web-content-fetcher
Fetches web content and converts it to clean Markdown using Scrapling, Jina Reader, and domain-aware routing.
Install
npx skills add https://github.com/shirenchuang/web-content-fetcher --skill web-content-fetcherStats
| Total installs | 1,169 |
| Weekly installs | 1.2K |
| GitHub stars | 484 |
| First seen | Mar 9, 2026 |
| Source | @shirenchuang/web-content-fetcher |
Summary
- Implements cascading extraction methods: Jina Reader (fast, 200 requests/day free), Scrapling + html2text (unlimited, handles paywalled content), and direct web_fetch (static pages fallback)
- Preserves Markdown structure including headings, links, images, lists, code blocks, and blockquotes
- Domain-aware routing skips Jina for WeChat articles, Zhihu, Juejin, and CSDN to conserve quota and improve success rates
- Requires scrapling[fetchers] and html2text dependencies; includes built-in script at scripts/fetch.py for manual Scrapling extraction
Tags
Related skills
| Skill | Installs | vs web-content-fetcher |
|---|---|---|
| nuxt-seo | 1,046 | -123 |
| anti-render | 1,210 | +41 |
| release-management | 1,143 | -26 |
| beat-competitors | 1,257 | +88 |
| fix-linking | 1,241 | +72 |
FAQ
- How many installs does web-content-fetcher have?
- web-content-fetcher has 1,169 total installs and 1.2K installs this week.
- Where is web-content-fetcher hosted?
- web-content-fetcher is published by @shirenchuang/web-content-fetcher at https://github.com/shirenchuang/web-content-fetcher.
- How many GitHub stars does web-content-fetcher have?
- web-content-fetcher has 484 GitHub stars.
- When was web-content-fetcher first indexed?
- OrangeBot.AI first indexed web-content-fetcher on Mar 9, 2026.
- How do I install web-content-fetcher?
- Run: npx skills add https://github.com/shirenchuang/web-content-fetcher --skill web-content-fetcher