Icycoide/searxng
1
0
Fork 1
mirror of https://github.com/searxng/searxng.git synced 2025-08-03 02:22:22 +02:00
Code Issues Projects Releases Packages Wiki Activity

[mod] speed optimization

Browse source 
compile XPath only once
avoid redundant call to urlparse
get_locale(webapp.py): avoid useless call to request.accept_languages.best_match
This commit is contained in:
Dalf 2019-11-15 09:31:37 +01:00
parent 42d5e2c02c
commit 85b3723345
14 changed files with 106 additions and 103 deletions
Download patch file Download diff file Expand all files Collapse all files

15
searx/engines/duden.py
View file

@ -11,6 +11,7 @@
from lxml import html, etree
import re
from searx.engines.xpath import extract_text
from searx.utils import eval_xpath
from searx.url_utils import quote, urljoin
from searx import logger
@ -52,9 +53,9 @@ def response(resp):
dom = html.fromstring(resp.text)
try:
number_of_results_string = re.sub('[^0-9]', '', dom.xpath(
'//a[@class="active" and contains(@href,"/suchen/dudenonline")]/span/text()')[0]
)
number_of_results_string =\
re.sub('[^0-9]', '',
eval_xpath(dom, '//a[@class="active" and contains(@href,"/suchen/dudenonline")]/span/text()')[0])
results.append({'number_of_results': int(number_of_results_string)})
@ -62,12 +63,12 @@ def response(resp):
logger.debug("Couldn't read number of results.")
pass
for result in dom.xpath('//section[not(contains(@class, "essay"))]'):
for result in eval_xpath(dom, '//section[not(contains(@class, "essay"))]'):
try:
url = result.xpath('.//h2/a')[0].get('href')
url = eval_xpath(result, './/h2/a')[0].get('href')
url = urljoin(base_url, url)
title = result.xpath('string(.//h2/a)').strip()
content = extract_text(result.xpath('.//p'))
title = eval_xpath(result, 'string(.//h2/a)').strip()
content = extract_text(eval_xpath(result, './/p'))
# append result
results.append({'url': url,
'title': title,