mirror of
https://github.com/searxng/searxng.git
synced 2024-11-30 06:31:04 +00:00
e9588b70a6
Use httpx.Response.json() to avoid charset_normalizer issues: DEBUG charset_normalizer : override steps (5) and chunk_size (512) as content does not fit (153 byte(s) given) parameters. INFO charset_normalizer : ascii passed initial chaos probing. Mean measured chaos is 0.000000 % DEBUG charset_normalizer : ascii should target any language(s) of ['Latin Based'] INFO charset_normalizer : ascii is most likely the one. Stopping the process. [1] https://www.python-httpx.org/api/#response Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
152 lines
3.9 KiB
Python
152 lines
3.9 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
# lint: pylint
|
|
"""This module implements functions needed for the autocompleter.
|
|
|
|
"""
|
|
|
|
from json import loads
|
|
from urllib.parse import urlencode
|
|
|
|
from lxml import etree
|
|
from httpx import HTTPError
|
|
|
|
from searx import settings
|
|
from searx.data import ENGINES_LANGUAGES
|
|
from searx.network import get as http_get
|
|
from searx.exceptions import SearxEngineResponseException
|
|
|
|
# a fetch_supported_languages() for XPath engines isn't available right now
|
|
# _brave = ENGINES_LANGUAGES['brave'].keys()
|
|
|
|
|
|
def get(*args, **kwargs):
|
|
if 'timeout' not in kwargs:
|
|
kwargs['timeout'] = settings['outgoing']['request_timeout']
|
|
kwargs['raise_for_httperror'] = True
|
|
return http_get(*args, **kwargs)
|
|
|
|
|
|
def brave(query, _lang):
|
|
# brave search autocompleter
|
|
url = 'https://search.brave.com/api/suggest?'
|
|
url += urlencode({'q': query})
|
|
country = 'all'
|
|
# if lang in _brave:
|
|
# country = lang
|
|
kwargs = {'cookies': {'country': country}}
|
|
resp = get(url, **kwargs)
|
|
|
|
results = []
|
|
|
|
if resp.ok:
|
|
data = resp.json()
|
|
for item in data[1]:
|
|
results.append(item)
|
|
return results
|
|
|
|
|
|
def dbpedia(query, _lang):
|
|
# dbpedia autocompleter, no HTTPS
|
|
autocomplete_url = 'https://lookup.dbpedia.org/api/search.asmx/KeywordSearch?'
|
|
|
|
response = get(autocomplete_url + urlencode(dict(QueryString=query)))
|
|
|
|
results = []
|
|
|
|
if response.ok:
|
|
dom = etree.fromstring(response.content)
|
|
results = dom.xpath('//Result/Label//text()')
|
|
|
|
return results
|
|
|
|
|
|
def duckduckgo(query, _lang):
|
|
# duckduckgo autocompleter
|
|
url = 'https://ac.duckduckgo.com/ac/?{0}&type=list'
|
|
|
|
resp = loads(get(url.format(urlencode(dict(q=query)))).text)
|
|
if len(resp) > 1:
|
|
return resp[1]
|
|
return []
|
|
|
|
|
|
def google(query, lang):
|
|
# google autocompleter
|
|
autocomplete_url = 'https://suggestqueries.google.com/complete/search?client=toolbar&'
|
|
|
|
response = get(autocomplete_url + urlencode(dict(hl=lang, q=query)))
|
|
|
|
results = []
|
|
|
|
if response.ok:
|
|
dom = etree.fromstring(response.text)
|
|
results = dom.xpath('//suggestion/@data')
|
|
|
|
return results
|
|
|
|
|
|
def startpage(query, lang):
|
|
# startpage autocompleter
|
|
lui = ENGINES_LANGUAGES['startpage'].get(lang, 'english')
|
|
url = 'https://startpage.com/suggestions?{query}'
|
|
resp = get(url.format(query=urlencode({'q': query, 'segment': 'startpage.udog', 'lui': lui})))
|
|
data = resp.json()
|
|
return [e['text'] for e in data.get('suggestions', []) if 'text' in e]
|
|
|
|
|
|
def swisscows(query, _lang):
|
|
# swisscows autocompleter
|
|
url = 'https://swisscows.ch/api/suggest?{query}&itemsCount=5'
|
|
|
|
resp = loads(get(url.format(query=urlencode({'query': query}))).text)
|
|
return resp
|
|
|
|
|
|
def qwant(query, lang):
|
|
# qwant autocompleter (additional parameter : lang=en_en&count=xxx )
|
|
url = 'https://api.qwant.com/api/suggest?{query}'
|
|
|
|
resp = get(url.format(query=urlencode({'q': query, 'lang': lang})))
|
|
|
|
results = []
|
|
|
|
if resp.ok:
|
|
data = loads(resp.text)
|
|
if data['status'] == 'success':
|
|
for item in data['data']['items']:
|
|
results.append(item['value'])
|
|
|
|
return results
|
|
|
|
|
|
def wikipedia(query, lang):
|
|
# wikipedia autocompleter
|
|
url = 'https://' + lang + '.wikipedia.org/w/api.php?action=opensearch&{0}&limit=10&namespace=0&format=json'
|
|
|
|
resp = loads(get(url.format(urlencode(dict(search=query)))).text)
|
|
if len(resp) > 1:
|
|
return resp[1]
|
|
return []
|
|
|
|
|
|
backends = {
|
|
'dbpedia': dbpedia,
|
|
'duckduckgo': duckduckgo,
|
|
'google': google,
|
|
'startpage': startpage,
|
|
'swisscows': swisscows,
|
|
'qwant': qwant,
|
|
'wikipedia': wikipedia,
|
|
'brave': brave,
|
|
}
|
|
|
|
|
|
def search_autocomplete(backend_name, query, lang):
|
|
backend = backends.get(backend_name)
|
|
if backend is None:
|
|
return []
|
|
|
|
try:
|
|
return backend(query, lang)
|
|
except (HTTPError, SearxEngineResponseException):
|
|
return []
|