enudimmud/skills/scrapling
skills/scrapling/SKILL.md
# Scrapling Skill - Advanced Web Scraping ## Overview Scrapling is a modern web scraping framework with: - **Adaptive element finding** — Survives website redesigns - **Anti-bot bypass** — Handles Cloudflare Turnstile - **MCP Server** — Token-optimized content extraction for AI - **Multiple fetchers** — HTTP (fast) or browser-based (stealth) ## Installation Already installed in venv at `~/.openclaw/workspace/skills/scrapling/venv/` **Dependencies:** - Python 3.10+ - Chromium browser (instal
tools
Updated Apr 4, 2026
$ install --global
skillsauthnpx skillsauth add enudimmud/enki-openclaw skills/scraplingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 4, 2026, 8:24 PM27.6s7 files scanned
SKILL.md
Scrapling Skill - Advanced Web Scraping
Overview
Scrapling is a modern web scraping framework with:
- Adaptive element finding — Survives website redesigns
- Anti-bot bypass — Handles Cloudflare Turnstile
- MCP Server — Token-optimized content extraction for AI
- Multiple fetchers — HTTP (fast) or browser-based (stealth)
Installation
Already installed in venv at ~/.openclaw/workspace/skills/scrapling/venv/
Dependencies:
- Python 3.10+
- Chromium browser (installed in
~/.cache/ms-playwright/) - MCP support enabled via
scrapling[ai]
Usage Patterns
1. Simple HTTP Scraping (Fast)
from scrapling.fetchers import Fetcher
page = Fetcher.get('https://example.com')
data = page.css('.product .title::text').getall()
Use when:
- No anti-bot protection
- Static content
- Speed matters
2. Adaptive Mode (Survives Redesigns)
from scrapling.fetchers import Fetcher
# First scrape - save element locations
page = Fetcher.get('https://example.com')
products = page.css('.product', auto_save=True)
# Later, after website changes
page2 = Fetcher.get('https://example.com')
products2 = page2.css('.product', adaptive=True) # Auto-relocates!
Use when:
- Monitoring long-term
- Website changes frequently
3. Stealth Mode (Bypass Anti-Bot)
from scrapling.fetchers import StealthyFetcher
page = StealthyFetcher.fetch('https://protected-site.com',
headless=True,
solve_cloudflare=True)
data = page.css('.content').get()
Use when:
- Cloudflare protected
- Anti-bot systems detected
- Need browser fingerprinting
4. MCP Server (Token-Optimized for AI)
Start server:
venv/bin/scrapling mcp --http --port 8000
Features:
- Extracts targeted content BEFORE sending to LLM
- Strips useless HTML tags
- Reduces token consumption significantly
- Compatible with Claude Desktop, VS Code Copilot
Use when:
- Processing large pages
- Want to reduce API costs
- Need structured extraction
Command Reference
Interactive shell:
venv/bin/scrapling shell
Direct extraction (no code):
venv/bin/scrapling extract get 'https://example.com' content.md --css-selector '.main'
Performance
- Parsing: 2.02ms (baseline, fastest)
- Adaptive finding: 2.39ms (~5x faster than AutoScraper)
- HTTP requests: TLS fingerprint spoofing, HTTP/3 support
Limitations
On SteamOS:
- ⚠️ Browser system deps failed (sudo required)
- ✅ HTTP fetcher works perfectly
- ⚠️ Stealth/Dynamic fetchers untested (may work despite warnings)
- ✅ MCP server functional
General:
- Respect robots.txt
- Cloudflare bypass may violate ToS
- Educational/research use only
Integration Ideas
- Replace web_fetch for complex scraping
- MCP server for token reduction (priority)
- Monitoring skill — Adaptive mode for long-term tracking
- Token metrics scraper — Solana explorers (with stealth)
- Lore research — NeukoAI community posts
References
- Repo: https://github.com/D4Vinci/Scrapling
- Docs: https://scrapling.readthedocs.io
- Latest: v0.4.1
- Installed:
~/.openclaw/workspace/skills/scrapling/
Philosophy alignment: Grey mastery tool. Learn to audit data, bypass restrictions when necessary, but always respect the law and ethics.
Related Skills
enudimmud/twitter-post
documentation
VerifiedTrustedCommunity
Post tweets to @HelvetiVault with validation and posting rules enforcement. Supports text, threads, and media. Enforces daily limits and content guidelines.
SKILL.mdUpdated Apr 4, 2026
enudimmud/sponge-wallet
development
VerifiedTrustedCommunity
Crypto wallet, token swaps, cross-chain bridges, Tempo transfers, and access to paid external services (search, image gen, web scraping, AI, and more) via x402 and MPP micropayments.
SKILL.mdUpdated Apr 4, 2026
enudimmud/plantnet-identify
development
VerifiedTrustedCommunity
Identify plants, detect diseases, and provide biodynamic care recommendations using Pl@ntNet API. Supports image URLs and local files. Returns species name, confidence score, care tips aligned with lunar calendar, and treatment recommendations.
SKILL.mdUpdated Apr 4, 2026
enudimmud/lunar
tools
VerifiedTrustedCommunity
Get lunar phases, biodynamic calendar (Michel Gros method), and holistic environmental readings. Use when discussing moon influence, planting calendars, biodynamic agriculture, or requesting environmental/holistic context.
SKILL.mdUpdated Apr 4, 2026