main.py

from fastapi import FastAPI, Query, Response
from pydantic import BaseModel
from playwright.sync_api import sync_playwright
import json

app = FastAPI(title="TeraBox Scraper API")

# --- CORE SCRAPER FUNCTION ---
def run_scraper(terabox_url: str):
    print(f"Processing URL: {terabox_url}")
    try:
        with sync_playwright() as p:
            # Launch browser (headless for server environment)
            browser = p.chromium.launch(headless=True)
            
            # Create context with standard user agent
            context = browser.new_context(
                user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
            )
            page = context.new_page()
            
            # Track network requests
            captured_urls = []
            
            def capture_video_urls(response):
                url = response.url
                if any(ext in url for ext in ['.m3u8', '.mp4', 'stream', 'fast']):
                    if url not in captured_urls:
                        captured_urls.append(url)
            
            page.on('response', capture_video_urls)
            
            # Navigate to helper site
            target_url = f"https://iteraplay.com/?url={terabox_url}"
            page.goto(target_url, wait_until='networkidle', timeout=60000)
            
            # Wait for video element
            try:
                page.wait_for_selector('video', timeout=30000)
            except:
                pass
            
            # Extract data
            video_data = page.evaluate("""
                () => ({
                    qualities: window.videoQualityURLs || {},
                    videos: window.allVideoData || [],
                    current: window.currentVideoData || {},
                    metadata: window.currentVideoMetadata || {}
                })
            """)
            
            # Get src attribute
            video_src = None
            try:
                video_src = page.locator('video').get_attribute('src')
            except:
                pass
            
            browser.close()
            
            return {
                "status": "success",
                "original_url": terabox_url,
                "video_source": video_src,
                "qualities": video_data.get('qualities', {}),
                "all_videos": video_data.get('videos', []),
                "captured_network_urls": captured_urls
            }

    except Exception as e:
        return {"status": "error", "message": str(e)}

# --- API ENDPOINTS ---

class ScrapeRequest(BaseModel):
    url: str

@app.get("/")
def home():
    return {"message": "Add /scrape?url=YOUR_URL to the address bar to use."}

# 1. GET Request (For Browser Use)
@app.get("/scrape")
def scrape_get(url: str = Query(..., description="The TeraBox URL to scrape")):
    data = run_scraper(url)
    # Return formatted JSON
    return Response(content=json.dumps(data, indent=2), media_type="application/json")

# 2. POST Request (For Code/API Use)
@app.post("/scrape")
def scrape_post(request: ScrapeRequest):
    data = run_scraper(request.url)
    # Return formatted JSON
    return Response(content=json.dumps(data, indent=2), media_type="application/json")

if __name__ == "__main__":
    import uvicorn
    uvicorn.run(app, host="0.0.0.0", port=7860)