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
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
|
# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
"""Processores for engine-type: ``online``
"""
from timeit import default_timer
import asyncio
import httpx
import searx.network
from searx.utils import gen_useragent
from searx.exceptions import (
SearxEngineAccessDeniedException,
SearxEngineCaptchaException,
SearxEngineTooManyRequestsException,
)
from searx.metrics.error_recorder import count_error
from .abstract import EngineProcessor
def default_request_params():
"""Default request parameters for ``online`` engines."""
return {
# fmt: off
'method': 'GET',
'headers': {},
'data': {},
'url': '',
'cookies': {},
'verify': True,
'auth': None
# fmt: on
}
class OnlineProcessor(EngineProcessor):
"""Processor class for ``online`` engines."""
engine_type = 'online'
def initialize(self):
# set timeout for all HTTP requests
searx.network.set_timeout_for_thread(self.engine.timeout, start_time=default_timer())
# reset the HTTP total time
searx.network.reset_time_for_thread()
# set the network
searx.network.set_context_network_name(self.engine_name)
super().initialize()
def get_params(self, search_query, engine_category):
params = super().get_params(search_query, engine_category)
if params is None:
return None
# add default params
params.update(default_request_params())
# add an user agent
params['headers']['User-Agent'] = gen_useragent()
# add Accept-Language header
if self.engine.send_accept_language_header and search_query.locale:
ac_lang = search_query.locale.language
if search_query.locale.territory:
ac_lang = "%s-%s,%s;q=0.9,*;q=0.5" % (
search_query.locale.language,
search_query.locale.territory,
search_query.locale.language,
)
params['headers']['Accept-Language'] = ac_lang
return params
def _send_http_request(self, params):
# create dictionary which contain all
# informations about the request
request_args = dict(
headers=params['headers'], cookies=params['cookies'], verify=params['verify'], auth=params['auth']
)
# max_redirects
max_redirects = params.get('max_redirects')
if max_redirects:
request_args['max_redirects'] = max_redirects
# allow_redirects
if 'allow_redirects' in params:
request_args['allow_redirects'] = params['allow_redirects']
# soft_max_redirects
soft_max_redirects = params.get('soft_max_redirects', max_redirects or 0)
# raise_for_status
request_args['raise_for_httperror'] = params.get('raise_for_httperror', True)
# specific type of request (GET or POST)
if params['method'] == 'GET':
req = searx.network.get
else:
req = searx.network.post
request_args['data'] = params['data']
# send the request
response = req(params['url'], **request_args)
# check soft limit of the redirect count
if len(response.history) > soft_max_redirects:
# unexpected redirect : record an error
# but the engine might still return valid results.
status_code = str(response.status_code or '')
reason = response.reason_phrase or ''
hostname = response.url.host
count_error(
self.engine_name,
'{} redirects, maximum: {}'.format(len(response.history), soft_max_redirects),
(status_code, reason, hostname),
secondary=True,
)
return response
def _search_basic(self, query, params):
# update request parameters dependent on
# search-engine (contained in engines folder)
self.engine.request(query, params)
# ignoring empty urls
if params['url'] is None:
return None
if not params['url']:
return None
# send request
response = self._send_http_request(params)
# parse the response
response.search_params = params
return self.engine.response(response)
def search(self, query, params, result_container, start_time, timeout_limit):
# set timeout for all HTTP requests
searx.network.set_timeout_for_thread(timeout_limit, start_time=start_time)
# reset the HTTP total time
searx.network.reset_time_for_thread()
# set the network
searx.network.set_context_network_name(self.engine_name)
try:
# send requests and parse the results
search_results = self._search_basic(query, params)
self.extend_container(result_container, start_time, search_results)
except (httpx.TimeoutException, asyncio.TimeoutError) as e:
# requests timeout (connect or read)
self.handle_exception(result_container, e, suspend=True)
self.logger.error(
"HTTP requests timeout (search duration : {0} s, timeout: {1} s) : {2}".format(
default_timer() - start_time, timeout_limit, e.__class__.__name__
)
)
except (httpx.HTTPError, httpx.StreamError) as e:
# other requests exception
self.handle_exception(result_container, e, suspend=True)
self.logger.exception(
"requests exception (search duration : {0} s, timeout: {1} s) : {2}".format(
default_timer() - start_time, timeout_limit, e
)
)
except SearxEngineCaptchaException as e:
self.handle_exception(result_container, e, suspend=True)
self.logger.exception('CAPTCHA')
except SearxEngineTooManyRequestsException as e:
if "google" in self.engine_name:
self.logger.warn(
"Set to 'true' the use_mobile_ui parameter in the 'engines:'"
" section of your settings.yml file if google is blocked for you."
)
self.handle_exception(result_container, e, suspend=True)
self.logger.exception('Too many requests')
except SearxEngineAccessDeniedException as e:
self.handle_exception(result_container, e, suspend=True)
self.logger.exception('Searx is blocked')
except Exception as e: # pylint: disable=broad-except
self.handle_exception(result_container, e)
self.logger.exception('exception : {0}'.format(e))
def get_default_tests(self):
tests = {}
tests['simple'] = {
'matrix': {'query': ('life', 'computer')},
'result_container': ['not_empty'],
}
if getattr(self.engine, 'paging', False):
tests['paging'] = {
'matrix': {'query': 'time', 'pageno': (1, 2, 3)},
'result_container': ['not_empty'],
'test': ['unique_results'],
}
if 'general' in self.engine.categories:
# avoid documentation about HTML tags (<time> and <input type="time">)
tests['paging']['matrix']['query'] = 'news'
if getattr(self.engine, 'time_range', False):
tests['time_range'] = {
'matrix': {'query': 'news', 'time_range': (None, 'day')},
'result_container': ['not_empty'],
'test': ['unique_results'],
}
if getattr(self.engine, 'supported_languages', []):
tests['lang_fr'] = {
'matrix': {'query': 'paris', 'lang': 'fr'},
'result_container': ['not_empty', ('has_language', 'fr')],
}
tests['lang_en'] = {
'matrix': {'query': 'paris', 'lang': 'en'},
'result_container': ['not_empty', ('has_language', 'en')],
}
if getattr(self.engine, 'safesearch', False):
tests['safesearch'] = {'matrix': {'query': 'porn', 'safesearch': (0, 2)}, 'test': ['unique_results']}
return tests
|
