extractor
Firecrawl
Used as a fallback when HTML extraction looks blocked or too thin — and as a preferred Markdown source in extract-only mode (when configured).
Key
- Set
FIRECRAWL_API_KEY. - Control behavior with
--firecrawl off|auto|always.
Extract-only + Markdown
--extract-onlyprints the extracted content.--markdown auto|llmcan output Markdown for non-YouTube URLs.
If you only want plain text: use
--firecrawl off --markdown off.