mirror of
https://github.com/searxng/searxng.git
synced 2025-08-02 18:12:21 +02:00
[feat] add Sogou WeChat article search support
This commit is contained in:
parent
97aa5a779b
commit
76f52b5b45
4 changed files with 88 additions and 3 deletions
75
searx/engines/sogou_wechat.py
Normal file
75
searx/engines/sogou_wechat.py
Normal file
|
@ -0,0 +1,75 @@
|
|||
# SPDX-License-Identifier: AGPL-3.0-or-later
|
||||
"""Sogou-WeChat search engine for retrieving WeChat Article from Sogou"""
|
||||
|
||||
from urllib.parse import urlencode
|
||||
from datetime import datetime
|
||||
import re
|
||||
from lxml import html
|
||||
|
||||
from searx.utils import extract_text
|
||||
|
||||
# Metadata
|
||||
about = {
|
||||
"website": "https://weixin.sogou.com/",
|
||||
"use_official_api": False,
|
||||
"require_api_key": False,
|
||||
"results": "HTML",
|
||||
}
|
||||
|
||||
# Engine Configuration
|
||||
categories = ["news"]
|
||||
paging = True
|
||||
|
||||
# Base URL
|
||||
base_url = "https://weixin.sogou.com"
|
||||
|
||||
|
||||
def request(query, params):
|
||||
query_params = {
|
||||
"query": query,
|
||||
"page": params["pageno"],
|
||||
"type": 2,
|
||||
}
|
||||
|
||||
params["url"] = f"{base_url}/weixin?{urlencode(query_params)}"
|
||||
return params
|
||||
|
||||
|
||||
def response(resp):
|
||||
dom = html.fromstring(resp.text)
|
||||
results = []
|
||||
|
||||
for item in dom.xpath('//li[contains(@id, "sogou_vr_")]'):
|
||||
title = extract_text(item.xpath('.//h3/a'))
|
||||
url = extract_text(item.xpath('.//h3/a/@href'))
|
||||
|
||||
if url.startswith("/link?url="):
|
||||
url = f"{base_url}{url}"
|
||||
|
||||
content = extract_text(item.xpath('.//p[@class="txt-info"]'))
|
||||
if not content:
|
||||
content = extract_text(item.xpath('.//p[contains(@class, "txt-info")]'))
|
||||
|
||||
thumbnail = extract_text(item.xpath('.//div[@class="img-box"]/a/img/@src'))
|
||||
if thumbnail and thumbnail.startswith("//"):
|
||||
thumbnail = f"https:{thumbnail}"
|
||||
|
||||
published_date = None
|
||||
timestamp = extract_text(item.xpath('.//script[contains(text(), "timeConvert")]'))
|
||||
if timestamp:
|
||||
match = re.search(r"timeConvert\('(\d+)'\)", timestamp)
|
||||
if match:
|
||||
published_date = datetime.fromtimestamp(int(match.group(1)))
|
||||
|
||||
if title and url:
|
||||
results.append(
|
||||
{
|
||||
"title": title,
|
||||
"url": url,
|
||||
"content": content,
|
||||
'thumbnail': thumbnail,
|
||||
"publishedDate": published_date,
|
||||
}
|
||||
)
|
||||
|
||||
return results
|
Loading…
Add table
Add a link
Reference in a new issue