Forgedemy
CatalogPreview source

shirenchuang

Web Content Fetcher — 网页正文提取

Extract clean Markdown content from any URL using a three-tier strategy: Jina Reader, Scrapling, or web_fetch.

Price

Free

Files

0

Rating

0.0

Reviews

0

Source

Source repo

Get freePreview source

About

Fetches web page main content and converts it to clean Markdown (preserving headings, links, images, code blocks) via a three-tier fallback: Jina Reader (fast, 200/day free), Scrapling+html2text (unlimited, handles WeChat/anti-bot sites like Substack and Medium), and direct web_fetch (static pages). Includes domain-based routing shortcuts to skip Jina for known anti-scraping platforms. Has a two-failure stop rule to prevent infinite retries.

By shirenchuang

Identity GitHub shirenchuang

What the agent sees

name

skills-sh-shirenchuang-web-content-fetcher-web-content-fetcher

description

Extract clean Markdown content from any URL using a three-tier strategy: Jina Reader, Scrapling, or web_fetch.

Tags

web-scrapingcontent-extractionmarkdownjinascraplingchineseTools: skills-cli, external-adapter, upstream-install

Technical details

Source repoOriginal GitHub linkPublisher site

Source repo

https://github.com/shirenchuang/web-content-fetcher

Original GitHub link

https://github.com/shirenchuang/web-content-fetcher

Publisher site

https://skills.sh/shirenchuang/web-content-fetcher/web-content-fetcher

Packaging note

Imported from the public skills.sh trending snapshot fetched at 2026-03-18T00:58:16.450Z. Snapshot rank #441 with 332 weekly installs. Bundle files are not mirrored into Forgedemy.

Recent reviews

No reviews yet.