1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-22 20:17:45 +01:00

Fix conflicts

This commit is contained in:
Plague Doctor 2021-04-09 06:54:03 +10:00
commit 599ff39ddf
4 changed files with 90 additions and 1 deletions

View File

@ -8,6 +8,7 @@ transifex-client==0.14.2
selenium==3.141.0 selenium==3.141.0
twine==3.4.1 twine==3.4.1
Pallets-Sphinx-Themes==1.2.3 Pallets-Sphinx-Themes==1.2.3
docutils==0.16
Sphinx==3.5.3 Sphinx==3.5.3
sphinx-issues==1.2.0 sphinx-issues==1.2.0
sphinx-jinja==1.1.1 sphinx-jinja==1.1.1

77
searx/engines/wordnik.py Normal file
View 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

View File

@ -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
- name: słownik języka polskiego - name: słownik języka polskiego
engine: sjp engine: sjp
shortcut: sjp shortcut: sjp

View File

@ -1133,11 +1133,14 @@ class ReverseProxyPathFix:
base_url = urlparse(settings['server']['base_url']) base_url = urlparse(settings['server']['base_url'])
self.script_name = base_url.path self.script_name = base_url.path
if self.script_name.endswith('/'):
# remove trailing slash to avoid infinite redirect on the index
# see https://github.com/searx/searx/issues/2729
self.script_name = self.script_name[:-1]
self.scheme = base_url.scheme self.scheme = base_url.scheme
self.server = base_url.netloc self.server = base_url.netloc
def __call__(self, environ, start_response): def __call__(self, environ, start_response):
script_name = self.script_name or environ.get('HTTP_X_SCRIPT_NAME', '') script_name = self.script_name or environ.get('HTTP_X_SCRIPT_NAME', '')
if script_name: if script_name:
environ['SCRIPT_NAME'] = script_name environ['SCRIPT_NAME'] = script_name