🌐 CyberScraper 2077

Rip data from the net, leaving no trace. Welcome to the future of web scraping.

🔍 About

CyberScraper 2077 is not just another web scraping tool – it's a glimpse into the future of data extraction. Born from the neon-lit streets of a cyberpunk world, this AI-powered scraper uses OpenAI to slice through the web's defenses, extracting the data you need with unparalleled precision and style.

Whether you're a corpo data analyst, a street-smart netrunner, or just someone looking to pull information from the digital realm, CyberScraper 2077 has got you covered.

✨ Features

🤖 AI-Powered Extraction: Utilizes cutting-edge AI models to understand and parse web content intelligently.
💻 Sleek Streamlit Interface: User-friendly GUI that even a chrome-armed street samurai could navigate.
🔄 Multi-Format Support: Export your data in JSON, CSV, HTML, SQL or Excel – whatever fits your cyberdeck.
🌐 Stealth Mode: Implemented stealth mode parameters that helps it from getting detected as bot.
🤖 Ollama Support (Experimental Branch): Use a huge libarary of open source LLMs.
🚀 Async Operations: Lightning-fast scraping that would make a Trauma Team jealous.
🧠 Smart Parsing: Structures scraped content as if it was extracted straight from the engram of a master netrunner.
🛡️ Ethical Scraping: Respects robots.txt and site policies. We may be in 2077, but we still have standards.
🌐 Proxy Mode (Coming Soon): Built-in proxy support to keep you ghosting through the net.
🛡️ Navigate through the Pages (Coming Soon): Navigate through the webpage and scrap the data from different pages.

🎥 Demo

Check out our YouTube video for a full walkthrough of CyberScraper 2077's capabilities.

🛠 Installation

Clone this repository:

git clone https://github.com/itsOwen/CyberScraper-2077.git
cd CyberScraper-2077

Create and activate a virtual environment:

virtualenv even
source venv/bin/activate  # Optional

Install the required packages:
```
pip install -r requirements.txt
```
Install the playwright:
```
playwright install
```

Set OpenAI Key in your enviornment:

Linux/Mac:

export OPENAI_API_KEY='your-api-key-here'

For Windows:

set OPENAI_API_KEY="your-api-key-here"

If you want to use the experminal Ollama Branch:

1. git checkout ollama_experimental
2. Setup Ollama using `pip install ollama`
3. Download the Ollama from the official website: https://ollama.com/download
4. Now type: ollama run llama3.1 or whatever LLM you want to use.
5. Now follow the rest of the steps below.

🚀 Usage

Fire up the Streamlit app:
```
streamlit run main.py
```
Open your browser and navigate to http://localhost:8501.
Enter the URL of the site you want to scrape or ask a question about the data you need.
Ask the chatbot to extract the data in any format, Select whatever data you want to export or even everything from the webpage.
Watch as CyberScraper 2077 tears through the net, extracting your data faster than you can say "flatline"!

🤝 Contributing

We welcome all cyberpunks, netrunners, and code samurais to contribute to CyberScraper 2077!

🔧 Troubleshooting

Ran into a glitch in the matrix? Let me know by adding the issue to this repo so that we can fix it together.

❓ FAQ

Q: Is CyberScraper 2077 legal to use? A: CyberScraper 2077 is designed for ethical web scraping. Always ensure you have the right to scrape a website and respect their robots.txt file.

Q: Can I use this for commercial purposes? A: Yes, under the terms of the MIT License. But remember, in Night City, there's always a price to pay, Just kidding!

📄 License

This project is licensed under the MIT License - see the LICENSE file for details. Use it, mod it, sell it – just don't blame us if you end up flatlined.

📞 Contact

Got questions? Need support? Want to hire me for a gig?

📧 Email: owensingh72@gmail.com
🐦 Twitter: @_owensingh
💬 Website: Portfolio

🚨 Disclaimer

Listen up, choombas! Before you jack into this code, you better understand the risks. Here's the lowdown in plain language:

This software is provided "as is", without warranty of any kind, express or implied.
The authors are not liable for any damages or losses resulting from the use of this software.
This tool is intended for educational and research purposes only. Any illegal use is strictly prohibited.
We do not guarantee the accuracy, completeness, or reliability of any data obtained through this tool.
By using this software, you acknowledge that you are doing so at your own risk.
You are responsible for complying with all applicable laws and regulations in your use of this software.
We reserve the right to modify or discontinue the software at any time without notice.

Remember, samurai: In the dark future of the NET, knowledge is power, but it's also a double-edged sword. Use this tool wisely, and may your connection always be strong and your firewalls impenetrable. Stay frosty out there in the digital frontier.

CyberScraper 2077 – Because in 2077, what makes someone a criminal? Getting caught.

onlyforbakup/CyberScraper-2077