summaryrefslogtreecommitdiff
path: root/searx/autocomplete.py
blob: 6c69ff7c5decc8d6f08840475f3607076c8d7c01 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
'''
searx is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.

searx is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU Affero General Public License for more details.

You should have received a copy of the GNU Affero General Public License
along with searx. If not, see < http://www.gnu.org/licenses/ >.

(C) 2013- by Adam Tauber, <asciimoo@gmail.com>
'''


from lxml import etree
from json import loads
from urllib.parse import urlencode

from httpx import HTTPError


from searx import settings
from searx.data import ENGINES_LANGUAGES
from searx.network import get as http_get
from searx.exceptions import SearxEngineResponseException


def get(*args, **kwargs):
    if 'timeout' not in kwargs:
        kwargs['timeout'] = settings['outgoing']['request_timeout']
    kwargs['raise_for_httperror'] = True
    return http_get(*args, **kwargs)


def brave(query, lang):
    # brave search autocompleter
    url = 'https://search.brave.com/api/suggest?{query}'
    resp = get(url.format(query=urlencode({'q': query})))

    results = []

    if resp.ok:
        data = loads(resp.text)
        for item in data[1]:
            results.append(item)
    return results


def dbpedia(query, lang):
    # dbpedia autocompleter, no HTTPS
    autocomplete_url = 'https://lookup.dbpedia.org/api/search.asmx/KeywordSearch?'

    response = get(autocomplete_url + urlencode(dict(QueryString=query)))

    results = []

    if response.ok:
        dom = etree.fromstring(response.content)
        results = dom.xpath('//Result/Label//text()')

    return results


def duckduckgo(query, lang):
    # duckduckgo autocompleter
    url = 'https://ac.duckduckgo.com/ac/?{0}&type=list'

    resp = loads(get(url.format(urlencode(dict(q=query)))).text)
    if len(resp) > 1:
        return resp[1]
    return []


def google(query, lang):
    # google autocompleter
    autocomplete_url = 'https://suggestqueries.google.com/complete/search?client=toolbar&'

    response = get(autocomplete_url + urlencode(dict(hl=lang, q=query)))

    results = []

    if response.ok:
        dom = etree.fromstring(response.text)
        results = dom.xpath('//suggestion/@data')

    return results


def startpage(query, lang):
    # startpage autocompleter
    lui = ENGINES_LANGUAGES['startpage'].get(lang, 'english')
    url = 'https://startpage.com/suggestions?{query}'
    resp = get(url.format(query=urlencode({'q': query, 'segment': 'startpage.udog', 'lui': lui})))
    data = resp.json()
    return [e['text'] for e in data.get('suggestions', []) if 'text' in e]


def swisscows(query, lang):
    # swisscows autocompleter
    url = 'https://swisscows.ch/api/suggest?{query}&itemsCount=5'

    resp = loads(get(url.format(query=urlencode({'query': query}))).text)
    return resp


def qwant(query, lang):
    # qwant autocompleter (additional parameter : lang=en_en&count=xxx )
    url = 'https://api.qwant.com/api/suggest?{query}'

    resp = get(url.format(query=urlencode({'q': query, 'lang': lang})))

    results = []

    if resp.ok:
        data = loads(resp.text)
        if data['status'] == 'success':
            for item in data['data']['items']:
                results.append(item['value'])

    return results


def wikipedia(query, lang):
    # wikipedia autocompleter
    url = 'https://' + lang + '.wikipedia.org/w/api.php?action=opensearch&{0}&limit=10&namespace=0&format=json'

    resp = loads(get(url.format(urlencode(dict(search=query)))).text)
    if len(resp) > 1:
        return resp[1]
    return []


backends = {
    'dbpedia': dbpedia,
    'duckduckgo': duckduckgo,
    'google': google,
    'startpage': startpage,
    'swisscows': swisscows,
    'qwant': qwant,
    'wikipedia': wikipedia,
    'brave': brave,
}


def search_autocomplete(backend_name, query, lang):
    backend = backends.get(backend_name)
    if backend is None:
        return []

    try:
        return backend(query, lang)
    except (HTTPError, SearxEngineResponseException):
        return []