Chrome extension
Page Text Extractor
Clean readable text from a page, with the furniture removed.
All nine toolsNavigation, cookie banners, sidebars and footers make a page unreadable once you paste it somewhere else. This tool keeps the article and drops the rest, and keeps the heading structure so the text still has a shape.
Take it as plain text or as Markdown with headings, lists and links intact. Markdown is the one to use when the text is going into a model, because the structure survives.
Screenshot coming with the tool. Nothing here is a drawing, so this space stays empty until the real capture exists.
How it works
- Step 1
Open the page
One page, or a list of addresses if you are collecting a set of articles.
- Step 2
Check what was kept
The preview shows the extracted text next to what was dropped, so you can widen the selection when the page has an unusual layout.
- Step 3
Choose the format
Plain text, Markdown, or a table with one row per page and the text in a column, alongside the title and the word count.
- Step 4
Copy or export
Copy to the clipboard, save the file, or keep it in a table and let Claude read it over MCP.
When to reach for it
- Feeding documentation, articles or product descriptions into a model without the page furniture.
- Archiving text that might change or disappear.
- Reading a long page quickly, with the heading structure kept.
What it will not do
- It has to guess what the main content is. On a page that is mostly widgets, the guess can be wrong.
- Text inside an image or inside a PDF is out of scope: the tool reads HTML pages and does no character recognition.