从 JavaScript 密集型页面提取结构化数据

{
  "url": "https://example.com/dashboard",
  "mode": "inspect"
}

{
  "mode": "inspect",
  "page": {
    "url": "https://example.com/dashboard",
    "title": "Example Dashboard"
  },
  "candidates": {
    "dom": { "metrics": [], "tables": [] },
    "network": []
  },
  "suggestedPlan": {
    "fields": {},
    "schema": {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
  }
}

{
  "url": "https://example.com/dashboard",
  "mode": "extract",
  "waitFor": { "selector": "h1", "timeoutMs": 15000 },
  "fields": {
    "title": { "source": "dom", "selector": "h1", "parse": "string" },
    "price": { "source": "dom", "selector": ".price", "parse": "number" }
  }
}

{
  "url": "https://example.com/dashboard",
  "mode": "extract",
  "fields": {
    "visitorCount": {
      "source": "network",
      "urlIncludes": "/api/metrics",
      "path": "$.data.visitors"
    }
  }
}

curl -sS "https://api.adscrawl.net/spa-extract/templates" \
  -H "x-api-key: $ADSCRAWL_API_KEY"

{
  "template": "similarweb-overview",
  "url": "https://www.similarweb.com/website/example.com/#overview",
  "countryCode": "GLOBAL"
}

{
  "template": "google-trends-explore",
  "keyword": "playwright,puppeteer"
}

{
  "url": "https://example.com/dashboard",
  "mode": "extract",
  "actions": [
    { "type": "click", "selector": "#load-more" },
    { "type": "wait", "milliseconds": 1500 },
    { "type": "scroll", "y": 800 }
  ],
  "fields": {
    "title": { "source": "dom", "selector": "h1", "parse": "string" },
    "price": { "source": "dom", "selector": ".price", "parse": "number" }
  }
}

{
  "mode": "extract",
  "page": {
    "url": "https://example.com/dashboard",
    "title": "Example Dashboard"
  },
  "data": {
    "title": "Example Dashboard",
    "price": 49.99
  },
  "missingFields": []
}