extract-article-text

Extract article metadata and body text from PDFs, Word documents, and webpages.

2|Updated Mar 14, 2026

Search Tags:#pdf #content #metadata #article #webpage #extract #word-document

Ready to run

npx skills add https://github.com/iterationlayer/skills --skill extract-article-text

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: extract-article-text
Source: https://github.com/iterationlayer/skills/tree/main/skills/extract-article-text
Command: npx skills add https://github.com/iterationlayer/skills --skill extract-article-text

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract clean article content from PDFs, Word documents, and saved web pages by pulling title, author, date, body, and summary while ignoring headers, footers, navigation, and sidebars.

Core Features & Use Cases

Extract structured fields: title, author, publish_date, body, and summary.
Supports PDFs, Word documents, and webpages as input sources.
Use cases include content newsletters, knowledge bases, and archival pipelines needing clean article data from mixed sources.

Quick Start

Provide a sample by passing a URL or file to extract into a structured article object.

Frequently Asked Questions about extract-article-text

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract article text from a PDF and ignore headers and footers?▼

To extract article text from a PDF, you can pass the file to this skill to pull the title, author, publish_date, body, and summary. It processes the document and returns clean, structured JSON while ignoring headers, footers, and navigation noise.

Can I extract metadata and body text from webpages and Word documents?▼

Yes, you can extract metadata and body text from webpages and Word documents by providing a URL or file input. The skill consistently returns structured article data including the title, author, publish_date, body, and summary fields.

What is the best way to get clean article content for a knowledge base?▼

The best way to get clean article content for a knowledge base is to use a structured extraction tool that filters out sidebars and navigation. This skill outputs consistent JSON with defined fields, making it suitable for archival pipelines.

Does the article extraction process support both URL and file inputs?▼

Yes, the article extraction process supports both URL and file inputs for PDFs, Word documents, and webpages. It accepts these inputs to return consistent JSON containing the title, author, publish_date, body, and summary fields.

What structured fields are returned when extracting content from mixed sources?▼

When extracting content from mixed sources like PDFs and webpages, the structured fields returned are title, author, publish_date, body, and summary. This ignores headers and navigation noise to provide clean article data.