mirror of
https://github.com/searxng/searxng.git
synced 2026-07-17 21:41:24 +00:00
9e25585aec
Refactor engines that parse ISO 8601 dates with strptime to use
fromisoformat instead. In most cases this is a direct replacement of
strptime(text, "format") with fromisoformat(text).
For engines where the source has a trailing "Z" that strptime consumed
as a literal (e.g. "%Y-%m-%dT%H:%M:%S.%fZ" in huggingface.py), add
rstrip("Z") to keep the output naive and preserve the existing behavior.
In sogou.py the date is extracted with a regular expression, which can
yield strings like "2026-7-11". strptime accepts this via its format
string, but fromisoformat does not. To preserve the existing behavior
and satisfy the format fromisoformat expects, add zero-padding for the
month and day.
Closes: #6098
---------
Signed-off-by: OneVth <onebrotravel@gmail.com>
82 lines
2.2 KiB
Python
82 lines
2.2 KiB
Python
# 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.fromisoformat(entry['date'])
|
|
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
|