Crawl4AI Plus Advanced icon

Crawl4AI Plus Advanced

Advanced web crawling and extraction with full Crawl4AI API control

Actions15

Process Raw HTML

AI-generated

Summary

Processes supplied raw HTML through the Crawl4AI API to produce formatted crawl results, with optional content filtering, table extraction, and output fields. It does not navigate a browser page; screenshot and PDF options have no effect.

Inputs

  • HTML Content (required) — Raw HTML to process, up to 5 MB.
  • Base URL — Base URL for resolving relative links; defaults to https://example.com.
  • Crawl Settings — Optional extraction settings, including CSS selector, excluded tags, JavaScript, wait conditions, link filtering, caching, retries, and word-count threshold. Browser-oriented settings such as screenshot and PDF do not apply to raw HTML.
  • Output & Filtering — Controls returned markdown and optional HTML, links, media, tables, and verbose details. Can apply BM25, LLM, or pruning content filtering, and default or LLM table extraction; LLM options require credentials. Defaults include links and tables, with markdown set to both raw and fit formats.

Output shape

A single formatted crawl result for the supplied HTML.

Optional output fields depend on the selected output and filtering settings. Screenshot and PDF output are not produced for this operation.

Links

Discussion