← All toolsWeb & Researchweb_searchAll editions

EXTRACT_STRUCTURED_DATA

Fetch a URL and extract structured data: JSON-LD schemas, Open Graph tags, Twitter Card tags, and HTML tables.

Parameters

NameTypeRequiredDescription
urlstringyesURL to extract structured data from
max_tablesinteger—Maximum number of HTML tables to extract (default 5)

How to use it

You normally trigger this by describing what you want in chat — the agent selects EXTRACT_STRUCTURED_DATA automatically. For example:

Try saying
“use web search to extract …”

In a workflow

As a step in a multi-step workflow DAG:

json
{
  "id": "s1",
  "agent": "web_search",
  "action": "EXTRACT_STRUCTURED_DATA",
  "args": {
    "url": "https://example.com",
    "max_tables": 5
  },
  "depends_on": [],
  "outputs": []
}

Direct call

For scripting, call it directly via POST /execute_tool. Every tool returns { success, message, data }.

bash
curl -X POST http://127.0.0.1:8000/execute_tool \
  -H "Content-Type: application/json" \
  -d '{"tool_name":"EXTRACT_STRUCTURED_DATA","args":{"url":"https://example.com","max_tables":5}}'

Part of the web_search plugin. Browse the full Plugin & Tool Catalog or the relevant feature guide.