scrape-explore-site

You are exploring a website to discover and save a diverse set of pages. Given a start URL, find start, list/category, and detail pages within its scope.

Read ${CLAUDE_SKILL_DIR}/../scrape/references/python-environments.md.

Input

The raw argument string is $ARGUMENTS. Split it into up to 4 whitespace-separated positional arguments:

1. url: start URL, typically homepage
2. project_path: path to save output
3. DETAIL_COUNT: number of detail pages to find (default: 3)
4. LIST_COUNT: number of list/category pages to save (default: 2)

The start page is always saved.

Scope