[fix] 1x engine

Browse Source 
1x changed the XML result layout.
This commit is contained in:
Léon Tiekötter 2022-01-30 15:59:58 +01:00 committed by Markus Heiser
parent 2a6d84dab5
commit a6673a1a94
1 changed files with 10 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
searx/engines/www1x.py
View File

@ -1,10 +1,12 @@
# SPDX-License-Identifier: AGPL-3.0-or-later # SPDX-License-Identifier: AGPL-3.0-or-later
""" # lint: pylint
1x (Images) """1x (Images)
""" """
from lxml import html, etree
from urllib.parse import urlencode, urljoin from urllib.parse import urlencode, urljoin
from lxml import html, etree
from searx.utils import extract_text, eval_xpath_list, eval_xpath_getindex from searx.utils import extract_text, eval_xpath_list, eval_xpath_getindex
# about # about
@ -38,13 +40,14 @@ def request(query, params):
def response(resp): def response(resp):
results = [] results = []
xmldom = etree.fromstring(resp.content) xmldom = etree.fromstring(resp.content)
xmlsearchresult = eval_xpath_getindex(xmldom, '//searchresult', 0) xmlsearchresult = eval_xpath_getindex(xmldom, '//data', 0)
dom = html.fragment_fromstring(xmlsearchresult.text, create_parent='div') dom = html.fragment_fromstring(xmlsearchresult.text, create_parent='div')
for link in eval_xpath_list(dom, '/div/table/tr/td/div[2]//a'): for link in eval_xpath_list(dom, '//a'):
url = urljoin(base_url, link.attrib.get('href')) url = urljoin(base_url, link.attrib.get('href'))
title = extract_text(link) title = extract_text(link)
thumbnail_src = urljoin(gallery_url, eval_xpath_getindex(link, './/img', 0).attrib['src']) thumbnail_src = urljoin(
gallery_url, (eval_xpath_getindex(link, './/img', 0).attrib['src']).replace(base_url, '')
)
# append result # append result
results.append( results.append(
{ {