[fix] update seznam engine to be compatible with the new website

This commit is contained in:
Adam Tauber 2021-03-27 15:29:00 +01:00
parent 672ac91f3e
commit 28286cf3f2

View file

@ -7,7 +7,12 @@ 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
from searx.utils import (
extract_text,
eval_xpath_list,
eval_xpath_getindex,
eval_xpath,
)
# about
about = {
@ -26,7 +31,10 @@ 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}
url_params = {
'q': query,
'oq': query,
}
for e in eval_xpath_list(dom, '//input[@type="hidden"]'):
name = e.get('name')
value = e.get('value')
@ -45,20 +53,15 @@ def response(resp):
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)})
for result_element in eval_xpath_list(dom, '//div[@data-dot="results"]/div'):
result_data = eval_xpath_getindex(result_element, './/div[contains(@class, "Result")]', 0, default=None)
if result_data is None:
continue
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(result_data, './/p[@class="Result-description"]')),
})
return results