VOOZH about

URL: https://apify.com/dtrungtin/stagehand-crawler

⇱ Stagehand Crawler Β· Apify


Pricing

from $20.00 / 1,000 results

Go to Apify Store

Stagehand is a browser automation framework used to control web browsers with natural language and code.

Pricing

from $20.00 / 1,000 results

Rating

0.0

(0)

Developer

πŸ‘ Tin

Tin

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

25 days ago

Last modified

Categories

Share

An Apify Actor that uses Stagehand β€” an AI-powered browser automation framework β€” to execute natural language instructions on web pages. Point it at any URL, describe what you want in plain English, and the AI agent will interact with the page and return results along with a final screenshot.

What it does

  1. Visits each URL in startUrls
  2. Runs an AI agent that follows your instruction using real browser interactions (clicks, typing, scrolling, navigation)
  3. Captures a screenshot of the final page state and saves it to the key-value store
  4. Pushes a result record to the dataset containing the outcome, a summary message, and the screenshot URL

Input

FieldTypeRequiredDescription
startUrlsarrayyesURLs the crawler will visit
instructionstringyesNatural language task for the AI agent (e.g. "Find the price of the first product")
modestringyesAgent mode: dom, hybrid, or cua
modelstringyesAI model in provider/model format (e.g. google/gemini-3-flash-preview)
apiKeystringyesAPI key for the selected model provider
proxyConfigobjectyesProxy settings β€” Apify Proxy recommended on the platform
maxStepsintegernoMax browser interactions before stopping (default: 20, range: 1–20)

Agent modes

  • dom β€” Reads the page DOM to determine actions. Fast and cost-efficient.
  • hybrid β€” Combines DOM and visual understanding. Best for complex layouts. Requires a vision-capable model (Gemini, Claude).
  • cua β€” Computer-use agent; operates purely from screenshots. Most powerful, highest cost.

Example input

{
"startUrls":[{"url":"https://www.ebay.com/"}],
"instruction":"Search for 'mechanical keyboard' and return the title and price of the first result.",
"mode":"hybrid",
"model":"google/gemini-3-flash-preview",
"apiKey":"YOUR_GOOGLE_AI_API_KEY",
"maxSteps":15,
"proxyConfig":{"useApifyProxy":true}
}

Output

Each processed URL produces one dataset record:

{
"url":"https://www.ebay.com/",
"success":true,
"message":"The first result is 'Keychron K2 Pro' priced at $89.99.",
"imageUrl":"https://api.apify.com/v2/key-value-stores/<storeId>/records/final_screenshot_<uuid>.png"
}

The imageUrl links directly to the PNG screenshot saved in the default key-value store.

Resources

You might also like

Puppeteer MCP

meysamazing/puppeteer-mcp

AI-powered browser automation via Model Context Protocol. Enable Claude, ChatGPT, and other AI assistants to control browsers, scrape data, and automate web tasks through natural language.

DEPRICATED Browser Mcp

nahom.network/depricated-browser-mcp

The Browser MCP Actor combines Browser with the Model Context Protocol (MCP) to let AI agents control web browsers via a standardized interface. It enables navigation, data extraction, form filling, testing, and complex web automation.

🎭 Playwright MCP β€” AI Browser Automation

nexgendata/playwright-mcp-server

MCP server for AI agents to control browsers via Playwright β€” navigate, click, type, screenshot & extract data. Give Claude or GPT web browsing abilities. 16 tools for browser automation.

21

5.0

AI Web Scraper with Playwright Browser (No-Code, MCP)

data_rig/ai-web-scraper

Run a real Playwright browser as an AI web scraper. Extract structured data from any site using natural languageβ€”no selectors or scripts. Handles JS-heavy pages, pagination, and interactions. Built for MCP agents like OpenCode and Claude Code.

Smartcontext AI Web Crawler

bluelightco/smartcontext-ai-crawler

Scrape any website and extract structured data using AI-powered instructions. Provide URLs and a natural language prompt to get tailored JSON outputs.

206

5.0

Propertyshark Discovery Scraper

getdataforme/propertyshark-discovery-scraper

Camoufox Playwright Crawler TypeScript is a robust web scraping tool for extracting detailed property data using the Playwright framework....

Apify Prompt Pilot

louvre/apify-prompt-pilot

The Prompt Pilot is a powerful AI-powered tool designed to automate web browser interactions using natural language prompts. It leverages OpenAI models to understand your instructions and perform complex browser automation tasks without writing traditional automation scripts.

13

5.0

Newsapi Ai

dc-codes426/newsapi-ai

LLM Agent for searching the news. Interact with structured or natural language, and receive responses in structured or natural language. Perfect for a chatbot or for your AI agents that need to look up the news.

Website Tech Stack Detector - CMS & Framework

logiover/website-tech-stack-detector

Bulk BuiltWith API alternative: detect any website's CMS, framework, analytics & hosting, then export the tech stack to CSV/JSON. No browser, pay per result.

Related articles

Browserbase vs. Nextbrowser for cloud-based browser automation
Read more
11 best open-source web crawlers and scrapers in 2026
Read more
Web scraping with JavaScript vs. Python in 2025
Read more