Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Unverified Commit a77d8c82 authored by Alexandre Flament's avatar Alexandre Flament Committed by GitHub
Browse files

Merge pull request #2359 from dalf/update-duden 

[mod] duden engine
parents bd4869ec 9bf594cb

searx/engines/duden.py

+19 −24
Original line number Original line Diff line number Diff line
@@ -8,11 +8,10 @@ 
 @parse       url, title, content

 @parse       url, title, content

"""

"""





from lxml import html, etree

import re

import re

from urllib.parse import quote, urljoin

from urllib.parse import quote, urljoin

from searx.utils import extract_text, eval_xpath

from lxml import html

from searx import logger

from searx.utils import extract_text, eval_xpath, eval_xpath_list, eval_xpath_getindex





categories = ['general']

categories = ['general']

paging = True

paging = True
@@ -40,6 +39,9 @@ def request(query, params): 
        params['url'] = search_url_fmt.format(query=quote(query))

        params['url'] = search_url_fmt.format(query=quote(query))

    else:

    else:

        params['url'] = search_url.format(offset=offset, query=quote(query))

        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

    return params
@@ -51,19 +53,15 @@ def response(resp): 




    dom = html.fromstring(resp.text)

    dom = html.fromstring(resp.text)





    try:

    number_of_results_element =\

        number_of_results_string =\

        eval_xpath_getindex(dom, '//a[@class="active" and contains(@href,"/suchen/dudenonline")]/span/text()',

            re.sub('[^0-9]', '',

                            0, default=None)

                   eval_xpath(dom, '//a[@class="active" and contains(@href,"/suchen/dudenonline")]/span/text()')[0])

    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)})

        results.append({'number_of_results': int(number_of_results_string)})





    except:

    for result in eval_xpath_list(dom, '//section[not(contains(@class, "essay"))]'):

        logger.debug("Couldn't read number of results.")

        url = eval_xpath_getindex(result, './/h2/a', 0).get('href')



    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)

        url = urljoin(base_url, url)

        title = eval_xpath(result, 'string(.//h2/a)').strip()

        title = eval_xpath(result, 'string(.//h2/a)').strip()

        content = extract_text(eval_xpath(result, './/p'))

        content = extract_text(eval_xpath(result, './/p'))
@@ -71,8 +69,5 @@ def response(resp): 
        results.append({'url': url,

        results.append({'url': url,

                        'title': title,

                        'title': title,

                        'content': content})

                        'content': content})

        except:

            logger.debug('result parse error in:\n%s', etree.tostring(result, pretty_print=True))

            continue





    return results
 
    return results