Site Mover
Scrape an old site's content and organize it for the new one
Redesigns mean content migration — scraping text, downloading images, mapping content to the new structure, and fixing broken links. This recipe crawls the old site, extracts everything, and organizes it into clean files ready for the new CMS.
INGREDIENTS
PROMPT
Create a skill called "Site Mover". When I give you an old website URL and a new site structure (sitemap or page list), crawl every page of the old site and extract: all text content, all images (downloaded at highest resolution), all PDFs and embedded files, page metadata (title, meta description, og tags), and existing alt text. Organize the extracted content to match the new site structure. Generate a redirect map (old URL → new URL) for 301 redirects. Detect broken links on the old site. Produce a gap analysis showing: old content with no home in the new structure, and new pages with no content from the old site. Output everything as clean Markdown files organized by page, with images in an assets folder. Also support export as WordPress XML import format.
How It Works
Give your Claw the old site URL and the new site's structure (sitemap
or page list). It crawls every page, extracts all content (text, images,
metadata, files), downloads assets, maps content to the new structure,
and outputs clean Markdown or CMS-importable files.
What You Get
- Full content extraction: text, images, PDFs, embedded files
- Content organized by page and section
- Images downloaded at highest available resolution
- Metadata preserved: page titles, meta descriptions, alt text
- Broken link detection across the old site
- Redirect map: old URLs → new URLs for 301 redirects
- Content mapped to the new site structure
- Output as clean Markdown, HTML, or CMS-importable format (WordPress XML, etc.)
- A gap analysis: content on the old site missing from the new sitemap
Setup Steps
- Provide the old site URL and the new site's sitemap or page structure
- Your Claw crawls and extracts everything
- Review the organized content and the gap analysis
- Import into your new CMS or codebase
- Set up 301 redirects using the generated redirect map
Tips
- Run this early in the project — it reveals how much content actually exists (often more or less than expected)
- The redirect map is critical for SEO — missing 301s tank search rankings
- The gap analysis catches orphaned content that doesn't fit the new structure
- Review extracted content for quality — migration is a good time to cut outdated pages
- Works on any CMS: WordPress, Squarespace, Wix, Webflow, static HTML