searxngRebrandZaclys/searx/autocomplete.py

223 lines
5.9 KiB
Python
Raw Normal View History

# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
"""This module implements functions needed for the autocompleter.
"""
# pylint: disable=use-dict-literal
2014-03-29 15:30:49 +00:00
from json import loads
from urllib.parse import urlencode
from lxml import etree
2021-03-18 18:59:01 +00:00
from httpx import HTTPError
2015-04-09 22:59:25 +00:00
from searx import settings
from searx.engines import engines
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()
2015-04-09 22:59:25 +00:00
def get(*args, **kwargs):
if 'timeout' not in kwargs:
kwargs['timeout'] = settings['outgoing']['request_timeout']
kwargs['raise_for_httperror'] = True
2015-04-09 22:59:25 +00:00
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?'
2014-03-29 15:30:49 +00:00
2016-01-18 11:47:31 +00:00
response = get(autocomplete_url + urlencode(dict(QueryString=query)))
2014-03-29 15:30:49 +00:00
results = []
if response.ok:
dom = etree.fromstring(response.content)
results = dom.xpath('//Result/Label//text()')
2014-03-29 15:30:49 +00:00
return results
[mod] DuckDuckGo: reversed engineered & upgrade to data_type: traits_v1 Partial reverse engineering of the DuckDuckGo (DDG) engines including a improved language and region handling based on the enigne.traits_v1 data. - DDG Lite - DDG Instant Answer API - DDG Images - DDG Weather docs/src/searx.engine.duckduckgo.rst: Online documentation of the DDG engines (make docs.live) searx/data/engine_traits.json Add data type "traits_v1" generated by the fetch_traits() functions from: - "duckduckgo" (WEB), - "duckduckgo images" and - "duckduckgo weather" and remove data from obsolete data type "supported_languages". searx/autocomplete.py: Reversed engineered Autocomplete from DDG. Supports DDG's languages. searx/engines/duckduckgo.py: - fetch_traits(): Fetch languages & regions from DDG. - get_ddg_lang(): Get DDG's language identifier from SearXNG's locale. DDG defines its languages by region codes. DDG-Lite does not offer a language selection to the user, only a region can be selected by the user. - Cache ``vqd`` value: The vqd value depends on the query string and is needed for the follow up pages or the images loaded by a XMLHttpRequest (DDG images). The ``vqd`` value of a search term is stored for 10min in the redis DB. - DDG Lite engine: reversed engineered request method with improved Language and region support and better ``vqd`` handling. searx/engines/duckduckgo_definitions.py: DDG Instant Answer API The *instant answers* API does not support languages, or at least we could not find out how language support should work. It seems that most of the features are based on English terms. searx/engines/duckduckgo_images.py: DDG Images Reversed engineered request method. Improved language and region handling based on cookies and the enigne.traits_v1 data. Response: add image format to the result list searx/engines/duckduckgo_weather.py: DDG Weather Improved language and region handling based on cookies and the enigne.traits_v1 data. Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-11-05 14:10:52 +00:00
def duckduckgo(query, sxng_locale):
"""Autocomplete from DuckDuckGo. Supports DuckDuckGo's languages"""
traits = engines['duckduckgo'].traits
args = {
'q': query,
'kl': traits.get_region(sxng_locale, traits.all_locale),
}
url = 'https://duckduckgo.com/ac/?type=list&' + urlencode(args)
resp = get(url)
ret_val = []
if resp.ok:
j = resp.json()
if len(j) > 1:
ret_val = j[1]
return ret_val
2014-09-07 21:56:06 +00:00
def google(query, lang):
2014-03-29 15:30:49 +00:00
# google autocompleter
autocomplete_url = 'https://suggestqueries.google.com/complete/search?client=toolbar&'
2014-03-29 15:30:49 +00:00
response = get(autocomplete_url + urlencode(dict(hl=lang, q=query)))
2014-03-29 15:30:49 +00:00
results = []
if response.ok:
2014-03-29 16:04:33 +00:00
dom = etree.fromstring(response.text)
2014-03-29 15:30:49 +00:00
results = dom.xpath('//suggestion/@data')
return results
2022-04-14 01:02:05 +00:00
def seznam(query, _lang):
# seznam search autocompleter
url = 'https://suggest.seznam.cz/fulltext/cs?{query}'
resp = get(
url.format(
query=urlencode(
{'phrase': query, 'cursorPosition': len(query), 'format': 'json-2', 'highlight': '1', 'count': '6'}
)
)
)
2022-04-14 01:02:05 +00:00
if not resp.ok:
return []
data = resp.json()
return [
''.join([part.get('text', '') for part in item.get('text', [])])
for item in data.get('result', [])
if item.get('itemType', None) == 'ItemType.TEXT'
]
2022-04-14 01:02:05 +00:00
def startpage(query, sxng_locale):
"""Autocomplete from Startpage. Supports Startpage's languages"""
lui = engines['startpage'].traits.get_language(sxng_locale, 'english')
2021-11-13 12:26:47 +00:00
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):
2020-02-14 18:19:24 +00:00
# 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, sxng_locale):
"""Autocomplete from Qwant. Supports Qwant's regions."""
2016-03-02 11:54:06 +00:00
results = []
locale = engines['qwant'].traits.get_region(sxng_locale, 'en_US')
url = 'https://api.qwant.com/v3/suggest?{query}'
resp = get(url.format(query=urlencode({'q': query, 'locale': locale, 'version': '2'})))
2016-03-02 11:54:06 +00:00
if resp.ok:
data = resp.json()
2016-03-02 11:54:06 +00:00
if data['status'] == 'success':
for item in data['data']['items']:
results.append(item['value'])
return results
def wikipedia(query, sxng_locale):
"""Autocomplete from Wikipedia. Supports Wikipedia's languages (aka netloc)."""
results = []
eng_traits = engines['wikipedia'].traits
wiki_lang = eng_traits.get_language(sxng_locale, 'en')
wiki_netloc = eng_traits.custom['wiki_netloc'].get(wiki_lang, 'en.wikipedia.org')
url = 'https://{wiki_netloc}/w/api.php?{args}'
args = urlencode(
{
'action': 'opensearch',
'format': 'json',
'formatversion': '2',
'search': query,
'namespace': '0',
'limit': '10',
}
)
resp = get(url.format(args=args, wiki_netloc=wiki_netloc))
if resp.ok:
data = resp.json()
if len(data) > 1:
results = data[1]
2014-03-29 15:30:49 +00:00
return results
2014-03-29 15:30:49 +00:00
2022-09-09 20:42:44 +00:00
def yandex(query, _lang):
# yandex autocompleter
url = "https://suggest.yandex.com/suggest-ff.cgi?{0}"
resp = loads(get(url.format(urlencode(dict(part=query)))).text)
if len(resp) > 1:
return resp[1]
return []
backends = {
'dbpedia': dbpedia,
'duckduckgo': duckduckgo,
'google': google,
2022-04-14 01:02:05 +00:00
'seznam': seznam,
'startpage': startpage,
'swisscows': swisscows,
'qwant': qwant,
'wikipedia': wikipedia,
'brave': brave,
2022-09-09 20:42:44 +00:00
'yandex': yandex,
}
def search_autocomplete(backend_name, query, sxng_locale):
backend = backends.get(backend_name)
if backend is None:
return []
if engines[backend_name].traits.data_type != "traits_v1":
# vintage / deprecated
if not sxng_locale or sxng_locale == 'all':
sxng_locale = 'en'
else:
sxng_locale = sxng_locale.split('-')[0]
try:
return backend(query, sxng_locale)
2021-03-18 18:59:01 +00:00
except (HTTPError, SearxEngineResponseException):
return []