mirror of
https://github.com/searxng/searxng.git
synced 2024-11-22 20:17:45 +01:00
Merge pull request #2735 from plague-doctor/wordnik
Add new engine: Wordnik.com
This commit is contained in:
commit
cc359345a8
77
searx/engines/wordnik.py
Normal file
77
searx/engines/wordnik.py
Normal file
@ -0,0 +1,77 @@
|
|||||||
|
# SPDX-License-Identifier: AGPL-3.0-or-later
|
||||||
|
"""Wordnik (general)
|
||||||
|
|
||||||
|
"""
|
||||||
|
|
||||||
|
from lxml.html import fromstring
|
||||||
|
from searx import logger
|
||||||
|
from searx.utils import extract_text
|
||||||
|
from searx.raise_for_httperror import raise_for_httperror
|
||||||
|
|
||||||
|
logger = logger.getChild('Wordnik engine')
|
||||||
|
|
||||||
|
# about
|
||||||
|
about = {
|
||||||
|
"website": 'https://www.wordnik.com',
|
||||||
|
"wikidata_id": 'Q8034401',
|
||||||
|
"official_api_documentation": None,
|
||||||
|
"use_official_api": False,
|
||||||
|
"require_api_key": False,
|
||||||
|
"results": 'HTML',
|
||||||
|
}
|
||||||
|
|
||||||
|
categories = ['general']
|
||||||
|
paging = False
|
||||||
|
|
||||||
|
URL = 'https://www.wordnik.com'
|
||||||
|
SEARCH_URL = URL + '/words/{query}'
|
||||||
|
|
||||||
|
|
||||||
|
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('//*[@id="headword"]/text()'))
|
||||||
|
|
||||||
|
definitions = []
|
||||||
|
for src in dom.xpath('//*[@id="define"]//h3[@class="source"]'):
|
||||||
|
src_text = extract_text(src).strip()
|
||||||
|
if src_text.startswith('from '):
|
||||||
|
src_text = src_text[5:]
|
||||||
|
|
||||||
|
src_defs = []
|
||||||
|
for def_item in src.xpath('following-sibling::ul[1]/li'):
|
||||||
|
def_abbr = extract_text(def_item.xpath('.//abbr')).strip()
|
||||||
|
def_text = extract_text(def_item).strip()
|
||||||
|
if def_abbr:
|
||||||
|
def_text = def_text[len(def_abbr):].strip()
|
||||||
|
src_defs.append((def_abbr, def_text))
|
||||||
|
|
||||||
|
definitions.append((src_text, src_defs))
|
||||||
|
|
||||||
|
if not definitions:
|
||||||
|
return results
|
||||||
|
|
||||||
|
infobox = ''
|
||||||
|
for src_text, src_defs in definitions:
|
||||||
|
infobox += f"<small>{src_text}</small>"
|
||||||
|
infobox += "<ul>"
|
||||||
|
for def_abbr, def_text in src_defs:
|
||||||
|
if def_abbr:
|
||||||
|
def_abbr += ": "
|
||||||
|
infobox += f"<li><i>{def_abbr}</i> {def_text}</li>"
|
||||||
|
infobox += "</ul>"
|
||||||
|
|
||||||
|
results.append({
|
||||||
|
'infobox': word,
|
||||||
|
'content': infobox,
|
||||||
|
})
|
||||||
|
|
||||||
|
return results
|
@ -1271,6 +1271,14 @@ engines:
|
|||||||
categories: videos
|
categories: videos
|
||||||
disabled : True
|
disabled : True
|
||||||
|
|
||||||
|
- name: wordnik
|
||||||
|
engine: wordnik
|
||||||
|
shortcut: def
|
||||||
|
base_url: https://www.wordnik.com/
|
||||||
|
categories: general
|
||||||
|
timeout: 5.0
|
||||||
|
disabled: True
|
||||||
|
|
||||||
# Doku engine lets you access to any Doku wiki instance:
|
# Doku engine lets you access to any Doku wiki instance:
|
||||||
# A public one or a privete/corporate one.
|
# A public one or a privete/corporate one.
|
||||||
# - name : ubuntuwiki
|
# - name : ubuntuwiki
|
||||||
|
Loading…
Reference in New Issue
Block a user