🎯

web-scraping

🎯Skill

from tatat/agents-playground

VibeIndex|
What it does

Extracts structured web data using CSS selectors and XPath, parsing HTML content into JSON or CSV formats with intelligent request handling.

πŸ“¦

Part of

tatat/agents-playground(25 items)

web-scraping

Installation

uv runRun with uv
uv run pre-commit install
uv runRun with uv
uv run jupyter notebook
uv runRun with uv
uv run agentchat-direct
uv runRun with uv
uv run agentchat-programmatic
MakeRun with Make
make lint # ruff check

+ 3 more commands

πŸ“– Extracted from docs: tatat/agents-playground
4Installs
-
AddedFeb 4, 2026

Skill Details

SKILL.md

Extract structured data from web pages using CSS selectors and XPath

Overview

# Web Scraping

Extract structured data from web pages.

Capabilities

  • Fetch HTML content from URLs
  • Parse and extract specific elements (tables, lists, text)
  • Handle pagination
  • Output in JSON or CSV format

Supported Selectors

  • CSS selectors: .class, #id, tag
  • XPath expressions
  • Text patterns (regex)

Rate Limiting

Always respect robots.txt and implement delays between requests.

Default delay: 1 second between requests.

Example

```

Scrape product names and prices from example.com/products

Output as JSON with fields: name, price, url

```