git.iko.soy/searx
on master help sign in
Merge pull request #2736 from plague-doctor/sjp
8362257Noémi Ványi
searx/engines/sjp.pynew file+92
compare with master
unifiedsplit
@@ -0,0 +1,92 @@
1+# SPDX-License-Identifier: AGPL-3.0-or-later
2+"""Słownik Języka Polskiego (general)
3+
4+"""
5+
6+from lxml.html import fromstring
7+from searx import logger
8+from searx.utils import extract_text
9+from searx.raise_for_httperror import raise_for_httperror
10+
11+logger = logger.getChild('sjp engine')
12+
13+# about
14+about = {
15+ "website": 'https://sjp.pwn.pl',
16+ "wikidata_id": 'Q55117369',
17+ "official_api_documentation": None,
18+ "use_official_api": False,
19+ "require_api_key": False,
20+ "results": 'HTML',
21+}
22+
23+categories = ['general']
24+paging = False
25+
26+URL = 'https://sjp.pwn.pl'
27+SEARCH_URL = URL + '/szukaj/{query}.html'
28+
29+word_xpath = '//div[@class="query"]'
30+dict_xpath = ['//div[@class="wyniki sjp-so-wyniki sjp-so-anchor"]',
31+ '//div[@class="wyniki sjp-wyniki sjp-anchor"]',
32+ '//div[@class="wyniki sjp-doroszewski-wyniki sjp-doroszewski-anchor"]']
33+
34+
35+def request(query, params):
36+ params['url'] = SEARCH_URL.format(query=query)
37+ logger.debug(f"query_url --> {params['url']}")
38+ return params
39+
40+
41+def response(resp):
42+ results = []
43+
44+ raise_for_httperror(resp)
45+ dom = fromstring(resp.text)
46+ word = extract_text(dom.xpath(word_xpath))
47+
48+ definitions = []
49+
50+ for dict_src in dict_xpath:
51+ for src in dom.xpath(dict_src):
52+ src_text = extract_text(src.xpath('.//span[@class="entry-head-title"]/text()')).strip()
53+
54+ src_defs = []
55+ for def_item in src.xpath('.//div[contains(@class, "ribbon-element")]'):
56+ if def_item.xpath('./div[@class="znacz"]'):
57+ sub_defs = []
58+ for def_sub_item in def_item.xpath('./div[@class="znacz"]'):
59+ def_sub_text = extract_text(def_sub_item).lstrip('0123456789. ')
60+ sub_defs.append(def_sub_text)
61+ src_defs.append((word, sub_defs))
62+ else:
63+ def_text = extract_text(def_item).strip()
64+ def_link = def_item.xpath('./span/a/@href')
65+ if 'doroszewski' in def_link[0]:
66+ def_text = f"<a href='{def_link[0]}'>{def_text}</a>"
67+ src_defs.append((def_text, ''))
68+
69+ definitions.append((src_text, src_defs))
70+
71+ if not definitions:
72+ return results
73+
74+ infobox = ''
75+ for src in definitions:
76+ infobox += f"<div><small>{src[0]}</small>"
77+ infobox += "<ul>"
78+ for (def_text, sub_def) in src[1]:
79+ infobox += f"<li>{def_text}</li>"
80+ if sub_def:
81+ infobox += "<ol>"
82+ for sub_def_text in sub_def:
83+ infobox += f"<li>{sub_def_text}</li>"
84+ infobox += "</ol>"
85+ infobox += "</ul></div>"
86+
87+ results.append({
88+ 'infobox': word,
89+ 'content': infobox,
90+ })
91+
92+ return results
searx/settings.yml+8
@@ -1284,6 +1284,14 @@ engines:
1284 timeout: 5.0
1284 timeout: 5.0
1285 disabled: True
1285 disabled: True
1286
1286
1287+ - name: słownik języka polskiego
1288+ engine: sjp
1289+ shortcut: sjp
1290+ base_url: https://sjp.pwn.pl/
1291+ categories: general
1292+ timeout: 5.0
1293+ disabled: True
1294+
1287# Doku engine lets you access to any Doku wiki instance:
1295# Doku engine lets you access to any Doku wiki instance:
1288# A public one or a privete/corporate one.
1296# A public one or a privete/corporate one.
1289# - name : ubuntuwiki
1297# - name : ubuntuwiki