Enables scraping of structured information from websites using standard CSS and XPath selection patterns.

Install

mkdir -p .claude/skills/web-scraping && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11755" && unzip -o skill.zip -d .claude/skills/web-scraping && rm skill.zip

Installs to .claude/skills/web-scraping

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Extract structured data from web pages using CSS selectors and XPath
68 charsno explicit “when” trigger
Beginner

Key capabilities

  • Fetch HTML content from URLs
  • Parse and extract specific elements
  • Handle pagination
  • Output data in JSON format
  • Output data in CSV format

How it works

This skill fetches HTML content from specified URLs and then parses it to extract data using CSS selectors, XPath expressions, or text patterns. It can also manage pagination.

Inputs & outputs

You give it
URL and CSS selectors or XPath expressions
You get back
Structured data in JSON or CSV format

When to use web-scraping

  • Scraping product pricing from a site
  • Collecting articles from a news page
  • Extracting table data to JSON

About this skill

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

When not to use it

  • The website's robots.txt disallows scraping
  • The task requires interacting with dynamic content that is not rendered in the initial HTML

Limitations

  • Must respect robots.txt
  • Implements a default delay of 1 second between requests
  • Limited to extracting data from web pages

How it compares

This skill automates the extraction of structured data from web pages using defined selectors, which is more efficient than manual data collection.

Compared to similar skills

web-scraping side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
web-scraping (this skill)07moNo flagsBeginner
firecrawl-scraper248moCautionBeginner
web-scraper03moReviewIntermediate
google-maps-reviews-api-skill01moReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry