Which extraction tools does this skill use?

The skill prioritizes @mozilla/readability-cli and Trafilatura for high-quality extraction, with a built-in Python fallback for environments where these tools are not yet installed.

Can it extract content from behind paywalls?

Generally, no. These extraction tools require public access to the URL to successfully retrieve content. If a site requires a login or subscription, the extraction will likely fail or return a login prompt.

How does it handle article titles and filenames?

It automatically extracts the article title from the metadata or headers and sanitizes it by removing illegal characters to create a clean, descriptive filename for your local filesystem.

What file format does the skill save to?

The skill is optimized to save content as clean .txt files, ensuring the content is easily searchable, readable, and compatible with other text-processing tools.

Article Extractor

Name: Article Extractor
Author: pur3v4d3r

bypur3v4d3r

•

ウェブスクレイピングとデータ収集

Extracts clean, distraction-free text content from web articles and blog posts for easy reading and local storage.

概要

The Article Extractor skill empowers Claude to strip away web clutter—including advertisements, navigation menus, and newsletter pop-ups—from any URL to retrieve the core written content. By leveraging industry-standard tools like Mozilla's Readability algorithm and Trafilatura, it converts complex HTML pages into well-structured, readable text files automatically named after the article's title. This skill is essential for developers and researchers who need to archive documentation, study tutorials offline, or build clean text-based knowledge bases without visual distractions.

主な機能

Automatic removal of ads, navigation sidebars, and cookie notices
Distraction-free extraction using Mozilla Readability or Trafilatura algorithms
Multi-tool fallback logic to ensure extraction success across different site structures
Instant content previewing for immediate verification of extraction quality
Intelligent filename generation based on sanitized article titles
1 GitHub stars

ユースケース

Archiving blog posts and news articles without visual noise or ads
Converting online technical documentation into local text files for persistent reference
Gathering clean text datasets from the web for research or knowledge base compilation

概要

主な機能

Automatic removal of ads, navigation sidebars, and cookie notices
Distraction-free extraction using Mozilla Readability or Trafilatura algorithms
Multi-tool fallback logic to ensure extraction success across different site structures
Instant content previewing for immediate verification of extraction quality
Intelligent filename generation based on sanitized article titles
1 GitHub stars

ユースケース

Archiving blog posts and news articles without visual noise or ads
Converting online technical documentation into local text files for persistent reference
Gathering clean text datasets from the web for research or knowledge base compilation