🤖 AI Tools Directory Scraper (AITopTools)

Scrape structured, high-quality data about AI tools from AITopTools.com — including product details, traffic metrics, and features.

---

✨ What this Actor extracts

For each AI tool:

• 🏷️ Title
• 📝 Description (cleaned, max ~300 chars)
• 🧠 Category (tool_tag)
• 💳 Pricing model (payment_plan)
• 🔗 Official website
• ⭐ Rating (float)
• 🗳️ Reviews count (integer)
• ⚙️ Key features
• 📈 Monthly visits (integer)
• 📉 Bounce rate (%) (integer)
• ⏱️ Avg visit duration (seconds, float)
• 📄 Pages per visit (float)
• 🌍 Country rank (integer)
• 🌐 Global rank (integer)

---

⚙️ Input

{
  "start_page": 1,
  "max_pages": 50,
  "max_items": 100
}

Parameters

Field	Type	Description
start_page	integer	Page to start scraping from
max_pages	integer	Maximum number of pages to crawl
max_items	integer	Maximum number of tools to scrape (recommended)

📦 Output

Each dataset item:

{
  "title": "Sheet+",
  "description": "AI-powered spreadsheet assistant for generating formulas and automating tasks.",
  "tool_tag": "Productivity",
  "payment_plan": "Freemium",
  "website": "https://sheetplus.ai",
  "rating": 0.0,
  "reviews_count": 2,
  "features": "Generate formulas from natural language, Automate tasks, Detect errors",
  "monthly_visits": 44000,
  "bounce_rate": 81,
  "avg_visit_duration": 56.37,
  "pages_per_visit": 0.59,
  "country_rank": 356,
  "global_rank": 1123217
}

🚀 Use cases

• 📊 Market research

• 🧠 Competitor analysis

• 🔍 SEO & content ideas

• 📚 Build AI directories

• 💼 Lead generation

• ⚡ Features

• 🚀 Fast HTTP scraping (no browser = low cost)

• 🧹 Clean, structured output (ready for analysis)

• 🔢 Automatic normalization (K/M → integers, % → numbers)

• 🛑 Smart limits (max_items, max_pages)

• 🔁 Reliable pagination handling

⚠️ Notes

• Data depends on availability on AITopTools

• Some tools may not have ratings or traffic data

• Website structure changes may affect scraping