Merge pull request #2566 from dalf/remove-yandex

[remove] yandex engine
This commit is contained in:
Alexandre Flament 2021-02-12 17:12:07 +01:00 committed by GitHub
commit 45027765e3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 0 additions and 77 deletions

View File

@ -1,72 +0,0 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""
Yahoo (Web)
"""
from urllib.parse import urlencode, urlparse
from lxml import html
from searx import logger
from searx.exceptions import SearxEngineCaptchaException
logger = logger.getChild('yandex engine')
# about
about = {
"website": 'https://yandex.ru/',
"wikidata_id": 'Q5281',
"official_api_documentation": "?",
"use_official_api": False,
"require_api_key": False,
"results": 'HTML',
}
# engine dependent config
categories = ['general']
paging = True
default_tld = 'com'
language_map = {'ru': 'ru',
'ua': 'ua',
'be': 'by',
'kk': 'kz',
'tr': 'com.tr'}
# search-url
base_url = 'https://yandex.{tld}/'
search_url = 'search/?{query}&p={page}'
results_xpath = '//li[@class="serp-item"]'
url_xpath = './/h2/a/@href'
title_xpath = './/h2/a//text()'
content_xpath = './/div[@class="text-container typo typo_text_m typo_line_m organic__text"]//text()'
def request(query, params):
lang = params['language'].split('-')[0]
host = base_url.format(tld=language_map.get(lang) or default_tld)
params['url'] = host + search_url.format(page=params['pageno'] - 1,
query=urlencode({'text': query}))
return params
# get response from search-request
def response(resp):
resp_url = urlparse(resp.url)
if resp_url.path.startswith('/showcaptcha'):
raise SearxEngineCaptchaException()
dom = html.fromstring(resp.text)
results = []
for result in dom.xpath(results_xpath):
try:
res = {'url': result.xpath(url_xpath)[0],
'title': ''.join(result.xpath(title_xpath)),
'content': ''.join(result.xpath(content_xpath))}
except:
logger.exception('yandex parse crash')
continue
results.append(res)
return results

View File

@ -1009,11 +1009,6 @@ engines:
shortcut : yh
disabled : True
- name : yandex
engine : yandex
shortcut : yn
disabled : True
- name : yahoo news
engine : yahoo_news
shortcut : yhn