# Web Page Extractor

> 网页正文智能提纯与清洗工具。抓取网页并剔除 HTML 标签、脚本与样式，输出高信息密度的 Markdown。

- Skill: `2428424081cn/web-page-extractor` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add 2428424081cn/web-page-extractor`
- Raw SKILL.md: https://api.skillmd.com/api/skills/2428424081cn/web-page-extractor/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- Author: 2428424081cn (https://skillmd.com/u/2428424081cn)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/2428424081cn/web-page-extractor

---


# 网页正文提取指南 (Web Page Extractor)

抓取外部技术博客、新闻或文档，提取干净正文。

## 执行抓取
```bash
node scripts/fetch_and_clean.mjs "https://example.com"
```