mirror of
https://github.com/searxng/searxng.git
synced 2026-06-16 06:46:52 +02:00
Markus Heiser
6c9dcd4242
Drop outdated engine attributes: supported_languages, language_aliases Complete, normalize and document the type definitions for the engine-module and engine-class. For the ``engine.about`` section of the configuration, a type check is performed based on structure ``searx.enginelib.EngineAbout``. The property ``engine.about.language`` no longer exists; existing values have been migrated to ``engine.language``. Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
77 lines
2.0 KiB
Python
77 lines
2.0 KiB
Python
# 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",
|
|
}
|
|
language = "zh"
|
|
|
|
# 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
|