article-extractor
Extract clean article content from URLs (blog posts, articles, tutorials) and save as readable text. Use when user wants to download, extract, or save an article/blog post from a URL without ads, navigation, or clutter.
Security Assessment
About article-extractor
The article-extractor skill is designed to extract clean and readable content from various web articles, blog posts, and tutorials. It addresses the common issue of clutter present in online articles, such as ads, navigation bars, and pop-ups, which can detract from the reading experience. By providing just the main text content, users can focus on the essential information without distractions, making it particularly useful for those who want to save or download articles for offline reading or reference purposes.
This skill employs multiple extraction methods, ensuring high accuracy in capturing main content. It primarily utilizes tools like Mozilla's Readability and trafilatura, both known for their effectiveness in parsing web content. The skill not only extracts the text but also cleans and formats it appropriately, saving the output as a text file named after the article title. Furthermore, it includes fallback mechanisms for situations where preferred tools are not available, making it versatile and reliable for users with different setups.
Target users include researchers, students, and professionals who frequently consume online content and want to save it in a clean format. Additionally, it serves anyone looking to quickly extract articles from the web without unnecessary elements, streamlining their reading and information-gathering process.
FAQ
How do I use the article-extractor skill?
You can activate the skill by providing an article or blog URL, or by expressing a desire to download or save the content.
What tools do I need to install to use this skill?
You should install either the 'reader' tool or 'trafilatura' for the best results. If these are not available, a fallback method using curl is also provided.
What types of content can I extract?
You can extract text from articles, blog posts, and tutorials while removing ads, navigation, and other distractions.
Is there any limitation on the types of URLs I can use?
The skill works best with standard web articles and may have varying success with sites that have unconventional structures.
What happens if the extraction tools are not installed?
The skill will revert to a fallback method using basic curl and parsing techniques, though this may be less reliable.
Install article-extractor
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill