🔥 fireSummarize – AI Summarizer for Any Website Content

🧠 Overview

fireSummarize is an AI-powered web content summarizer built using Crawlee and Puppeteer. It scrapes one or more web pages, extracts the content in your preferred format (Markdown, text, or HTML), and sends it through OpenRouter (Gemini 2.5 Flash) to generate high-quality summaries.

Ideal for research, documentation, content analysis, and LLM dataset preparation.

---

🚀 Features

• 🌐 Crawl one or more webpages
• ✍️ Extract visible text, raw HTML, or clean Markdown
• 🤖 Summarize content using OpenRouter AI models
• 🔁 Supports pagination and deep crawling via enqueue
• 🧩 Handles large content with smart chunking
• 📦 Outputs full metadata and AI summary

---

🧾 Input Schema

Field	Type	Description
startUrls	Array	List of URLs to start crawling from.
maxPages	Integer	Maximum number of pages to crawl (default: 5).
proxyConfig	Object	Apify proxy configuration.
enqueue	Boolean	Whether to follow links and enqueue new pages (default: true).
getMarkdown	Boolean	Extract and convert content to Markdown format (default: false).
getText	Boolean	Extract only the visible text content (default: true).
getHtml	Boolean	Extract the full HTML content of the page (default: false).

---

📤 Output Example

{
  "url": "https://apify.com/resources/nonprofits",
  "title": "Apify for nonprofits and NGOs · Apify",
  "Summary": "This page announces Apify's discount program for non-profit organizations.\n\n**Key takeaways:**\n- Apify offers a 30% discount on paid plans for qualifying non-profits.\n- Organizations must be verified NGOs or non-profits.\n- The discount lasts 6–12 months with conditions.\n- An application form must be filled to be considered.\n- Apify offers dedicated support to approved organizations.",
  "metadata": {
    "title": "Apify for nonprofits and NGOs · Apify",
    "description": "We believe that online data can help your organization have more impact, so we're offering a substantial discount from our plans to nonprofits and NGOs.",
    "language": "en",
    "keywords": "web scraper,web crawler,scraping,data extraction,API",
    "robots": "index,follow",
    "ogTitle": "Apify for nonprofits and NGOs · Apify",
    "ogDescription": "We believe that online data can help your organization have more impact...",
    "ogUrl": "https://apify.com/resources/nonprofits",
    "ogImage": "https://apify.com/og-image?title=Apify+for+nonprofits+and+NGOs",
    "sourceURL": "https://apify.com/resources/nonprofits"
  },
  "markdown": "...",        // if getMarkdown is enabled
  "textContent": "...",     // if getText is enabled
  "htmlContent": "..."      // if getHtml is enabled
}

---

💡 Use Cases

• ✍️ Summarize blog posts and documentation pages automatically
• 📚 Generate LLM training data with Markdown and AI summaries
• 📈 Analyze competitors’ product/service pages
• 📰 Automate news aggregation for newsletters or alerts
• 📋 Extract key points from Terms of Service, policies, FAQ, etc.

---

🎁 Bonus: Free n8n Workflow Integration

As a standing note, you can use this n8n workflow with this actor as a free bonus for using this actor:

• Instagram Automation Suite
• Automated YouTube Leads

📬 Contact

Made by Mohamed el hadi Msaid. For feature requests, support, or bug reports, feel free to open an issue or email me.

---