Skip to main content

​
Overview

The general-purpose parser handles any URL that doesn’t match a specialized platform parser. It provides intelligent content extraction with support for Markdown output, link/image extraction, custom JSON schemas, and AI enrichment.
This parser is currently in early access. Documentation will be expanded as the parser matures.

​
Supported URLs

Any URL not matched by a specialized parser. This is the default fallback parser.

​
Example Requests

​
Markdown Extraction

{
  "url": "https://example.com/blog/article",
  "options": {
    "markdown": true
  }
}

​
Custom JSON Schema

{
  "url": "https://example.com/product",
  "options": {
    "json_schema": {
      "properties": [
        { "name": "title", "type": "string" },
        { "name": "price", "type": "number" },
        { "name": "description", "type": "string" }
      ]
    }
  }
}

​
Full Extraction with AI Summary

{
  "url": "https://example.com/research-paper",
  "options": {
    "markdown": true,
    "include_links": true,
    "image_urls": true,
    "ai": {
      "summary": true
    }
  }
}

JSON Schema

Define custom extraction schemas

Output Formats

Available output format options