---
name: "newspaper4k-article-scraper"
description: "Scrape, parse, and analyze multilingual news articles with Newspaper4k."
metadata:
  author: "Newspaper4k"
  version: "1.0.0"
  runtime_compatibility:
    - "codex"
    - "claude-code"
    - "cursor"
    - "windsurf"
triggers:
  - "scrape news article python"
  - "extract news image and author"
  - "newspaper4k article parsing"
permissions:
  fs_read: true
  fs_write: "workspace"
  shell_exec: false
  net_access: false
---

# Newspaper4k Multi-Language News Article Scraper

Extracts news article content in Python using Newspaper4k: automatic language detection, extracting authors, publication dates, top images, videos, and generating extractive text summaries.

## When to Invoke
Invoke this skill whenever you need to:
- scrape news article python
- extract news image and author
- newspaper4k article parsing

## Execution SOP & Rules
1. Initialize article with article = Article(url) and run article.download(); article.parse().
2. Access extracted fields: article.title, article.authors, article.publish_date, article.text.
3. Run article.nlp() to extract keywords and automated article summaries.
4. Respect site rate limits and handle 403/404 HTTP errors gracefully during batch runs.

## Verification Checklist
- Run local linting, syntax validation, and type-checks before reporting completion.
- Ensure all created or modified files adhere to workspace boundaries and avoid uncommitted secrets.
- Verify tests or build commands exit cleanly with return code 0.