← Back to Skills Marketplace
431
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install scrapling-yoo
Description
Advanced web scraping with Scrapling — MCP-native guidance for extraction, crawling, and anti-bot handling. Use via mcporter (MCP) for execution; this skill...
Usage Guidance
This package appears to be legitimate-sounding scraping guidance and helper scripts, but take these precautions before installing or running:
1) Verify provenance: check the upstream project (GitHub/ PyPI) and confirm the maintainer matches the registry listing; the included _meta.json ownerId differs from the registry ownerId which may indicate repackaging.
2) Inspect and pin the pip package: if you pip install scrapling, confirm the exact PyPI project name, version, and upstream repository. Prefer installing in a fresh virtualenv or container.
3) Be careful with credentials and external services: features like proxy rotation or 'solve_cloudflare' commonly require external providers and API keys—do not reuse sensitive credentials. The skill does not request env vars but examples expect you to supply credentials if you use those features.
4) Legal/ethical reminder: the docs include explicit warnings about not scraping private or paywalled data. Only use stealthy/rotation features on targets you are authorized to access.
5) Run in a sandbox first: execute the included smoke test script in an isolated environment and review network traffic if you are concerned about exfiltration.
If you want a stronger assurance, ask the maintainer for the canonical repository URL and signed release artifacts, or prefer packages that are traceable to a known PyPI/GitHub owner.
Capability Analysis
Type: OpenClaw Skill
Name: scrapling-yoo
Version: 1.0.0
This skill bundle provides advanced web scraping capabilities via the Scrapling library, including fetching arbitrary URLs, browser automation, anti-bot bypass (e.g., Cloudflare/Turnstile solving), and proxy rotation, as demonstrated in `scripts/scrapling_scrape.py` and `scripts/scrapling_smoke_test.py`. While the `SKILL.md` and `references/anti-bot.md` contain explicit 'Guardrails' and warnings against unauthorized use, the inherent power of these features presents a significant risk of misuse for unauthorized data collection or denial-of-service activities. There is no evidence of intentional malicious behavior (e.g., data exfiltration to unauthorized endpoints, persistence mechanisms) within the code itself, but the high-risk capabilities warrant a 'suspicious' classification.
Capability Assessment
Purpose & Capability
Name/description match the included files: SKILL.md, reference docs, and helper scripts all describe and call a 'scrapling' Python package and MCP integration. However _meta.json contains a different ownerId/slug/version than the registry metadata, which suggests the package may have been copied or repackaged; verify provenance before trusting.
Instruction Scope
Runtime instructions are focused on scraping, MCP integration, and anti-bot strategies. The guidance explicitly warns to avoid scraping private/paywalled data and includes escalation steps (stealthy fetchers, Cloudflare solving, proxy rotation). Those are within the stated purpose but expand the skill into potentially sensitive territory (anti-bot evasion). The SKILL.md and scripts do not instruct reading unrelated system files or exfiltrating data to hidden endpoints.
Install Mechanism
This is an instruction-only skill with example pip install commands (pip install scrapling[mcp,etc.]). There is no bundled install script or downloaded binary. Relying on pip is typical, but you should confirm the package's identity on PyPI/GitHub before installing.
Credentials
The skill declares no required environment variables or credentials (good). But reference docs and recipes show examples that use proxies with credentials and API bearer tokens, and anti-bot instructions (solve_cloudflare) imply use of external solver services which commonly require keys—none are declared. That absence isn't malicious by itself but means the skill expects you to supply sensitive credentials when you choose to use features like proxy rotation or third-party solvers.
Persistence & Privilege
Skill is not always-enabled, has no requested persistent privileges, and does not modify other skills' configs. It simply contains guidance and helper scripts that run in the user's environment.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install scrapling-yoo - After installation, invoke the skill by name or use
/scrapling-yoo - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
scrapling-yoo 1.0.0
- Initial release providing web scraping guidance, strategies, and best practices for the Scrapling framework integrated with MCP (mcporter/OpenClaw).
- Covers fetcher selection, anti-bot techniques, spider patterns, and adaptive scraping.
- Includes step-by-step quick start instructions for MCP integration and usage.
- Documents core concepts, spider framework usage, parser API, proxy rotation, CLI commands, and common scraping recipes.
Metadata
Frequently Asked Questions
What is Scrapling Yoo?
Advanced web scraping with Scrapling — MCP-native guidance for extraction, crawling, and anti-bot handling. Use via mcporter (MCP) for execution; this skill... It is an AI Agent Skill for Claude Code / OpenClaw, with 431 downloads so far.
How do I install Scrapling Yoo?
Run "/install scrapling-yoo" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Scrapling Yoo free?
Yes, Scrapling Yoo is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Scrapling Yoo support?
Scrapling Yoo is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Scrapling Yoo?
It is built and maintained by C5Q5 (@cccccqqqqq); the current version is v1.0.0.
More Skills