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
|
# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
"""Presearch (general, images, videos, news)
.. hint::
The results in the video category are most often links to pages that contain
a video, for instance many links from preasearch's video category link
content from facebook (aka Meta) or Twitter (aka X). Since these are not
real links to video streams SearXNG can't use the video template for this and
if SearXNG can't use this template, then the user doesn't want to see these
hits in the videos category.
TL;DR; by default presearch's video category is placed into categories::
categories: [general, web]
"""
from urllib.parse import urlencode
from searx.network import get
from searx.utils import gen_useragent, html_to_text
about = {
"website": "https://presearch.io",
"wikidiata_id": "Q7240905",
"official_api_documentation": "https://docs.presearch.io/nodes/api",
"use_official_api": False,
"require_api_key": False,
"results": "JSON",
}
paging = True
safesearch = True
time_range_support = True
categories = ["general", "web"] # general, images, videos, news
search_type = "search"
"""must be any of ``search``, ``images``, ``videos``, ``news``"""
base_url = "https://presearch.com"
safesearch_map = {0: 'false', 1: 'true', 2: 'true'}
def init(_):
if search_type not in ['search', 'images', 'videos', 'news']:
raise ValueError(f'presearch search_type: {search_type}')
def _get_request_id(query, page, time_range, safesearch_param):
args = {
"q": query,
"page": page,
}
if time_range:
args["time"] = time_range
url = f"{base_url}/{search_type}?{urlencode(args)}"
headers = {
'User-Agent': gen_useragent(),
'Cookie': f"b=1;presearch_session=;use_safe_search={safesearch_map[safesearch_param]}",
}
resp_text = get(url, headers=headers).text # type: ignore
for line in resp_text.split("\n"):
if "window.searchId = " in line:
return line.split("= ")[1][:-1].replace('"', "")
return None
def request(query, params):
request_id = _get_request_id(query, params["pageno"], params["time_range"], params["safesearch"])
params["headers"]["Accept"] = "application/json"
params["url"] = f"{base_url}/results?id={request_id}"
return params
def _strip_leading_strings(text):
for x in ['wikipedia', 'google']:
if text.lower().endswith(x):
text = text[: -len(x)]
return text.strip()
def parse_search_query(json_results):
results = []
for item in json_results.get('specialSections', {}).get('topStoriesCompact', {}).get('data', []):
result = {
'url': item['link'],
'title': item['title'],
'img_src': item['image'],
'content': '',
'metadata': item.get('source'),
}
results.append(result)
for item in json_results.get('standardResults', []):
result = {
'url': item['link'],
'title': item['title'],
'content': html_to_text(item['description']),
}
results.append(result)
info = json_results.get('infoSection', {}).get('data')
if info:
attributes = []
for item in info.get('about', []):
label, value = html_to_text(item).split(':', 1)
value = _strip_leading_strings(value)
attributes.append({'label': label, 'value': value})
content = []
for item in [info['subtitle'], info['description']]:
item = _strip_leading_strings(html_to_text(item))
if item:
content.append(item)
results.append(
{
'infobox': info['title'],
'id': info['title'],
'img_src': info.get('image'),
'content': ' | '.join(content),
'attributes': attributes,
}
)
return results
def response(resp):
results = []
json_resp = resp.json()
if search_type == 'search':
results = parse_search_query(json_resp['results'])
elif search_type == 'images':
for item in json_resp.get('images', []):
results.append(
{
'template': 'images.html',
'title': item['title'],
'url': item['link'],
'img_src': item['image'],
'thumbnail_src': item['thumbnail'],
}
)
elif search_type == 'videos':
# The results in the video category are most often links to pages that contain
# a video and not to a video stream --> SearXNG can't use the video template.
for item in json_resp.get('videos', []):
metadata = [x for x in [item.get('description'), item.get('duration')] if x]
results.append(
{
'title': item['title'],
'url': item['link'],
'content': '',
'metadata': ' / '.join(metadata),
'img_src': item.get('image'),
}
)
elif search_type == 'news':
for item in json_resp.get('news', []):
metadata = [x for x in [item.get('source'), item.get('time')] if x]
results.append(
{
'title': item['title'],
'url': item['link'],
'content': item['description'],
'metadata': ' / '.join(metadata),
'img_src': item.get('image'),
}
)
return results
|
