Automate web content extraction via browser MCP into JSON or Markdown.
npx skills add https://github.com/RosenGray/sima --skill dom-scraper
Please help me install this Agent Skill. Skill: dom-scraper Source: https://github.com/RosenGray/sima/tree/main/.cursor/skills/dom-scraper Command: npx skills add https://github.com/RosenGray/sima --skill dom-scraper
This Skill automates web content extraction by navigating pages through a browser-based MCP to convert unstructured web content into clean, structured data.
Use the dom-scraper to go to a target URL and request the data you need (e.g., scrape article cards from https://example.com).
High-intent search queries and answers about installing and using this skill.
To extract structured data from dynamic websites into JSON, you can use a browser-based MCP to navigate pages and query the DOM. This approach automates pulling articles, products, and metadata while handling dynamic content and lazy-loading directly into JSON or Markdown formats.
The best way to scrape product titles and prices from an online catalog is by automating web content extraction through a browser MCP. It allows you to navigate category menus, query the DOM, and format the captured structured data into clean JSON or Markdown for analytics.
Yes, you can capture visible text, headings, links, images, and key sections during a full-page scrape. By applying a browser MCP to navigate the target URL, the tool queries the DOM to gather and format these navigation elements and content structures.
Web scraping with a browser MCP does handle lazy-loading on dynamic sites. It automates page navigation and DOM querying to ensure dynamically loaded content is fully rendered before extracting the structured data into your desired output format.
To pull articles and metadata into Markdown from web pages, apply a browser MCP to navigate the target URL and query the DOM. This automates the extraction of unstructured web content, converting it into clean, structured Markdown output.
BorisserzInspect DOM, console, network, and performance data via Chrome DevTools MCP.
aws-samplesProcess and analyze CSV, JSON, and text data files with automated cleaning and transformation.
BURHANDEV-ENTERPRISEAutomate web browser interactions and data extraction via accessibility tree snapshots.
kennyolofsson23-netizenOrchestrate search, scrape, map, crawl, and browser-driven extraction for web research.
