spotify: search_artist_discography con dedupe top-tracks+album

core/spotify_client.py

@@ -3,6 +3,8 @@
 from __future__ import annotations
 
 import re
+import time
+
 import requests
 
 
@@ -314,3 +316,89 @@ def _track_to_dict(t: dict) -> dict:
         "album": t.get("album", {}).get("name", ""),
         "duration_sec": int(t.get("duration_ms", 0)) // 1000,
     }
+
+
+def search_artist_discography(token: str, artist_name: str) -> list:
+    """Trova l'artista esatto (o il piu' popolare tra i match) e ritorna
+    tutti i suoi brani: top tracks + tracce di ogni album/single.
+    Deduplica per (name.lower().strip(), first_artist.lower().strip()).
+
+    Raises:
+        ValueError: se nessun artista trovato per il nome dato.
+    """
+    headers = {"Authorization": f"Bearer {token}"}
+
+    # 1. Cerca artista
+    resp = requests.get(
+        "https://api.spotify.com/v1/search",
+        headers=headers,
+        params={"q": artist_name, "type": "artist", "limit": 5},
+        timeout=15,
+    )
+    resp.raise_for_status()
+    candidates = resp.json().get("artists", {}).get("items", [])
+    if not candidates:
+        raise ValueError(f"Artista '{artist_name}' non trovato")
+
+    # Match esatto (case-insensitive) se possibile, altrimenti piu' popolare
+    query_lower = artist_name.lower().strip()
+    exact = [c for c in candidates if c.get("name", "").lower().strip() == query_lower]
+    if exact:
+        artist = exact[0]
+    else:
+        artist = max(candidates, key=lambda c: c.get("popularity", 0))
+    artist_id = artist["id"]
+
+    collected: list = []
+
+    # 2. Top tracks
+    r_top = requests.get(
+        f"https://api.spotify.com/v1/artists/{artist_id}/top-tracks",
+        headers=headers,
+        params={"market": "IT"},
+        timeout=15,
+    )
+    r_top.raise_for_status()
+    for t in r_top.json().get("tracks", []):
+        collected.append(_track_to_dict(t))
+
+    # 3. Albums (album + single)
+    r_alb = requests.get(
+        f"https://api.spotify.com/v1/artists/{artist_id}/albums",
+        headers=headers,
+        params={"include_groups": "album,single", "limit": 50, "market": "IT"},
+        timeout=15,
+    )
+    r_alb.raise_for_status()
+    albums = r_alb.json().get("items", [])
+
+    # 4. Per ogni album, tracce (album/track object non ha "album" sub-field, iniettiamola)
+    for alb in albums:
+        alb_id = alb.get("id")
+        alb_name = alb.get("name", "")
+        if not alb_id:
+            continue
+        time.sleep(0.1)  # rate limit interno
+        r_at = requests.get(
+            f"https://api.spotify.com/v1/albums/{alb_id}/tracks",
+            headers=headers,
+            params={"limit": 50},
+            timeout=15,
+        )
+        r_at.raise_for_status()
+        for t in r_at.json().get("items", []):
+            t = dict(t)
+            # Album tracks non hanno "album" nested; iniettiamo il nome
+            t.setdefault("album", {"name": alb_name})
+            collected.append(_track_to_dict(t))
+
+    # 5. Dedupe
+    seen: set = set()
+    unique: list = []
+    for t in collected:
+        key = (t["name"].lower().strip(), t["artists"].split(",")[0].lower().strip())
+        if key in seen:
+            continue
+        seen.add(key)
+        unique.append(t)
+    return unique