Does this skill handle paywalled content?

No, the extractor generally cannot bypass authentication or paywalls that require a user session or subscription to view the full text.

What tools need to be installed for this skill to work?

The skill works best if 'reader-cli' (Node.js) or 'trafilatura' (Python) is installed, but it includes a built-in fallback method using curl and Python for basic extraction.

How does it handle file naming?

It automatically extracts the article's title from metadata or headers and sanitizes it into a filesystem-compatible filename.

Can I use the extracted text for other Claude tasks?

Yes, once extracted, the text is saved as a local file which Claude can then read, summarize, or use as a reference for coding and learning plans.

Is it compatible with JavaScript-heavy websites?

While it handles many modern sites, extremely complex Single Page Applications (SPAs) that require heavy JavaScript rendering may yield limited results compared to static or server-rendered articles.

Article Content Extractor

Name: Article Content Extractor
Author: kivilaid

bykivilaid

•

Web Scraping & Data Collection

Extracts clean, readable text from blog posts and articles by removing ads, navigation, and clutter.

About

The Article Extractor skill allows Claude to transform cluttered web pages into clean, distraction-free text files. By leveraging industry-standard tools like Mozilla's Readability algorithm and Trafilatura, it intelligently identifies the core content of an article while stripping away intrusive advertisements, newsletter signups, and navigation menus. This skill is essential for developers and researchers who need to archive documentation, ingest tutorials into their local environment, or gather clean training data from the web without the noise of modern web design.

Key Features

Removes ads, sidebars, and navigation menus automatically
Generates instant text previews to verify extraction quality
Auto-generates clean, filesystem-safe filenames from article titles
Provides a robust Python fallback for environments without external dependencies
6 GitHub stars
Supports high-precision extraction via Mozilla Readability and Trafilatura

Use Cases

Saving technical tutorials or blog posts for offline reference and local archiving
Converting web-based documentation into clean text to use as context for LLM tasks
Gathering distraction-free research material from news sites and academic blogs

About

Key Features

Removes ads, sidebars, and navigation menus automatically
Generates instant text previews to verify extraction quality
Auto-generates clean, filesystem-safe filenames from article titles
Provides a robust Python fallback for environments without external dependencies
6 GitHub stars
Supports high-precision extraction via Mozilla Readability and Trafilatura

Use Cases

Saving technical tutorials or blog posts for offline reference and local archiving
Converting web-based documentation into clean text to use as context for LLM tasks
Gathering distraction-free research material from news sites and academic blogs