Scrape

Include the HTML version of the content on page. Will output a html key in the response.

Include the raw HTML content of the page. Will output a rawHtml key in the response.

Only return the main content of the page excluding headers, navs, footers, etc.

Replace all relative paths with absolute paths for images and links

Include a screenshot of the top of the page that you are scraping.

Include a full page screenshot of the page that you are scraping.

Wait x amount of milliseconds for the page to load to fetch content

The extraction mode to use. 'markdown': Returns the scraped markdown content, does not perform LLM extraction. 'llm-extraction': Extracts information from the cleaned and parsed content using LLM. 'llm-extraction-from-raw-html': Extracts information directly from the raw HTML using LLM. 'llm-extraction-from-markdown': Extracts information from the markdown content using LLM.

A prompt describing what information to extract from the page, applicable for LLM extraction modes.