Extract fields
~6.25 credits / page (up to 250)Pulls specific named data points off a page and returns them as a structured JSON object rather than the full page text. Useful when you want a price, a title, a set of specs, or any defined set of attributes without the surrounding content.
Use when
You want named data points from a page (price, title, author, specs) as a clean object, not the whole article.
Not for
Reading a whole page as prose (use Read a page), or listing a site's URLs (use Map a site).
Cost
~6.25 credits / page (up to 250)
Priced per page read; a hard anti-bot page or a long page costs more.
Estimated; the actual charge depends on your input and is shown in the response.
What it accepts
Set these inside the intent when you run it.
The full URL of the page to extract fields from.
The fields to extract, as a list of names or a description of what you want.
What you get back
A JSON object whose keys are the fields you requested, populated from the page.
Run it
Run this sub-skill directly: pin it with operation and pass its inputs in the intent. (Omit operation and the Generic Scrapers skill will route from your intent instead.)
curl -X POST "https://skill.askfaro.com/skills/web-scraping/run" \
-H "Authorization: Bearer $FARO_TOKEN" \
-H "Content-Type: application/json" \
-d '{"intent":{"operation":"extract_fields","url":"https://example.com/products/widget","fields":"product name, price, stock status"}}'Example requests
- ›Scrape the product name, price, and rating from this page
- ›Pull the author, publish date, and headline from this article
- ›Extract the phone number and address from this business page