fuckaudiochan.py

#!/usr/bin/env python3
"""
AudioChan Stream Capture Tool (Manual Mode Only)
Uses Playwright to capture stream URLs and full headers (including HttpOnly cookies).
Generates the robust FFmpeg command for manual copy-pasting.
"""
import argparse
import asyncio
from playwright.async_api import async_playwright
import os
import re
import sys
# Force UTF-8 output so emojis aren't mangled on Windows
sys.stdout.reconfigure(encoding='utf-8')
if sys.platform == 'win32':
    os.system('chcp 65001 > nul')

# Path to store browser session (cookies, etc.) so you don't have to login every time
USER_DATA_DIR = os.path.join(os.getcwd(), 'playwright_data')

async def capture_stream_manual(url):
    print(f"🚀 Launching browser for: {url}")
    print(f"📂 User Data Dir: {USER_DATA_DIR}")

    async with async_playwright() as p:
        # Launch persistent context to save login state
        context = await p.chromium.launch_persistent_context(
            user_data_dir=USER_DATA_DIR,
            headless=True,  # Change if cloudflare is an issue
            channel="chrome", # Try to use installed Chrome if available for better realism
            args=[
                '--disable-blink-features=AutomationControlled', # Hide automation flag
            ]
        )

        page = await context.new_page()

        # storage for captured info
        stream_info = {
            'url': None,
            'headers': None
        }

        # Event listener for requests
        async def handle_request(request):
            try:
                # Print ALL requests so we can see what's happening
                print(f"  [REQUEST] {request.url}")

                # Filter strictly for the stream URL
                if 'stream.audiochan.com' in request.url and '&st=' in request.url:
                    print(f"\n✅ CAPTURED STREAM REQUEST! (Updating...)")
                    stream_info['url'] = request.url
                    try:
                        # This can sometimes fail if the request is closed too quickly
                        stream_info['headers'] = await request.all_headers()
                    except Exception as e:
                        print(f"⚠️ Warning: Could not fetch full headers: {e}")
                        # Fallback to basic headers if available, or just use what we have
                        if not stream_info['headers']: # Only overwrite if we don't have good headers yet
                            stream_info['headers'] = request.headers
            except Exception as e:
                # Catch-all for any other issues in the handler to prevent loop crash
                pass

        page.on("request", handle_request)

        try:
            print("⏳ Navigating to page...")
            await page.goto(url)

            print("👀 Waiting for stream to start... (Press Play on the page if needed)")

            # Wait until we capture the stream AND it stabilizes
            stability_count = 0
            required_stability = 3

            for _ in range(60):
                if stream_info['url'] and stream_info['headers']:
                    stability_count += 1
                    print(f"   Stream detected... stabilizing ({stability_count}/{required_stability})")
                    if stability_count >= required_stability:
                        break
                else:
                    stability_count = 0 # Reset if lost (unlikely but good safety)

                await asyncio.sleep(1)

            if stream_info['url'] and stream_info['headers']:

                # Sanitize title: Replace invalid Windows filename characters with underscore
                # Invalid characters for Windows filenames: < > : " / \ | ? *
                invalid_chars = r'[<>:"/\\|?*]'

                # Wait for the h1 to have content
                await page.wait_for_selector('h1.text-foreground:not(:empty)')

                h1_title = await page.evaluate('''() => {
                    const el = document.querySelector('h1.text-foreground');
                    return el ? el.innerText.trim() : null;
                }''')

                title = h1_title or await page.title()
                safe_title = re.sub(invalid_chars, '_', title).strip()
                safe_title = re.sub(r'[ .]+$', '', safe_title)
                output_filename = f"{safe_title}.mp4"

                # Grab artist from span, strip the "u/" prefix
                artist = await page.evaluate('''() => {
                    const el = document.querySelector('span.truncate.text-muted-foreground.text-sm.no-underline');
                    return el ? el.innerText.trim().replace(/^u\//, '') : null;
                }''')
                artist = artist or ""

                # Grab description from <em> tag
                description = await page.evaluate('''() => {
                    const el = document.querySelector('p');
                    return el ? el.innerText.trim() : null;
                }''')

                description = description.replace('"', '\\"') if description else ""

                safe_title = re.sub(invalid_chars, '_', title).strip()
                # Also remove any trailing periods or spaces that Windows dislikes
                safe_title = re.sub(r'[ .]+$', '', safe_title)

                print("\n" + "="*80)
                print("🎉 SUCCESS! Stream info captured.")
                print("="*80)

                # Construct FFmpeg Command
                headers_dict = stream_info['headers']

                # Format headers for FFmpeg (-headers "Key: Value\r\nKey: Value\r\n")
                ffmpeg_headers = ""

                # Critical headers
                keys_to_keep = ['user-agent', 'referer', 'cookie', 'accept', 'accept-language', 'origin']

                for key, value in headers_dict.items():
                    if key.lower() in keys_to_keep:
                        # Escape double quotes inside header values with a backslash
                        safe_val = value.replace('"', '\\"')
                        # Capitalize keys nicely
                        nice_key = key.title()
                        ffmpeg_headers += f"{nice_key}: {safe_val}\r\n"

                # Add connection keep-alive if missing
                if 'connection' not in headers_dict:
                    ffmpeg_headers += "Connection: keep-alive\r\n"

                # Construct the full command
                # Note: We use .mp4 container for better compatibility with streams
                output_filename = f"{safe_title}.m4a"

                # String version for manual copy-pasting
                cmd_str = f'ffmpeg -reconnect 1 -reconnect_streamed 1 -reconnect_delay_max 5 -headers "{ffmpeg_headers}" -i "{stream_info["url"]}" -vn -c:a copy -metadata title="{h1_title or safe_title}" -metadata artist="{artist}" -metadata comment=" {description} - Captured from {url}" "{output_filename}"'

                print("\n📋 FFmpeg Command (Auto-Generated):")
                print("-" * 20)
                print(cmd_str.encode('utf-8').decode('utf-8'))
                print("-" * 20)
                print("\n⚠️  Copy the command above and run it in your terminal.")
            else:
                print("\n❌ Timeout: Stream request not found.")
                print("Did you play the audio? Is the site asking for login?")

        except Exception as e:
            print(f"\n❌ Error: {e}")

        finally:
            # Safely close the browser context
            try:
                if context.pages: # Simple check if it might still be open
                    print("\nClosing browser...")
                    await context.close()
            except Exception as e:
                # Ignore errors during shutdown (e.g., Target closed, Loop closed)
                pass

def main():
    if sys.platform == 'win32':
        asyncio.set_event_loop_policy(asyncio.WindowsProactorEventLoopPolicy())

    parser = argparse.ArgumentParser(description="AudioChan Stream Capture Tool (Manual Mode Only)")
    parser.add_argument('url', nargs='?', help='The URL of the AudioChan page (optional)')
    args = parser.parse_args()

    target_url = args.url

    # Interactive URL Input if not provided
    if not target_url:
        print("Enter the AudioChan URL:")
        target_url = input("> ").strip()
        if not target_url:
            print("Error: No URL provided. Exiting.")
            return

    asyncio.run(capture_stream_manual(target_url))

if __name__ == "__main__":
    main()