[feat] add Sogou WeChat article search support

searx/engines/sogou.py

@@ -18,7 +18,6 @@ about = {
 # Engine Configuration
 categories = ["general"]
 paging = True
-max_page = 10
 time_range_support = True
 
 time_range_dict = {'day': 'inttime_day', 'week': 'inttime_week', 'month': 'inttime_month', 'year': 'inttime_year'}

searx/engines/sogou_images.py

@@ -3,7 +3,7 @@
 
 import json
 import re
-from urllib.parse import quote_plus
+from urllib.parse import urlencode
 
 # about
 about = {
@@ -16,12 +16,18 @@ about = {
 
 # engine dependent config
 categories = ["images"]
+paging = True
 
 base_url = "https://pic.sogou.com"
 
 
 def request(query, params):
-    params["url"] = f"{base_url}/pics?query={quote_plus(query)}"
+    query_params = {
+        "query": query,
+        "start": (params["pageno"] - 1) * 48,
+    }
+
+    params["url"] = f"{base_url}/pics?{urlencode(query_params)}"
     return params
 
 

searx/engines/sogou_wechat.py

@@ -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

searx/settings.yml

@@ -1726,6 +1726,11 @@ engines:
     shortcut: sogouv
     disabled: true
 
+  - name: sogou wechat
+    engine: sogou_wechat
+    shortcut: sogouw
+    disabled: true
+
   - name: soundcloud
     engine: soundcloud
     shortcut: sc