Merge odesli-link-resolution: any link -> Lidarr-first, YouTube fallback

Resolve any streaming link (Spotify/Apple/Tidal/...) via the Odesli/song.link
API, then run the existing Lidarr-first, exact-YouTube-fallback flow. YouTube
and SoundCloud links keep direct yt-dlp download; text queries unchanged.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

README.md

@@ -8,6 +8,10 @@ whatever you choose. It accepts:
 - A **free-form query**: an artist, an album, a track title, or combos like
   `"Artist - Title"` or `"Artist - Album"` (e.g. `"ODESZA - Bloom"`, `"Daft Punk"`, `"Discovery"`).
 - A **URL** (e.g. `"https://music.youtube.com/watch?v=..."` or a regular YouTube URL).
+- **Any streaming link** (Spotify, Apple Music, Tidal, Deezer, …): resolved to
+  metadata via [Odesli/song.link](https://odesli.co), then searched on Lidarr
+  first and downloaded from the matching YouTube track if no Lidarr release is
+  available. YouTube and SoundCloud links download directly.
 
 Lidarr is tried first by default. If you pick a Lidarr album but **no indexer
 release is available**, MusicFetch automatically falls through to the top

musicfetch

@@ -95,6 +95,21 @@ class Hit:
         return self.title or self.album or self.artist
 
 
+@dataclass
+class Resolved:
+    title: str = ""
+    artist: str = ""
+    thumb: str = ""
+    youtube_url: str = ""
+
+
+class OdesliError(Exception):
+    """Raised when an Odesli link can't be resolved to usable metadata."""
+
+
+ODESLI_URL = "https://api.song.link/v1-alpha.1/links"
+
+
 # ---------------------------------------------------------------------------
 # Helpers
 # ---------------------------------------------------------------------------
@@ -731,6 +746,19 @@ def _is_youtube_playlist_url(url: str) -> bool:
     return "list" in qs and "v" not in qs
 
 
+_DIRECT_DOMAINS = ("youtube.com", "youtu.be", "soundcloud.com")
+
+
+def _is_direct_url(url: str) -> bool:
+    """True for links yt-dlp downloads well directly (YouTube, SoundCloud).
+    These skip Odesli resolution and use the existing handle_url path. Matches on
+    a label boundary so look-alikes (notyoutube.com) don't slip through."""
+    if not is_url(url):
+        return False
+    host = (urlparse(url).hostname or "").lower()
+    return any(host == d or host.endswith("." + d) for d in _DIRECT_DOMAINS)
+
+
 def _ytmusic_playlist(pid: str) -> tuple[str, list[Hit]]:
     """Expand a YouTube Music playlist via ytmusicapi. Returns ("", []) on failure."""
     try:
@@ -762,6 +790,32 @@ def _entry_to_hit(entry: dict) -> Hit:
                         "extractor": source})
 
 
+def odesli_resolve(url: str) -> Optional[Resolved]:
+    """Resolve any streaming link to {title, artist, thumb, youtube_url} via the
+    Odesli (song.link) public API. Returns None on any failure (network, non-200,
+    malformed body, missing title+artist) so callers can fall back loudly."""
+    try:
+        resp = requests.get(ODESLI_URL,
+                            params={"url": url, "userCountry": "US"},
+                            timeout=8)
+        if resp.status_code != 200:
+            dbg(f"odesli {resp.status_code} for {url}")
+            return None
+        data = resp.json()
+        entity = data["entitiesByUniqueId"][data["entityUniqueId"]]
+        title = entity.get("title", "")
+        artist = entity.get("artistName", "")
+        if not title and not artist:
+            return None
+        platforms = data.get("linksByPlatform", {})
+        yt = (platforms.get("youtubeMusic") or platforms.get("youtube") or {}).get("url", "")
+        return Resolved(title=title, artist=artist,
+                        thumb=entity.get("thumbnailUrl", ""), youtube_url=yt)
+    except (RequestException, ValueError, KeyError, TypeError) as e:
+        dbg(f"odesli resolve failed for {url}: {e}")
+        return None
+
+
 def probe_url(url: str) -> tuple[str, str, list[Hit]]:
     """Classify a URL via yt-dlp. Returns (kind, title, hits) where kind is
     'playlist' (hits populated) or 'track' (hits empty; caller downloads the URL).
@@ -842,6 +896,42 @@ def get_artist_from_metadata(meta: dict) -> str:
     return "Unknown Artist"
 
 
+def resolve_link_hits(url: str, limit: int) -> tuple[str, list[Hit]]:
+    """Resolve a non-YouTube/SoundCloud link via Odesli into a search query plus
+    hits: Lidarr album candidates for "Artist - Title", followed by the EXACT
+    YouTube track from the shared link (not a fuzzy re-search). Raises OdesliError
+    if the link can't be resolved."""
+    r = odesli_resolve(url)
+    if r is None:
+        raise OdesliError(url)
+    query = f"{r.artist} - {r.title}".strip(" -")
+    hits = lidarr_search(query, limit)
+    if r.youtube_url:
+        hits = hits + [Hit(source="youtube", kind="track", title=r.title,
+                           artist=r.artist, thumbnail=r.thumb,
+                           payload={"url": r.youtube_url})]
+    return query, hits
+
+
+def handle_link(url: str, root: str, quality: str, dry_run: bool,
+                noninteractive: bool, yt_first: bool, limit: int) -> None:
+    """CLI path for a non-direct link: resolve via Odesli, then run the normal
+    Lidarr-first pick/dispatch with the exact YouTube track as fallback."""
+    try:
+        query, hits = resolve_link_hits(url, limit)
+    except OdesliError:
+        err(f"Couldn't resolve {url}. Try the direct YouTube/SoundCloud link.")
+        return
+    if not hits:
+        err(f"No Lidarr or YouTube source found for '{query}'.")
+        return
+    chosen = pick(hits, query, noninteractive, yt_first)
+    if not chosen:
+        print("Nothing selected.")
+        return
+    _dispatch_chosen(chosen, hits, root, quality, dry_run, False, False)
+
+
 def handle_url(url: str, root: str, quality: str, dry_run: bool):
     kind, title, hits = probe_url(url)
     if kind == "playlist":
@@ -1226,6 +1316,26 @@ def parse_args():
     return p.parse_args()
 
 
+def _dispatch_chosen(chosen: Hit, hits: list[Hit], root: str, quality: str,
+                     dry_run: bool, lidarr_only: bool, search_all: bool) -> None:
+    """Act on a picked Hit: Lidarr album (add+search, fall to top YouTube hit on
+    no release), Lidarr artist, or a YouTube track. Shared by main() and handle_link."""
+    if chosen.source == "lidarr":
+        if chosen.kind == "album":
+            handled = act_lidarr_album(chosen, root, search_all, dry_run)
+            if not handled and not lidarr_only:
+                yt_fallback = next((h for h in hits if h.source == "youtube"), None)
+                if yt_fallback:
+                    print("Using top YouTube hit as fallback.")
+                    act_youtube(yt_fallback, root, quality, dry_run)
+                else:
+                    print("No YouTube fallback available.")
+        else:
+            act_lidarr_artist(chosen, root, search_all, dry_run)
+    else:
+        act_youtube(chosen, root, quality, dry_run)
+
+
 def main():
     global DEBUG, COOKIES_FILE, COOKIES_FROM_BROWSER
     args = parse_args()
@@ -1253,7 +1363,11 @@ def main():
         sys.exit(1)
 
     if is_url(query):
+        if _is_direct_url(query):
             handle_url(query, args.root, args.quality, args.dry_run)
+        else:
+            handle_link(query, args.root, args.quality, args.dry_run,
+                        args.noninteractive, args.ytsearch, args.limit)
         return
 
     hits = build_combined_hits(query, args.limit, args.ytsearch,
@@ -1267,21 +1381,8 @@ def main():
         print("Nothing selected.")
         return
 
-    if chosen.source == "lidarr":
+    _dispatch_chosen(chosen, hits, args.root, args.quality, args.dry_run,
-        if chosen.kind == "album":
+                     args.lidarr_only, args.search_all)
-            handled = act_lidarr_album(chosen, args.root, args.search_all, args.dry_run)
-            if not handled and not args.lidarr_only:
-                # Fall through to the top YouTube hit for the same query.
-                yt_fallback = next((h for h in hits if h.source == "youtube"), None)
-                if yt_fallback:
-                    print("Using top YouTube hit as fallback.")
-                    act_youtube(yt_fallback, args.root, args.quality, args.dry_run)
-                else:
-                    print("No YouTube fallback available.")
-        else:
-            act_lidarr_artist(chosen, args.root, args.search_all, args.dry_run)
-    else:
-        act_youtube(chosen, args.root, args.quality, args.dry_run)
 
 
 if __name__ == "__main__":

server/app.py

@@ -53,6 +53,7 @@ def fetch(q: str = Query(..., min_length=1),
         raise HTTPException(status_code=422, detail=f"Invalid quality '{quality}'.")
 
     if mf.is_url(q):
+        if mf._is_direct_url(q):
             kind, title, hits = mf.probe_url(q)
             syn = mf.Hit(source="youtube", kind=kind, title=title, artist="")
             job = jobs.create_job(hit=syn, message=actions.url_started_message(kind, title))
@@ -66,6 +67,28 @@ def fetch(q: str = Query(..., min_length=1),
             )
             return response
 
+        # Non-direct link (Spotify/Apple/...): resolve via Odesli, then run the
+        # normal Lidarr-first pick/dispatch with the exact YouTube track fallback.
+        try:
+            query, hits = mf.resolve_link_hits(q, 10)
+        except mf.OdesliError:
+            raise HTTPException(status_code=422,
+                                detail=f"Couldn't resolve {q}. Try the direct YouTube or SoundCloud link.")
+        if not hits:
+            raise HTTPException(status_code=404, detail=f"No results found for '{q}'.")
+        chosen = mf.pick(hits, query, True, False)
+        if chosen is None:
+            raise HTTPException(status_code=404, detail=f"No results found for '{q}'.")
+        job = jobs.create_job(hit=chosen, message=actions.started_message(chosen))
+        response = _job_public(job)
+        jobs.run_job(
+            job.id,
+            lambda: actions.perform_fetch(chosen, hits, quality, ROOT),
+            done_message=actions.done_message(chosen),
+            fail_message=actions.failed_message(chosen),
+        )
+        return response
+
     if source not in ("auto", "lidarr", "youtube"):
         raise HTTPException(status_code=422, detail=f"Invalid source '{source}'.")
 

server/mf.py

@@ -28,7 +28,14 @@ is_url = _mod.is_url
 probe_url = _mod.probe_url
 download_hits = _mod.download_hits
 download_single = _mod.download_single
+_is_direct_url = _mod._is_direct_url
+odesli_resolve = _mod.odesli_resolve
+resolve_link_hits = _mod.resolve_link_hits
+handle_link = _mod.handle_link
+OdesliError = _mod.OdesliError
 
 __all__ = ["Hit", "build_combined_hits", "pick", "act_youtube",
            "act_lidarr_album", "act_lidarr_artist", "QUALITY_CHOICES",
-           "is_url", "probe_url", "download_hits", "download_single"]
+           "is_url", "probe_url", "download_hits", "download_single",
+           "_is_direct_url", "odesli_resolve", "resolve_link_hits",
+           "handle_link", "OdesliError"]

tests/test_api_url.py

@@ -73,3 +73,43 @@ def test_search_query_still_works(client, auth, monkeypatch):
     r = client.post("/fetch", params={"q": "Daft Punk - Discovery"}, headers=auth)
     assert r.status_code == 200
     assert r.json()["status"] == "queued"
+
+
+def test_non_direct_link_resolves_and_fetches(client, auth, monkeypatch):
+    from server import mf
+    lid = mf.Hit(source="lidarr", kind="album", title="A Moment Apart",
+                 artist="ODESZA", album="A Moment Apart", year="2017",
+                 payload={"album": {"id": 9}})
+    yt = mf.Hit(source="youtube", kind="track", title="Bloom", artist="ODESZA",
+                payload={"url": "https://music.youtube.com/watch?v=YYY"})
+    monkeypatch.setattr("server.app.mf.resolve_link_hits",
+                        lambda url, limit: ("ODESZA - Bloom", [lid, yt]))
+    monkeypatch.setattr("server.app.mf.pick", lambda hits, q, ni, yf: hits[0])
+    monkeypatch.setattr("server.app.actions.perform_fetch",
+                        lambda chosen, hits, quality, root: {"path": None, "lidarr_album_id": 9})
+    r = client.post("/fetch", params={"q": "https://open.spotify.com/track/abc"}, headers=auth)
+    assert r.status_code == 200
+    body = r.json()
+    assert body["status"] == "queued"
+    assert body["hit"]["album"] == "A Moment Apart"
+    done = _wait_done(client, auth, body["job_id"])
+    assert done["status"] == "done"
+
+
+def test_non_direct_link_resolve_failure_422(client, auth, monkeypatch):
+    from server import mf as mf_mod
+
+    def boom(url, limit):
+        raise mf_mod.OdesliError(url)
+
+    monkeypatch.setattr("server.app.mf.resolve_link_hits", boom)
+    r = client.post("/fetch", params={"q": "https://open.spotify.com/track/bad"}, headers=auth)
+    assert r.status_code == 422
+    assert "resolve" in r.json()["message"].lower()
+
+
+def test_non_direct_link_no_hits_404(client, auth, monkeypatch):
+    monkeypatch.setattr("server.app.mf.resolve_link_hits",
+                        lambda url, limit: ("ODESZA - Bloom", []))
+    r = client.post("/fetch", params={"q": "https://open.spotify.com/track/abc"}, headers=auth)
+    assert r.status_code == 404

tests/test_mf_url_exports.py

@@ -6,3 +6,11 @@ def test_url_helpers_reexported():
     assert callable(smf.probe_url)
     assert callable(smf.download_hits)
     assert callable(smf.download_single)
+
+
+def test_odesli_symbols_reexported():
+    import server.mf as smf
+    assert callable(smf._is_direct_url)
+    assert callable(smf.odesli_resolve)
+    assert callable(smf.resolve_link_hits)
+    assert callable(smf.handle_link)

tests/test_odesli.py

@@ -0,0 +1,159 @@
+import server.mf  # noqa: F401 — loads musicfetch, registers musicfetch_core
+import musicfetch_core as mf
+
+
+class _FakeResp:
+    def __init__(self, status, payload):
+        self.status_code = status
+        self._payload = payload
+
+    def json(self):
+        return self._payload
+
+
+FULL = {
+    "entityUniqueId": "SPOTIFY_SONG::abc",
+    "entitiesByUniqueId": {
+        "SPOTIFY_SONG::abc": {
+            "title": "Bloom",
+            "artistName": "ODESZA",
+            "thumbnailUrl": "https://img/cover.jpg",
+        }
+    },
+    "linksByPlatform": {
+        "youtubeMusic": {"url": "https://music.youtube.com/watch?v=YYY"},
+        "youtube": {"url": "https://youtube.com/watch?v=YYY"},
+    },
+}
+
+
+def test_odesli_resolve_full(monkeypatch):
+    monkeypatch.setattr(mf.requests, "get", lambda *a, **k: _FakeResp(200, FULL))
+    r = mf.odesli_resolve("https://open.spotify.com/track/abc")
+    assert r.title == "Bloom"
+    assert r.artist == "ODESZA"
+    assert r.thumb == "https://img/cover.jpg"
+    assert r.youtube_url == "https://music.youtube.com/watch?v=YYY"
+
+
+def test_odesli_resolve_prefers_ytmusic_then_youtube(monkeypatch):
+    payload = {**FULL, "linksByPlatform": {"youtube": {"url": "https://youtube.com/watch?v=ZZZ"}}}
+    monkeypatch.setattr(mf.requests, "get", lambda *a, **k: _FakeResp(200, payload))
+    r = mf.odesli_resolve("https://open.spotify.com/track/abc")
+    assert r.youtube_url == "https://youtube.com/watch?v=ZZZ"
+
+
+def test_odesli_resolve_no_youtube_link(monkeypatch):
+    payload = {**FULL, "linksByPlatform": {}}
+    monkeypatch.setattr(mf.requests, "get", lambda *a, **k: _FakeResp(200, payload))
+    r = mf.odesli_resolve("https://open.spotify.com/track/abc")
+    assert r.youtube_url == ""
+    assert r.title == "Bloom"
+
+
+def test_odesli_resolve_non_200_returns_none(monkeypatch):
+    monkeypatch.setattr(mf.requests, "get", lambda *a, **k: _FakeResp(429, {}))
+    assert mf.odesli_resolve("https://open.spotify.com/track/abc") is None
+
+
+def test_odesli_resolve_malformed_returns_none(monkeypatch):
+    monkeypatch.setattr(mf.requests, "get", lambda *a, **k: _FakeResp(200, {"nope": 1}))
+    assert mf.odesli_resolve("https://open.spotify.com/track/abc") is None
+
+
+def test_odesli_resolve_network_error_returns_none(monkeypatch):
+    def boom(*a, **k):
+        raise mf.RequestException("down")
+    monkeypatch.setattr(mf.requests, "get", boom)
+    assert mf.odesli_resolve("https://open.spotify.com/track/abc") is None
+
+
+def test_is_direct_url_youtube():
+    assert mf._is_direct_url("https://music.youtube.com/watch?v=abc")
+    assert mf._is_direct_url("https://www.youtube.com/watch?v=abc")
+    assert mf._is_direct_url("https://youtu.be/abc")
+
+
+def test_is_direct_url_soundcloud():
+    assert mf._is_direct_url("https://soundcloud.com/dj/track")
+
+
+def test_is_direct_url_other_platforms_false():
+    assert not mf._is_direct_url("https://open.spotify.com/track/abc")
+    assert not mf._is_direct_url("https://music.apple.com/us/album/x/1?i=2")
+    assert not mf._is_direct_url("https://tidal.com/browse/track/123")
+
+
+def test_is_direct_url_youtube_playlist_true():
+    assert mf._is_direct_url("https://www.youtube.com/playlist?list=PLabc")
+
+
+def test_is_direct_url_lookalike_hosts_false():
+    # Trailing-substring look-alikes must NOT be treated as direct (label boundary).
+    assert not mf._is_direct_url("https://notyoutube.com/watch?v=abc")
+    assert not mf._is_direct_url("https://myyoutube.com/x")
+    assert not mf._is_direct_url("https://evilyoutu.be/x")
+    assert not mf._is_direct_url("https://youtube.com.evil.com/x")
+
+
+def test_is_direct_url_subdomains_true():
+    assert mf._is_direct_url("https://m.youtube.com/watch?v=abc")
+    assert mf._is_direct_url("https://on.soundcloud.com/x")
+    assert mf._is_direct_url("https://api.soundcloud.com/tracks/1")
+
+
+def _resolved(yt="https://music.youtube.com/watch?v=YYY"):
+    return mf.Resolved(title="Bloom", artist="ODESZA",
+                       thumb="https://img/cover.jpg", youtube_url=yt)
+
+
+def test_resolve_link_hits_builds_query_and_exact_yt(monkeypatch):
+    monkeypatch.setattr(mf, "odesli_resolve", lambda url: _resolved())
+    lid = mf.Hit(source="lidarr", kind="album", title="A Moment Apart",
+                 artist="ODESZA", album="A Moment Apart", year="2017",
+                 payload={"album": {"id": 9}})
+    monkeypatch.setattr(mf, "lidarr_search", lambda q, limit: [lid])
+    query, hits = mf.resolve_link_hits("https://open.spotify.com/track/abc", 10)
+    assert query == "ODESZA - Bloom"
+    assert hits[0].source == "lidarr"
+    yt = hits[-1]
+    assert yt.source == "youtube" and yt.kind == "track"
+    assert yt.title == "Bloom" and yt.artist == "ODESZA"
+    assert yt.payload["url"] == "https://music.youtube.com/watch?v=YYY"
+
+
+def test_resolve_link_hits_no_yt_link_lidarr_only(monkeypatch):
+    monkeypatch.setattr(mf, "odesli_resolve", lambda url: _resolved(yt=""))
+    lid = mf.Hit(source="lidarr", kind="album", title="X", artist="ODESZA",
+                 payload={"album": {"id": 9}})
+    monkeypatch.setattr(mf, "lidarr_search", lambda q, limit: [lid])
+    query, hits = mf.resolve_link_hits("https://open.spotify.com/track/abc", 10)
+    assert all(h.source == "lidarr" for h in hits)
+
+
+def test_resolve_link_hits_odesli_miss_raises(monkeypatch):
+    import pytest
+    monkeypatch.setattr(mf, "odesli_resolve", lambda url: None)
+    with pytest.raises(mf.OdesliError):
+        mf.resolve_link_hits("https://open.spotify.com/track/abc", 10)
+
+
+def test_handle_link_miss_prints_and_returns(monkeypatch, capsys):
+    monkeypatch.setattr(mf, "odesli_resolve", lambda url: None)
+    mf.handle_link("https://open.spotify.com/track/abc", "/m", "best",
+                   False, True, False, 10)
+    out = capsys.readouterr()
+    assert "Couldn't resolve" in (out.err + out.out)
+
+
+def test_handle_link_dispatches_chosen(monkeypatch):
+    monkeypatch.setattr(mf, "odesli_resolve", lambda url: _resolved())
+    monkeypatch.setattr(mf, "lidarr_search", lambda q, limit: [])
+    chosen = {}
+    monkeypatch.setattr(mf, "pick", lambda hits, q, ni, yf: hits[0])
+    monkeypatch.setattr(mf, "_dispatch_chosen",
+                        lambda c, hits, root, quality, dry, lo, sa: chosen.update(c=c, root=root))
+    mf.handle_link("https://open.spotify.com/track/abc", "/m", "best",
+                   False, True, False, 10)
+    assert chosen["c"].source == "youtube"
+    assert chosen["root"] == "/m"