ohm_streaming/app/downloaders/lpayer.py

from .base import BaseDownloader
from bs4 import BeautifulSoup
import re
import asyncio


class LpayerDownloader(BaseDownloader):
    """Downloader for lpayer.embed4me.com video player"""

    def can_handle(self, url: str) -> bool:
        return 'lpayer.embed4me.com' in url.lower()

    async def get_download_link(self, url: str) -> tuple[str, str]:
        """
        Extract download link from Lpayer video page
        Lpayer uses a React app with dynamic JavaScript - requires Playwright
        """
        try:
            print(f"[LPAYER] Extracting link from: {url}")

            # Try using Playwright to extract video URL
            video_url = await self._extract_with_playwright(url)

            if not video_url:
                raise Exception("Could not find video URL in Lpayer page")

            print(f"[LPAYER] Found video URL: {video_url[:80]}...")

            # Generate filename
            filename = "lpayer_video.mp4"

            return video_url, filename

        except Exception as e:
            raise Exception(f"Error extracting Lpayer link: {str(e)}")

    async def _extract_with_playwright(self, url: str) -> str | None:
        """Extract video URL using Playwright with network interception"""
        try:
            from playwright.async_api import async_playwright

            print("[LPAYER] Launching browser with network interception...")

            video_urls = []

            async with async_playwright() as p:
                browser = await p.chromium.launch(
                    headless=True,
                    args=['--no-sandbox', '--disable-setuid-sandbox', '--disable-dev-shm-usage']
                )

                context = await browser.new_context(
                    user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36'
                )

                page = await context.new_page()

                # Set up request interception
                async def handle_request(route):
                    req_url = route.request.url

                    # Look for video files
                    if any(ext in req_url.lower() for ext in ['.m3u8', '.mp4', '.mkv']):
                        if 'lpayer' not in req_url.lower():
                            print(f"[LPAYER] 🎥 Captured video URL: {req_url[:100]}...")
                            video_urls.append(req_url)

                    await route.continue_()

                await page.route('**', handle_request)

                print("[LPAYER] Navigating to page...")

                try:
                    await page.goto(url, wait_until='domcontentloaded', timeout=30000)
                except Exception as e:
                    print(f"[LPAYER] Navigation warning: {e}")

                # Wait for page to load
                print("[LPAYER] Waiting for video player to load...")
                await asyncio.sleep(5)

                # Try to find and click play button
                try:
                    play_selectors = [
                        'button[aria-label="Play"]',
                        '.play-button',
                        'video',
                    ]

                    for selector in play_selectors:
                        try:
                            element = await page.query_selector(selector)
                            if element:
                                print(f"[LPAYER] Found element: {selector}")
                                if 'button' in selector:
                                    await element.click()
                                    await asyncio.sleep(3)
                                break
                        except:
                            continue
                except Exception as e:
                    print(f"[LPAYER] Play button interaction: {e}")

                # Wait more for network requests
                await asyncio.sleep(3)

                # Try JavaScript extraction
                try:
                    js_result = await page.evaluate("""
                        () => {
                            // Check all video elements
                            const videos = document.querySelectorAll('video');
                            for (let v of videos) {
                                if (v.src) {
                                    return v.src;
                                }
                                const sources = v.querySelectorAll('source');
                                for (let s of sources) {
                                    if (s.src && (s.src.includes('.m3u8') || s.src.includes('.mp4'))) {
                                        return s.src;
                                    }
                                }
                            }

                            // Check window object for video URLs
                            for (let key in window) {
                                if (typeof window[key] === 'string') {
                                    const str = window[key];
                                    if ((str.includes('.m3u8') || str.includes('.mp4')) && str.startsWith('http')) {
                                        return str;
                                    }
                                }
                            }

                            return null;
                        }
                    """)

                    if js_result and ('.m3u8' in js_result or '.mp4' in js_result):
                        print(f"[LPAYER] Found video URL via JavaScript")
                        video_urls.append(js_result)
                except Exception as e:
                    print(f"[LPAYER] JS extraction error: {e}")

                # Parse page HTML for video URLs
                try:
                    content = await page.content()
                    patterns = [
                        r'"file"\s*:\s*"([^"]+\.m3u8[^"]*)"',
                        r'"file"\s*:\s*"([^"]+\.mp4[^"]*)"',
                        r'(https?://[^\s"\'<>]+\.m3u8[^\s"\'<>]*)',
                        r'(https?://[^\s"\'<>]+\.mp4[^\s"\'<>]*)',
                    ]

                    for pattern in patterns:
                        matches = re.findall(pattern, content)
                        for match in matches:
                            match = match.replace('\\', '').replace('\/', '/')
                            if 'http' in match and 'lpayer' not in match:
                                print(f"[LPAYER] Found in HTML: {match[:100]}...")
                                video_urls.append(match)
                except Exception as e:
                    print(f"[LPAYER] HTML parsing error: {e}")

                await browser.close()

                # Return first valid video URL
                if video_urls:
                    seen = set()
                    unique_urls = []
                    for url in video_urls:
                        if url not in seen:
                            seen.add(url)
                            unique_urls.append(url)

                    if unique_urls:
                        print(f"[LPAYER] ✅ Found {len(unique_urls)} video URL(s)")
                        return unique_urls[0]

                print("[LPAYER] ❌ No video URLs found")
                return None

        except ImportError:
            print("[LPAYER] Playwright not installed")
            return None
        except Exception as e:
            print(f"[LPAYER] Playwright error: {e}")
            import traceback
            traceback.print_exc()
            return None