mirror of
https://github.com/searxng/searxng
synced 2024-01-01 18:24:07 +00:00
2499899554
Partial reverse engineering of the Google engines including a improved language and region handling based on the engine.traits_v1 data. When ever possible the implementations of the Google engines try to make use of the async REST APIs. The get_lang_info() has been generalized to a get_google_info() function / especially the region handling has been improved by adding the cr parameter. searx/data/engine_traits.json Add data type "traits_v1" generated by the fetch_traits() functions from: - Google (WEB), - Google images, - Google news, - Google scholar and - Google videos and remove data from obsolete data type "supported_languages". A traits.custom type that maps region codes to *supported_domains* is fetched from https://www.google.com/supported_domains searx/autocomplete.py: Reversed engineered autocomplete from Google WEB. Supports Google's languages and subdomains. The old API suggestqueries.google.com/complete has been replaced by the async REST API: https://{subdomain}/complete/search?{args} searx/engines/google.py Reverse engineering and extensive testing .. - fetch_traits(): Fetch languages & regions from Google properties. - always use the async REST API (formally known as 'use_mobile_ui') - use *supported_domains* from traits - improved the result list by fetching './/div[@data-content-feature]' and parsing the type of the various *content features* --> thumbnails are added searx/engines/google_images.py Reverse engineering and extensive testing .. - fetch_traits(): Fetch languages & regions from Google properties. - use *supported_domains* from traits - if exists, freshness_date is added to the result - issue 1864: result list has been improved a lot (due to the new cr parameter) searx/engines/google_news.py Reverse engineering and extensive testing .. - fetch_traits(): Fetch languages & regions from Google properties. *supported_domains* is not needed but a ceid list has been added. - different region handling compared to Google WEB - fixed for various languages & regions (due to the new ceid parameter) / avoid CONSENT page - Google News do no longer support time range - result list has been fixed: XPath of pub_date and pub_origin searx/engines/google_videos.py - fetch_traits(): Fetch languages & regions from Google properties. - use *supported_domains* from traits - add paging support - implement a async request ('asearch': 'arc' & 'async': 'use_ac:true,_fmt:html') - simplified code (thanks to '_fmt:html' request) - issue 1359: fixed xpath of video length data searx/engines/google_scholar.py - fetch_traits(): Fetch languages & regions from Google properties. - use *supported_domains* from traits - request(): include patents & citations - response(): fixed CAPTCHA detection (Scholar has its own CATCHA manager) - hardening XPath to iterate over results - fixed XPath of pub_type (has been change from gs_ct1 to gs_cgt2 class) - issue 1769 fixed: new request implementation is no longer incompatible Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
240 lines
6.4 KiB
Python
240 lines
6.4 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
# lint: pylint
|
|
"""This module implements functions needed for the autocompleter.
|
|
|
|
"""
|
|
# pylint: disable=use-dict-literal
|
|
|
|
import json
|
|
from urllib.parse import urlencode
|
|
|
|
import lxml
|
|
from httpx import HTTPError
|
|
|
|
from searx import settings
|
|
from searx.engines import (
|
|
engines,
|
|
google,
|
|
)
|
|
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 = lxml.etree.fromstring(response.content)
|
|
results = dom.xpath('//Result/Label//text()')
|
|
|
|
return results
|
|
|
|
|
|
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
|
|
|
|
|
|
def google_complete(query, sxng_locale):
|
|
"""Autocomplete from Google. Supports Google's languages and subdomains
|
|
(:py:obj:`searx.engines.google.get_google_info`) by using the async REST
|
|
API::
|
|
|
|
https://{subdomain}/complete/search?{args}
|
|
|
|
"""
|
|
|
|
google_info = google.get_google_info({'searxng_locale': sxng_locale}, engines['google'].traits)
|
|
|
|
url = 'https://{subdomain}/complete/search?{args}'
|
|
args = urlencode(
|
|
{
|
|
'q': query,
|
|
'client': 'gws-wiz',
|
|
'hl': google_info['params']['hl'],
|
|
}
|
|
)
|
|
results = []
|
|
resp = get(url.format(subdomain=google_info['subdomain'], args=args))
|
|
if resp.ok:
|
|
json_txt = resp.text[resp.text.find('[') : resp.text.find(']', -3) + 1]
|
|
data = json.loads(json_txt)
|
|
for item in data[0]:
|
|
results.append(lxml.html.fromstring(item[0]).text_content())
|
|
return results
|
|
|
|
|
|
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'}
|
|
)
|
|
)
|
|
)
|
|
|
|
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'
|
|
]
|
|
|
|
|
|
def startpage(query, sxng_locale):
|
|
"""Autocomplete from Startpage. Supports Startpage's languages"""
|
|
lui = engines['startpage'].traits.get_language(sxng_locale, '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 = json.loads(get(url.format(query=urlencode({'query': query}))).text)
|
|
return resp
|
|
|
|
|
|
def qwant(query, sxng_locale):
|
|
"""Autocomplete from Qwant. Supports Qwant's regions."""
|
|
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'})))
|
|
|
|
if resp.ok:
|
|
data = resp.json()
|
|
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]
|
|
|
|
return results
|
|
|
|
|
|
def yandex(query, _lang):
|
|
# yandex autocompleter
|
|
url = "https://suggest.yandex.com/suggest-ff.cgi?{0}"
|
|
|
|
resp = json.loads(get(url.format(urlencode(dict(part=query)))).text)
|
|
if len(resp) > 1:
|
|
return resp[1]
|
|
return []
|
|
|
|
|
|
backends = {
|
|
'dbpedia': dbpedia,
|
|
'duckduckgo': duckduckgo,
|
|
'google': google_complete,
|
|
'seznam': seznam,
|
|
'startpage': startpage,
|
|
'swisscows': swisscows,
|
|
'qwant': qwant,
|
|
'wikipedia': wikipedia,
|
|
'brave': brave,
|
|
'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)
|
|
except (HTTPError, SearxEngineResponseException):
|
|
return []
|