2021-04-08 01:58:00 +02:00
|
|
|
# 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
|
[httpx] replace searx.poolrequests by searx.network
settings.yml:
* outgoing.networks:
* can contains network definition
* propertiers: enable_http, verify, http2, max_connections, max_keepalive_connections,
keepalive_expiry, local_addresses, support_ipv4, support_ipv6, proxies, max_redirects, retries
* retries: 0 by default, number of times searx retries to send the HTTP request (using different IP & proxy each time)
* local_addresses can be "192.168.0.1/24" (it supports IPv6)
* support_ipv4 & support_ipv6: both True by default
see https://github.com/searx/searx/pull/1034
* each engine can define a "network" section:
* either a full network description
* either reference an existing network
* all HTTP requests of engine use the same HTTP configuration (it was not the case before, see proxy configuration in master)
2021-04-05 10:43:33 +02:00
|
|
|
from searx.network import raise_for_httperror
|
2021-04-08 01:58:00 +02:00
|
|
|
|
|
|
|
|
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
|
