From 08d08475fc555bcb6dd272b67680097ac5829714 Mon Sep 17 00:00:00 2001
From: Zhijie He <hezhijie0327@hotmail.com>
Date: Tue, 4 Mar 2025 21:55:17 +0800
Subject: [PATCH] [feat] engines: add www.chinaso.com

Co-authored-by: Bnyro <bnyro@tutanota.com>
---
 searx/engines/chinaso.py | 142 +++++++++++++++++++++++++++++++++++++++
 searx/settings.yml       |  18 +++++
 2 files changed, 160 insertions(+)
 create mode 100644 searx/engines/chinaso.py

diff --git a/searx/engines/chinaso.py b/searx/engines/chinaso.py
new file mode 100644
index 000000000..509006aa3
--- /dev/null
+++ b/searx/engines/chinaso.py
@@ -0,0 +1,142 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""ChinaSo: A search engine from ChinaSo."""
+
+from urllib.parse import urlencode
+from datetime import datetime
+
+from searx.exceptions import SearxEngineAPIException
+from searx.utils import html_to_text
+
+about = {
+    "website": "https://www.chinaso.com/",
+    "wikidata_id": "Q10846064",
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "JSON",
+}
+
+paging = True
+time_range_support = True
+results_per_page = 10
+categories = []
+chinaso_category = 'news'
+"""ChinaSo supports news, videos, images search.
+
+- ``news``: search for news
+- ``videos``: search for videos
+- ``images``: search for images
+"""
+
+time_range_dict = {'day': '24h', 'week': '1w', 'month': '1m', 'year': '1y'}
+
+base_url = "https://www.chinaso.com"
+
+
+def init(_):
+    if chinaso_category not in ('news', 'videos', 'images'):
+        raise SearxEngineAPIException(f"Unsupported category: {chinaso_category}")
+
+
+def request(query, params):
+    query_params = {"q": query}
+
+    if time_range_dict.get(params['time_range']):
+        query_params["stime"] = time_range_dict[params['time_range']]
+        query_params["etime"] = 'now'
+
+    category_config = {
+        'news': {'endpoint': '/v5/general/v1/web/search', 'params': {'pn': params["pageno"], 'ps': results_per_page}},
+        'images': {
+            'endpoint': '/v5/general/v1/search/image',
+            'params': {'start_index': (params["pageno"] - 1) * results_per_page, 'rn': results_per_page},
+        },
+        'videos': {
+            'endpoint': '/v5/general/v1/search/video',
+            'params': {'start_index': (params["pageno"] - 1) * results_per_page, 'rn': results_per_page},
+        },
+    }
+
+    query_params.update(category_config[chinaso_category]['params'])
+
+    params["url"] = f"{base_url}{category_config[chinaso_category]['endpoint']}?{urlencode(query_params)}"
+
+    return params
+
+
+def response(resp):
+    try:
+        data = resp.json()
+    except Exception as e:
+        raise SearxEngineAPIException(f"Invalid response: {e}") from e
+
+    parsers = {'news': parse_news, 'images': parse_images, 'videos': parse_videos}
+
+    return parsers[chinaso_category](data)
+
+
+def parse_news(data):
+    results = []
+    if not data.get("data", {}).get("data"):
+        raise SearxEngineAPIException("Invalid response")
+
+    for entry in data["data"]["data"]:
+        published_date = None
+        if entry.get("timestamp"):
+            try:
+                published_date = datetime.fromtimestamp(int(entry["timestamp"]))
+            except (ValueError, TypeError):
+                pass
+
+        results.append(
+            {
+                'title': html_to_text(entry["title"]),
+                'url': entry["url"],
+                'content': html_to_text(entry["snippet"]),
+                'publishedDate': published_date,
+            }
+        )
+    return results
+
+
+def parse_images(data):
+    results = []
+    if not data.get("data", {}).get("arrRes"):
+        raise SearxEngineAPIException("Invalid response")
+
+    for entry in data["data"]["arrRes"]:
+        results.append(
+            {
+                'url': entry["web_url"],
+                'title': html_to_text(entry["title"]),
+                'content': html_to_text(entry["ImageInfo"]),
+                'template': 'images.html',
+                'img_src': entry["url"].replace("http://", "https://"),
+                'thumbnail_src': entry["largeimage"].replace("http://", "https://"),
+            }
+        )
+    return results
+
+
+def parse_videos(data):
+    results = []
+    if not data.get("data", {}).get("arrRes"):
+        raise SearxEngineAPIException("Invalid response")
+
+    for entry in data["data"]["arrRes"]:
+        published_date = None
+        if entry.get("VideoPubDate"):
+            try:
+                published_date = datetime.fromtimestamp(int(entry["VideoPubDate"]))
+            except (ValueError, TypeError):
+                pass
+
+        results.append(
+            {
+                'url': entry["url"],
+                'title': html_to_text(entry["raw_title"]),
+                'template': 'videos.html',
+                'publishedDate': published_date,
+                'thumbnail': entry["image_src"].replace("http://", "https://"),
+            }
+        )
+    return results
diff --git a/searx/settings.yml b/searx/settings.yml
index 6aafaeb63..8a5069736 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -573,6 +573,24 @@ engines:
     # to show premium or plus results too:
     # skip_premium: false
 
+  - name: chinaso news
+    chinaso_category: news
+    engine: chinaso
+    shortcut: chinaso
+    disabled: true
+
+  - name: chinaso images
+    chinaso_category: images
+    engine: chinaso
+    shortcut: chinasoi
+    disabled: true
+
+  - name: chinaso videos
+    chinaso_category: videos
+    engine: chinaso
+    shortcut: chinasov
+    disabled: true
+
   - name: cloudflareai
     engine: cloudflareai
     shortcut: cfai