swipenode

Lightning-fast web extraction for AI agents. Extracts structured JSON from Next.js, Nuxt.js, Gatsby, Remix without headless browsers. TLS spoofing bypasses Cloudflare. 98% fewer tokens vs raw HTML. Use for e-commerce, news scraping, API-less data collection, or when web_fetch/browser overhead is too high.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "swipenode" with this command: npx skills add Nefas11/swipenode-2

SwipeNode Skill

Lightning-fast, zero-render web extraction CLI built for AI agents.
Extracts structured data (Next.js/Nuxt.js) without headless browsers.

Repo: https://github.com/sirToby99/swipenode


Binary

~/.openclaw/workspace/skills/swipenode/swipenode

Built from source (Go 1.24), single static binary, no runtime dependencies.


Commands

Extract (single URL)

~/.openclaw/workspace/skills/swipenode/swipenode extract --url <url>

Extract + filter with jq

~/.openclaw/workspace/skills/swipenode/swipenode extract --url https://shop.example.com | jq '.props.pageProps.product'

Batch (multiple URLs concurrently)

~/.openclaw/workspace/skills/swipenode/swipenode batch --urls "https://a.com,https://b.com"

MCP Server (for Claude Desktop / local agents)

~/.openclaw/workspace/skills/swipenode/swipenode mcp

Install as MCP in Claude Desktop

~/.openclaw/workspace/skills/swipenode/swipenode install-mcp

What it extracts

FrameworkData source
Next.js__NEXT_DATA__ JSON blob
Nuxt.jswindow.__NUXT__
Gatsbywindow.___gatsby
Remixwindow.__remixContext
JSON-LD<script type="application/ld+json">
FallbackClean visible text (boilerplate stripped)

Smart pruning: Strips tracking pixels, telemetry, base64 images, UI noise → up to 98% fewer tokens vs raw HTML.


When to use vs web_fetch

SituationTool
Data-rich site (Next.js shop, news portal)swipenode
Cloudflare-protected siteswipenode (TLS spoofing)
Need structured JSON from React/Vue appswipenode
Simple static page / docsweb_fetch
Need screenshots / DOM interactionbrowser
308/421 redirect errorstry web_fetch as fallback

Known Limitations

  • HTTP 308/421 redirect errors on some CDN-hosted sites (e.g. vercel.com, nextjs.org) — use web_fetch as fallback
  • No JavaScript execution — if data is loaded client-side only, won't help
  • No DOM interaction (no clicks, forms)

Examples

HN front page (clean text fallback)

~/.openclaw/workspace/skills/swipenode/swipenode extract --url https://news.ycombinator.com
# Returns: clean list of titles, points, comments

E-Commerce product data (Next.js)

~/.openclaw/workspace/skills/swipenode/swipenode extract --url https://shop.example.com/product/123 | jq '.props.pageProps'

Token savings comparison

Raw HTML → LLM:      ~15.000 tokens (div soup, scripts, tracking)
SwipeNode extract:   ~300 tokens (clean structured JSON)
Savings:             ~98%

Build from source

# Requires Go 1.24+
export PATH="/tmp/go/bin:$PATH"  # or system Go
git clone https://github.com/sirToby99/swipenode.git /tmp/swipenode-build
cd /tmp/swipenode-build
go build -o ~/.openclaw/workspace/skills/swipenode/swipenode .

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

LinkedIn Data Scraper

Scrape LinkedIn profiles, job listings, and company pages. Bypass LinkedIn's aggressive anti-bot detection with sticky residential proxy sessions. Extract na...

Registry SourceRecently Updated
Automation

Tinder Dating Automation

Manage multiple Tinder, Bumble, and Hinge accounts for A/B testing profiles, expanding match radius, and scaling outreach. Use mobile-grade residential proxi...

Registry SourceRecently Updated
Automation

moltbook

The social network for AI agents. Post, comment, upvote, and create communities.

Registry SourceRecently Updated