Merge pull request #2564 from dalf/fix-seznam

[fix] fix seznam engine
This commit is contained in:
Alexandre Flament 2021-02-12 10:56:53 +01:00 committed by GitHub
commit 2b60d0d243
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 65 additions and 17 deletions

64
searx/engines/seznam.py Normal file
View File

@ -0,0 +1,64 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""
Seznam
"""
from urllib.parse import urlencode, urlparse
from lxml import html
from searx.poolrequests import get
from searx.exceptions import SearxEngineAccessDeniedException
from searx.utils import extract_text, eval_xpath_list, eval_xpath_getindex
# about
about = {
"website": "https://www.seznam.cz/",
"wikidata_id": "Q3490485",
"official_api_documentation": "https://api.sklik.cz/",
"use_official_api": False,
"require_api_key": False,
"results": "HTML",
}
base_url = 'https://search.seznam.cz/'
def request(query, params):
response_index = get(base_url, headers=params['headers'], raise_for_httperror=True)
dom = html.fromstring(response_index.text)
url_params = {'q': query}
for e in eval_xpath_list(dom, '//input[@type="hidden"]'):
name = e.get('name')
value = e.get('value')
url_params[name] = value
params['url'] = base_url + '?' + urlencode(url_params)
params['cookies'] = response_index.cookies
return params
def response(resp):
resp_url = urlparse(resp.url)
if resp_url.path.startswith('/verify'):
raise SearxEngineAccessDeniedException()
results = []
dom = html.fromstring(resp.content.decode())
for result_element in eval_xpath_list(dom, '//div[@id="searchpage-root"]//div[@data-dot="results"]/div'):
dot_data = eval_xpath_getindex(result_element, './div/div[@data-dot-data]/@data-dot-data', 0, default=None)
if dot_data is None:
title_element = eval_xpath_getindex(result_element, './/h3/a', 0)
results.append({
'url': title_element.get('href'),
'title': extract_text(title_element),
'content': extract_text(eval_xpath_getindex(title_element, '../../div[2]', 0)),
})
elif dot_data == '{"reporter_name":"hint/related/relates"}':
suggestions_element = eval_xpath_getindex(result_element,
'./div/div[@data-dot="main-box"]', 0, default=None)
if suggestions_element is not None:
for suggestion in eval_xpath_list(suggestions_element, './/ul/li'):
results.append({'suggestion': extract_text(suggestion)})
return results

View File

@ -1170,24 +1170,8 @@ engines:
- name : seznam - name : seznam
shortcut: szn shortcut: szn
engine: xpath engine: seznam
paging : True
search_url : https://search.seznam.cz/?q={query}&count=10&from={pageno}
results_xpath: //div[@class="Page-content"]//div[contains(@class, "Result ")]
url_xpath : ./h3/a/@href
title_xpath : ./h3
content_xpath : .//p[@class="Result-description"]
suggestion_xpath: //div[@class="Related-container"]//div[@class="RelatedItem"]/div/span/a
first_page_num : 0
page_size : 10
disabled : True disabled : True
about:
website: https://www.seznam.cz/
wikidata_id: Q3490485
official_api_documentation: https://api.sklik.cz/
use_official_api: false
require_api_key: false
results: HTML
- name : mojeek - name : mojeek
shortcut: mjk shortcut: mjk