Refactor audio processing to improve job ID handling and update .gitignore for separated files

.gitignore

@@ -15,7 +15,8 @@ __pycache__/
 /__pycache__
 separated/htdemucs/
 separated/htdemucs_6s/
-*.webm
+separated/*.mp4
+separated/*.webm
 *.pyi
 .claude/settings.json
 /.claude/settings.json

README.md

@@ -55,15 +55,16 @@ If an upload is present, it takes precedence over the YouTube field.
 ## Outputs
 
 Separated files are written under `separated/htdemucs_6s/{job_id}/`.
-For YouTube sources, `job_id` is the extracted video ID. For uploaded audio,
-`job_id` is a sanitized version of the uploaded filename stem.
-Each stem card in the gallery can be played in place or downloaded directly.
+For YouTube sources, `job_id` is the sanitized video title when available,
+falling back to the video ID. For uploaded audio, `job_id` is a sanitized
+version of the uploaded filename stem. Each stem card in the gallery can be
+played in place or downloaded directly.
 
 ## Extractors & Cookies
 
 For details about yt-dlp extractor behavior, see the official documentation:
 
-- https://github.com/yt-dlp/yt-dlp-wiki/blob/master/Extractors.md
+- <https://github.com/yt-dlp/yt-dlp-wiki/blob/master/Extractors.md>
 
 If you need authenticated extraction (for age-restricted or otherwise protected
 content), one way to provide cookies safely is via a private/incognito browser
@@ -71,7 +72,7 @@ session:
 
 1. Open a new private browsing/incognito window and log into YouTube.
 2. In the same window and same tab from step 1, navigate to
-   https://www.youtube.com/robots.txt (this should be the only
+   <https://www.youtube.com/robots.txt> (this should be the only
    private/incognito browsing tab open).
 3. Export youtube.com cookies from the browser, then close the private/
    incognito window so that the session is never opened in the browser again.

app.py

@@ -1,8 +1,6 @@
 # app.py — SeparateTracks Gradio application
 # Entry point: python app.py  (runs on http://localhost:7860)
 # MCP endpoint: http://localhost:7860/gradio_api/mcp/sse
-import os
-import re
 import shutil
 import sys
 from importlib import import_module
@@ -11,7 +9,12 @@ from urllib.parse import parse_qs, urlparse
 
 import gradio as gr
 
-from modules.yt_audio_get_tracks import download_audio, separate_tracks
+from modules.yt_audio_get_tracks import (
+    download_audio,
+    get_title,
+    sanitize_job_id,
+    separate_tracks,
+)
 from modules.file_utils import make_gradio_file_url
 
 
@@ -60,10 +63,6 @@ def _extract_video_id(video_input: str) -> str:
     return ""
 
 
-def _sanitize_job_id(name: str) -> str:
-    return re.sub(r"[^A-Za-z0-9_-]+", "_", name).strip("_") or "uploaded_audio"
-
-
 def _build_audio_gallery(paths) -> str:
     audio_urls = [make_gradio_file_url(path) for path in paths]
     return audio_gallery_module.AudioGallery._build_html(
@@ -79,10 +78,20 @@ def _prepare_uploaded_audio(uploaded_audio: str) -> tuple[str, str]:
     if suffix not in {".wav", ".mp3"}:
         raise ValueError("Please upload a .wav or .mp3 file.")
 
-    job_id = _sanitize_job_id(source_path.stem)
+    job_id = sanitize_job_id(source_path.stem)
     target_path = SEPARATED_DIR / f"{job_id}{suffix}"
     shutil.copy2(source_path, target_path)
     return str(target_path), job_id
+
+
+def _resolve_youtube_job_id(video_input: str) -> tuple[str, str]:
+    video_id = _extract_video_id(video_input)
+    if not video_id:
+        return "", ""
+
+    url = f"https://www.youtube.com/watch?v={video_id}"
+    title = get_title(url)
+    return video_id, sanitize_job_id(title or video_id)
 # ---------------------------------------------------------------------------
 # AudioGallery CSS — injected inline so the component is self-contained
 # ---------------------------------------------------------------------------
@@ -115,7 +124,7 @@ def _process_video_impl(video_id: str, progress=None):
     def on_progress(message):
         progress_messages.append(message)
 
-    video_id = _extract_video_id(video_id)
+    video_id, job_id = _resolve_youtube_job_id(video_id)
     if not video_id:
         return (
             "<p style='color:red;'>Please enter a YouTube video ID or URL.</p>",
@@ -128,12 +137,12 @@ def _process_video_impl(video_id: str, progress=None):
         url = f"https://www.youtube.com/watch?v={video_id}"
         if progress is not None:
             progress(0.15, desc="Downloading audio")
-        wav = download_audio(url, video_id, progress_callback=on_progress)
+        wav = download_audio(url, job_id, progress_callback=on_progress)
         if progress is not None:
             progress(0.45, desc="Separating tracks")
         drums, vocals, guitar, bass, other, piano, music = separate_tracks(
             wav,
-            video_id,
+            job_id,
             progress_callback=on_progress,
         )
         if progress is not None:
@@ -164,14 +173,14 @@ def process_video(video_id: str, progress=gr.Progress(track_tqdm=True)) -> str:
     Returns:
         HTML string containing the AudioGallery with all separated stems.
     """
-    video_id = _extract_video_id(video_id)
+    video_id, job_id = _resolve_youtube_job_id(video_id)
     if not video_id:
         return "<p style='color:red;'>Please enter a YouTube video ID or URL.</p>"
 
     try:
         url = f"https://www.youtube.com/watch?v={video_id}"
-        wav = download_audio(url, video_id)
-        drums, vocals, guitar, bass, other, piano, music = separate_tracks(wav, video_id)
+        wav = download_audio(url, job_id)
+        drums, vocals, guitar, bass, other, piano, music = separate_tracks(wav, job_id)
     except Exception as exc:
         return f"<p style='color:red;'>Error: {exc}</p>"
 
@@ -199,15 +208,15 @@ def process_video_with_progress(
             audio_path, job_id = _prepare_uploaded_audio(uploaded_audio)
             status_lines.append("Using uploaded audio file.")
         else:
-            job_id = _extract_video_id(video_id)
-            if not job_id:
+            video_id, job_id = _resolve_youtube_job_id(video_id)
+            if not video_id:
                 yield (
                     "<p style='color:red;'>Please enter a YouTube video ID or URL, or upload an audio file.</p>",
                     "No video ID, URL, or audio file provided.",
                 )
                 return
 
-            url = f"https://www.youtube.com/watch?v={job_id}"
+            url = f"https://www.youtube.com/watch?v={video_id}"
             progress(0.05, desc="Downloading audio")
             yield "", "Downloading audio from YouTube..."
             audio_path = download_audio(url, job_id, progress_callback=on_progress)

modules/yt_audio_get_tracks.py

@@ -1,7 +1,12 @@
 # yt_separator.py
 # pip install yt-dlp demucs pydub (ffmpeg required)
-import os, sys, subprocess
+import os
+import re
 import shutil
+import subprocess
+import sys
+from typing import Any, cast
+
 import yt_dlp
 from pydub import AudioSegment
 
@@ -9,9 +14,23 @@ def _emit_progress(progress_callback, message):
     if progress_callback is not None:
         progress_callback(message)
 
+
+def sanitize_job_id(name):
+    return re.sub(r"[^A-Za-z0-9_-]+", "_", name).strip("_") or "uploaded_audio"
+
+
+def get_title(url_or_id):
+    with yt_dlp.YoutubeDL({"quiet": True, "no_warnings": True}) as ydl:
+        try:
+            info = ydl.extract_info(url_or_id, download=False) or {}
+        except Exception:
+            return ""
+
+    return info.get("title") or info.get("id") or ""
+
 cookie_path = os.path.join(os.path.dirname(__file__), 'cookies.txt')
 
-def download_audio(url, video_id, progress_callback=None):
+def download_audio(url, job_id, progress_callback=None):
     temp_dir = 'separated'
     os.makedirs(temp_dir, exist_ok=True)
     _emit_progress(progress_callback, 'Downloading audio from YouTube...')
@@ -24,7 +43,7 @@ def download_audio(url, video_id, progress_callback=None):
 
     ydl_opts = {
         'format': 'bestaudio/best',
-        'outtmpl': os.path.join(temp_dir, f'{video_id}.%(ext)s'),
+        'outtmpl': os.path.join(temp_dir, f'{job_id}.%(ext)s'),
         'postprocessors': [{'key': 'FFmpegExtractAudio', 'preferredcodec': 'wav'}],
         'keepvideo': True,
         'quiet': False,
@@ -55,12 +74,12 @@ def download_audio(url, video_id, progress_callback=None):
     #         return None
     #     _emit_progress(progress_callback, f"Found {len(audio)} audio formats")
 
-    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+    with yt_dlp.YoutubeDL(cast(Any, ydl_opts)) as ydl:
         ydl.download([url])
     _emit_progress(progress_callback, 'Converting downloaded audio to WAV...')
-    return os.path.join(temp_dir, f'{video_id}.wav')
+    return os.path.join(temp_dir, f'{job_id}.wav')
 
-def separate_tracks(input_wav, video_id, progress_callback=None):
+def separate_tracks(input_wav, job_id, progress_callback=None):
     if not os.path.exists(input_wav):
         raise FileNotFoundError(f"{input_wav} does not exist")
     
@@ -68,7 +87,7 @@ def separate_tracks(input_wav, video_id, progress_callback=None):
     _emit_progress(progress_callback, 'Separating tracks with Demucs...')
     subprocess.run(['demucs', '-n', 'htdemucs_6s', '--mp3', '--out', output_dir, input_wav], check=True)
     
-    base = os.path.join('.', output_dir, 'htdemucs_6s', video_id)
+    base = os.path.join('.', output_dir, 'htdemucs_6s', job_id)
     
     drums = f'{base}/drums.mp3'
     vocals = f'{base}/vocals.mp3'
@@ -92,8 +111,10 @@ def main():
     video_id = input("enter youtube video id: ")
     url = f"https://www.youtube.com/watch?v={video_id}"
     try:
-        wav = download_audio(url, video_id)
-        d, v, g, b, o, p, m = separate_tracks(wav, video_id)
+        title = get_title(url)
+        job_id = sanitize_job_id(title or video_id)
+        wav = download_audio(url, job_id)
+        d, v, g, b, o, p, m = separate_tracks(wav, job_id)
         print(d, v, g, b, o, p, m)
     except Exception as exc:
         print(exc)