Runs in your browser. Files not uploaded to us.

Convert a saved web page to text in your browser.

Drop a page you saved from your browser and get the article back as markdown, without the menus and ads around it, ready to paste into ChatGPT, Claude or Gemini.

  • Pages saved whole from Chrome, Edge or SingleFile
  • Forty pages in, one text file out
  • No sign-up, no account

Drop your saved page here

Read in your browser.

What a saved web page looks like once FileConcat has read it

A sample blog post saved from Chrome. The article comes back as markdown; the cookie banner, the menu, the sale box and the footer do not.

Sample web page, read by FileConcat 2.9.

What comes through, and what does not

In the text

  • The article as markdown, a formula as its TeX source, and a form field as the value it shows.

Not read

  • Menus, ads, text the page hides and everything else outside the article. HTML source code stays code.
Web page (HTML)Weighted coverage, higher is better
98.3
91.7
66.4
54.7
FileConcat 2.9FileConcat 2.3markitdown 0.1.5Tika 3.3.2

198 real files.

Every FileConcat benchmark

What gets lost converting documents to text

Forty saved pages, one file to paste

Drop a folder of saved pages and they come back as one text file, each under its own name, with a token count for the whole set. An assistant that caps attachments counts it as one.

research/
  four-day-week.html
  remote-work-study.html
  shift-patterns.html
  support-metrics.html
1 file
to attach

How many files ChatGPT takes

It reads more than web pages

Also Kindle books, notebooks, subtitles and ZIP archives.Every format it reads

Common questions

Is my page uploaded to a server?

Not to us. FileConcat reads the page in your browser and there is no account to create. The only upload is the one you choose to make, when you paste or attach the text at your assistant.

Which saved pages does it read as an article?

A page saved from Chrome or Edge as Webpage, Complete, which marks the file with the address it came from, and a page saved with the SingleFile extension. Webpage, HTML only and Firefox leave no such mark, so the page is read as HTML source, markup included, the same as an .html file from a code project.

What is left out?

Menus, ads, cookie banners, text the page hides and everything else around the article. A formula comes through as its TeX source and a form field as the value it shows.

Can I get a page without saving it first?

Yes, with the FileConcat Clipper for Chrome. It reads the page you are on and turns the article into text without saving a file first.

Can I get plain text without tags?

Yes. Set Format to Plain before you copy or download. The tags go, and each file sits between two rules with its name, under a short summary and the file list.

Can I convert many web pages at once?

Yes. Drop several files or a whole folder. They come back as one text file with each page under its own name, so an assistant that limits attachments takes them as one.

Drop your saved page here

Read in your browser.