mirrors/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2024-11-26 21:01:01 +00:00
Code Issues Projects Releases Wiki Activity

Merge pull request #2359 from dalf/update-duden

Browse source 
[mod] duden engine
This commit is contained in:
Alexandre Flament 2020-12-08 20:33:38 +01:00 committed by GitHub
commit a77d8c8227
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 19 additions and 24 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

43
searx/engines/duden.py
View file

@ -8,11 +8,10 @@
@parse url, title, content
"""
from lxml import html, etree
import re
from urllib.parse import quote, urljoin
from searx.utils import extract_text, eval_xpath
from searx import logger
from lxml import html
from searx.utils import extract_text, eval_xpath, eval_xpath_list, eval_xpath_getindex
categories = ['general']
paging = True
@ -40,6 +39,9 @@ def request(query, params):
params['url'] = search_url_fmt.format(query=quote(query))
else:
params['url'] = search_url.format(offset=offset, query=quote(query))
# after the last page of results, spelling corrections are returned after a HTTP redirect
# whatever the page number is
params['soft_max_redirects'] = 1
return params
@ -51,28 +53,21 @@ def response(resp):
dom = html.fromstring(resp.text)
try:
number_of_results_string =\
re.sub('[^0-9]', '',
eval_xpath(dom, '//a[@class="active" and contains(@href,"/suchen/dudenonline")]/span/text()')[0])
number_of_results_element =\
eval_xpath_getindex(dom, '//a[@class="active" and contains(@href,"/suchen/dudenonline")]/span/text()',
0, default=None)
if number_of_results_element is not None:
number_of_results_string = re.sub('[^0-9]', '', number_of_results_element)
results.append({'number_of_results': int(number_of_results_string)})
except:
logger.debug("Couldn't read number of results.")
for result in eval_xpath(dom, '//section[not(contains(@class, "essay"))]'):
try:
url = eval_xpath(result, './/h2/a')[0].get('href')
url = urljoin(base_url, url)
title = eval_xpath(result, 'string(.//h2/a)').strip()
content = extract_text(eval_xpath(result, './/p'))
# append result
results.append({'url': url,
'title': title,
'content': content})
except:
logger.debug('result parse error in:\n%s', etree.tostring(result, pretty_print=True))
continue
for result in eval_xpath_list(dom, '//section[not(contains(@class, "essay"))]'):
url = eval_xpath_getindex(result, './/h2/a', 0).get('href')
url = urljoin(base_url, url)
title = eval_xpath(result, 'string(.//h2/a)').strip()
content = extract_text(eval_xpath(result, './/p'))
# append result
results.append({'url': url,
'title': title,
'content': content})
return results