extract
Pull structured data from web pages without AI by applying CSS or XPath schemas or built-in patterns for emails, phone numbers, URLs, money, percentages, dates, times, and postal codes.
Instructions
Pull data out of a page without AI: a CSS or XPath schema {"baseSelector", "fields": [...]}, or ready-made patterns (email, phone, url, money, percent, date, time, postal_code, ...).
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>"
},
"name": "extract"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| patterns | No | ||
| css_schema | No | ||
| xpath_schema | No |