Summary
A straightforward news scraper that pulls article content from 12 platforms including WeChat Official Accounts, Toutiao, BBC, CNN, and Twitter, then outputs both JSON and Markdown. It auto-detects the platform from the URL and handles the HTTP juggling with curl_cffi for browser impersonation. The Twitter support is nice because it works with public tweets out of the box and accepts cookies for protected ones. Built with uv for dependency management and includes all the crawler code in one package, so you can lift it into another project without hunting down pieces. Good for when you need clean article extraction without building parsers for each platform yourself.
Install to Claude Code
npx -y skills add nanmicoder/newscrawler --skill china-news-crawler --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →First SeenJun 3, 2026
