reels-app/scripts/yt_download.py

#!/usr/bin/env python3
"""
yt_download.py — Download YouTube video v 1080p (16:9) za reels pipeline.

Primer:
  python3 yt_download.py "https://youtu.be/dQw4w9WgXcQ" /data/uploads/video.mp4
"""
import argparse
import os
import subprocess
import sys
from pathlib import Path
import json


def download(url, output, max_height=1080, format_str=None, cookies_file=None):
    """
    Download YT video. Privzeto: best mp4 ≤1080p z audiotrackom.
    """
    if format_str is None:
        format_str = (
            f"bestvideo[height<={max_height}][ext=mp4]+bestaudio[ext=m4a]/"
            f"best[height<={max_height}][ext=mp4]/best"
        )

    cmd = [
        "yt-dlp",
        "-f", format_str,
        "--merge-output-format", "mp4",
        "--no-playlist",
        "--write-info-json",
        "--restrict-filenames",
        "-o", str(output),
    ]

    # Auto-detect cookies file če ni eksplicitno podan
    if cookies_file is None:
        for candidate in [
            "/data/cookies/youtube.txt",
            os.environ.get("YT_COOKIES_FILE", ""),
        ]:
            if candidate and Path(candidate).exists():
                cookies_file = candidate
                break

    if cookies_file and Path(cookies_file).exists():
        cmd += ["--cookies", str(cookies_file)]
        print(f"🍪 Using cookies: {cookies_file}", file=sys.stderr)

    cmd.append(url)
    print(f"⬇  Downloading {url}...", file=sys.stderr)
    result = subprocess.run(cmd, capture_output=True, text=True)
    if result.returncode != 0:
        print(f"❌ yt-dlp napaka:\n{result.stderr[-1500:]}", file=sys.stderr)
        sys.exit(1)
    print(f"✅ {output}", file=sys.stderr)
    return output


def get_info(url, cookies_file=None):
    """Vrni metadata brez prenosa."""
    cmd = ["yt-dlp", "--dump-json", "--no-playlist"]
    if cookies_file is None:
        for candidate in ["/data/cookies/youtube.txt", os.environ.get("YT_COOKIES_FILE", "")]:
            if candidate and Path(candidate).exists():
                cookies_file = candidate
                break
    if cookies_file and Path(cookies_file).exists():
        cmd += ["--cookies", str(cookies_file)]
    cmd.append(url)
    result = subprocess.run(cmd, capture_output=True, text=True)
    if result.returncode != 0:
        return None
    return json.loads(result.stdout.strip().split("\n")[0])


def get_playlist(url, cookies_file=None):
    """Vrni listo videov v playlistu (samo metadata, ne pobere).

    Returns:
      {
        "is_playlist": bool,
        "playlist_title": str,
        "items": [
          {"id": "VIDEO_ID", "title": "...", "url": "https://...", "duration": 234},
          ...
        ]
      }

    Če URL ni playlist, vrne is_playlist=False in samo en item.
    """
    cmd = ["yt-dlp", "--flat-playlist", "--dump-json"]
    if cookies_file is None:
        for candidate in ["/data/cookies/youtube.txt", os.environ.get("YT_COOKIES_FILE", "")]:
            if candidate and Path(candidate).exists():
                cookies_file = candidate
                break
    if cookies_file and Path(cookies_file).exists():
        cmd += ["--cookies", str(cookies_file)]
    cmd.append(url)
    print(f"📋 Resolving playlist: {url}", file=sys.stderr)
    result = subprocess.run(cmd, capture_output=True, text=True, timeout=120)
    if result.returncode != 0:
        print(f"❌ yt-dlp playlist napaka:\n{result.stderr[-1500:]}", file=sys.stderr)
        return {"is_playlist": False, "playlist_title": "", "items": [], "error": result.stderr[-500:]}

    items = []
    playlist_title = ""
    for line in result.stdout.strip().split("\n"):
        if not line.strip():
            continue
        try:
            entry = json.loads(line)
        except json.JSONDecodeError:
            continue
        # Playlist header (typ=playlist)
        if entry.get("_type") == "playlist":
            playlist_title = entry.get("title", "")
            continue
        # Video entry
        vid = entry.get("id")
        if not vid:
            continue
        items.append({
            "id": vid,
            "title": entry.get("title", "") or "",
            "url": entry.get("url") or f"https://www.youtube.com/watch?v={vid}",
            "duration": entry.get("duration"),
            "uploader": entry.get("uploader") or entry.get("channel") or "",
        })

    is_playlist = len(items) > 1 or ("list=" in url)
    return {
        "is_playlist": is_playlist,
        "playlist_title": playlist_title or (items[0]["title"] if items else ""),
        "items": items,
    }


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("url")
    ap.add_argument("output")
    ap.add_argument("--max-height", type=int, default=1080)
    ap.add_argument("--cookies", default=None,
                    help="Pot do cookies.txt (Netscape format)")
    ap.add_argument("--info-only", action="store_true",
                    help="Samo metadata, brez prenosa")
    args = ap.parse_args()

    if args.info_only:
        info = get_info(args.url, cookies_file=args.cookies)
        if info:
            print(json.dumps({
                "title": info.get("title"),
                "duration": info.get("duration"),
                "uploader": info.get("uploader"),
                "thumbnail": info.get("thumbnail"),
            }, indent=2))
        else:
            print("❌ Ne morem dobiti info", file=sys.stderr)
            sys.exit(1)
        return

    download(args.url, args.output, max_height=args.max_height, cookies_file=args.cookies)


if __name__ == "__main__":
    main()