feat: add real yt-dlp client and opt-in live test; ffmpeg in worker image

worker/Dockerfile

@@ -1,5 +1,6 @@
 FROM python:3.12-slim
 WORKDIR /app
+RUN apt-get update && apt-get install -y --no-install-recommends ffmpeg && rm -rf /var/lib/apt/lists/*
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 COPY lyra_worker ./lyra_worker

worker/lyra_worker/adapters/_ytdlp.py

@@ -0,0 +1,56 @@
+import os
+from typing import Callable
+
+import yt_dlp
+
+
+class YtDlpClient:
+    """Real YtClient backed by yt_dlp. Not unit-tested offline; see test_youtube_live.py."""
+
+    def search_album(self, artist: str, album: str) -> list[dict]:
+        query = f"ytsearch5:{artist} {album} full album"
+        opts = {
+            "quiet": True,
+            "no_warnings": True,
+            "extract_flat": "in_playlist",
+            "skip_download": True,
+        }
+        with yt_dlp.YoutubeDL(opts) as ydl:
+            info = ydl.extract_info(query, download=False)
+        results: list[dict] = []
+        for e in (info.get("entries") or []):
+            if not e:
+                continue
+            results.append(
+                {
+                    "source_ref": e.get("url") or e.get("webpage_url") or e.get("id"),
+                    "title": e.get("title") or "",
+                    "artist": e.get("uploader") or e.get("channel") or "",
+                    "track_count": e.get("playlist_count") or 1,
+                }
+            )
+        return results
+
+    def download(self, source_ref: str, dest: str, on_progress: Callable[[float], None]) -> dict:
+        os.makedirs(dest, exist_ok=True)
+
+        def hook(d: dict) -> None:
+            if d.get("status") == "downloading":
+                total = d.get("total_bytes") or d.get("total_bytes_estimate")
+                if total:
+                    on_progress(min(1.0, d.get("downloaded_bytes", 0) / total))
+            elif d.get("status") == "finished":
+                on_progress(1.0)
+
+        opts = {
+            "quiet": True,
+            "no_warnings": True,
+            "format": "bestaudio/best",
+            "outtmpl": os.path.join(dest, "%(playlist_index)s-%(title)s.%(ext)s"),
+            "progress_hooks": [hook],
+            "postprocessors": [{"key": "FFmpegExtractAudio", "preferredcodec": "opus"}],
+        }
+        with yt_dlp.YoutubeDL(opts) as ydl:
+            info = ydl.extract_info(source_ref, download=True)
+        entries = info.get("entries") if info.get("entries") is not None else [info]
+        return {"track_count": len([e for e in entries if e]), "path": dest}

worker/requirements.txt

@@ -1,3 +1,4 @@
 psycopg[binary]>=3.2,<4
 pytest>=8.3,<9
 cryptography>=42,<46
+yt-dlp>=2024.1

worker/tests/test_youtube_live.py

@@ -0,0 +1,16 @@
+import os
+
+import pytest
+
+from lyra_worker.adapters._ytdlp import YtDlpClient
+
+pytestmark = pytest.mark.skipif(
+    not os.environ.get("LYRA_LIVE_TESTS"),
+    reason="live network test; set LYRA_LIVE_TESTS=1 to run",
+)
+
+
+def test_live_search_returns_results():
+    results = YtDlpClient().search_album("Radiohead", "In Rainbows")
+    assert len(results) >= 1
+    assert all(r["source_ref"] for r in results)