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
|
# SPDX-License-Identifier: AGPL-3.0-or-later
# pylint: disable=line-too-long
"""Naver for SearXNG"""
from urllib.parse import urlencode
from lxml import html
from searx.exceptions import SearxEngineAPIException, SearxEngineXPathException
from searx.result_types import EngineResults, MainResult
from searx.utils import (
eval_xpath_getindex,
eval_xpath_list,
eval_xpath,
extract_text,
extr,
html_to_text,
parse_duration_string,
js_obj_str_to_python,
get_embeded_stream_url,
)
# engine metadata
about = {
"website": "https://search.naver.com",
"wikidata_id": "Q485639",
"use_official_api": False,
"require_api_key": False,
"results": "HTML",
"language": "ko",
}
categories = []
paging = True
time_range_support = True
time_range_dict = {"day": "1d", "week": "1w", "month": "1m", "year": "1y"}
base_url = "https://search.naver.com"
naver_category = "general"
"""Naver supports general, images, news, videos search.
- ``general``: search for general
- ``images``: search for images
- ``news``: search for news
- ``videos``: search for videos
"""
# Naver cannot set the number of results on one page, set default value for paging
naver_category_dict = {
"general": {
"start": 15,
"where": "web",
},
"images": {
"start": 50,
"where": "image",
},
"news": {
"start": 10,
"where": "news",
},
"videos": {
"start": 48,
"where": "video",
},
}
def init(_):
if naver_category not in ('general', 'images', 'news', 'videos'):
raise SearxEngineAPIException(f"Unsupported category: {naver_category}")
def request(query, params):
query_params = {
"query": query,
}
if naver_category in naver_category_dict:
query_params["start"] = (params["pageno"] - 1) * naver_category_dict[naver_category]["start"] + 1
query_params["where"] = naver_category_dict[naver_category]["where"]
if params["time_range"] in time_range_dict:
query_params["nso"] = f"p:{time_range_dict[params['time_range']]}"
params["url"] = f"{base_url}/search.naver?{urlencode(query_params)}"
return params
def response(resp) -> EngineResults:
parsers = {'general': parse_general, 'images': parse_images, 'news': parse_news, 'videos': parse_videos}
return parsers[naver_category](resp.text)
def parse_general(data):
results = EngineResults()
dom = html.fromstring(data)
for item in eval_xpath_list(dom, "//ul[contains(@class, 'lst_total')]/li[contains(@class, 'bx')]"):
thumbnail = None
try:
thumbnail = eval_xpath_getindex(item, ".//div[contains(@class, 'thumb_single')]//img/@data-lazysrc", 0)
except (ValueError, TypeError, SearxEngineXPathException):
pass
results.add(
MainResult(
title=extract_text(eval_xpath(item, ".//a[contains(@class, 'link_tit')]")),
url=eval_xpath_getindex(item, ".//a[contains(@class, 'link_tit')]/@href", 0),
content=extract_text(
eval_xpath(item, ".//div[contains(@class, 'total_dsc_wrap')]//a[contains(@class, 'api_txt_lines')]")
),
thumbnail=thumbnail,
)
)
return results
def parse_images(data):
results = []
match = extr(data, '<script>var imageSearchTabData=', '</script>')
if match:
json = js_obj_str_to_python(match.strip())
items = json.get('content', {}).get('items', [])
for item in items:
results.append(
{
"template": "images.html",
"url": item.get('link'),
"thumbnail_src": item.get('thumb'),
"img_src": item.get('originalUrl'),
"title": html_to_text(item.get('title')),
"source": item.get('source'),
"resolution": f"{item.get('orgWidth')} x {item.get('orgHeight')}",
}
)
return results
def parse_news(data):
results = EngineResults()
dom = html.fromstring(data)
for item in eval_xpath_list(
dom, "//div[contains(@class, 'sds-comps-base-layout') and contains(@class, 'sds-comps-full-layout')]"
):
title = extract_text(eval_xpath(item, ".//span[contains(@class, 'sds-comps-text-type-headline1')]/text()"))
url = eval_xpath_getindex(item, ".//a[@href and @nocr='1']/@href", 0)
content = extract_text(eval_xpath(item, ".//span[contains(@class, 'sds-comps-text-type-body1')]"))
thumbnail = None
try:
thumbnail = eval_xpath_getindex(
item,
".//div[contains(@class, 'sds-comps-image') and contains(@class, 'sds-rego-thumb-overlay')]//img[@src]/@src",
0,
)
except (ValueError, TypeError, SearxEngineXPathException):
pass
if title and content and url:
results.add(
MainResult(
title=title,
url=url,
content=content,
thumbnail=thumbnail,
)
)
return results
def parse_videos(data):
results = []
dom = html.fromstring(data)
for item in eval_xpath_list(dom, "//li[contains(@class, 'video_item')]"):
url = eval_xpath_getindex(item, ".//a[contains(@class, 'info_title')]/@href", 0)
thumbnail = None
try:
thumbnail = eval_xpath_getindex(item, ".//img[contains(@class, 'thumb')]/@src", 0)
except (ValueError, TypeError, SearxEngineXPathException):
pass
length = None
try:
length = parse_duration_string(extract_text(eval_xpath(item, ".//span[contains(@class, 'time')]")))
except (ValueError, TypeError):
pass
results.append(
{
"template": "videos.html",
"title": extract_text(eval_xpath(item, ".//a[contains(@class, 'info_title')]")),
"url": url,
"thumbnail": thumbnail,
"length": length,
"iframe_src": get_embeded_stream_url(url),
}
)
return results
|
