986 lines
39 KiB
Python
986 lines
39 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Karaoke Playlist Downloader
|
|
A Python-based Windows command-line tool that wraps yt-dlp.exe to batch-download karaoke videos from YouTube playlists.
|
|
"""
|
|
|
|
import os
|
|
import sys
|
|
import argparse
|
|
import subprocess
|
|
import json
|
|
import re
|
|
from pathlib import Path
|
|
from urllib.parse import urlparse, parse_qs
|
|
import logging
|
|
from datetime import datetime
|
|
from tracking_manager import TrackingManager, SongStatus, FormatType
|
|
|
|
# Try to import mutagen for ID3 tagging
|
|
try:
|
|
from mutagen.mp4 import MP4, MP4Tags
|
|
MUTAGEN_AVAILABLE = True
|
|
except ImportError:
|
|
MUTAGEN_AVAILABLE = False
|
|
print("⚠️ mutagen not available - ID3 tagging will be disabled")
|
|
print(" Install with: pip install mutagen")
|
|
|
|
|
|
class KaraokeDownloader:
|
|
def __init__(self):
|
|
self.yt_dlp_path = Path("downloader/yt-dlp.exe")
|
|
self.downloads_dir = Path("downloads")
|
|
self.logs_dir = Path("logs")
|
|
|
|
# Create necessary directories
|
|
self.downloads_dir.mkdir(exist_ok=True)
|
|
self.logs_dir.mkdir(exist_ok=True)
|
|
|
|
# Initialize tracking manager
|
|
self.tracker = TrackingManager()
|
|
|
|
# Load configuration
|
|
self.config = self._load_config()
|
|
|
|
# Songlist tracking file
|
|
self.songlist_tracking_file = Path("songlist_tracking.json")
|
|
self.songlist_tracking = self._load_songlist_tracking()
|
|
|
|
def _get_channel_info(self, channel_url):
|
|
"""Extract channel information from URL."""
|
|
# Fallback: extract channel info from URL (faster and more reliable)
|
|
if '@' in channel_url:
|
|
# Handle @username format
|
|
channel_name = channel_url.split('@')[1].split('/')[0]
|
|
channel_id = f"@{channel_name}"
|
|
else:
|
|
# Handle other formats
|
|
channel_name = "unknown_channel"
|
|
channel_id = "unknown_channel"
|
|
|
|
# Clean the channel name for use as directory name
|
|
channel_name = re.sub(r'[<>:"/\\|?*]', '_', channel_name)
|
|
return channel_name, channel_id
|
|
|
|
def _get_playlist_info(self, playlist_url):
|
|
"""Extract playlist information from URL (backward compatibility)."""
|
|
return self._get_channel_info(playlist_url)
|
|
|
|
def _load_config(self):
|
|
"""Load configuration from config.json file."""
|
|
config_file = Path("config.json")
|
|
if config_file.exists():
|
|
try:
|
|
with open(config_file, 'r', encoding='utf-8') as f:
|
|
return json.load(f)
|
|
except (json.JSONDecodeError, FileNotFoundError) as e:
|
|
print(f"Warning: Could not load config.json: {e}")
|
|
|
|
# Return default configuration
|
|
return {
|
|
"download_settings": {
|
|
"format": "best[height<=720][ext=mp4]/best[height<=720]/best[ext=mp4]/best",
|
|
"preferred_resolution": "720p",
|
|
"audio_format": "mp3",
|
|
"audio_quality": "0",
|
|
"subtitle_language": "en",
|
|
"subtitle_format": "srt",
|
|
"write_metadata": False,
|
|
"write_thumbnail": False,
|
|
"write_description": False,
|
|
"write_annotations": False,
|
|
"write_comments": False,
|
|
"write_subtitles": False,
|
|
"embed_metadata": False,
|
|
"add_metadata": False,
|
|
"continue_downloads": True,
|
|
"no_overwrites": True,
|
|
"ignore_errors": True,
|
|
"no_warnings": False
|
|
},
|
|
"folder_structure": {
|
|
"downloads_dir": "downloads",
|
|
"logs_dir": "logs",
|
|
"tracking_file": "karaoke_tracking.json"
|
|
},
|
|
"logging": {
|
|
"level": "INFO",
|
|
"format": "%(asctime)s - %(levelname)s - %(message)s",
|
|
"include_console": True,
|
|
"include_file": True
|
|
},
|
|
"yt_dlp_path": "downloader/yt-dlp.exe"
|
|
}
|
|
|
|
def _load_songlist(self):
|
|
"""Load songlist from docs/songList.json file."""
|
|
songlist_file = Path("docs/songList.json")
|
|
if not songlist_file.exists():
|
|
print("⚠️ Songlist file not found: docs/songList.json")
|
|
return []
|
|
|
|
try:
|
|
with open(songlist_file, 'r', encoding='utf-8') as f:
|
|
data = json.load(f)
|
|
|
|
# Extract all songs from all categories
|
|
all_songs = []
|
|
for category in data:
|
|
if "songs" in category:
|
|
for song in category["songs"]:
|
|
if "artist" in song and "title" in song:
|
|
all_songs.append({
|
|
"artist": song["artist"].strip(),
|
|
"title": song["title"].strip(),
|
|
"position": song.get("position", 0)
|
|
})
|
|
|
|
print(f"📋 Loaded {len(all_songs)} songs from songlist")
|
|
return all_songs
|
|
|
|
except (json.JSONDecodeError, FileNotFoundError) as e:
|
|
print(f"⚠️ Could not load songlist: {e}")
|
|
return []
|
|
|
|
def _load_songlist_tracking(self):
|
|
"""Load songlist tracking data."""
|
|
if not self.songlist_tracking_file.exists():
|
|
return {}
|
|
|
|
try:
|
|
with open(self.songlist_tracking_file, 'r', encoding='utf-8') as f:
|
|
return json.load(f)
|
|
except (json.JSONDecodeError, FileNotFoundError) as e:
|
|
print(f"⚠️ Could not load songlist tracking: {e}")
|
|
return {}
|
|
|
|
def _save_songlist_tracking(self):
|
|
"""Save songlist tracking data."""
|
|
try:
|
|
with open(self.songlist_tracking_file, 'w', encoding='utf-8') as f:
|
|
json.dump(self.songlist_tracking, f, indent=2, ensure_ascii=False)
|
|
except Exception as e:
|
|
print(f"⚠️ Could not save songlist tracking: {e}")
|
|
|
|
def _is_songlist_song_downloaded(self, artist, title):
|
|
"""Check if a songlist song has been downloaded from any channel."""
|
|
key = f"{artist.lower()}_{self._normalize_title(title)}"
|
|
return key in self.songlist_tracking
|
|
|
|
def _mark_songlist_song_downloaded(self, artist, title, channel_name, file_path):
|
|
"""Mark a songlist song as downloaded."""
|
|
key = f"{artist.lower()}_{self._normalize_title(title)}"
|
|
self.songlist_tracking[key] = {
|
|
"artist": artist,
|
|
"title": title,
|
|
"channel": channel_name,
|
|
"file_path": str(file_path),
|
|
"downloaded_at": datetime.now().isoformat()
|
|
}
|
|
self._save_songlist_tracking()
|
|
|
|
def _normalize_title(self, title):
|
|
"""Normalize title for comparison (remove karaoke suffixes, etc.)."""
|
|
# Remove common karaoke suffixes
|
|
normalized = title.replace("(Karaoke Version)", "").replace("(Karaoke)", "").strip()
|
|
# Remove extra spaces and convert to lowercase for comparison
|
|
return " ".join(normalized.split()).lower()
|
|
|
|
def _find_songlist_matches(self, cached_videos, songlist, songlist_only=False):
|
|
"""Find videos that match songs in the songlist."""
|
|
matches = []
|
|
songlist_lookup = {}
|
|
unique_matches = set()
|
|
already_downloaded = 0
|
|
new_downloads = 0
|
|
|
|
# Create lookup for songlist songs (normalized)
|
|
for song in songlist:
|
|
normalized_title = self._normalize_title(song["title"])
|
|
key = f"{song['artist'].lower()}_{normalized_title}"
|
|
songlist_lookup[key] = song
|
|
|
|
print(f"🔍 Searching for {len(songlist)} songlist songs in {len(cached_videos)} cached videos...")
|
|
|
|
for video in cached_videos:
|
|
# Extract artist and title from video title
|
|
artist, title = self._extract_artist_title(video['title'])
|
|
normalized_title = self._normalize_title(title)
|
|
key = f"{artist.lower()}_{normalized_title}"
|
|
|
|
if key in songlist_lookup:
|
|
songlist_song = songlist_lookup[key]
|
|
|
|
# Check if already downloaded from any channel
|
|
if self._is_songlist_song_downloaded(artist, title):
|
|
already_downloaded += 1
|
|
print(f"⏭️ Already downloaded: {artist} - {title}")
|
|
continue
|
|
|
|
matches.append({
|
|
'video': video,
|
|
'songlist_song': songlist_song,
|
|
'priority_score': songlist_song.get('position', 9999) # Lower position = higher priority
|
|
})
|
|
unique_matches.add(key)
|
|
new_downloads += 1
|
|
print(f"🎯 Found match: {artist} - {title} (position {songlist_song.get('position', 'N/A')})")
|
|
|
|
print(f"🎯 Matching Results:")
|
|
print(f" • Total matches found: {len(matches) + already_downloaded}")
|
|
print(f" • Unique songs matched: {len(unique_matches) + already_downloaded}")
|
|
print(f" • Already downloaded: {already_downloaded}")
|
|
print(f" • New downloads available: {new_downloads}")
|
|
print(f" • Duplicate matches: {len(matches) - len(unique_matches)}")
|
|
|
|
return matches
|
|
|
|
def _get_playlist_name(self, playlist_url):
|
|
"""Extract playlist name from URL (backward compatibility)."""
|
|
return self._get_playlist_info(playlist_url)[0]
|
|
|
|
def _setup_logging(self, playlist_name):
|
|
"""Setup logging for the current playlist."""
|
|
log_file = self.logs_dir / f"{playlist_name}.log"
|
|
|
|
# Configure logging
|
|
logging.basicConfig(
|
|
level=logging.INFO,
|
|
format='%(asctime)s - %(levelname)s - %(message)s',
|
|
handlers=[
|
|
logging.FileHandler(log_file),
|
|
logging.StreamHandler(sys.stdout)
|
|
]
|
|
)
|
|
|
|
return logging.getLogger(__name__)
|
|
|
|
def _get_channel_videos(self, channel_url):
|
|
"""Get list of videos from a channel."""
|
|
try:
|
|
cmd = [
|
|
str(self.yt_dlp_path),
|
|
"--flat-playlist",
|
|
"--print", "id,title,duration,upload_date",
|
|
channel_url
|
|
]
|
|
|
|
result = subprocess.run(cmd, capture_output=True, text=True, timeout=120)
|
|
if result.returncode == 0 and result.stdout.strip():
|
|
videos = []
|
|
lines = result.stdout.strip().split('\n')
|
|
for i in range(0, len(lines), 4):
|
|
if i + 3 < len(lines):
|
|
video_id = lines[i].strip()
|
|
title = lines[i + 1].strip()
|
|
duration = lines[i + 2].strip()
|
|
upload_date = lines[i + 3].strip()
|
|
try:
|
|
duration_int = int(duration) if duration != 'NA' else None
|
|
except ValueError:
|
|
duration_int = None
|
|
|
|
videos.append({
|
|
'video_id': video_id,
|
|
'title': title,
|
|
'duration': duration_int,
|
|
'upload_date': upload_date
|
|
})
|
|
return videos
|
|
except (subprocess.TimeoutExpired, subprocess.CalledProcessError) as e:
|
|
print(f"Error getting channel videos: {e}")
|
|
|
|
return []
|
|
|
|
def _get_playlist_songs(self, playlist_url):
|
|
"""Get list of songs in a playlist (backward compatibility)."""
|
|
return self._get_channel_videos(playlist_url)
|
|
|
|
def _extract_artist_title(self, video_title):
|
|
"""Extract artist and title from karaoke video title."""
|
|
# Remove common karaoke suffixes
|
|
title = video_title.replace("(Karaoke Version)", "").replace("(Karaoke)", "").strip()
|
|
|
|
# Look for common patterns
|
|
if " - " in title:
|
|
# Format: "Artist - Song Title"
|
|
parts = title.split(" - ", 1)
|
|
if len(parts) == 2:
|
|
artist = parts[0].strip()
|
|
song_title = parts[1].strip()
|
|
|
|
# Handle special cases
|
|
if artist == "d4vd, Hyunjin":
|
|
return "d4vd, Hyunjin", song_title
|
|
elif artist == "Adrianne Lenker":
|
|
return "Adrianne Lenker", song_title
|
|
else:
|
|
return artist, song_title
|
|
|
|
# Handle special cases without clear artist - title pattern
|
|
if "Nothing Beats A Jet2 Holiday" in title:
|
|
return "Jet2", "Nothing Beats A Jet2 Holiday"
|
|
elif "Spin The Wheel" in title:
|
|
return "SingKingKaraoke", "Spin The Wheel - Your Song Requests"
|
|
|
|
# If no clear pattern, assume the whole title is the song name
|
|
return "Unknown Artist", title
|
|
|
|
def _add_id3_tags(self, file_path, video_title, channel_name):
|
|
"""Add ID3 tags to the downloaded MP4 file."""
|
|
if not MUTAGEN_AVAILABLE:
|
|
print("⚠️ mutagen not available - skipping ID3 tagging")
|
|
return
|
|
|
|
try:
|
|
artist, title = self._extract_artist_title(video_title)
|
|
|
|
# Load the MP4 file
|
|
mp4 = MP4(str(file_path))
|
|
|
|
# Add metadata tags
|
|
mp4['\xa9nam'] = title # Title
|
|
mp4['\xa9ART'] = artist # Artist
|
|
mp4['\xa9alb'] = f"{channel_name} Karaoke" # Album
|
|
mp4['\xa9gen'] = "Karaoke" # Genre
|
|
mp4['\xa9day'] = str(datetime.now().year) # Year
|
|
|
|
# Save the metadata
|
|
mp4.save()
|
|
|
|
print(f"📝 Added ID3 tags: Artist='{artist}', Title='{title}'")
|
|
|
|
except Exception as e:
|
|
print(f"⚠️ Could not add ID3 tags: {e}")
|
|
|
|
def _cleanup_extra_files(self, mp4_file_path):
|
|
"""Remove extra files (info.json, meta) that yt-dlp creates alongside MP4 files."""
|
|
try:
|
|
# Get the base path without extension
|
|
base_path = mp4_file_path.with_suffix('')
|
|
|
|
# Files to remove
|
|
extra_files = [
|
|
base_path.with_suffix('.info.json'),
|
|
base_path.with_suffix('.meta')
|
|
]
|
|
|
|
removed_count = 0
|
|
for extra_file in extra_files:
|
|
if extra_file.exists():
|
|
extra_file.unlink()
|
|
removed_count += 1
|
|
print(f"🧹 Removed extra file: {extra_file.name}")
|
|
|
|
if removed_count > 0:
|
|
print(f"🧹 Cleaned up {removed_count} extra file(s)")
|
|
|
|
except Exception as e:
|
|
print(f"⚠️ Could not clean up extra files: {e}")
|
|
|
|
def download_channel_videos(self, channel_url, force_refresh=False):
|
|
"""Download all videos from a YouTube channel."""
|
|
print(f"🎤 Starting download for channel: {channel_url}")
|
|
|
|
# Get channel info
|
|
print("🔍 Extracting channel information...")
|
|
channel_name, channel_id = self._get_channel_info(channel_url)
|
|
print(f"📺 Channel name: {channel_name}")
|
|
print(f"🆔 Channel ID: {channel_id}")
|
|
|
|
# Setup logging
|
|
print("📝 Setting up logging...")
|
|
logger = self._setup_logging(channel_name)
|
|
logger.info(f"Starting download for channel: {channel_url}")
|
|
|
|
# Add channel to tracking
|
|
print("📋 Adding channel to tracking system...")
|
|
self.tracker.add_playlist(channel_id, channel_name, channel_url)
|
|
|
|
# Check cache first (unless force refresh is requested)
|
|
print("💾 Checking channel cache...")
|
|
current_videos = None
|
|
if not force_refresh:
|
|
current_videos = self.tracker.get_cached_channel_videos(channel_id)
|
|
if current_videos:
|
|
print(f"📋 Using cached channel data: {len(current_videos)} videos")
|
|
else:
|
|
print("📋 Cache miss or expired, fetching fresh channel data...")
|
|
|
|
# Fetch fresh data if needed
|
|
if not current_videos:
|
|
print("📋 Fetching channel videos from YouTube...")
|
|
current_videos = self._get_channel_videos(channel_url)
|
|
print(f"🎵 Found {len(current_videos)} videos in channel")
|
|
|
|
# Cache the results
|
|
if current_videos:
|
|
print("💾 Caching channel data for future use...")
|
|
self.tracker.cache_channel_videos(channel_id, current_videos)
|
|
print(f"💾 Cached channel data for future use")
|
|
else:
|
|
print(f"🎵 Using {len(current_videos)} cached videos")
|
|
|
|
# Sync channel with tracking
|
|
print("🔄 Syncing channel with tracking system...")
|
|
sync_result = self.tracker.sync_playlist(channel_id, current_videos)
|
|
print(f"🔄 Sync result: {sync_result['added']} new, {sync_result['removed']} removed, {sync_result['total']} total")
|
|
|
|
# Create channel-specific downloads directory
|
|
print("📁 Creating downloads directory...")
|
|
downloads_dir = self.downloads_dir / channel_name
|
|
downloads_dir.mkdir(parents=True, exist_ok=True)
|
|
print(f"📁 Downloads will be saved to: {downloads_dir}")
|
|
|
|
# Load songlist for prioritization (if enabled)
|
|
songlist = []
|
|
if hasattr(self, 'use_songlist_priority') and self.use_songlist_priority:
|
|
print("📋 Loading songlist for prioritization...")
|
|
songlist = self._load_songlist()
|
|
|
|
# Show songlist statistics
|
|
unique_songs = len(set(f"{song['artist']}_{song['title']}" for song in songlist))
|
|
print(f"📊 Songlist Statistics:")
|
|
print(f" • Total songs in list: {len(songlist)}")
|
|
print(f" • Unique songs: {unique_songs}")
|
|
print(f" • Duplicates in list: {len(songlist) - unique_songs}")
|
|
else:
|
|
print("📋 Songlist prioritization disabled")
|
|
|
|
# Get videos that need downloading
|
|
print("🔍 Checking which videos need to be downloaded...")
|
|
videos_to_download = []
|
|
found_existing = 0
|
|
|
|
# Get list of existing MP4 files once (more efficient)
|
|
existing_files = set()
|
|
for file_path in downloads_dir.glob(f"*.mp4"):
|
|
if file_path.is_file():
|
|
existing_files.add(file_path.stem)
|
|
|
|
# Also check root downloads directory
|
|
for file_path in self.downloads_dir.glob(f"*.mp4"):
|
|
if file_path.is_file():
|
|
existing_files.add(file_path.stem)
|
|
|
|
print(f"📁 Found {len(existing_files)} existing MP4 files in directories")
|
|
|
|
# Separate videos into songlist matches and others
|
|
songlist_matches = []
|
|
other_videos = []
|
|
|
|
for video in current_videos:
|
|
if not self.tracker.is_song_downloaded(video['video_id'], channel_id):
|
|
if video['title'] in existing_files:
|
|
# File exists but not tracked, mark as downloaded
|
|
self.tracker.update_song_status(
|
|
video['video_id'],
|
|
channel_id,
|
|
SongStatus.DOWNLOADED,
|
|
FormatType.MP4,
|
|
downloads_dir / f"{video['title']}.mp4" # Assume it's in channel dir
|
|
)
|
|
found_existing += 1
|
|
else:
|
|
other_videos.append(video)
|
|
|
|
# Find songlist matches and prioritize them
|
|
if songlist:
|
|
songlist_matches = self._find_songlist_matches(other_videos, songlist, songlist_only=getattr(self, 'songlist_only', False))
|
|
|
|
# Remove matched videos from other_videos to avoid duplicates
|
|
matched_video_ids = {match['video']['video_id'] for match in songlist_matches}
|
|
other_videos = [v for v in other_videos if v['video_id'] not in matched_video_ids]
|
|
|
|
# Sort songlist matches by priority (lower position = higher priority)
|
|
songlist_matches.sort(key=lambda x: x['priority_score'])
|
|
|
|
# Add songlist matches first, then other videos (unless songlist_only is enabled)
|
|
if getattr(self, 'songlist_only', False):
|
|
videos_to_download = [match['video'] for match in songlist_matches]
|
|
print(f"🎯 Songlist-only mode: {len(songlist_matches)} songlist matches")
|
|
else:
|
|
videos_to_download = [match['video'] for match in songlist_matches] + other_videos
|
|
print(f"🎯 Prioritized {len(songlist_matches)} songlist matches")
|
|
print(f"📝 Added {len(other_videos)} other videos")
|
|
else:
|
|
videos_to_download = other_videos
|
|
|
|
if found_existing > 0:
|
|
print(f"📁 Found {found_existing} existing files that weren't tracked")
|
|
|
|
# Apply limit if specified
|
|
if hasattr(self, 'download_limit') and self.download_limit:
|
|
videos_to_download = videos_to_download[:self.download_limit]
|
|
print(f"📥 Videos to download: {len(videos_to_download)} (limited to {self.download_limit})")
|
|
else:
|
|
print(f"📥 Videos to download: {len(videos_to_download)}")
|
|
|
|
if not videos_to_download:
|
|
print("✅ All videos already downloaded!")
|
|
return True
|
|
|
|
# Build yt-dlp command for each video
|
|
for i, video in enumerate(videos_to_download, 1):
|
|
print(f"\n🎵 Downloading {i} of {len(videos_to_download)}: {video['title']}")
|
|
|
|
# Update status to downloading
|
|
self.tracker.update_song_status(
|
|
video['video_id'],
|
|
channel_id,
|
|
SongStatus.DOWNLOADING
|
|
)
|
|
|
|
# Build yt-dlp command for this specific video using config
|
|
download_settings = self.config["download_settings"]
|
|
|
|
cmd = [
|
|
str(self.yt_dlp_path),
|
|
"--format", download_settings["format"],
|
|
"--output", str(downloads_dir / "%(title)s.%(ext)s"),
|
|
]
|
|
|
|
# Only add metadata options if enabled in config
|
|
if download_settings.get("add_metadata", False):
|
|
cmd.append("--add-metadata")
|
|
if download_settings.get("embed_metadata", False):
|
|
cmd.append("--embed-metadata")
|
|
if download_settings.get("write_metadata", False):
|
|
cmd.append("--write-info-json")
|
|
|
|
# Add optional settings based on config (only essential ones)
|
|
if download_settings.get("no_overwrites", True):
|
|
cmd.append("--no-overwrites")
|
|
if download_settings.get("continue_downloads", True):
|
|
cmd.append("--continue")
|
|
if download_settings.get("ignore_errors", True):
|
|
cmd.append("--ignore-errors")
|
|
if download_settings.get("no_warnings", False):
|
|
cmd.append("--no-warnings")
|
|
|
|
# Add progress and display options
|
|
cmd.extend([
|
|
"--progress",
|
|
"--newline",
|
|
"--console-title",
|
|
f"https://www.youtube.com/watch?v={video['video_id']}"
|
|
])
|
|
|
|
try:
|
|
print(f"🚀 Starting download for: {video['title']}")
|
|
logger.info(f"Starting download for video ID: {video['video_id']}")
|
|
|
|
# Run yt-dlp
|
|
process = subprocess.Popen(
|
|
cmd,
|
|
stdout=subprocess.PIPE,
|
|
stderr=subprocess.STDOUT,
|
|
text=True,
|
|
bufsize=1,
|
|
universal_newlines=True
|
|
)
|
|
|
|
# Process output in real-time
|
|
for line in process.stdout:
|
|
line = line.strip()
|
|
if line:
|
|
print(line)
|
|
logger.info(line)
|
|
|
|
process.wait()
|
|
|
|
# Check if download was successful (more lenient - if MP4 exists, consider success)
|
|
downloaded_file = None
|
|
|
|
# Look for the file in the channel directory by title (since yt-dlp uses title as filename)
|
|
for file_path in downloads_dir.glob(f"*.mp4"):
|
|
if file_path.is_file():
|
|
# Check if this file matches the video title
|
|
file_name = file_path.stem # filename without extension
|
|
if file_name == video['title']:
|
|
downloaded_file = file_path
|
|
break
|
|
|
|
# If not found, also check the root downloads directory
|
|
if not downloaded_file:
|
|
for file_path in self.downloads_dir.glob(f"*.mp4"):
|
|
if file_path.is_file():
|
|
# Check if this file matches the video title
|
|
file_name = file_path.stem # filename without extension
|
|
if file_name == video['title']:
|
|
downloaded_file = file_path
|
|
break
|
|
|
|
if downloaded_file:
|
|
# MP4 file exists, consider download successful
|
|
format_type = FormatType.MP4
|
|
|
|
# Update tracking with successful download
|
|
self.tracker.update_song_status(
|
|
video['video_id'],
|
|
channel_id,
|
|
SongStatus.DOWNLOADED,
|
|
format_type,
|
|
downloaded_file
|
|
)
|
|
|
|
print(f"✅ Successfully downloaded: {video['title']} ({format_type})")
|
|
logger.info(f"Successfully downloaded: {video['title']} ({format_type})")
|
|
|
|
# Add ID3 tags to the downloaded file
|
|
self._add_id3_tags(downloaded_file, video['title'], channel_name)
|
|
|
|
# Clean up extra files (info.json, meta files)
|
|
self._cleanup_extra_files(downloaded_file)
|
|
|
|
# Mark as downloaded in songlist tracking if it's a songlist song
|
|
if hasattr(self, 'use_songlist_priority') and self.use_songlist_priority:
|
|
artist, title = self._extract_artist_title(video['title'])
|
|
self._mark_songlist_song_downloaded(artist, title, channel_name, downloaded_file)
|
|
print(f"📋 Marked songlist song as downloaded: {artist} - {title}")
|
|
else:
|
|
# No MP4 file found, mark as failed
|
|
self.tracker.update_song_status(
|
|
video['video_id'],
|
|
channel_id,
|
|
SongStatus.FAILED,
|
|
error_message=f"Download failed - no MP4 file found (return code: {process.returncode})"
|
|
)
|
|
print(f"❌ Download failed for: {video['title']} (return code: {process.returncode})")
|
|
logger.error(f"Download failed for: {video['title']} (return code: {process.returncode})")
|
|
|
|
except subprocess.CalledProcessError as e:
|
|
error_msg = f"Error running yt-dlp for {video['title']}: {e}"
|
|
print(f"❌ {error_msg}")
|
|
logger.error(error_msg)
|
|
|
|
self.tracker.update_song_status(
|
|
video['video_id'],
|
|
channel_id,
|
|
SongStatus.FAILED,
|
|
error_message=str(e)
|
|
)
|
|
|
|
except KeyboardInterrupt:
|
|
print("\n⏹️ Download interrupted by user")
|
|
logger.info("Download interrupted by user")
|
|
|
|
# Mark current video as partial
|
|
self.tracker.update_song_status(
|
|
video['video_id'],
|
|
channel_id,
|
|
SongStatus.PARTIAL
|
|
)
|
|
return False
|
|
|
|
# Force save tracking data
|
|
self.tracker.force_save()
|
|
|
|
# Show final statistics
|
|
stats = self.tracker.get_statistics()
|
|
print(f"\n📊 Download Statistics:")
|
|
print(f" Total songs: {stats['total_songs']}")
|
|
print(f" Downloaded: {stats['downloaded_songs']}")
|
|
print(f" Failed: {stats['failed_songs']}")
|
|
print(f" Partial: {stats['partial_songs']}")
|
|
print(f" Total size: {stats['total_size_mb']} MB")
|
|
|
|
return True
|
|
|
|
def download_playlist(self, playlist_url):
|
|
"""Download all videos from a YouTube playlist (backward compatibility)."""
|
|
return self.download_channel_videos(playlist_url)
|
|
|
|
def download_from_file(self, file_path, force_refresh=False):
|
|
"""Download multiple playlists from a text file."""
|
|
file_path = Path(file_path)
|
|
|
|
if not file_path.exists():
|
|
print(f"❌ File not found: {file_path}")
|
|
return False
|
|
|
|
print(f"📄 Reading playlists from: {file_path}")
|
|
|
|
with open(file_path, 'r') as f:
|
|
playlist_urls = [line.strip() for line in f if line.strip()]
|
|
|
|
print(f"📋 Found {len(playlist_urls)} URL(s) to download")
|
|
|
|
success_count = 0
|
|
for i, url in enumerate(playlist_urls, 1):
|
|
print(f"\n{'='*50}")
|
|
print(f"📥 Processing URL {i}/{len(playlist_urls)}: {url}")
|
|
print(f"{'='*50}")
|
|
|
|
if self.download_channel_videos(url, force_refresh=force_refresh):
|
|
success_count += 1
|
|
|
|
print(f"\n🎉 Download summary: {success_count}/{len(playlist_urls)} URLs completed successfully")
|
|
|
|
# Force save any pending tracking data
|
|
self.tracker.force_save()
|
|
|
|
return success_count == len(playlist_urls)
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(
|
|
description="Karaoke Video Downloader - Download YouTube playlists and channel videos for karaoke",
|
|
formatter_class=argparse.RawDescriptionHelpFormatter,
|
|
epilog="""
|
|
Examples:
|
|
python download_karaoke.py https://www.youtube.com/playlist?list=XYZ
|
|
python download_karaoke.py https://www.youtube.com/@SingKingKaraoke/videos
|
|
python download_karaoke.py --file playlists.txt
|
|
python download_karaoke.py --limit 5 https://www.youtube.com/@SingKingKaraoke/videos
|
|
python download_karaoke.py --refresh https://www.youtube.com/@SingKingKaraoke/videos
|
|
python download_karaoke.py --cache-info
|
|
python download_karaoke.py --clear-cache all
|
|
"""
|
|
)
|
|
|
|
parser.add_argument(
|
|
'url',
|
|
nargs='?',
|
|
help='YouTube playlist or channel URL to download'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--file', '-f',
|
|
help='Text file containing playlist or channel URLs (one per line)'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--status', '-s',
|
|
action='store_true',
|
|
help='Show download status and statistics'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--report', '-r',
|
|
metavar='PLAYLIST_ID',
|
|
help='Generate a detailed report for a specific playlist'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--sync', '--sync-only',
|
|
action='store_true',
|
|
help='Only sync playlist without downloading (update tracking)'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--cleanup',
|
|
action='store_true',
|
|
help='Clean up orphaned tracking entries'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--resolution', '--res',
|
|
choices=['480p', '720p', '1080p', '1440p', '2160p'],
|
|
default='720p',
|
|
help='Preferred video resolution (default: 720p)'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--limit', '-l',
|
|
type=int,
|
|
help='Limit the number of videos to download (e.g., --limit 10)'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--refresh', '--force-refresh',
|
|
action='store_true',
|
|
help='Force refresh channel cache (ignore cached data)'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--cache-info',
|
|
action='store_true',
|
|
help='Show channel cache information'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--clear-cache',
|
|
metavar='CHANNEL_ID',
|
|
nargs='?',
|
|
const='all',
|
|
help='Clear cache for specific channel or all channels (use --clear-cache all)'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--cache-duration',
|
|
type=int,
|
|
metavar='HOURS',
|
|
help='Set cache duration in hours (default: 24)'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--songlist-priority',
|
|
action='store_true',
|
|
help='Prioritize downloads based on docs/songList.json (default: enabled)'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--no-songlist-priority',
|
|
action='store_true',
|
|
help='Disable songlist prioritization'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--songlist-only',
|
|
action='store_true',
|
|
help='Only download songs that are in the songlist (skip all others)'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--songlist-status',
|
|
action='store_true',
|
|
help='Show songlist download status and statistics'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--version', '-v',
|
|
action='version',
|
|
version='Karaoke Playlist Downloader v1.0'
|
|
)
|
|
|
|
args = parser.parse_args()
|
|
|
|
# Check if yt-dlp.exe exists
|
|
yt_dlp_path = Path("downloader/yt-dlp.exe")
|
|
if not yt_dlp_path.exists():
|
|
print("❌ Error: yt-dlp.exe not found in downloader/ directory")
|
|
print("Please ensure yt-dlp.exe is present in the downloader/ folder")
|
|
sys.exit(1)
|
|
|
|
# Initialize downloader
|
|
downloader = KaraokeDownloader()
|
|
|
|
# Set download limit if specified
|
|
if args.limit:
|
|
downloader.download_limit = args.limit
|
|
print(f"🎯 Download limit set to: {args.limit} videos")
|
|
|
|
# Set songlist priority setting
|
|
if args.no_songlist_priority:
|
|
downloader.use_songlist_priority = False
|
|
print("🎯 Songlist prioritization disabled")
|
|
else:
|
|
downloader.use_songlist_priority = True
|
|
print("🎯 Songlist prioritization enabled")
|
|
|
|
# Set songlist-only mode
|
|
if args.songlist_only:
|
|
downloader.songlist_only = True
|
|
print("🎯 Songlist-only mode enabled (will only download songlist songs)")
|
|
|
|
# Update resolution if specified
|
|
if args.resolution != '720p':
|
|
resolution_map = {
|
|
'480p': '480',
|
|
'720p': '720',
|
|
'1080p': '1080',
|
|
'1440p': '1440',
|
|
'2160p': '2160'
|
|
}
|
|
height = resolution_map[args.resolution]
|
|
downloader.config["download_settings"]["format"] = f"best[height<={height}][ext=mp4]/best[height<={height}]/best[ext=mp4]/best"
|
|
downloader.config["download_settings"]["preferred_resolution"] = args.resolution
|
|
print(f"🎬 Using resolution: {args.resolution}")
|
|
|
|
# Process arguments
|
|
if args.status:
|
|
# Show status and statistics
|
|
stats = downloader.tracker.get_statistics()
|
|
print("🎤 Karaoke Downloader Status")
|
|
print("=" * 40)
|
|
print(f"Total Songs: {stats['total_songs']}")
|
|
print(f"Total Playlists: {stats['total_playlists']}")
|
|
print(f"Downloaded Songs: {stats['downloaded_songs']}")
|
|
print(f"Failed Songs: {stats['failed_songs']}")
|
|
print(f"Partial Downloads: {stats['partial_songs']}")
|
|
print(f"Total Size: {stats['total_size_mb']} MB")
|
|
print(f"Last Updated: {stats['last_updated']}")
|
|
sys.exit(0)
|
|
|
|
elif args.cache_info:
|
|
# Show cache information
|
|
cache_info = downloader.tracker.get_cache_info()
|
|
print("💾 Channel Cache Information")
|
|
print("=" * 40)
|
|
print(f"Total Channels: {cache_info['total_channels']}")
|
|
print(f"Total Cached Videos: {cache_info['total_cached_videos']}")
|
|
print(f"Cache Duration: {cache_info['cache_duration_hours']} hours")
|
|
print(f"Last Updated: {cache_info['last_updated']}")
|
|
sys.exit(0)
|
|
|
|
elif args.clear_cache:
|
|
# Clear cache
|
|
if args.clear_cache == 'all':
|
|
downloader.tracker.clear_channel_cache()
|
|
print("🧹 Cleared all channel caches")
|
|
else:
|
|
downloader.tracker.clear_channel_cache(args.clear_cache)
|
|
print(f"🧹 Cleared cache for channel: {args.clear_cache}")
|
|
sys.exit(0)
|
|
|
|
elif args.cache_duration:
|
|
# Set cache duration
|
|
downloader.tracker.set_cache_duration(args.cache_duration)
|
|
print(f"⏰ Cache duration set to {args.cache_duration} hours")
|
|
sys.exit(0)
|
|
|
|
elif args.report:
|
|
# Generate playlist report
|
|
report = downloader.tracker.export_playlist_report(args.report)
|
|
print(report)
|
|
sys.exit(0)
|
|
|
|
elif args.cleanup:
|
|
# Clean up orphaned entries
|
|
orphaned = downloader.tracker.cleanup_orphaned_files(downloader.downloads_dir)
|
|
print(f"🧹 Cleaned up {len(orphaned)} orphaned tracking entries")
|
|
sys.exit(0)
|
|
|
|
elif args.songlist_status:
|
|
# Show songlist status and statistics
|
|
songlist = downloader._load_songlist()
|
|
tracking = downloader.songlist_tracking
|
|
|
|
print("📋 Songlist Download Status")
|
|
print("=" * 40)
|
|
print(f"Total songs in list: {len(songlist)}")
|
|
print(f"Songs downloaded: {len(tracking)}")
|
|
print(f"Songs remaining: {len(songlist) - len(tracking)}")
|
|
print(f"Progress: {(len(tracking) / len(songlist) * 100):.1f}%")
|
|
|
|
if tracking:
|
|
print(f"\n📁 Downloaded songs:")
|
|
for key, info in list(tracking.items())[:10]: # Show first 10
|
|
print(f" • {info['artist']} - {info['title']} (from {info['channel']})")
|
|
if len(tracking) > 10:
|
|
print(f" ... and {len(tracking) - 10} more")
|
|
|
|
sys.exit(0)
|
|
|
|
elif args.file:
|
|
success = downloader.download_from_file(args.file, force_refresh=args.refresh)
|
|
elif args.url:
|
|
success = downloader.download_channel_videos(args.url, force_refresh=args.refresh)
|
|
else:
|
|
parser.print_help()
|
|
sys.exit(1)
|
|
|
|
# Force save any pending tracking data before exit
|
|
downloader.tracker.force_save()
|
|
|
|
if success:
|
|
print("\n🎤 All downloads completed successfully!")
|
|
sys.exit(0)
|
|
else:
|
|
print("\n⚠️ Some downloads may have failed. Check the logs for details.")
|
|
sys.exit(1)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main() |