Pricing

$15.00 / 1,000 promptresults

Go to Store

🔥fireScraper AI Prompt Website Content Markdown Scraper

Try for free

Developed by

mohamed el hadi msaid

fireScrape AI is an advanced web scraper built with Crawlee and Puppeteer. It crawls websites, extracts meaningful content, converts it into Markdown, then runs your custom prompt on the extracted text—ideal for generating enriched datasets, summaries or analyses for LLMs and AI pipelines

5.0 (1)

Pricing

$15.00 / 1,000 promptresults

Total users

Monthly users

Runs succeeded

>99%

Last modified

2 days ago

Developer tools

Automation

🔥 fireScrape AI Prompt Website Content Markdown Scraper

Overview

fireScrape AI is an advanced web scraper built with Crawlee and Puppeteer. It crawls websites, extracts meaningful content, converts it into Markdown, then runs your custom prompt on the extracted text—ideal for generating enriched datasets, summaries or analyses for LLMs and AI pipelines.

🎯 Features

📝 Extracts visible text, full HTML, or both
🔄 Applies your custom prompt (e.g. “Summarize this page”) to each page
📝 Converts content to clean Markdown
📸 Captures full‑page screenshots
🌐 Supports proxy configurations (Apify Proxy, custom)
🔗 Follows links for deep multi-page crawling
⚙️ Easily extended for JS‑heavy sites, login flows, or custom selectors

🛠️ Input Schema

{
  "startUrls": [
    { "url": "https://apify.com" }
  ],
  "prompt": "Summarize the key points of this page in bullet form.",
  "maxPages": 5,
  "proxyConfig": {
    "useApifyProxy": true
  },
  "screenshot": true,
  "enqueue": true,
  "getText": false,
  "getHtml": false
}

Field	Type	Description
`startUrls`	Array	List of seed URLs to crawl. Required.
`prompt`	String	Custom instruction or question to run on each page’s extracted content.
`maxPages`	Integer	Maximum number of pages to visit. Default: `5`.
`proxyConfig`	Object	Proxy settings (supports Apify Proxy).
`screenshot`	Boolean	Capture a screenshot of each page. Default: `true`.
`enqueue`	Boolean	Follow and enqueue new links found on each page. Default: `true`.
`getText`	Boolean	Extract only visible text content. Default: `false`.
`getHtml`	Boolean	Extract full raw HTML. Default: `false`.

✅ Output Format

Each page yields a JSON object with:

{
  "url": "https://example.com",
  "title": "Example Page",
  "promptResult": "• Point one\n• Point two\n• Point three",
  "metadata": {
    "description": "An example page",
    "keywords": ["example","page"]
  },
  "markdown": "# Example Page\n\nThis is the markdown content…",
  "textContent": "This is the visible text…",
  "htmlContent": "<html>…</html>",
  "screenshot": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUg…"
}

🚀 Use Cases

LLM Dataset Creation Collect and pre‑process web content into Markdown, then run custom prompts to generate training samples, summaries, or question‑answer pairs.
Automated Content Summaries Crawl blogs, news sites or documentation to produce concise, prompt‑driven summaries for research or reporting.
SEO & Content Audits Extract headings, metadata and full text, then prompt your model to analyze keyword usage, readability and suggestions.
Knowledge Base Generation Pull FAQs, tutorials or API docs and transform them into structured Markdown + AI‑enriched annotations for internal wikis or help desks.
Competitive Intelligence Scrape competitor sites at scale, run custom prompts to highlight feature comparisons, pricing tables, or sentiment across pages.

🚀 How to Run

Deploy the actor on Apify or run locally.
Configure startUrls, prompt and other options via UI or API.
Click Run, monitor logs in real time.
Download the dataset as JSON or Markdown for downstream use.

🔧 Customization Tips

Chain multiple prompts or different prompts per domain
Add login/authentication handlers for gated content
Integrate NLP post‑processing (e.g. entity extraction)
Output to alternate formats (PDF, DOCX, CSV)

Happy scraping and AI‑driven insights! 🚀🔥

On this page

🔥 fireScrape AI Prompt Website Content Markdown Scraper

Share Actor:

🔥 FireScrape AI Website Content Markdown Scraper

mohamedgb00714/fireScraper-AI-Website-Content-Markdown-Scraper

Advanced web scraper powered by Crawlee and Puppeteer — extracts website content, converts it to Markdown, and structures it for LLM training datasets.

mohamed el hadi msaid

2.4

Website Content Crawler

apify/website-content-crawler

Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with 🦜🔗 LangChain, LlamaIndex, and the wider LLM ecosystem.

Apify

61K

4.0

RAG Web Browser

apify/rag-web-browser

Web browser for OpenAI Assistants, RAG pipelines, or AI agents, similar to a web browser in ChatGPT. It queries Google Search, scrapes the top N pages, and returns their content as Markdown for further processing by an LLM. It can also scrape individual URLs. Supports Model Context Protocol (MCP).

Apify

4.2K

4.3

AI Website Content Markdown Scraper

quaking_pail/ai-website-content-markdown-scraper

This Apify Actor, "Website Content Crawler with Markdown Extraction," is designed to perform a comprehensive crawl of specified websites, extract their text content, convert it into Markdown format, and store it in a structured dataset. The extracted content is suitable for feeding LLMs.

AI_Builder

598

4.3

Ai SEO Content Curator

quaking_pail/ai-seo-content-markdown-scraper

The SEO Actor performs a full SEO audit for each URL, extracting key SEO metrics like titles, meta descriptions, and keywords. It also retrieves network information and integrates SEO audit data providing a comprehensive analysis stored in an organized database for further use.

AI_Builder

5.0

Dynamic Markdown Scraper

louisdeconinck/dynamic-markdown-scraper

Effortlessly feed LLM AIs with clean Markdown using our advanced web scraper. Seamlessly scrape dynamic, JavaScript-rendered websites while preserving original formatting. Ideal for AI training, documentation, and content migration.

Louis Deconinck

5.0

LinkedIn Jobs & Company Scraper

fetchclub/linkedin-jobs-scraper

Actively Maintained - Cheap Rental & Run Cost - LinkedIn Jobs Scraper + Companies - to extract job listings worldwide. Export results for analysis, connect via API, & integrate with other apps. Please note that LinkedIn may block some requests leading their being to fewer results than expected.

FetchClub

531

1.3

Tester MCP Client

jiri.spilka/tester-mcp-client

A model context protocol (MCP) client that connects to any MCP server using Server-Sent Events (SSE) and displays the conversation in a chat-like UI. It is a standalone Actor server designed for testing MCP servers over SSE.

Jiří Spilka

589

4.9

Website Content to Markdown for LLM Training

easyapi/website-content-to-markdown-for-llm-training

🚀 Transform web content into clean, LLM-ready Markdown! 📘 Scrape multiple pages, extract main content, and convert to Markdown format. Perfect for AI researchers, data scientists, and LLM developers. Fast, efficient, and customizable. Supercharge your AI training data today! 🌐📝🧠

EasyApi

5.0

Get Site to Markdown

jhaisley/get-site

Website to Markdown Crawler An asynchronous web crawler that mirrors websites into a single organized markdown file, with handling for images and directory structure preservation. Designed to operate with low cost. This works great to build context for AI agents.