crawl_config.json 1.87 KB
{
  "name": "trend-hunter",
  "description": "热点抓取爬虫配置",
  "version": "1.0.0",
  "data_sources": [
    {
      "name": "百度热搜",
      "url": "https://top.baidu.com/board?tab=realtime",
      "method": "GET",
      "headers": {
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
        "Accept": "text/html,application/xhtml+xml"
      },
      "parser": {
        "type": "html",
        "extract_method": "regex",
        "pattern": "(\\d+)\\s+(\\d+)\\s+(.*?)热搜指数\\s+(.*?)(?=\\d+\\s+\\d+\\s+|</div>)"
      },
      "rate_limit": 3,
      "enabled": true
    },
    {
      "name": "B站热门",
      "url": "https://api.bilibili.com/x/web-interface/popular?ps=50&pn=1",
      "method": "GET",
      "headers": {
        "User-Agent": "Mozilla/5.0",
        "Referer": "https://www.bilibili.com"
      },
      "parser": {
        "type": "json",
        "path": "data.list"
      },
      "rate_limit": 2,
      "enabled": true
    },
    {
      "name": "今日头条热榜",
      "url": "https://www.toutiao.com/hot-event/hot-board/",
      "method": "GET",
      "headers": {
        "User-Agent": "Mozilla/5.0"
      },
      "parser": {
        "type": "json",
        "path": "data"
      },
      "rate_limit": 3,
      "enabled": true
    },
    {
      "name": "腾讯新闻热榜",
      "url": "https://r.inews.qq.com/gw/event/hot_ranking",
      "method": "GET",
      "headers": {
        "User-Agent": "Mozilla/5.0"
      },
      "parser": {
        "type": "json",
        "path": "idlist"
      },
      "rate_limit": 3,
      "enabled": true
    }
  ],
  "output": {
    "format": "json",
    "fields": ["title", "rank", "hot_value", "category", "tags", "description", "source", "crawl_time"]
  },
  "schedule": {
    "interval_minutes": 15,
    "max_records": 100
  }
}