searxng/searx/engines/wordnik.py
Markus Heiser ac0c6cc2d1 [chore] remove invalid base_url from settings.yml engines
The engines do not have / do not need a property `base_url`, lets remove it from
the settings.yml

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2024-11-26 10:06:07 +01:00

72 lines
1.8 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-or-later
"""Wordnik (general)
"""
from lxml.html import fromstring
from searx.utils import extract_text
from searx.network import raise_for_httperror
# 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
def request(query, params):
params['url'] = f"https://www.wordnik.com/words/{query}"
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