MerchantryTidbits

doc-parsing / library

mozilla-readability

Capability: mozilla-readability

Use it when

  • extract main article text from messy HTML
  • readability cleaning before RAG or summaries

What it solves

Install

npm i @mozilla/readability jsdom

Invoke

import { Readability } from '@mozilla/readability'; new Readability(document).parse()

Alternatives

No reviewed alternatives recorded yet.