readability
Extract article text and metadata from any web page, removing ads and clutter for clean reading or AI processing.
Instructions
Extract the main article text and metadata from a web page.
Uses Mozilla's Readability algorithm (the same engine as Firefox Reader Mode)
to strip navigation, ads, and boilerplate and return only the article content.
Ideal for summarising articles, building reading lists, or feeding clean text
into further AI processing without HTML noise.
Args:
url: Full URL of the article or page to extract (must include https://).
Returns:
title: Article or page title.
byline: Author name(s) if detected.
content: Plain text of the main article body.
word_count: Number of words in the extracted content.
published_at: Publication date if found in page metadata (may be null).
excerpt: Short description/lead paragraph if available.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |