Openclaw Cn 百度搜索

通过百度 AI 搜索 API 进行网页搜索，获取实时信息和搜索结果。

Security Scan

The skill's code, runtime instructions, and requested secret (BAIDU_API_KEY) align with its stated purpose of proxying Baidu AI web search; nothing in the package appears disproportionate or malicious.

Purpose & Capability

Name/description describe a Baidu web-search proxy and the package contains a FastAPI app that calls Baidu's qianfan web_search endpoint. The single required secret (BAIDU_API_KEY) is appropriate and declared as the primary credential. Requiring a 'uv' CLI is plausible given the SKILL.md uses that tool to manage venv and run uvicorn.

Instruction Scope

SKILL.md instructs creating a .env with BAIDU_API_KEY, building a venv, and running a local FastAPI server; the runtime steps and example curl calls match the service purpose. Minor notes: the validation error handler logs request bodies/errors (may record user queries to logs), and several example commands embed an absolute workspace path (/home/node/...), which is environment-specific but not harmful.

Install Mechanism

Install uses a Homebrew formula named 'uv' to provide the 'uv' binary. This is unusual for a Python FastAPI app (users often use pip/venv directly), but not inherently malicious. Users should verify the 'uv' formula source before installing (especially on non-macOS systems) to ensure it is the expected tool.

Credentials

Only BAIDU_API_KEY is required and used. No other credentials, system config paths, or unrelated environment variables are requested. The code reads OPENAPI_SERVER_URL for FastAPI server metadata but does not treat it as a secret.

Persistence & Privilege

The skill does not request always: true, does not modify other skills or system settings, and only runs a local server when the user elects to start it. Autonomous invocation defaults are unchanged (normal).

Assessment

This skill appears to do what it claims, but take these precautions before installing: (1) Only provide a Baidu API key you trust—treat BAIDU_API_KEY like any secret. (2) Verify the 'uv' Homebrew formula/source before installing (it is an unusual install path for a Python service). (3) When running the service, bind it to localhost and avoid exposing it publicly; example defaults use 127.0.0.1 but double-check any deployment. (4) Logs may include request bodies (queries/errors), so avoid sending sensitive secrets or PII in search queries or secure your logs. (5) If you plan to deploy to a server, store the API key in a secure secret store and restrict network access to Baidu endpoints only.

🔍 百度搜索

Search the web with Baidu AI

通过百度 AI 搜索 API 进行网页搜索，获取中文互联网的实时信息。

Setup

cd {baseDir}
echo "BAIDU_API_KEY=your-api-key" > .env
uv venv && uv pip install -e ".[dev]"
uv run --env-file .env uvicorn baidu_search.main:app --host 127.0.0.1 --port 8001

需要在 .env 或环境变量中设置 BAIDU_API_KEY。

获取 API Key

1. 访问 百度智能云控制台
2. 创建应用获取 API Key

启动服务 (推荐)

# 方法1: 直接使用 python -m uvicorn (推荐)
cd /home/node/.openclaw/workspace/skills/openclaw-cn-百度搜索
PYTHONPATH=src .venv/bin/python -m uvicorn baidu_search.main:app --host 127.0.0.1 --port 8001

# 后台运行
PYTHONPATH=src .venv/bin/python -m uvicorn baidu_search.main:app --host 127.0.0.1 --port 8001 &

快速启动 (已验证)

cd /home/node/.openclaw/workspace/skills/openclaw-cn-百度搜索
PYTHONPATH=src .venv/bin/python -m uvicorn baidu_search.main:app --host 127.0.0.1 --port 8001

⚠️ 注意：不要使用 source .venv/bin/activate (sh 环境不支持)，直接用绝对路径调用 .venv/bin/python

3. 带时间过滤的搜索:

curl -X POST http://127.0.0.1:8001/search \
  -H "Content-Type: application/json" \
  -d '{
    "query": "最新科技新闻",
    "top_k": 5,
    "recency_filter": "week"
  }'

4. 限定网站搜索:

curl -X POST http://127.0.0.1:8001/search \
  -H "Content-Type: application/json" \
  -d '{
    "query": "天气预报",
    "top_k": 5,
    "site_filter": ["www.weather.com.cn"]
  }'

API 参数

参数	类型	默认值	说明
query	string	必填	搜索关键词
top_k	int	10	返回结果数量 (1-20)
recency_filter	string	null	时间过滤: day, week, month, year
site_filter	list	null	限定搜索的网站列表

Response Format

{
  "results": [
    {
      "title": "北京十大必去景点",
      "url": "https://example.com/beijing-attractions",
      "snippet": "北京作为中国的首都，拥有众多著名景点...",
      "site_name": "旅游网"
    }
  ],
  "total": 10
}

Conversation Flow

1. 用户提问需要搜索的内容
2. 判断是否需要时间过滤（如"最新"、"今天"等）
3. 调用搜索 API 获取结果
4. 整理并展示相关信息
5. 可根据需要深入查看某个结果

使用场景

• 查询实时信息（新闻、天气、股票等）
• 搜索中文互联网内容
• 获取特定网站的信息
• 时效性要求高的查询

已修复问题

• 响应解析: 百度 API 返回数据在 references 字段而非 search_results
• 启动方式: 使用 PYTHONPATH=src .venv/bin/python -m uvicorn 而非直接调用 uvicorn