2lab-ai

Scraping — Data skill for Claude Code

Data community

A Claude Code skill for web scraping and data extraction using Scrapling.

How to install Scraping

This entry records only its repository, not the path inside it, so there is no exact command to give. Open 2lab-ai/scraping and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Scraping does

A Claude Code skill for web scraping and data extraction using [Scrapling](https://github.com/D4Vinci/Scrapling).

Alternatives in Data

Bitbucket Data Center 71.9k ★
Financial Services — Reference agents, skills, and data connectors for the financial-services workflows we see most — investment ba 34.5k ★
Data Contract — This document defines which files belong to the system (auto-updatable) and which belong to the user (never to 32.5k ★

README

scraping

A Claude Code skill for web scraping and data extraction using [Scrapling](https://github.com/D4Vinci/Scrapling).

What is this?

This is a **skill** (in [Anthropic skill-creator](https://github.com/anthropics/skills/tree/main/skills/skill-creator) format) that gives Claude Code the ability to scrape websites, extract structured data, search e-commerce sites, and compare prices across multiple stores.

Installation

As a Claude Code Skill

# From this repo
claude install-skill /path/to/scraping

# Or from GitHub
claude install-skill https://github.com/2lab-ai/scraping

Prerequisites

The skill expects a Python venv with Scrapling installed:

# Create venv
python3 -m venv ~/.scrapling-venv

# Install Scrapling with all extras
~/.scrapling-venv/bin/pip install "scrapling[all]"

# Install Chromium for headless browsing
~/.scrapling-venv/bin/python3 -c "from scrapling.fetchers import StealthyFetcher; StealthyFetcher.setup()"

**Note**: On servers without root access, Chromium shared libraries (libnspr4, libnss3, etc.) may need manual installation. See [SKILL.md](SKILL.md) for the `LD_LIBRARY_PATH` workaround.

Capabilities

Feature	Fetcher	Bot Protection
Static HTML scraping	`Fetcher`	None
Anti-bot bypass (Akamai, Cloudflare)	`StealthyFetcher`	Yes
JS-rendered SPA content	`DynamicFetcher`	Yes
Multi-page crawling	`Spider`	None
Stateful sessions (login, cookies)	`StealthySession`	Yes

Supported Sites

Site-specific parsing patterns are documented in [`references/sites.md`](references/sites.md):

Coupang (coupang.com) — Akamai-protected, React SPA, requires StealthyFetcher
Amazon.de — ASIN-based product extraction
DocMorris.de — German pharmacy, static HTML