SIE                                              SCRAPPER
  │                                                  │
  ├── Brave/Chrome/Firefox mit Erweiterung öffnen ────►│
  │                                                  │
  ├── In Websites einloggen, die Sie automatisieren ──►│ erfasst:
  │                                                  │  • Cookies
  ├── Normal surfen, auf Schaltflächen klicken ───────►│  • Tokens
  │                                                  │  • Fingerprint
  └── Surfen beendet ─────────────────────────────────►│  • API-Anfragen
                                                     │  • DOM-Struktur

IHR SKRIPT ──── GET /api/v1/session/all ────► SCRAPPER API (localhost:8080)
              ◄── { cookies, tokens, fingerprint } ────────────────────────┘
                │
                ▼
         Puppeteer / Playwright / Selenium / Python requests / curl
                │
                ▼
         ✅ Authentifizierte Anfragen mit IHRER echten Session

📦 Session-Daten
   ├── 🍪 Cookies (einschließlich HttpOnly, Secure, alle Domains)
   ├── 💾 localStorage & sessionStorage
   ├── 🔑 Auth-Tokens (Bearer, JWT, CSRF, benutzerdefiniert)
   └── 📨 Alle HTTP-Header

🖥️ Browser-Fingerprint
   ├── 📱 User-Agent
   ├── 🖼️ Bildschirmauflösung & Farbtiefe
   ├── 🌍 Zeitzone & Spracheinstellungen
   └── 📨 Vollständiger Headersatz (Accept, Accept-Language usw.)

📡 Netzwerkverkehr
   ├── 📤 Alle HTTP-Anfragen (URLs, Methoden, Header, POST-Daten)
   ├── 📥 Alle HTTP-Antworten (Status, Header, Bodies)
   └── 🔄 WebSocket-Frames

🌳 DOM-Zustand
   ├── 📄 DOM-Schnappschüsse
   ├── 🎯 Live-Selektor-Tests
   └── 🗺️ DOM-Karten (alle Tags, Klassen, IDs)

curl -fsSL https://raw.githubusercontent.com/BunElysiaReact/SCRAPY/main/install.sh | bash

# Schritt 1 – Erweiterung in Brave laden:
# brave://extensions → Entwicklermodus EIN → Entpackte Erweiterung laden
# → auswählen: ~/.scrapper/extension/brave/

# Schritt 2 – Ihre Erweiterungs-ID registrieren
scrapper-register-ext IHRE_ERWEITERUNGS_ID

# Schritt 3 – SCRAPPER starten
scrapper-start

# Schritt 4 – Dashboard öffnen
# http://localhost:8080

# Repository klonen
git clone https://github.com/BunElysiaReact/SCRAPY.git ~/scrapper
cd ~/scrapper

# C Native Host bauen
gcc -O2 -o linux/c_core/native_host/debug_host linux/c_core/native_host/debug_host.c -lpthread

# Rust-Selektor-Engine bauen
cd linux/rust_finder && cargo build --release && cd ../..

# API-Server starten
cd linux/python_api && python3 api.py

irm https://raw.githubusercontent.com/BunElysiaReact/SCRAPY/main/install.ps1 | iex

%USERPROFILE%\.scrapper\
├── bin\
│   ├── debug_host.exe         ← C Native Messaging Host
│   ├── scraper_cli.exe        ← CLI-Client
│   ├── rust_finder.exe        ← Schnelle HTML-Selektor-Engine
│   ├── scrapper-start.bat     ← Alles starten
│   └── scrapper-stop.bat      ← Alles stoppen
├── data\                      ← Alle erfassten Session-Daten
├── logs\                      ← Host-Protokolle
├── python_api\
│   └── api.py                 ← REST-API-Server
├── extension\
│   ├── brave\                 ← In Brave / Chrome / Edge laden
│   └── firefox\               ← In Firefox laden
└── ui\scrapperui\             ← Dashboard-Quellcode

from curl_cffi import requests

API = "http://localhost:8080"
domain = "example.com"

cookies_raw = requests.get(f"{API}/api/v1/session/cookies?domain={domain}").json()
fp = requests.get(f"{API}/api/v1/fingerprint?domain={domain}").json()

session = requests.Session(impersonate="chrome120")
for c in cookies_raw:
    session.cookies.set(c["name"], c["value"], domain=c.get("domain", domain).lstrip("."))
session.headers.update({"User-Agent": fp.get("userAgent", "")})

response = session.get(f"https://{domain}/api/data")
print(response.json())

import requests

session_data = requests.get('http://localhost:8080/api/v1/session/all').json()

s = requests.Session()
s.cookies.update({c['name']: c['value'] for c in session_data['cookies']})
s.headers.update({'User-Agent': session_data['fingerprint']['userAgent']})

response = s.get('https://api.example.com/data')

source <(curl -s http://localhost:8080/api/v1/export/env)

curl -X POST "https://api.example.com/upload" \
  -H "Authorization: Bearer $SCRAPPER_BEARER_TOKEN" \
  -b "$SCRAPPER_COOKIES" \
  -F "[email protected]"

import requests
from playwright.async_api import async_playwright

session = requests.get('http://localhost:8080/api/v1/session/all').json()

async with async_playwright() as p:
    context = await p.chromium.launch_persistent_context(
        user_data_dir="./profile",
        user_agent=session['fingerprint']['userAgent'],
    )
    await context.add_cookies(session['cookies'])
    page = await context.new_page()
    await page.goto('https://example.com')

const session = await fetch('http://localhost:8080/api/v1/session/all').then(r => r.json());

const browser = await puppeteer.launch();
const page = await browser.newPage();
await page.setCookie(...session.cookies);
await page.setUserAgent(session.fingerprint.userAgent);
await page.goto('https://example.com/dashboard');

# Neueste Session-Daten exportieren
curl -s "http://localhost:8080/api/v1/bulk/all?format=jsonl" > session.jsonl

# In Ihrem Scraper verwenden
python3 my-scraper.py --session session.jsonl

# session_refresh.py – Wöchentliche Session-Aktualisierungspipeline
import requests, schedule, time

def refresh_session():
    notify_user("Bitte loggen Sie sich in Ihrem Browser in die Ziel-Websites ein")
    time.sleep(300)  # 5 Minuten für den Benutzer zum Surfen
    data = requests.get('http://localhost:8080/api/v1/bulk/all?format=json').json()
    with open(f'session_{int(time.time())}.json', 'w') as f:
        import json; json.dump(data, f)

schedule.every().monday.at("09:00").do(refresh_session)
while True:
    schedule.run_pending()
    time.sleep(60)