Octagon Scraper Agent

Model Name: octagon-scraper-agent

Specialized agent for financial data extraction from investor websites.

Capabilities

• Extract structured financial data from investor relations websites
• Parse tables and financial statements from online sources
• Convert unstructured web data into structured formats
• Navigate multi-page financial resources
• Support for regional localization parameters

Use Cases

The Scraper Agent is best for:

• Gathering financial data from websites that don't have accessible APIs
• Extracting data from investor relations portals
• Collecting pricing information from e-commerce sites
• Gathering real estate listing data
• Compiling structured data from financial information portals

Example Queries

• "Extract all data fields from zillow.com/san-francisco-ca/ max_pages:2"
• "Extract all data fields from www.carvana.com/cars/ country:us"

Customizable Parameters

Control the scraping depth and localization with additional options. Add in prompt for usage:

• max_pages: int Limit the number of pages the scraper will traverse.
• country: str Specify a two-letter country code (default is "us"). This parameter requires exactly two characters.

Code Examples

Python

response = client.responses.create(
    model="octagon-scraper-agent",
    input="Extract all data fields from zillow.com/san-francisco-ca/ max_pages:2, country:us",
    stream=True
)

JavaScript

const response = await client.responses.create({
  model: "octagon-scraper-agent",
  input: "Extract all data fields from zillow.com/san-francisco-ca/ max_pages:2, country:us",
  stream: true
});

cURL

curl -X POST https://api.octagonagents.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-octagon-api-key" \
  -d '{
    "model": "octagon-scraper-agent",
    "input": "Extract all data fields from zillow.com/san-francisco-ca/ max_pages:2, country:us",
    "stream": true
  }' \
  --no-buffer