[ free tool ]
Website to plain text
Enter the address of a public page and get its main text as plain text: no HTML, no Markdown marks, no menus or cookie banners. Copy it or download it as a .txt file.
What it does#
- Reads the page through Clawifi (a plain fetch first, a real browser only when the page needs one) and keeps the main text, leaving out navigation, banners and footers.
- Removes the formatting: headings, bold and italics lose their marks, links and images keep their words but not their addresses, and table rows become tab-separated lines.
- Shows the word count and the text in a panel you can copy or download as a
.txtfile.
Limits#
- The free preview stops at 20,000 characters of the page’s text; longer pages are cut, and the result says so.
- Link addresses are dropped on purpose. To keep them, use URL to Markdown or the link extractor.
- Public pages only, one page per run, and 12 runs a minute per address shared with the other free tools.
Do this from your agent#
An agent can ask scrape_url for the text format with an API key. Without a key, the hosted MCP server’s scrape_url returns Markdown as a trial (12 a minute and 50 a day per address).
scrape_url(url="https://example.com", formats=["text"])curl https://api.clawifi.dev/scrape \
-H "Authorization: Bearer $CLAWIFI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"https://example.com","formats":["text"]}'from clawifi import Clawifi
client = Clawifi() # reads CLAWIFI_API_KEY
page = client.scrape("https://example.com", formats=["text"])
print(page["formats"]["text"])Read more: Fetch and scrape · POST /scrape · Remote MCP · Docs · Pricing
Questions#
How do I convert a website to plain text?
Paste the page’s URL above and press Get text. Clawifi reads the page, keeps the main text and removes the markup, and you can copy the text or download it as a .txt file.
What is the difference between plain text and Markdown?
Markdown keeps structure as marks: # for headings, brackets around link labels with the address after them, | for tables. Plain text keeps the words only. Markdown suits an LLM prompt; plain text suits word counts, diffs, search indexes and reading aloud.
Does it work on pages that need JavaScript?
Often, yes. Clawifi tries a plain fetch first and renders the page in a browser only when the text is not in the HTML. Pages behind a login or a bot challenge will not come through.
Is there a limit?
The free tool allows 12 runs a minute per address and cuts long pages at 20,000 characters. A free API key includes 1,000 credits a month; see Pricing.