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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
|
# SPDX-License-Identifier: AGPL-3.0-or-later
"""YaCy_ is a free distributed search engine, built on the principles of
peer-to-peer (P2P) networks.
API: Dev:APIyacysearch_
Releases:
- https://github.com/yacy/yacy_search_server/tags
- https://download.yacy.net/
.. _Yacy: https://yacy.net/
.. _Dev:APIyacysearch: https://wiki.yacy.net/index.php/Dev:APIyacysearch
Configuration
=============
The engine has the following (additional) settings:
- :py:obj:`http_digest_auth_user`
- :py:obj:`http_digest_auth_pass`
- :py:obj:`search_mode`
- :py:obj:`search_type`
.. code:: yaml
- name: yacy
engine: yacy
categories: general
search_type: text
base_url: https://yacy.searchlab.eu
shortcut: ya
- name: yacy images
engine: yacy
categories: images
search_type: image
base_url: https://yacy.searchlab.eu
shortcut: yai
disabled: true
Implementations
===============
"""
# pylint: disable=fixme
from json import loads
from urllib.parse import urlencode
from dateutil import parser
from httpx import DigestAuth
from searx.utils import html_to_text
# about
about = {
"website": 'https://yacy.net/',
"wikidata_id": 'Q1759675',
"official_api_documentation": 'https://wiki.yacy.net/index.php/Dev:API',
"use_official_api": True,
"require_api_key": False,
"results": 'JSON',
}
# engine dependent config
categories = ['general']
paging = True
number_of_results = 10
http_digest_auth_user = ""
"""HTTP digest user for the local YACY instance"""
http_digest_auth_pass = ""
"""HTTP digest password for the local YACY instance"""
search_mode = 'global'
"""Yacy search mode ``global`` or ``local``. By default, Yacy operates in ``global``
mode.
``global``
Peer-to-Peer search
``local``
Privacy or Stealth mode, restricts the search to local yacy instance.
"""
search_type = 'text'
"""One of ``text``, ``image`` / The search-types ``app``, ``audio`` and
``video`` are not yet implemented (Pull-Requests are welcome).
"""
# search-url
base_url = 'https://yacy.searchlab.eu'
search_url = (
'/yacysearch.json?{query}'
'&startRecord={offset}'
'&maximumRecords={limit}'
'&contentdom={search_type}'
'&resource={resource}'
)
def init(_):
valid_types = [
'text',
'image',
# 'app', 'audio', 'video',
]
if search_type not in valid_types:
raise ValueError('search_type "%s" is not one of %s' % (search_type, valid_types))
def request(query, params):
offset = (params['pageno'] - 1) * number_of_results
params['url'] = base_url + search_url.format(
query=urlencode({'query': query}),
offset=offset,
limit=number_of_results,
search_type=search_type,
resource=search_mode,
)
if http_digest_auth_user and http_digest_auth_pass:
params['auth'] = DigestAuth(http_digest_auth_user, http_digest_auth_pass)
# add language tag if specified
if params['language'] != 'all':
params['url'] += '&lr=lang_' + params['language'].split('-')[0]
return params
def response(resp):
results = []
raw_search_results = loads(resp.text)
# return empty array if there are no results
if not raw_search_results:
return []
search_results = raw_search_results.get('channels', [])
if len(search_results) == 0:
return []
for result in search_results[0].get('items', []):
# parse image results
if search_type == 'image':
result_url = ''
if 'url' in result:
result_url = result['url']
elif 'link' in result:
result_url = result['link']
else:
continue
# append result
results.append(
{
'url': result_url,
'title': result['title'],
'content': '',
'img_src': result['image'],
'template': 'images.html',
}
)
# parse general results
else:
publishedDate = None
if 'pubDate' in result:
publishedDate = parser.parse(result['pubDate'])
# append result
results.append(
{
'url': result['link'] or '',
'title': result['title'],
'content': html_to_text(result['description']),
'publishedDate': publishedDate,
}
)
# TODO parse video, audio and file results
return results
|
