Research · Intermediate
Web documentation to markdown pipeline
Crawl complex web pages and convert content into structured markdown for research
- When you askReceive target URLs
- ThenParse and clean page text
- ResultSave markdown notes
Crawl target web links, strip extraneous navigation, footers, and scripts, and convert the primary page content into clean, readable markdown notes complete with preserved tables and citation links.
Prompt to start with
BotBentoRecommended
When the user provides web addresses, fetch the page contents using the browser tool. Strip out banners, menus, and scripts while preserving headings, lists, tables, and reference links. Format the output into clean markdown. Always ask for user confirmation before writing or saving the resulting files to the notes repository.