# Web Browse

> Fetch and parse web pages using curl + python for HTML-to-text extraction.

- Skill: `thinkfleetai/web-browse` (Agent Skill)
- Install (CLI): `npx skillmds@latest add thinkfleetai/web-browse`
- Raw SKILL.md: https://api.skillmd.com/api/skills/thinkfleetai/web-browse/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- Author: thinkfleetai (https://skillmd.com/u/thinkfleetai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/thinkfleetai/web-browse

---


# Web Browse

Fetch web pages and extract readable text content.

## Quick fetch (raw HTML)

```bash
curl -sL "https://example.com" | head -200
```

## Extract text with Python

```bash
curl -sL "https://example.com" | python3 -c "
import sys, html, re
raw = sys.stdin.read()
text = re.sub(r'<script[^>]*>.*?</script>', '', raw, flags=re.DOTALL)
text = re.sub(r'<style[^>]*>.*?</style>', '', text, flags=re.DOTALL)
text = re.sub(r'<[^>]+>', ' ', text)
text = html.unescape(text)
text = re.sub(r'\s+', ' ', text).strip()
print(text[:8000])
"
```

## Get page title and meta

```bash
curl -sL "https://example.com" | python3 -c "
import sys, re
h = sys.stdin.read()
title = re.search(r'<title>(.*?)</title>', h, re.I|re.S)
desc = re.search(r'<meta[^>]*name=[\"']description[\"'][^>]*content=[\"'](.*?)[\"']', h, re.I)
print(f'Title: {title.group(1).strip() if title else \"N/A\"}')
print(f'Description: {desc.group(1).strip() if desc else \"N/A\"}')
"
```

## Download a file

```bash
curl -sL -o /tmp/file.pdf "https://example.com/report.pdf"
```

## Notes

- Respect robots.txt. Do not scrape excessively.
- Use `-L` to follow redirects.
- For JavaScript-heavy sites, consider the browser skill.