LurkAPI

Website to text

Any web page's main text, without the menus, ads and code around it.

Try

Free, no signup: 5 tries a day

How to extract text from a website

  1. Copy the page's address. A bare domain like example.com works too.

  2. Paste it and press Get text.

  3. You get the main text without menus or code. Copy text or save it as .txt.

What people use it for

  • Read without the clutter

    Strip an article of ads, pop-ups and menus, down to the words.

  • Give a page to ChatGPT or Claude

    Paste the text into the chat; the token count shows whether it fits.

  • Copy text you can't select

    Some sites block highlighting, but they still send the text, and you get all of it.

FAQ

How do I copy text from a website that won't let me select it?

Paste its link here. Those sites still send the text; they only stop you highlighting it.

How do I give ChatGPT or Claude the text of a web page?

Copy the text here and paste it into the chat. The token count is an estimate, at about 4 characters a token.

Does it work on JavaScript sites?

On most. It reads pages that send their text, like articles, docs and shops. Pages built in your browser, or behind a “Checking your browser” screen, fail without using a try; the API's Render endpoint opens those.

Is it free? How many tries do I get?

Yes. No account: 5 free tries a day. A free account gets 100 credits, topped up to 20 daily. Each page uses one try, or 1 credit with an account. Blocked or dead sites don't count.

Does it keep links and tables?

It keeps their words, not their formatting. For links, headings and tables, use Website to markdown.

Does it work on paywalled or login pages?

No. It reads public pages as a logged-out visitor sees them: up to the paywall, or the sign-in page.

Get this as an API

One GET, clean JSON. 1 credit a call, from $0.59 per 1,000 calls.

GET/v1/web/fetch?url=https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/Overview&format=text&main=true
{
  "status": 200,
  "url": "https://books.toscrape.c…",
  "title": "All products | Books to…",
  "content_type": "text/html",
  …
}