Web page data extractor

Give it page links. Get tables, lists and prices as a CSV or JSON file. Collects data from websites.

Web page data extractor is a free AI skill for the job "Make documents, sheets and slides". Give the instructions to an AI assistant that supports the required files and tools, then review its output.

Free · No account · CC BY 4.0 licence · Made by sickn33

Made by sickn33. See the original on GitHub; we copied it as it is, with its licence.

What it does

Tables, lists and prices pulled from web pages into a CSV or JSON file you can open in a spreadsheet. It saves hours of copying and pasting. You give the page links and say what data you want. The skill tries more than one approach to read each page, so it copes with different layouts. It follows page numbers to collect every result, not just the first page, and can re-run the job to watch for changes such as price moves. It exports to CSV or JSON. It collects data from websites, so check the site's terms and robots rules first, and go slowly. It runs as a script and may need Python.

You give it

One or more page links
The data you want, such as name and price
Number of pages to follow (optional)
How often to re-run (optional)

You get

A CSV or JSON file
One row per item found
Data from all result pages
A re-run script for tracking changes

Use it when

You want a price list from several product pages.
A table on a site is too long to copy by hand.
You track a competitor's prices over time.
You need a list of items in a clean file.

How to use it

Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
Ask for the job in your own words. Your AI opens the skill when it fits.
It works best when your AI can run code and reach the web.