summaryrefslogtreecommitdiff
path: root/searx/settings.yml
diff options
context:
space:
mode:
authorApply55gx <Apply55gx@users.noreply.github.com>2017-10-25 10:42:37 +0200
committerGitHub <noreply@github.com>2017-10-25 10:42:37 +0200
commit18a4e7035f72a3c31239ae0bd1ee67cc2ad354b8 (patch)
tree84d23adbd84e88b5998b5a510f56194acd2466b6 /searx/settings.yml
parent636b76019668960417c1253d1aa383b832c18a4d (diff)
downloadsearxng-18a4e7035f72a3c31239ae0bd1ee67cc2ad354b8.tar.gz
searxng-18a4e7035f72a3c31239ae0bd1ee67cc2ad354b8.zip
removed unused indicies array
Diffstat (limited to 'searx/settings.yml')
0 files changed, 0 insertions, 0 deletions
d-color: #ffffcc } .highlight .c { color: #888888 } /* Comment */ .highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */ .highlight .k { color: #008800; font-weight: bold } /* Keyword */ .highlight .ch { color: #888888 } /* Comment.Hashbang */ .highlight .cm { color: #888888 } /* Comment.Multiline */ .highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */ .highlight .cpf { color: #888888 } /* Comment.PreprocFile */ .highlight .c1 { color: #888888 } /* Comment.Single */ .highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */ .highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */ .highlight .ge { font-style: italic } /* Generic.Emph */ .highlight .ges { font-weight: bold; font-style: italic } /* Generic.EmphStrong */ .highlight .gr { color: #aa0000 } /* Generic.Error */ .highlight .gh { color: #333333 } /* Generic.Heading */ .highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */ .highlight .go { color: #888888 } /* Generic.Output */ .highlight .gp { color: #555555 } /* Generic.Prompt */ .highlight .gs { font-weight: bold } /* Generic.Strong */ .highlight .gu { color: #666666 } /* Generic.Subheading */ .highlight .gt { color: #aa0000 } /* Generic.Traceback */ .highlight .kc { color: #008800; font-weight: bold } /* Keyword.Constant */ .highlight .kd { color: #008800; font-weight: bold } /* Keyword.Declaration */ .highlight .kn { color: #008800; font-weight: bold } /* Keyword.Namespace */ .highlight .kp { color: #008800 } /* Keyword.Pseudo */ .highlight .kr { color: #008800; font-weight: bold } /* Keyword.Reserved */ .highlight .kt { color: #888888; font-weight: bold } /* Keyword.Type */ .highlight .m { color: #0000DD; font-weight: bold } /* Literal.Number */ .highlight .s { color: #dd2200; background-color: #fff0f0 } /* Literal.String */ .highlight .na { color: #336699 } /* Name.Attribute */ .highlight .nb { color: #003388 } /* Name.Builtin */ .highlight .nc { color: #bb0066; font-weight: bold } /* Name.Class */ .highlight .no { color: #003366; font-weight: bold } /* Name.Constant */ .highlight .nd { color: #555555 } /* Name.Decorator */ .highlight .ne { color: #bb0066; font-weight: bold } /* Name.Exception */ .highlight .nf { color: #0066bb; font-weight: bold } /* Name.Function */ .highlight .nl { color: #336699; font-style: italic } /* Name.Label */ .highlight .nn { color: #bb0066; font-weight: bold } /* Name.Namespace */ .highlight .py { color: #336699; font-weight: bold } /* Name.Property */ .highlight .nt { color: #bb0066; font-weight: bold } /* Name.Tag */ .highlight .nv { color: #336699 } /* Name.Variable */ .highlight .ow { color: #008800 } /* Operator.Word */ .highlight .w { color: #bbbbbb } /* Text.Whitespace */ .highlight .mb { color: #0000DD; font-weight: bold } /* Literal.Number.Bin */ .highlight .mf { color: #0000DD; font-weight: bold } /* Literal.Number.Float */ .highlight .mh { color: #0000DD; font-weight: bold } /* Literal.Number.Hex */ .highlight .mi { color: #0000DD; font-weight: bold } /* Literal.Number.Integer */ .highlight .mo { color: #0000DD; font-weight: bold } /* Literal.Number.Oct */ .highlight .sa { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Affix */ .highlight .sb { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Backtick */ .highlight .sc { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Char */ .highlight .dl { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Delimiter */ .highlight .sd { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Doc */ .highlight .s2 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Double */ .highlight .se { color: #0044dd; background-color: #fff0f0 } /* Literal.String.Escape */ .highlight .sh { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Heredoc */ .highlight .si { color: #3333bb; background-color: #fff0f0 } /* Literal.String.Interpol */ .highlight .sx { color: #22bb22; background-color: #f0fff0 } /* Literal.String.Other */ .highlight .sr { color: #008800; background-color: #fff0ff } /* Literal.String.Regex */ .highlight .s1 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Single */ .highlight .ss { color: #aa6600; background-color: #fff0f0 } /* Literal.String.Symbol */ .highlight .bp { color: #003388 } /* Name.Builtin.Pseudo */ .highlight .fm { color: #0066bb; font-weight: bold } /* Name.Function.Magic */ .highlight .vc { color: #336699 } /* Name.Variable.Class */ .highlight .vg { color: #dd7700 } /* Name.Variable.Global */ .highlight .vi { color: #3333bb } /* Name.Variable.Instance */ .highlight .vm { color: #336699 } /* Name.Variable.Magic */ .highlight .il { color: #0000DD; font-weight: bold } /* Literal.Number.Integer.Long */
# SPDX-License-Identifier: AGPL-3.0-or-later
"""
 Wikipedia (Web)
"""

from urllib.parse import quote
from json import loads
from lxml.html import fromstring
from searx.utils import match_language, searx_useragent
from searx.raise_for_httperror import raise_for_httperror

# about
about = {
    "website": 'https://www.wikipedia.org/',
    "wikidata_id": 'Q52',
    "official_api_documentation": 'https://en.wikipedia.org/api/',
    "use_official_api": True,
    "require_api_key": False,
    "results": 'JSON',
}

# search-url
search_url = 'https://{language}.wikipedia.org/api/rest_v1/page/summary/{title}'
supported_languages_url = 'https://meta.wikimedia.org/wiki/List_of_Wikipedias'
language_variants = {"zh": ("zh-cn", "zh-hk", "zh-mo", "zh-my", "zh-sg", "zh-tw")}


# set language in base_url
def url_lang(lang):
    lang_pre = lang.split('-')[0]
    if lang_pre == 'all' or lang_pre not in supported_languages and lang_pre not in language_aliases:
        return 'en'
    return match_language(lang, supported_languages, language_aliases).split('-')[0]


# do search-request
def request(query, params):
    if query.islower():
        query = query.title()

    language = url_lang(params['language'])
    params['url'] = search_url.format(title=quote(query),
                                      language=language)

    if params['language'].lower() in language_variants.get(language, []):
        params['headers']['Accept-Language'] = params['language'].lower()

    params['headers']['User-Agent'] = searx_useragent()
    params['raise_for_httperror'] = False
    params['soft_max_redirects'] = 2

    return params


# get response from search-request
def response(resp):
    if resp.status_code == 404:
        return []

    if resp.status_code == 400:
        try:
            api_result = loads(resp.text)
        except:
            pass
        else:
            if api_result['type'] == 'https://mediawiki.org/wiki/HyperSwitch/errors/bad_request' \
               and api_result['detail'] == 'title-invalid-characters':
                return []

    raise_for_httperror(resp)

    results = []
    api_result = loads(resp.text)

    # skip disambiguation pages
    if api_result.get('type') != 'standard':
        return []

    title = api_result['title']
    wikipedia_link = api_result['content_urls']['desktop']['page']

    results.append({'url': wikipedia_link, 'title': title})

    results.append({'infobox': title,
                    'id': wikipedia_link,
                    'content': api_result.get('extract', ''),
                    'img_src': api_result.get('thumbnail', {}).get('source'),
                    'urls': [{'title': 'Wikipedia', 'url': wikipedia_link}]})

    return results


# get supported languages from their site
def _fetch_supported_languages(resp):
    supported_languages = {}
    dom = fromstring(resp.text)
    tables = dom.xpath('//table[contains(@class,"sortable")]')
    for table in tables:
        # exclude header row
        trs = table.xpath('.//tr')[1:]
        for tr in trs:
            td = tr.xpath('./td')
            code = td[3].xpath('./a')[0].text
            name = td[2].xpath('./a')[0].text
            english_name = td[1].xpath('./a')[0].text
            articles = int(td[4].xpath('./a/b')[0].text.replace(',', ''))
            # exclude languages with too few articles
            if articles >= 100:
                supported_languages[code] = {"name": name, "english_name": english_name}

    return supported_languages