groovy-zilean/cogs/music/translate.py

# Handles translating urls and search terms

import yt_dlp as ytdlp
import spotipy

# Updated yt-dlp options to handle current YouTube changes
ydl_opts = {
    'format': 'bestaudio/best',
    'quiet': True,
    'no_warnings': False,  # Show warnings for debugging
    'default_search': 'ytsearch',
    'ignoreerrors': True,
    'source_address': '0.0.0.0',  # Bind to IPv4 to avoid IPv6 issues
    'extract_flat': False,
    'nocheckcertificate': True,
    # Add extractor args to handle YouTube's new requirements
    'extractor_args': {
        'youtube': {
            'player_skip': ['webpage', 'configs'],
            'player_client': ['android', 'web'],
        }
    },
}

async def main(url, sp):

    #url = url.lower()

    # Check if link or search
    if not url.startswith("https://") and not url.startswith("http://"):
        return await search_song(url)

    #TODO add better regex or something
    if 'spotify' in url:
        if 'track' in url:
            return await spotify_song(url, sp)
        elif 'playlist' in url:
            return await spotify_playlist(url, sp)

    soundcloud_song = 'soundcloud' in url and 'sets' not in url
    # Not implemented yet
    # soundcloud_playlist = 'soundcloud' in url and 'sets' in url

    youtube_song = 'watch?v=' in url or 'youtu.be/' in url
    youtube_playlist = 'playlist?list=' in url

    # Check for direct audio/video file URLs
    # Supported formats: mp3, mp4, wav, ogg, flac, m4a, webm, aac, opus
    audio_extensions = ('.mp3', '.mp4', '.wav', '.ogg', '.flac', '.m4a', '.webm', '.aac', '.opus')
    is_direct_file = any(url.lower().endswith(ext) for ext in audio_extensions)
    # Also check for URLs with query parameters (e.g., file.mp3?download=true)
    is_direct_file = is_direct_file or any(ext in url.lower() for ext in audio_extensions)

    if soundcloud_song or youtube_song or is_direct_file:
        return await song_download(url)

    if youtube_playlist:
        return await playlist_download(url)

    return []


async def search_song(search):
    with ytdlp.YoutubeDL(ydl_opts) as ydl:
        try:
           info = ydl.extract_info(f"ytsearch1:{search}", download=False)
        except Exception as e:
            print(f"Error searching for '{search}': {e}")
            return []
    if info is None:
        return []

    if 'entries' not in info or len(info['entries']) == 0:
        return []

    info = info['entries'][0]  # Get first search result
    
    # Get the best audio stream URL
    if 'url' not in info:
        print(f"No URL found for: {search}")
        return []
    
    data = {
        'url': info['url'],
        'title': info.get('title', 'Unknown'),
        'thumbnail': info.get('thumbnail', ''),
        'duration': info.get('duration', 0)
    }
    return [data]


async def spotify_song(url, sp):
        track = sp.track(url.split("/")[-1].split("?")[0])
        search = ""

        for i in track["artists"]:
            # grabs all the artists name's if there's more than one
            search = search + (i['name'] + ", ")

        # remove last comma
        search = search[:-2]

        # set search to name
        query = search + " - " + track['name']

        return await search_song(query)


async def spotify_playlist(url, sp):
    # Get the playlist uri code
    code = url.split("/")[-1].split("?")[0]

    # Grab the tracks if the playlist is correct
    try:
        results = sp.playlist_tracks(code)['items']
    except spotipy.exceptions.SpotifyException:
        return []
    
     # Go through the tracks
    songs = []
    for track in results:
        search = ""

        # Fetch all artists
        for artist in track['track']['artists']:

            # Add all artists to search
            search += f"{artist['name']}, "

        # Remove last column
        search = search[:-2]
        search += f" - {track['track']['name']}"
        songs.append(search)

        #searched_result = search_song(search)
        #if searched_result == []:
            #continue

        #songs.append(searched_result[0])
    
    while True:
        search_result = await search_song(songs[0])
        if search_result == []:
            songs.pop(0)
            continue
        else:
            songs[0] = search_result[0]
            break
    
    return songs


async def song_download(url):
    with ytdlp.YoutubeDL(ydl_opts) as ydl:
        try:
            info = ydl.extract_info(url, download=False)
        except Exception as e:
            print(f"Error downloading '{url}': {e}")
            return []
    
    if info is None:
        return []

    # Handle both direct videos and playlists with single entry
    if 'entries' in info:
        if len(info['entries']) == 0:
            return []
        info = info['entries'][0]
    
    if 'url' not in info:
        print(f"No URL found for: {url}")
        return []

    data = {
        'url': info['url'],
        'title': info.get('title', 'Unknown'),
        'thumbnail': info.get('thumbnail', ''),
        'duration': info.get('duration', 0)
    }
    return [data]


async def playlist_download(url):
    with ytdlp.YoutubeDL(ydl_opts) as ydl:
        try:
            info = ydl.extract_info(url, download=False)
        except Exception as e:
            print(f"Error downloading playlist '{url}': {e}")
            return []
    
    if info is None:
        return []

    info = info['entries']  # Grabbing all songs in playlist
    urls = []

    for song in info:
        if song is None or 'url' not in song:
            continue
        
        data = {
            'url': song['url'],
            'title': song.get('title', 'Unknown'),
            'thumbnail': song.get('thumbnail', ''),
            'duration': song.get('duration', 0)
        }
        urls.append(data)

    return urls