# itsOwen/CyberScraper-2077

A Powerful web scraper powered by LLM | OpenAI, Gemini & Ollama

Repository: https://github.com/itsOwen/CyberScraper-2077
Canonical: https://ross.abutalabs.com/products/cyberscraper-2077
Language: Python
License: MIT
License Family: permissive
Topics: ai-scraping, llm, openai, scraper, webscraping, gemini-api, llm-scraper, web-scraper
Last push: 2026-08-20T10:26:04+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 53
- inputs: {"age_days": 746, "days_push": 13, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3245, forks 355 (observed 2026-08-28T04:07:50.568675+00:00)

## What it is
CyberScraper 2077 is an AI-powered web scraping application with a Streamlit GUI that uses OpenAI, Gemini, or local Ollama models to intelligently extract and structure web data. It supports exporting to JSON, CSV, HTML, SQL, and Excel, with stealth mode, Tor support for .onion sites, and async operations.

## Use cases
- scrape websites using an llm
- extract structured data from web pages with ai
- scrape onion sites through tor
- export scraped data to csv or excel
- run a local llm web scraper with ollama
- scrape websites without getting blocked as a bot

## When to choose
- you want natural-language-driven scraping without writing selectors
- you need multiple export formats like JSON, CSV, SQL, or Excel
- you want to scrape .onion sites via Tor with a GUI
- you prefer using local models via Ollama for privacy

## When to avoid
- you need a lightweight headless scraper for CI pipelines
- you want a pure library to embed in your own Python code
- you need massive-scale distributed crawling
- you cannot rely on external LLM APIs and lack hardware for local models

## Facets
- artifact type: application
- maturity: active
- function: web-scraping, llm-inference, gui, caching, data-science
- domain: crawlers, artificial-intelligence, large-language-models, data-science
- platform: python, cross-platform, self-hosted
- tags: ai-powered-scraping, streamlit, openai, gemini, ollama, tor-support, stealth-scraping, data-export, automation

## Member repositories
- itsOwen/CyberScraper-2077 (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:50.568675+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:24:28.779935+00:00, confidence not recorded.
  - readme: https://github.com/itsOwen/CyberScraper-2077 (fetched 2026-08-28T04:07:50.568675+00:00, sha fc8ba3dc8080)
- Data as of 2026-08-30T08:39:29.467469+00:00.