Web Content Fetcher
by shirenchuang670f8b36197fNo license610 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 6 months ago
Extract article content from any URL as clean Markdown. Uses Scrapling script as primary method (with auto fast→stealth fallback), Jina Reader as alternative for simple pages. Preserves headings, links, images, lists, and code blocks. Use this skill whenever the user wants to fetch, read, extract, scrape, or summarize content from a URL — including blog posts, news articles, WeChat articles (微信公众号), documentation pages, or any web page. Also trigger when the user says things like "帮我读一下这篇文章", "抓取这个网页", "提取正文", or "read this page for me".
Only the file list is public. File contents are available once the skill is installed in a workspace.
| Path | Size | Type |
|---|---|---|
| .gitignore | 14 B | text/plain |
| qrcode_for_shizhen.jpg | 38.8 KB | image/jpeg |
| README.md | 6 KB | text/markdown |
| requirements.txt | 20 B | text/plain |
| scripts/fetch.py | 7 KB | text/plain |
| SKILL.md | 3.6 KB | text/markdown |
Source and attribution
Source:shirenchuang/web-content-fetcherat commit670f8b3
License: No license
Content belongs to its original authors. SourceWeft indexes it from a public repository.