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
|
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Sogou search engine for searxng"""
import re
from datetime import datetime
from urllib.parse import urlencode
from lxml import html
from searx.exceptions import SearxEngineCaptchaException
from searx.utils import extract_text
# Metadata
about = {
"website": "https://www.sogou.com/",
"wikidata_id": "Q7554565",
"use_official_api": False,
"require_api_key": False,
"results": "HTML",
}
language = "zh"
# Engine Configuration
categories = ["general"]
paging = True
time_range_support = True
time_range_dict = {
"day": "inttime_day",
"week": "inttime_week",
"month": "inttime_month",
"year": "inttime_year",
}
# Base URL
base_url = "https://www.sogou.com"
def request(query, params):
query_params = {
"query": query,
"page": params["pageno"],
}
if time_range_dict.get(params["time_range"]):
query_params["s_from"] = time_range_dict.get(params["time_range"])
query_params["tsn"] = 1
params["allow_redirects"] = False
params["url"] = f"{base_url}/web?{urlencode(query_params)}"
return params
def response(resp):
if (
resp.status_code == 302
and resp.next_request is not None
and str(resp.next_request.url).startswith("http://www.sogou.com/antispider")
):
raise SearxEngineCaptchaException()
dom = html.fromstring(resp.text)
results = []
# pylint: disable=line-too-long
for item in dom.xpath(
'//div[contains(@class, "rb")] | //div[contains(@class, "vrwrap") and not(.//div[contains(@class, "special-wrap")])]'
):
item_html = html.tostring(item, encoding="unicode")
if item.xpath('.//h3[@class="pt"]/a'):
result = _parse_results(item, item_html)
elif item.xpath('.//h3[contains(@class, "vr-title")]/a'):
result = _parse_results_with_image(item, item_html)
else:
continue
if result["title"] and result["url"]:
results.append(result)
return results
def _extract_url(url, item_html):
if url and url.startswith("/link?url="):
match = re.search(r'data-url="([^"]+)"', item_html)
if match:
return match.group(1)
return f"{base_url}{url}"
return url
def _parse_date(text):
if text:
text = text.strip().lstrip("-").strip()
date_match = re.search(r"(\d{4}-\d{1,2}-\d{1,2})", text)
if date_match:
try:
y, m, d = date_match.group(1).split("-")
return datetime(year=int(y), month=int(m), day=int(d))
except (ValueError, TypeError):
pass
return None
def _parse_results(item, item_html):
title = extract_text(item.xpath('.//h3[@class="pt"]/a'))
content = extract_text(item.xpath('.//div[@class="ft"]'))
url = _extract_url(extract_text(item.xpath('.//h3[@class="pt"]/a/@href')), item_html)
publishedDate = _parse_date(extract_text(item.xpath(".//cite")))
return {
"title": title,
"url": url,
"content": content,
"publishedDate": publishedDate,
}
def _parse_results_with_image(item, item_html):
title = extract_text(item.xpath('.//h3[contains(@class, "vr-title")]/a'))
content = extract_text(item.xpath('.//div[contains(@class, "attribute-centent")]'))
if not content:
content = extract_text(item.xpath('.//div[contains(@class, "fz-mid space-txt")]'))
url = _extract_url(extract_text(item.xpath('.//h3[contains(@class, "vr-title")]/a/@href')), item_html)
publishedDate = _parse_date(extract_text(item.xpath('.//span[@class="cite-date"]')))
thumbnail = None
try:
thumbnail_src = extract_text(item.xpath('.//div[contains(@class, "img-layout")]//img/@src'))
if thumbnail_src:
thumbnail = thumbnail_src.replace("http://", "https://")
except (ValueError, TypeError):
pass
return {
"title": title,
"url": url,
"content": content,
"publishedDate": publishedDate,
"thumbnail": thumbnail,
}
|
