scraper4.py

import asyncio
import urllib.parse
import json
from playwright.async_api import async_playwright
from bs4 import BeautifulSoup
import re

DOMENA = "https://mrkaj.me"

class TorBrowserManager:
    _instance = None

    def __init__(self):
        self.playwright = None
        self.context = None
        self._setup_done = False
        self._lock = asyncio.Lock()

    @classmethod
    def get_instance(cls):
        if cls._instance is None:
            cls._instance = cls()
        return cls._instance

    async def reset_identity(self):
        """Reštartuje prehliadač a vyžiada novú IP"""
        try:
            # 1. Zavrieme starý kontext (vyčistí cache spojení)
            if self.context:
                await self.context.close()

            # 2. Vyžiadame novú identitu od Toru
            reader, writer = await asyncio.open_connection('127.0.0.1', 9051)
            writer.write(b'AUTHENTICATE ""\r\n')
            writer.write(b'SIGNAL NEWNYM\r\n')
            writer.write(b'QUIT\r\n')
            await writer.drain()
            writer.close()
            
            print("[TOR] Vyžiadaná nová IP. Reštartujem prehliadač...")
            await asyncio.sleep(8) 

            # 3. Znova vytvoríme kontext (úplne nové spojenie)
            self.context = await self.playwright.chromium.launch_persistent_context(
                "/tmp/playwright_tor",
                headless=True,
                proxy={"server": "socks5://127.0.0.1:9050"},
                args=["--no-sandbox", "--disable-setuid-sandbox"]
            )
            await self.get_current_ip()
        except Exception as e:
            print(f"[TOR RESET ERROR] {e}")


    async def get_current_ip(self):
        page = await self.context.new_page()
        try:
            await page.goto("https://api.ipify.org", timeout=20000)
            ip = (await page.inner_text("body")).strip()
            print(f"[TOR] Aktuálna IP adresa: {ip}")
            return ip
        except Exception as e:
            print(f"[TOR IP ERROR] {e}")
            return "unknown"
        finally:
            await page.close()

    async def start(self):
        async with self._lock:
            if self._setup_done:
                return
            
            print("[TOR] Inicializujem prehliadač cez Tor SOCKS5...")
            self.playwright = await async_playwright().start()
            
            self.context = await self.playwright.chromium.launch_persistent_context(
                "/tmp/playwright_tor",
                headless=True,
                proxy={"server": "socks5://127.0.0.1:9050"},
                args=["--no-sandbox", "--disable-setuid-sandbox"]
            )
            
            await asyncio.sleep(10)
            await self.get_current_ip()
            self._setup_done = True

    async def get_page(self):
        if not self._setup_done:
            await self.start()
        return await self.context.new_page()

    async def goto_with_fallback(self, page, url, timeout=60000):
        try:
            await page.goto(url, wait_until="domcontentloaded", timeout=timeout)
            return True
        except Exception as e:
            print(f"[TOR GOTO ERROR] {e}")
            return False

manager = TorBrowserManager.get_instance()

async def search_movies(query):
    print(f"[SEARCH] Hľadám cez Tor: {query}")
    if not manager._setup_done: await manager.start()
    
    # Skúsime až 4 rôzne Tor okruhy (identity), ak nás web blokuje
    for pokus in range(4):
        page = await manager.get_page()
        try:
            url = f"{DOMENA}/se/j/json?q={urllib.parse.quote(query)}"
            success = await manager.goto_with_fallback(page, url)
            
            if success:
                content = await page.inner_text("body")
                
                if content and len(content.strip()) > 10:
                    print(f"[TOR] ÚSPECH na {pokus+1}. pokus!")
                    return json.loads(content)
                
                print(f"[TOR] Pokus {pokus+1} vrátil prázdny obsah (blokovaná IP). Mením identitu...")
            
            await page.close()
            await manager.reset_identity() # Zmena IP adresy
            
        except Exception as e:
            print(f"[SEARCH ERROR] Pokus {pokus+1}: {e}")
            await page.close()
            await manager.reset_identity()
            
    return []

async def get_details(slug, media_type):
    print(f"[DETAILS] Info cez Tor: {slug}")
    page = await manager.get_page()
    url = f"{DOMENA}/p/{slug}" if media_type in ["movie", "film"] else f"{DOMENA}/tv/{slug}/S01E01"
    res = {"languages": [], "seasons": []}
    try:
        success = await manager.goto_with_fallback(page, url)
        if not success: return res
        
        await asyncio.sleep(2)
        soup = BeautifulSoup(await page.content(), "html.parser")
        
        kw_div = soup.find("div", class_="movie-keyword")
        if kw_div:
            res["languages"] = [p.get_text(strip=True) for p in kw_div.find_all(recursive=False)]
        
        matches = re.findall(r'Séria\s+(\d+)', soup.get_text())
        for seria in sorted(set(matches), key=int):
            res["seasons"].append({"season": int(seria), "episodes": 0})
    except Exception as e:
        print(f"[DETAILS ERROR] {e}")
    finally:
        await page.close()
    return res

async def get_stream_url(slug, media_type, season=None, episode=None, lang=None, source_idx=0):
    print(f"[STREAM] Skenujem stream cez Tor: {slug}")
    page = await manager.get_page()
    url = f"{DOMENA}/p/{slug}" if media_type in ["movie", "film"] else f"{DOMENA}/tv/{slug}/S{int(season):02d}E{int(episode):02d}"
    
    params = [f"source={source_idx}"]
    if lang: params.append(f"lng={urllib.parse.quote(lang)}")
    url += "?" + "&".join(params)
    
    found = {"stream": None, "vtt": None}
    page.on("request", lambda req: zachyt_request(req, found))
    
    try:
        success = await manager.goto_with_fallback(page, url, timeout=90000)
        if not success: return found
        
        for _ in range(25):
            if found["stream"]: break
            await asyncio.sleep(1)
            
        if not found["stream"]:
            iframe = page.locator("iframe#frm, video").first
            if await iframe.count() > 0:
                await iframe.click(force=True)
                for _ in range(15):
                    if found["stream"]: break
                    await asyncio.sleep(1)
    except Exception as e:
        print(f"[STREAM ERROR] {e}")
    finally:
        await page.close()
    return found

def zachyt_request(request, found):
    if ".m3u8" in request.url and not found["stream"]:
        found["stream"] = request.url
    if request.url.endswith(".vtt") and not found["vtt"]:
        found["vtt"] = request.url