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
|
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Mojeek (general, images, news)"""
from typing import TYPE_CHECKING
from datetime import datetime
from urllib.parse import urlencode
from lxml import html
from dateutil.relativedelta import relativedelta
from searx.utils import eval_xpath, eval_xpath_list, extract_text
from searx.enginelib.traits import EngineTraits
about = {
'website': 'https://mojeek.com',
'wikidata_id': 'Q60747299',
'official_api_documentation': 'https://www.mojeek.com/support/api/search/request_parameters.html',
'use_official_api': False,
'require_api_key': False,
'results': 'HTML',
}
paging = True # paging is only supported for general search
safesearch = True
time_range_support = True # time range search is supported for general and news
max_page = 10
base_url = "https://www.mojeek.com"
categories = ["general", "web"]
search_type = "" # leave blank for general, other possible values: images, news
results_xpath = '//ul[@class="results-standard"]/li/a[@class="ob"]'
url_xpath = './@href'
title_xpath = '../h2/a'
content_xpath = '..//p[@class="s"]'
suggestion_xpath = '//div[@class="top-info"]/p[@class="top-info spell"]/em/a'
image_results_xpath = '//div[@id="results"]/div[contains(@class, "image")]'
image_url_xpath = './a/@href'
image_title_xpath = './a/@data-title'
image_img_src_xpath = './a/img/@src'
news_results_xpath = '//section[contains(@class, "news-search-result")]//article'
news_url_xpath = './/h2/a/@href'
news_title_xpath = './/h2/a'
news_content_xpath = './/p[@class="s"]'
language_param = 'lb'
region_param = 'arc'
_delta_kwargs = {'day': 'days', 'week': 'weeks', 'month': 'months', 'year': 'years'}
if TYPE_CHECKING:
import logging
logger = logging.getLogger()
traits: EngineTraits
def init(_):
if search_type not in ('', 'images', 'news'):
raise ValueError(f"Invalid search type {search_type}")
def request(query, params):
args = {
'q': query,
'safe': min(params['safesearch'], 1),
'fmt': search_type,
language_param: traits.get_language(params['searxng_locale'], traits.custom['language_all']),
region_param: traits.get_region(params['searxng_locale'], traits.custom['region_all']),
}
if search_type == '':
args['s'] = 10 * (params['pageno'] - 1)
if params['time_range'] and search_type != 'images':
kwargs = {_delta_kwargs[params['time_range']]: 1}
args["since"] = (datetime.now() - relativedelta(**kwargs)).strftime("%Y%m%d") # type: ignore
logger.debug(args["since"])
params['url'] = f"{base_url}/search?{urlencode(args)}"
return params
def _general_results(dom):
results = []
for result in eval_xpath_list(dom, results_xpath):
results.append(
{
'url': extract_text(eval_xpath(result, url_xpath)),
'title': extract_text(eval_xpath(result, title_xpath)),
'content': extract_text(eval_xpath(result, content_xpath)),
}
)
for suggestion in eval_xpath(dom, suggestion_xpath):
results.append({'suggestion': extract_text(suggestion)})
return results
def _image_results(dom):
results = []
for result in eval_xpath_list(dom, image_results_xpath):
results.append(
{
'template': 'images.html',
'url': extract_text(eval_xpath(result, image_url_xpath)),
'title': extract_text(eval_xpath(result, image_title_xpath)),
'img_src': base_url + extract_text(eval_xpath(result, image_img_src_xpath)), # type: ignore
'content': '',
}
)
return results
def _news_results(dom):
results = []
for result in eval_xpath_list(dom, news_results_xpath):
results.append(
{
'url': extract_text(eval_xpath(result, news_url_xpath)),
'title': extract_text(eval_xpath(result, news_title_xpath)),
'content': extract_text(eval_xpath(result, news_content_xpath)),
}
)
return results
def response(resp):
dom = html.fromstring(resp.text)
if search_type == '':
return _general_results(dom)
if search_type == 'images':
return _image_results(dom)
if search_type == 'news':
return _news_results(dom)
raise ValueError(f"Invalid search type {search_type}")
def fetch_traits(engine_traits: EngineTraits):
# pylint: disable=import-outside-toplevel
from searx import network
from searx.locales import get_official_locales, region_tag
from babel import Locale, UnknownLocaleError
import contextlib
resp = network.get(base_url + "/preferences", headers={'Accept-Language': 'en-US,en;q=0.5'})
dom = html.fromstring(resp.text) # type: ignore
languages = eval_xpath_list(dom, f'//select[@name="{language_param}"]/option/@value')
engine_traits.custom['language_all'] = languages[0]
for code in languages[1:]:
with contextlib.suppress(UnknownLocaleError):
locale = Locale(code)
engine_traits.languages[locale.language] = code
regions = eval_xpath_list(dom, f'//select[@name="{region_param}"]/option/@value')
engine_traits.custom['region_all'] = regions[1]
for code in regions[2:]:
for locale in get_official_locales(code, engine_traits.languages):
engine_traits.regions[region_tag(locale)] = code
|
