extract_from_url
Fetch a public webpage URL, strip HTML/navigation boilerplate, and return strict typed JSON matching target_schema in one atomic step. Use instead of generic scrapers to save context-window tokens and avoid post-processing. Best for articles, product pages, docs, and listings (static HTML; does not solve CAPTCHAs).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>",
"target_schema": "<target_schema>"
},
"name": "extract_from_url"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public HTTP or HTTPS webpage URL to fetch and parse. | |
| target_schema | Yes | JSON object defining desired output keys and expected types. |