Logo
Deploy Now

Categories

Self-Hosted Developer Tools Privacy AI Automation Web Scraping Data Extraction

Developer links

Last Updated: 01-01-2023 12:00 AM (UTC)

CyberScraper 2077

With 3,100+ GitHub stars, CyberScraper 2077 replaces brittle CSS selectors and XPath queries with natural language data extraction powered by Large Language Models. Users paste a URL, describe the data they want in plain English, and the AI extracts structured results from any website — no HTML parsing knowledge required. The tool supports three LLM backends: OpenAI GPT models for maximum accuracy, Google Gemini for cost-effective extraction, and local Ollama instances for fully private scraping where URLs and data never leave your server. Built on Python asyncio with Playwright browser automation, it handles concurrent page fetching with content-based and query-based LRU caching to minimize redundant API calls. The Streamlit web interface runs on port 8501 and provides one-click export to JSON, CSV, HTML, SQL, Excel, and direct Google Sheets upload. Tor network integration routes requests through onion routing for anonymous scraping of both clearnet and .onion hidden service sites with automatic circuit management and stream isolation. Stealth mode randomizes user agents, manages cookies, and controls JavaScript execution timing to bypass bot detection systems. Multi-page scraping navigates through paginated results with automatic URL pattern detection. Docker deployment packages all dependencies including Playwright browsers into a single container. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

CyberScraper 2077
CyberScraper 2077
CyberScraper 2077

Benefits

  • Natural Language Data Extraction
  • Describe what data you need in plain English instead of writing CSS selectors or XPath queries, with AI models parsing and structuring the results automatically.
  • Three LLM Backend Options
  • Choose between OpenAI GPT for accuracy, Google Gemini for cost efficiency, or local Ollama models for fully private extraction where data never leaves your server.
  • Anonymous Tor Network Scraping
  • Route requests through Tor onion routing with automatic circuit management and stream isolation to anonymously scrape both clearnet websites and .onion hidden services.
  • Multi-Format Export Pipeline
  • Export extracted data as JSON, CSV, HTML, SQL, or Excel files, plus direct one-click upload to Google Sheets for immediate collaboration and analysis.

Features

  • Streamlit Web Interface
  • Browser-based GUI on port 8501 for entering URLs, writing natural language extraction prompts, viewing results, and exporting data in multiple formats.
  • Stealth Anti-Detection Mode
  • Randomizes user agents, manages cookies, controls JavaScript execution timing, and optionally uses your local browser instance to bypass bot detection systems.
  • Async Playwright Automation
  • Built on Python asyncio with Playwright browser engine for concurrent page fetching, JavaScript rendering, and multi-page navigation with automatic pagination detection.
  • LRU Caching System
  • Content-based and query-based least-recently-used caching reduces redundant LLM API calls when re-scraping pages or running similar extraction queries.
  • Docker Deployment
  • Single container packages Python runtime, Playwright browsers, and all dependencies for consistent deployment without manual dependency management.