rocketkind
DevTools

WebScraping.AI

WebScraping.AI fetches web pages through rotating proxies and a headless Chromium browser, then hands back the HTML, clean Markdown, a selected element, or an LLM's answer about the page.

Authentication

  • API key

Actions

Generic API request. Call any WebScraping.AI API endpoint on this connection, for the case where no shipped action covers it yet. The connection supplies the base URL, the authentication and the egress route, so only the path and query are yours to fill.

  • Ask a question about a pageFetch a web page and have an LLM answer a question or follow an instruction about its content — summarize it, list the top stories, say whether an item is in stock.
  • Extract fields from a pageFetch a web page and have an LLM extract the fields you name, each with a short instruction — for example title, price and rating from a product page — returning them as structured values instead of HTML.
  • Get accountRead the WebScraping.AI account's remaining credits (monthly, pay-as-you-go and total), when the monthly quota resets and how many concurrent requests are still available.
  • Get multiple selected HTMLFetch a web page once and return the HTML of every area matched by a list of CSS selectors — for example a product's title, price and stock line together — which costs one request instead of one per selector.
  • Get page HTMLFetch the full HTML of a web page through WebScraping.AI's rotating proxies and headless Chromium, so JavaScript-built content and bot-protected sites come back rendered.
  • Get page textConvert a web page to clean Markdown with boilerplate stripped and headings, lists, tables and links kept — the input to reach for when feeding a page to an LLM step, summarizing it, or indexing it for search.
  • Get selected HTMLFetch a web page and return only the HTML of the area a CSS selector matches — a price, a headline, a results list — so a workflow does not have to parse the whole page.

Product names, logos and brands are the property of their respective owners and are used here for identification only. Their use does not imply endorsement by, or affiliation with, those owners.