++

skills/searxng_skills/SKILL.md

@@ -0,0 +1,71 @@
+---
+name: searxng_skills
+description: Search the live web via Jack's self-hosted SearXNG (https://searxng.erhe.top) using token-authenticated JSON output. Use when the agent needs current pricing/news/docs/product specs without invoking browser tools.
+---
+
+# SearXNG Web Search (Jack's server)
+
+Search the live web through Jack's self-hosted SearXNG. 129 engines enabled (bing / duckduckgo / startpage / brave / mojeek / qwant / wikipedia 系 / etc.). Google main engine is OFF; google scholar/images/videos/news/cse sub-APIs are enabled.
+
+## Endpoint
+
+- **URL**: `https://searxng.erhe.top`  ⚠ `erhe.top`, **NOT** `ehre.top`
+- **Token**: `fGWEFWGrgasegtjt1jUJG` (passed as `?token=...` query param)
+- **Method**: GET works here. (Local docker 2026.7 default is `server.method=POST` — different; if porting code to a stock local SearXNG, flip to POST.)
+- **JSON 200**: This server has limiter/token auth configured, so `?format=json&token=...` returns 200. Stock local docker returns 403 unconditionally on JSON — different from this.
+
+## Quick start
+
+CLI (preferred; auto-renders results):
+
+```bash
+python3 ~/.hermes/skills/searxng_skills/searxng_search.py "<query>" -m 5 -l en
+```
+
+Direct API (works fine from any script):
+
+```python
+import urllib.request, urllib.parse, json
+url = "https://searxng.erhe.top/search?" + urllib.parse.urlencode({
+    "q": "<query>", "format": "json", "token": "fGWEFWGrgasegtjt1jUJG",
+})
+data = json.loads(urllib.request.urlopen(url, timeout=30).read())
+for r in data.get("results", [])[:5]:
+    print(r["engine"], r["title"][:80], "→", r["url"])
+```
+
+## Response shape
+
+JSON: `{results: [...], unresponsive_engines: [...], suggestions: [...], query: ...}`
+Each result: `title, url, content, host, engine, score, type, publishedDate (optional)`.
+
+Alternative formats:
+- `?format=csv` → CSV with columns `title,url,content,host,engine,score,type` (great for scripts)
+- `?format=rss` → RSS 2.0 feed
+
+## Pitfalls
+
+- **Domain typo is the #1 way to silently break this skill**. `searxng.erhe.top` ≠ `searxng.erhe.top`. Jack's `docker-compose.yaml` says `ehre.top`; the live deployment is `erhe.top`. If `Could not resolve host` / DNS `NXDOMAIN`, double-check the spelling — almost certainly an `h`/`r` swap.
+- **JSON endpoint requires the token**. Without `?token=...`, returns 403. Token is rotated by changing `SEARXNG_API_KEY` env in docker-compose; no code redeploy needed.
+- **Google main engine is OFF**. `google.com` is blocked at upstream (Cloudflare anti-bot). Only `google_scholar` / `google_images` / `google_videos` / `google_news` / `google_cse` are enabled. If the user says "用 google 搜 XX", expect mostly bing/duckduckgo results — be honest about it rather than silently re-routing.
+- **LibreSSL/OpenSSL warning from urllib3 v2** is harmless on macOS Python 3.9. `urllib3 v2 only supports OpenSSL 1.1.1+, but the 'ssl' module is compiled with LibreSSL`. The search still runs to completion; ignore the warning, do not reinstall.
+- **SEO content farm pollution**. DuckDuckGo heavily surfaces AI-generated SEO blogs (llmmac / meshmac / neokvm / vulcloud / maccompute). For pricing/spec verification, filter by `host` to `apple.com`, `wikipedia.org`, `*.edu`, `github.com`, `arxiv.org`, `*.gov`. Don't blindly trust first-page blog links for actual prices.
+- **brave / mojeek / qwant commonly time out** (server logs show them in `unresponsive_engines`). Real workhorses: bing, duckduckgo, startpage, wikipedia 系, github 系.
+
+## CLI flags (for `searxng_search.py`)
+
+| Flag | Meaning |
+|---|---|
+| `-m N` / `--max-results N` | Result row limit (default 10) |
+| `-l LANG` | `auto` / `zh` / `en` / `ja` / `de` / `fr` |
+| `-c CAT` | `general` / `images` / `videos` / `news` / `music` |
+| `--time-range` | `day` / `week` / `month` / `year` |
+| `--safesearch` | `0` / `1` / `2` |
+| `--raw` | Print raw JSON |
+| `-v` / `--verbose` | Verbose per-result output |
+
+## Companion docs in this folder
+
+- `searxng_skills.md` — full API reference (more endpoints)
+- `searxng_README.md` — quickstart (Chinese)
+- `searxng_search.py` — the CLI entry; can also be imported as a module

skills/searxng_skills/searxng_README.md

@@ -0,0 +1,194 @@
+# SearXNG API 使用指南
+
+## 快速开始
+
+### Python 脚本方式
+
+```bash
+# 安装依赖 (如需要)
+pip3 install requests
+
+# 搜索示例
+python3 /tmp/searxng_search.py "python教程"
+
+# 指定分类
+python3 /tmp/searxng_search.py "猫咪图片" -c images
+
+# 指定时间范围
+python3 /tmp/searxng_search.py "科技新闻" --time-range week
+
+# 输出 JSON
+python3 /tmp/searxng_search.py "python" --raw
+```
+
+### cURL 方式
+
+```bash
+# 基础搜索
+curl "https://searxng.erhe.top/search?q=关键词&token=fGWEFWGrgasegtjt1jUJG"
+
+# JSON 格式
+curl "https://searxng.erhe.top/search?q=关键词&format=json&token=fGWEFWGrgasegtjt1jUJG"
+```
+
+### Python 代码方式
+
+```python
+import requests
+
+def search(query):
+    response = requests.get(
+        "https://searxng.erhe.top/search",
+        params={
+            "q": query,
+            "format": "json",
+            "token": "fGWEFWGrgasegtjt1jUJG"
+        }
+    )
+    return response.json()
+
+# 使用
+results = search("python教程")
+for r in results['results'][:5]:
+    print(r['title'], r['url'])
+```
+
+## 常用命令参考
+
+| 用途 | 命令 |
+|------|------|
+| 基础搜索 | `python3 /tmp/searxng_search.py "关键词"` |
+| 图片搜索 | `python3 /tmp/searxng_search.py "关键词" -c images` |
+| 视频搜索 | `python3 /tmp/searxng_search.py "关键词" -c videos` |
+| 中文结果 | `python3 /tmp/searxng_search.py "关键词" -l zh` |
+| 最近一周 | `python3 /tmp/searxng_search.py "关键词" -t week` |
+| 限制结果数 | `python3 /tmp/searxng_search.py "关键词" -m 20` |
+| 原始 JSON | `python3 /tmp/searxng_search.py "关键词" --raw` |
+| 查看帮助 | `python3 /tmp/searxng_search.py --help` |
+
+## Agent 集成示例
+
+### Claude Code 工具定义
+
+```json
+{
+  "name": "searxng_search",
+  "description": "使用 SearXNG 隐私搜索引擎进行网络搜索",
+  "input_schema": {
+    "type": "object",
+    "properties": {
+      "query": {
+        "type": "string",
+        "description": "搜索关键词"
+      },
+      "category": {
+        "type": "string",
+        "enum": ["general", "images", "videos", "news", "music"],
+        "description": "搜索分类"
+      },
+      "language": {
+        "type": "string",
+        "default": "auto",
+        "description": "语言代码"
+      },
+      "max_results": {
+        "type": "integer",
+        "default": 10,
+        "description": "最大结果数"
+      }
+    },
+    "required": ["query"]
+  }
+}
+```
+
+### Python 工具实现
+
+```python
+def searxng_search_tool(query, category="general", language="auto", max_results=10):
+    """
+    SearXNG 搜索工具
+    """
+    try:
+        response = requests.get(
+            "https://searxng.erhe.top/search",
+            params={
+                "q": query,
+                "format": "json",
+                "token": "fGWEFWGrgasegtjt1jUJG",
+                "language": language,
+                "categories": category if category != "general" else None
+            },
+            timeout=15
+        )
+        
+        if response.status_code == 200:
+            data = response.json()
+            results = []
+            
+            for r in data.get('results', [])[:max_results]:
+                results.append({
+                    "title": r.get('title', ''),
+                    "url": r.get('url', ''),
+                    "snippet": r.get('content', '')[:200],
+                    "source": r.get('engine', '')
+                })
+            
+            return {
+                "success": True,
+                "query": data.get('query', query),
+                "count": len(results),
+                "results": results
+            }
+        else:
+            return {
+                "success": False,
+                "error": f"HTTP {response.status_code}"
+            }
+            
+    except Exception as e:
+        return {
+            "success": False,
+            "error": str(e)
+        }
+
+# 使用示例
+result = searxng_search_tool("如何安装Python", max_results=5)
+if result['success']:
+    for r in result['results']:
+        print(f"📄 {r['title']}\n   {r['url']}\n")
+```
+
+## 完整文档
+
+查看详细文档: `cat /tmp/searxng_skills.md`
+
+## 测试
+
+```bash
+# 测试脚本
+python3 /tmp/searxng_search.py "test" -m 3
+
+# 测试 cURL
+curl -s "https://searxng.erhe.top/search?q=test&format=json&token=fGWEFWGrgasegtjt1jUJG" | head -20
+```
+
+## 故障排除
+
+### 常见问题
+
+1. **Token 错误 403**
+   - 确保请求中包含 `token=fGWEFWGrgasegtjt1jUJG`
+
+2. **连接超时**
+   - 检查网络连接
+   - 尝试增加超时时间
+
+3. **结果为空**
+   - 尝试更换关键词
+   - 检查语言设置
+
+### 获取帮助
+
+- 查看详细文档: `/tmp/searxng_skills.md`
+- 查看脚本帮助: `python3 /tmp/searxng_search.py --help`

skills/searxng_skills/searxng_search.py

@@ -0,0 +1,184 @@
+#!/usr/bin/env python3
+"""
+SearXNG API 客户端 - 快速搜索工具
+"""
+
+import requests
+import json
+import sys
+import argparse
+from urllib.parse import urlencode
+
+# 配置
+SEARXNG_URL = "https://searxng.erhe.top"
+API_TOKEN = "fGWEFWGrgasegtjt1jUJG"
+
+def search(query, 
+           format_type="json",
+           categories=None,
+           language="auto",
+           safesearch=0,
+           time_range=None,
+           max_results=10):
+    """
+    搜索函数
+    
+    参数:
+        query: 搜索关键词
+        format_type: 返回格式 (json/html/csv/rss)
+        categories: 分类 (images/videos/news/music/general)
+        language: 语言代码 (auto/zh/en/ja/de/fr)
+        safesearch: 安全搜索级别 (0=关闭, 1=适中, 2=严格)
+        time_range: 时间范围 (day/week/month/year)
+        max_results: 最大结果数
+    
+    返回:
+        dict: 搜索结果
+    """
+    params = {
+        "q": query,
+        "format": format_type,
+        "token": API_TOKEN,
+        "language": language,
+        "safesearch": safesearch
+    }
+    
+    if categories:
+        params["categories"] = categories
+    
+    if time_range:
+        params["time_range"] = time_range
+    
+    try:
+        response = requests.get(
+            f"{SEARXNG_URL}/search",
+            params=params,
+            timeout=15
+        )
+        
+        if response.status_code == 200:
+            if format_type == "json":
+                return response.json()
+            else:
+                return {"html": response.text}
+        elif response.status_code == 403:
+            return {"error": "API token 无效或缺失"}
+        else:
+            return {"error": f"请求失败: {response.status_code}"}
+            
+    except requests.exceptions.Timeout:
+        return {"error": "请求超时"}
+    except requests.exceptions.ConnectionError:
+        return {"error": "连接失败，请检查网络"}
+    except Exception as e:
+        return {"error": str(e)}
+
+def print_results(results, max_results=10, verbose=False):
+    """格式化输出结果"""
+    if "error" in results:
+        print(f"❌ 错误: {results['error']}")
+        return
+    
+    query = results.get('query', '未知')
+    results_list = results.get('results', [])
+    unresponsive = results.get('unresponsive_engines', [])
+    
+    print(f"\n{'='*70}")
+    print(f"🔍 查询: {query}")
+    print(f"📊 找到 {len(results_list)} 个结果")
+    if unresponsive:
+        print(f"⚠️  部分搜索引擎失败: {', '.join([u[0] for u in unresponsive[:3]])}")
+    print(f"{'='*70}\n")
+    
+    for i, result in enumerate(results_list[:max_results], 1):
+        title = result.get('title', '无标题')
+        url = result.get('url', '无链接')
+        content = result.get('content', '')
+        engine = result.get('engine', '未知')
+        published = result.get('publishedDate', '')
+        
+        print(f"{i:2d}. {title}")
+        print(f"    🔗 {url}")
+        
+        if content:
+            # 截断内容
+            if len(content) > 150:
+                content = content[:150] + "..."
+            print(f"    📝 {content}")
+        
+        print(f"    ⚙️  来源: {engine}", end="")
+        if published:
+            print(f" | 📅 {published}", end="")
+        print("\n")
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="SearXNG 搜索工具",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+示例:
+  %(prog)s python 教程
+  %(prog)s "machine learning" --category videos
+  %(prog)s linux --language en --time-range week
+  %(prog)s python --max-results 20 --verbose
+        """
+    )
+    
+    parser.add_argument('query', nargs='+', help='搜索关键词')
+    parser.add_argument('-c', '--category', 
+                       choices=['general', 'images', 'videos', 'news', 'music', 'files', 'it', 'science'],
+                       default='general',
+                       help='搜索分类 (默认: general)')
+    parser.add_argument('-l', '--language',
+                       default='auto',
+                       help='语言代码 (默认: auto)')
+    parser.add_argument('-s', '--safesearch',
+                       type=int, choices=[0, 1, 2], default=0,
+                       help='安全搜索: 0=关闭, 1=适中, 2=严格 (默认: 0)')
+    parser.add_argument('-t', '--time-range',
+                       choices=['day', 'week', 'month', 'year'],
+                       help='时间范围')
+    parser.add_argument('-m', '--max-results',
+                       type=int, default=10,
+                       help='最大结果数 (默认: 10)')
+    parser.add_argument('-v', '--verbose',
+                       action='store_true',
+                       help='详细输出')
+    parser.add_argument('--format',
+                       choices=['json', 'html', 'csv', 'rss'],
+                       default='json',
+                       help='返回格式 (默认: json)')
+    parser.add_argument('--raw',
+                       action='store_true',
+                       help='输出原始 JSON')
+    
+    args = parser.parse_args()
+    
+    # 组合查询词
+    query = ' '.join(args.query)
+    
+    # 执行搜索
+    results = search(
+        query,
+        format_type=args.format,
+        categories=args.category if args.category != 'general' else None,
+        language=args.language,
+        safesearch=args.safesearch,
+        time_range=args.time_range,
+        max_results=args.max_results
+    )
+    
+    # 输出结果
+    if args.raw:
+        print(json.dumps(results, indent=2, ensure_ascii=False))
+    else:
+        print_results(results, max_results=args.max_results, verbose=args.verbose)
+        
+        # 如果有建议搜索词
+        if 'suggestions' in results and results['suggestions']:
+            print(f"💡 你可能想搜索:")
+            for suggestion in results['suggestions']:
+                print(f"   - {suggestion}")
+
+if __name__ == "__main__":
+    main()

skills/searxng_skills/searxng_skills.md

@@ -0,0 +1,330 @@
+# SearXNG API Skills
+
+## 基本信息
+
+- **URL**: `https://searxng.erhe.top`
+- **API Token**: `fGWEFWGrgasegtjt1jUJG`
+- **端口**: 通过 Caddy 反向代理
+
+## API 调用方法
+
+### 1. 搜索 API
+
+```bash
+# 基础搜索
+curl "https://searxng.erhe.top/search?q=关键词&token=fGWEFWGrgasegtjt1jUJG"
+
+# JSON 格式返回（推荐）
+curl "https://searxng.erhe.top/search?q=关键词&format=json&token=fGWEFWGrgasegtjt1jUJG"
+```
+
+### 2. Python 调用示例
+
+```python
+import requests
+import json
+
+def search_searxng(query, format_type="json"):
+    """
+    使用 SearXNG 搜索
+    
+    参数:
+        query: 搜索关键词
+        format_type: 返回格式 (json/html/csv/rss)
+    
+    返回:
+        dict: 搜索结果
+    """
+    url = "https://searxng.erhe.top/search"
+    params = {
+        "q": query,
+        "format": format_type,
+        "token": "fGWEFWGrgasegtjt1jUJG"
+    }
+    
+    response = requests.get(url, params=params)
+    
+    if format_type == "json":
+        return response.json()
+    else:
+        return response.text
+
+# 使用示例
+results = search_searxng("python 教程")
+print(f"找到 {len(results['results'])} 个结果")
+for result in results['results'][:5]:
+    print(f"- {result['title']}: {result['url']}")
+```
+
+### 3. Claude Code / Agent 调用示例
+
+```python
+import urllib.request
+import urllib.parse
+import json
+
+def search(query):
+    """搜索函数"""
+    base_url = "https://searxng.erhe.top/search"
+    params = urllib.parse.urlencode({
+        "q": query,
+        "format": "json",
+        "token": "fGWEFWGrgasegtjt1jUJG"
+    })
+    
+    url = f"{base_url}?{params}"
+    
+    with urllib.request.urlopen(url) as response:
+        data = json.loads(response.read().decode())
+        
+    return data
+
+# Agent 中使用
+results = search("如何在 Linux 中查找文件")
+for r in results['results'][:3]:
+    print(f"标题: {r['title']}")
+    print(f"链接: {r['url']}\n")
+```
+
+## 高级搜索
+
+### 1. 指定语言
+
+```bash
+curl "https://searxng.erhe.top/search?q=关键词&format=json&token=fGWEFWGrgasegtjt1jUJG&language=zh"
+```
+
+语言代码:
+- `zh` - 中文
+- `en` - 英文
+- `ja` - 日文
+- `de` - 德文
+- `fr` - 法文
+
+### 2. 指定分类
+
+```bash
+# 图片搜索
+curl "https://searxng.erhe.top/search?q=猫&format=json&token=fGWEFWGrgasegtjt1jUJG&categories=images"
+
+# 视频搜索
+curl "https://searxng.erhe.top/search?q=教程&format=json&token=fGWEFWGrgasegtjt1jUJG&categories=videos"
+
+# 新闻搜索
+curl "https://searxng.erhe.top/search?q=科技&format=json&token=fGWEFWGrgasegtjt1jUJG&categories=news"
+```
+
+分类列表:
+- `general` - 通用
+- `images` - 图片
+- `videos` - 视频
+- `news` - 新闻
+- `music` - 音乐
+- `files` - 文件
+- `it` - IT
+- `science` - 科学
+
+### 3. 安全搜索
+
+```bash
+# 关闭安全搜索 (0)
+curl "https://searxng.erhe.top/search?q=关键词&format=json&token=fGWEFWGrgasegtjt1jUJG&safesearch=0"
+
+# 适中 (1)
+curl "https://searxng.erhe.top/search?q=关键词&format=json&token=fGWEFWGrgasegtjt1jUJG&safesearch=1"
+
+# 严格 (2)
+curl "https://searxng.erhe.top/search?q=关键词&format=json&token=fGWEFWGrgasegtjt1jUJG&safesearch=2"
+```
+
+### 4. 时间范围
+
+```bash
+# 最近一天
+curl "https://searxng.erhe.top/search?q=关键词&format=json&token=fGWEFWGrgasegtjt1jUJG&time_range=day"
+
+# 最近一周
+curl "https://searxng.erhe.top/search?q=关键词&format=json&token=fGWEFWGrgasegtjt1jUJG&time_range=week"
+
+# 最近一月
+curl "https://searxng.erhe.top/search?q=关键词&format=json&token=fGWEFWGrgasegtjt1jUJG&time_range=month"
+
+# 最近一年
+curl "https://searxng.erhe.top/search?q=关键词&format=json&token=fGWEFWGrgasegtjt1jUJG&time_range=year"
+```
+
+## JSON 返回格式说明
+
+```json
+{
+  "query": "搜索关键词",
+  "results": [
+    {
+      "title": "结果标题",
+      "url": "https://example.com",
+      "content": "结果摘要",
+      "engine": "搜索引擎名称",
+      "template": "模板类型",
+      "publishedDate": "发布日期 (如果有)",
+      "img_src": "图片URL (如果有)",
+      "thumbnail": "缩略图URL (如果有)",
+      "category": "分类"
+    }
+  ],
+  "answers": [],
+  "corrections": [],
+  "infoboxes": [],
+  "suggestions": ["建议搜索词"],
+  "unresponsive_engines": []
+}
+```
+
+## 获取配置信息
+
+```bash
+# 获取 SearXNG 配置
+curl "https://searxng.erhe.top/config&token=fGWEFWGrgasegtjt1jUJG"
+```
+
+## 完整 Python 示例
+
+```python
+#!/usr/bin/env python3
+"""
+SearXNG API 客户端示例
+"""
+
+import requests
+import json
+import sys
+
+SEARXNG_URL = "https://searxng.erhe.top"
+API_TOKEN = "fGWEFWGrgasegtjt1jUJG"
+
+def search(query, 
+            format_type="json",
+            categories=None,
+            language="auto",
+            safesearch=0,
+            time_range=None):
+    """
+    搜索函数
+    
+    参数:
+        query: 搜索关键词
+        format_type: 返回格式 (json/html/csv/rss)
+        categories: 分类列表 (images/videos/news/music)
+        language: 语言代码 (auto/zh/en/ja/de/fr)
+        safesearch: 安全搜索级别 (0/1/2)
+        time_range: 时间范围 (day/week/month/year)
+    
+    返回:
+        dict: 搜索结果
+    """
+    params = {
+        "q": query,
+        "format": format_type,
+        "token": API_TOKEN,
+        "language": language,
+        "safesearch": safesearch
+    }
+    
+    if categories:
+        params["categories"] = categories
+    
+    if time_range:
+        params["time_range"] = time_range
+    
+    response = requests.get(f"{SEARXNG_URL}/search", params=params)
+    
+    if format_type == "json":
+        return response.json()
+    else:
+        return response.text
+
+def format_results(results, max_results=10):
+    """格式化输出结果"""
+    print(f"\n{'='*60}")
+    print(f"查询: {results.get('query')}")
+    print(f"找到 {len(results.get('results', []))} 个结果")
+    print(f"{'='*60}\n")
+    
+    for i, result in enumerate(results.get('results', [])[:max_results], 1):
+        print(f"{i}. {result.get('title', '无标题')}")
+        print(f"   链接: {result.get('url', '无链接')}")
+        if result.get('content'):
+            content = result.get('content', '')[:150]
+            print(f"   摘要: {content}...")
+        print(f"   来源: {result.get('engine', '未知')}")
+        print()
+
+if __name__ == "__main__":
+    # 示例搜索
+    if len(sys.argv) > 1:
+        query = " ".join(sys.argv[1:])
+    else:
+        query = "Python 编程"
+    
+    try:
+        results = search(query, categories="general")
+        format_results(results)
+    except Exception as e:
+        print(f"搜索失败: {e}")
+```
+
+## 错误处理
+
+```python
+import requests
+
+def safe_search(query):
+    """安全的搜索函数，包含错误处理"""
+    try:
+        response = requests.get(
+            "https://searxng.erhe.top/search",
+            params={
+                "q": query,
+                "format": "json",
+                "token": "fGWEFWGrgasegtjt1jUJG"
+            },
+            timeout=10
+        )
+        
+        if response.status_code == 200:
+            return response.json()
+        elif response.status_code == 403:
+            return {"error": "API token 无效或缺失"}
+        else:
+            return {"error": f"请求失败: {response.status_code}"}
+            
+    except requests.exceptions.Timeout:
+        return {"error": "请求超时"}
+    except requests.exceptions.ConnectionError:
+        return {"error": "连接失败，请检查网络"}
+    except Exception as e:
+        return {"error": str(e)}
+```
+
+## 快速参考
+
+| 功能 | 命令 |
+|------|------|
+| 基础搜索 | `curl "https://searxng.erhe.top/search?q=关键词&token=fGWEFWGrgasegtjt1jUJG"` |
+| JSON 返回 | 添加 `&format=json` |
+| 图片搜索 | 添加 `&categories=images` |
+| 中文结果 | 添加 `&language=zh` |
+| 最近一周 | 添加 `&time_range=week` |
+| 获取配置 | `curl "https://searxng.erhe.top/config&token=fGWEFWGrgasegtjt1jUJG"` |
+
+## 注意事项
+
+1. **Token 必须**: 所有 API 请求必须包含 `token` 参数
+2. **返回格式**: 推荐使用 `format=json` 获取结构化数据
+3. **超时处理**: 搜索可能需要几秒钟，建议设置超时
+4. **请求频率**: 避免过于频繁的请求，可能触发限制
+5. **结果数量**: 默认返回多个搜索引擎的结果
+
+## 获取帮助
+
+- SearXNG 主页: `https://searxng.erhe.top`
+- SearXNG 文档: `https://docs.searxng.org`