skills.rest
CC90210
CC90210COMMUNITY
Explore all skills by this author →
WebsiteGitHub

web-scraping

Extract structured data from websites using Firecrawl and Playwright.

1|Updated Apr 18, 2026
Search Tags:#automation#research#scraping#data-extraction#lead-generation#browser-harness
One-click install
npx skills add https://github.com/CC90210/CMO-Agent --skill web-scraping-cc90210
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-scraping
Source: https://github.com/CC90210/CMO-Agent/tree/main/skills/web-scraping
Command: npx skills add https://github.com/CC90210/CMO-Agent --skill web-scraping-cc90210

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, firecrawl, and includes scripts (resource) components.

What problem does it solve?

This skill solves the challenge of gathering data from websites that lack APIs, require complex interactions, or demand authenticated sessions, effectively automating manual research and site-interaction workflows.

Core Features & Use Cases

  • Intelligent Extraction: Uses Firecrawl to convert public web pages into clean, structured markdown or JSON.
  • Browser Automation: Employs Playwright for deterministic web workflows and a Browser Harness to perform actions within your authenticated Chrome sessions.
  • Use Case: Automatically scrape competitor pricing pages, harvest leads from industry directories, or perform authenticated actions on internal SaaS dashboards without manual login.

Quick Start

Use the web-scraping skill to extract all pricing data from the competitor website at example.com and save it as a structured JSON file.

Frequently Asked Questions about web-scraping

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract structured data from web pages that lack an API?▼

Web data extraction from API-less sites uses Firecrawl to convert public pages into clean markdown or JSON. This approach automates manual research workflows and handles sites requiring complex interactions.

Can I automate actions on authenticated SaaS dashboards without manual login?▼

Automating authenticated SaaS dashboard actions is possible using a Browser Harness to perform interactions within your authenticated Chrome sessions. This enables session-persistent browser tasks without manual logins.

Does this web scraping approach work with Playwright for deterministic browser automation?▼

This web scraping approach works with Playwright for deterministic browser automation. It employs Playwright to execute reliable web workflows, while Firecrawl handles public content extraction.

What's the best way to scrape competitor pricing pages and save the results as JSON?▼

The best way to scrape competitor pricing pages into JSON is using Firecrawl for public content extraction. It intelligently converts the web pages into structured data files for competitor research.

Do I need Firecrawl and Playwright to harvest leads from industry directories?▼

You need Firecrawl to harvest leads from public industry directories, converting pages to structured data. Playwright is required separately for deterministic browser automation and complex web interactions.

Related Skills

Explore More Marketing & Sales Skills→
nillenille

browser-test

Automate browser UI tests with Playwright MCP and Chrome Bridge.

Community
Advanced
eKoh951eKoh951

apify-ultimate-scraper

Automate multi-platform data scraping across 55+ platforms with AI-driven actor selection.

Community
Advanced
CleanExpoCleanExpo
1

playwright-browser

Automate headless browser tasks and end-to-end tests with Playwright.

Community
Advanced
iamasters-academyiamasters-academy
20

tool-firecrawl-scraper

Scrape web pages and extract text and HTML content via the Firecrawl API.

Official
Intermediate