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
|
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Sogou-Videos: A search engine for retrieving videos from Sogou."""
from urllib.parse import urlencode
from datetime import datetime, timedelta
from searx.exceptions import SearxEngineAPIException
about = {
"website": "https://v.sogou.com/",
"use_official_api": False,
"require_api_key": False,
"results": "JSON",
"language": "zh",
}
categories = ["videos"]
paging = True
results_per_page = 10
# Base URL
base_url = "https://v.sogou.com"
def request(query, params):
query_params = {
"page": params["pageno"],
"pagesize": 10,
"query": query,
}
params["url"] = f"{base_url}/api/video/shortVideoV2?{urlencode(query_params)}"
return params
def response(resp):
try:
data = resp.json()
except Exception as e:
raise SearxEngineAPIException(f"Invalid response: {e}") from e
results = []
if not data.get("data", {}).get("list"):
raise SearxEngineAPIException("Invalid response")
for entry in data["data"]["list"]:
if not entry.get("titleEsc") or not entry.get("url"):
continue
video_url = entry.get("url")
if video_url.startswith("/vc/np"):
video_url = f"{base_url}{video_url}"
published_date = None
if entry.get("date") and entry.get("duration"):
try:
published_date = datetime.strptime(entry['date'], "%Y-%m-%d")
except (ValueError, TypeError):
published_date = None
length = None
if entry.get("date") and entry.get("duration"):
try:
timediff = datetime.strptime(entry['duration'], "%M:%S")
length = timedelta(minutes=timediff.minute, seconds=timediff.second)
except (ValueError, TypeError):
length = None
results.append(
{
'url': video_url,
'title': entry["titleEsc"],
'content': entry['site'],
'length': length,
'template': 'videos.html',
'publishedDate': published_date,
'thumbnail': entry["picurl"],
}
)
return results
|
