{
  "skill_name": "researcher",
  "description": "深度研究技能爬取配置",
  "data_sources": [
    {
      "name": "维基百科 API",
      "type": "api",
      "base_url": "https://zh.wikipedia.org/w/api.php",
      "endpoints": [
        {
          "path": "/w/api.php",
          "method": "GET",
          "params": {
            "action": "query",
            "prop": "extracts|info|images",
            "exintro": true,
            "explaintext": true,
            "format": "json",
            "titles": "{query}"
          }
        }
      ],
      "headers": {
        "User-Agent": "LemonAI-Hunter/1.0 (research purpose)"
      },
      "rate_limit": {
        "requests_per_second": 2,
        "delay_ms": 500
      }
    },
    {
      "name": "百度百科",
      "type": "web",
      "base_url": "https://baike.baidu.com",
      "endpoints": [
        {
          "path": "/item/{query}",
          "method": "GET"
        }
      ],
      "headers": {
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36"
      },
      "rate_limit": {
        "requests_per_second": 0.5,
        "delay_ms": 2000
      },
      "selectors": {
        "title": ".title .lemma-title",
        "content": ".lemma-text",
        "image": ".summary-pic img"
      }
    },
    {
      "name": "新闻源",
      "type": "web",
      "sources": [
        {
          "name": "新浪新闻",
          "base_url": "https://search.sina.com.cn",
          "search_path": "/?q={query}&c=news"
        },
        {
          "name": "腾讯新闻",
          "base_url": "https://news.qq.com",
          "search_path": "/cgi-bin/search?q={query}"
        },
        {
          "name": "澎湃新闻",
          "base_url": "https://www.thepaper.cn",
          "search_path": "/searchPageResult?keys={query}"
        }
      ],
      "headers": {
        "User-Agent": "Mozilla/5.0"
      },
      "rate_limit": {
        "delay_ms": 5000
      }
    },
    {
      "name": "社交媒体",
      "type": "web",
      "sources": [
        {
          "name": "微博热搜",
          "base_url": "https://weibo.com",
          "api": "https://weibo.com/ajax/side/hotSearch"
        },
        {
          "name": "知乎",
          "base_url": "https://www.zhihu.com",
          "search_path": "/search?q={query}&type=content"
        }
      ],
      "headers": {
        "User-Agent": "Mozilla/5.0"
      },
      "rate_limit": {
        "delay_ms": 10000
      },
      "note": "需登录态或模拟浏览器"
    }
  ],
  "crawl_rules": {
    "respect_robots_txt": true,
    "max_depth": 3,
    "retry_on_failure": 3,
    "timeout_ms": 30000
  },
  "output": {
    "format": "jsonl",
    "fields": [
      "query",
      "source_type",
      "source_url",
      "crawl_time",
      "title",
      "content",
      "summary",
      "tags",
      "confidence"
    ],
    "required_fields": ["query", "source_url", "crawl_time"]
  },
  "seed_queries": [
    "人物",
    "事件",
    "组织",
    "作品",
    "历史"
  ]
}