Merge pull request #2642 from return42/fix-apkmirror

[fix] APKMirror engine - update xpath selectors and fix img_src
This commit is contained in:
Alexandre Flament 2021-03-11 09:48:31 +01:00 committed by GitHub
commit af3e969c5a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 23 additions and 20 deletions

View File

@ -196,6 +196,7 @@ PYLINT_FILES=\
searx/engines/mediathekviewweb.py \
searx/engines/google_scholar.py \
searx/engines/yahoo_news.py \
searx/engines/apkmirror.py \
searx_extra/update/update_external_bangs.py
test.pylint: pyenvinstall

View File

@ -1,13 +1,21 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""APKMirror
"""
APK Mirror
"""
# pylint: disable=invalid-name, missing-function-docstring
from urllib.parse import urlencode
from lxml import html
from searx.utils import extract_text, eval_xpath_list, eval_xpath_getindex
# about
from searx import logger
from searx.utils import (
eval_xpath_list,
eval_xpath_getindex,
extract_text,
)
logger = logger.getChild('APKMirror engine')
about = {
"website": 'https://www.apkmirror.com',
"wikidata_id": None,
@ -18,11 +26,8 @@ about = {
}
# engine dependent config
categories = ['it']
categories = ['files']
paging = True
# I am not 100% certain about this, as apkmirror appears to be a wordpress site,
# which might support time_range searching. If you want to implement it, go ahead.
time_range_support = False
# search-url
@ -30,37 +35,34 @@ base_url = 'https://www.apkmirror.com'
search_url = base_url + '/?post_type=app_release&searchtype=apk&page={pageno}&{query}'
# do search-request
def request(query, params):
params['url'] = search_url.format(pageno=params['pageno'],
query=urlencode({'s': query}))
params['url'] = search_url.format(
pageno = params['pageno'],
query = urlencode({'s': query}),
)
logger.debug("query_url --> %s", params['url'])
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in eval_xpath_list(dom, './/div[@id="content"]/div[@class="listWidget"]//div[@class="appRow"]'):
for result in eval_xpath_list(dom, "//div[@id='content']//div[@class='listWidget']/div/div[@class='appRow']"):
link = eval_xpath_getindex(result, './/h5/a', 0)
url = base_url + link.attrib.get('href') + '#downloads'
title = extract_text(link)
thumbnail_src = base_url\
+ eval_xpath_getindex(result, './/img', 0).attrib.get('src').replace('&w=32&h=32', '&w=64&h=64')
img_src = base_url + eval_xpath_getindex(result, './/img/@src', 0)
res = {
'url': url,
'title': title,
'thumbnail_src': thumbnail_src
'img_src': img_src
}
# append result
results.append(res)
# return results
return results