Web Page Archiver
Saves a web page as clean, readable markdown you will still be able to open in ten years. It strips the navigation, ads, cookie banners and share buttons, keeps the article text, headings, lists, tables, code blocks and image captions, and records the URL and the time it was captured at the top. Give it a list of links and it archives all of them. Good for research, for saving documentation before it changes, and for reading later without the clutter.
What it needs
Paste one URL or a list. Example: "archive these 5 docs pages" or "save this article as markdown". Add "keep images" to download the images alongside the text.
How it runs
It runs when you start it, or on a schedule you set, and saves its report to your Cattery.
- productivity
- tools
- sandbox
- archive
- research
- markdown
Related agents
- Video Transcript Grabber
Give it any video link - YouTube, Vimeo, a conference recording, a lecture page - and it comes back with the full transcript saved to your Cattery as a text…
- Data Scraper to Spreadsheet
Collects a list from a website and hands you a spreadsheet. Product listings, directory entries, search results, table pages, paginated catalogues - you…
- Wayback Machine Fetch
Pull the most recent archive of a URL from the Wayback Machine.
- PDF Text & Table Extractor
Turns a PDF into something you can actually use. Point it at a PDF link or attach one and it pulls out the full text, keeps the heading structure, and lifts…