | 25 ------------------- .../simple/opensearch_response_rss.xml | 2 -- searx/templates/simple/results.html | 4 --- searx/webapp.py | 4 --- searx/webutils.py | 1 - tests/unit/test_webapp.py | 3 --- 15 files changed, 1 insertion(+), 74 deletions(-) diff --git a/searx/engines/ahmia.py b/searx/engines/ahmia.py index 952462244..32170f2dc 100644 --- a/searx/engines/ahmia.py +++ b/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) diff --git a/searx/engines/bing.py b/searx/engines/bing.py index 48537d679..cae89d24f 100644 --- a/searx/engines/bing.py +++ b/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 diff --git a/searx/engines/demo_offline.py b/searx/engines/demo_offline.py index d9e5d0eb5..26cd62554 100644 --- a/searx/engines/demo_offline.py +++ b/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) diff --git a/searx/engines/discourse.py b/searx/engines/discourse.py index 97f4ef0cf..d7e1a5720 100644 --- a/searx/engines/discourse.py +++ b/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 diff --git a/searx/engines/duden.py b/searx/engines/duden.py index c2e758d6f..b422d8339 100644 --- a/searx/engines/duden.py +++ b/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) diff --git a/searx/engines/mongodb.py b/searx/engines/mongodb.py index a183cc17f..8c3f18bfa 100644 --- a/searx/engines/mongodb.py +++ b/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()} diff --git a/searx/engines/searx_engine.py b/searx/engines/searx_engine.py index 1a67743f4..e0bb8133e 100644 --- a/searx/engines/searx_engine.py +++ b/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 diff --git a/searx/engines/tineye.py b/searx/engines/tineye.py index 2150e8f59..53c0f2861 100644 --- a/searx/engines/tineye.py +++ b/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 diff --git a/searx/result_types/_base.py b/searx/result_types/_base.py index e83be4382..3624d64ec 100644 --- a/searx/result_types/_base.py +++ b/searx/result_types/_base.py @@ -529,7 +529,7 @@ class LegacyResult(dict[str, t.Any]): # the img_src are equal. return hash(f"{self.template}|{self.url}|{self.img_src}") - if not any(cls in self for cls in ["suggestion", "correction", "infobox", "number_of_results", "engine_data"]): + if not any(cls in self for cls in ["suggestion", "correction", "infobox", "engine_data"]): # Ordinary url-results are equal if their values for template, # parsed_url (without schema) and img_src` are equal. diff --git a/searx/results.py b/searx/results.py index f3bac2eb7..01c80ae06 100644 --- a/searx/results.py +++ b/searx/results.py @@ -69,7 +69,6 @@ class ResultContainer: self.answers = AnswerSet() self.corrections = set() - self._number_of_results: list[int] = [] self.engine_data: dict[str, dict[str, str]] = defaultdict(dict) self._closed: bool = False self.paging: bool = False @@ -135,11 +134,6 @@ class ResultContainer: self._merge_infobox(result) continue - if "number_of_results" in result: - if self.on_result(result): - self._number_of_results.append(result["number_of_results"]) - continue - if "engine_data" in result: if self.on_result(result): if result.engine: @@ -252,25 +246,6 @@ class ResultContainer: self._main_results_sorted = gresults return self._main_results_sorted - @property - def number_of_results(self) -> int: - """Returns the average of results number, returns zero if the average - result number is smaller than the actual result count.""" - - if not self._closed: - log.error("call to ResultContainer.number_of_results before ResultContainer.close") - return 0 - - with self._lock: - resultnum_sum = sum(self._number_of_results) - if not resultnum_sum or not self._number_of_results: - return 0 - - average = int(resultnum_sum / len(self._number_of_results)) - if average < len(self.get_ordered_results()): - average = 0 - return average - def add_unresponsive_engine(self, engine_name: str, error_type: str, suspended: bool = False): with self._lock: if self._closed: diff --git a/searx/templates/simple/opensearch_response_rss.xml b/searx/templates/simple/opensearch_response_rss.xml index ab732aec2..ac36cd4b1 100644 --- a/searx/templates/simple/opensearch_response_rss.xml +++ b/searx/templates/simple/opensearch_response_rss.xml @@ -7,9 +7,7 @@ SearXNG search: {{ q|e }} {{ url_for('search', _external=True) }}?q={{ q|e }} Search results for "{{ q|e }}" - SearXNG - {{ number_of_results }} 1 - {{ number_of_results }}