From 78f5300830e0e897fd344f9c9022e556aae39fe9 Mon Sep 17 00:00:00 2001
From: Markus Heiser <markus.heiser@darmarit.de>
Date: Tue, 26 Nov 2024 15:30:32 +0100
Subject: [PATCH] [chore] drop sjp engine: WEB side has changed a long time ago

The WEB page (PL only) has changed and there is now also a kind of CAPTCHA.
There is currently no possibility to restore the function of this engine.

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
---
 searx/engines/sjp.py | 98 --------------------------------------------
 searx/settings.yml   |  6 ---
 2 files changed, 104 deletions(-)
 delete mode 100644 searx/engines/sjp.py

diff --git a/searx/engines/sjp.py b/searx/engines/sjp.py
deleted file mode 100644
index 639420095..000000000
--- a/searx/engines/sjp.py
+++ /dev/null
@@ -1,98 +0,0 @@
-# SPDX-License-Identifier: AGPL-3.0-or-later
-"""Słownik Języka Polskiego
-
-Dictionary of the polish language from PWN (sjp.pwn)
-"""
-
-from lxml.html import fromstring
-from searx import logger
-from searx.utils import extract_text
-from searx.network import raise_for_httperror
-
-logger = logger.getChild('sjp engine')
-
-# about
-about = {
-    "website": 'https://sjp.pwn.pl',
-    "wikidata_id": 'Q55117369',
-    "official_api_documentation": None,
-    "use_official_api": False,
-    "require_api_key": False,
-    "results": 'HTML',
-    "language": 'pl',
-}
-
-categories = ['dictionaries']
-paging = False
-
-URL = 'https://sjp.pwn.pl'
-SEARCH_URL = URL + '/szukaj/{query}.html'
-
-word_xpath = '//div[@class="query"]'
-dict_xpath = [
-    '//div[@class="wyniki sjp-so-wyniki sjp-so-anchor"]',
-    '//div[@class="wyniki sjp-wyniki sjp-anchor"]',
-    '//div[@class="wyniki sjp-doroszewski-wyniki sjp-doroszewski-anchor"]',
-]
-
-
-def request(query, params):
-    params['url'] = SEARCH_URL.format(query=query)
-    logger.debug(f"query_url --> {params['url']}")
-    return params
-
-
-def response(resp):
-    results = []
-
-    raise_for_httperror(resp)
-    dom = fromstring(resp.text)
-    word = extract_text(dom.xpath(word_xpath))
-
-    definitions = []
-
-    for dict_src in dict_xpath:
-        for src in dom.xpath(dict_src):
-            src_text = extract_text(src.xpath('.//span[@class="entry-head-title"]/text()')).strip()
-
-            src_defs = []
-            for def_item in src.xpath('.//div[contains(@class, "ribbon-element")]'):
-                if def_item.xpath('./div[@class="znacz"]'):
-                    sub_defs = []
-                    for def_sub_item in def_item.xpath('./div[@class="znacz"]'):
-                        def_sub_text = extract_text(def_sub_item).lstrip('0123456789. ')
-                        sub_defs.append(def_sub_text)
-                    src_defs.append((word, sub_defs))
-                else:
-                    def_text = extract_text(def_item).strip()
-                    def_link = def_item.xpath('./span/a/@href')
-                    if 'doroszewski' in def_link[0]:
-                        def_text = f"<a href='{def_link[0]}'>{def_text}</a>"
-                    src_defs.append((def_text, ''))
-
-            definitions.append((src_text, src_defs))
-
-    if not definitions:
-        return results
-
-    infobox = ''
-    for src in definitions:
-        infobox += f"<div><small>{src[0]}</small>"
-        infobox += "<ul>"
-        for def_text, sub_def in src[1]:
-            infobox += f"<li>{def_text}</li>"
-            if sub_def:
-                infobox += "<ol>"
-                for sub_def_text in sub_def:
-                    infobox += f"<li>{sub_def_text}</li>"
-                infobox += "</ol>"
-        infobox += "</ul></div>"
-
-    results.append(
-        {
-            'infobox': word,
-            'content': infobox,
-        }
-    )
-
-    return results
diff --git a/searx/settings.yml b/searx/settings.yml
index dd981e5e9..0baa60770 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -2277,12 +2277,6 @@ engines:
     seekr_category: videos
     disabled: true
 
-  - name: sjp.pwn
-    engine: sjp
-    shortcut: sjp
-    timeout: 5.0
-    disabled: true
-
   - name: stract
     engine: stract
     shortcut: str