added. playback aware lidarr discovery tool. still stand alone

2026-05-10 15:26:01 -04:00
parent a03280d6d3
commit dd55ec0761
2 changed files with 353 additions and 67 deletions
@@ -0,0 +1,332 @@
+import requests
+from collections import defaultdict
+from dataclasses import dataclass
+from datetime import datetime
+
+# =========================================================
+# CONFIG
+# =========================================================
+
+LASTFM_API_KEY = "YOUR_LASTFM_KEY"
+LASTFM_USER = "YOUR_USERNAME"
+
+EMBY_URL = "http://YOUR_EMBY:8096"
+EMBY_API_KEY = "YOUR_EMBY_API_KEY"
+
+# influence constraints
+MAX_USER_WEIGHT = 0.35   # no single user > 35%
+MIN_USER_ACTIVITY = 5     # ignore near-zero listeners
+
+# scoring thresholds
+CORE_THRESHOLD = 90
+CONTEXT_THRESHOLD = 80
+
+FINAL_SELECTION_LIMIT = 3
+
+
+# =========================================================
+# PLAYLIST CONTEXT (intentional listening structure)
+# =========================================================
+
+PLAYLIST_CONTEXTS = [
+    {"name": "90s Alternative", "tags": ["alternative", "rock", "90s"], "weight": 1.3},
+    {"name": "Favorites Mix", "tags": ["all-time", "mixed"], "weight": 1.5},
+    {"name": "ICP / Aggressive", "tags": ["hardcore", "rap", "aggressive"], "weight": 1.2},
+    {"name": "Country Party", "tags": ["country", "party"], "weight": 1.3},
+    {"name": "2000s Rock", "tags": ["rock", "2000s"], "weight": 1.25},
+]
+
+
+# =========================================================
+# DATA MODEL
+# =========================================================
+
+@dataclass
+class ArtistCandidate:
+    name: str
+    score: float = 0.0
+    tier: str = "rotation"  # core | context | rotation
+
+
+# =========================================================
+# EMBY: PLAYBACK ACTIVITY (TRUTH SOURCE)
+# =========================================================
+
+def get_emby_recent_events(days=30):
+    """
+    Pull recent playback activity from Emby.
+    Each event should include: user + artist
+    """
+
+    url = f"{EMBY_URL}/Users/{EMBY_API_KEY}/Items/Latest"
+    headers = {"X-Emby-Token": EMBY_API_KEY}
+
+    try:
+        r = requests.get(url, headers=headers)
+        data = r.json()
+    except Exception:
+        return []
+
+    events = []
+
+    for item in data:
+        if "ArtistName" in item and "UserId" in item:
+            events.append({
+                "user": item["UserId"],
+                "artist": item["ArtistName"]
+            })
+
+    return events
+
+
+# =========================================================
+# ACTIVE USER DETECTION (TIME-BOUND CONTEXT)
+# =========================================================
+
+def get_active_users(events):
+    user_activity = defaultdict(int)
+
+    for e in events:
+        user_activity[e["user"]] += 1
+
+    # filter low activity users
+    filtered = {
+        u: c for u, c in user_activity.items()
+        if c >= MIN_USER_ACTIVITY
+    }
+
+    if not filtered:
+        return {}
+
+    # normalize weights
+    max_count = max(filtered.values())
+
+    user_weights = {}
+
+    for u, c in filtered.items():
+        weight = c / max_count
+        user_weights[u] = min(weight, MAX_USER_WEIGHT)
+
+    return user_weights
+
+
+# =========================================================
+# LAST.FM SIGNALS (GLOBAL TASTE GRAPH)
+# =========================================================
+
+def lastfm_similar(artist):
+    url = "http://ws.audioscrobbler.com/2.0/"
+
+    params = {
+        "method": "artist.getsimilar",
+        "artist": artist,
+        "api_key": LASTFM_API_KEY,
+        "format": "json",
+        "limit": 20
+    }
+
+    try:
+        r = requests.get(url, params=params)
+        data = r.json()
+    except Exception:
+        return []
+
+    results = []
+
+    try:
+        for a in data["similarartists"]["artist"]:
+            results.append({
+                "name": a["name"],
+                "match": float(a["match"])
+            })
+    except Exception:
+        pass
+
+    return results
+
+
+def lastfm_top_artists():
+    url = "http://ws.audioscrobbler.com/2.0/"
+
+    params = {
+        "method": "user.gettopartists",
+        "user": LASTFM_USER,
+        "api_key": LASTFM_API_KEY,
+        "format": "json",
+        "limit": 50
+    }
+
+    try:
+        r = requests.get(url, params=params)
+        data = r.json()
+    except Exception:
+        return []
+
+    results = []
+
+    try:
+        for a in data["topartists"]["artist"]:
+            results.append((a["name"], int(a["playcount"])))
+    except Exception:
+        pass
+
+    return results
+
+
+# =========================================================
+# CONTEXT VECTOR (PLAYLIST BLENDING)
+# =========================================================
+
+def build_context_vector():
+    ctx = defaultdict(float)
+
+    for p in PLAYLIST_CONTEXTS:
+        for tag in p["tags"]:
+            ctx[tag] += p["weight"]
+
+    return ctx
+
+
+# =========================================================
+# SCORING ENGINE (TIME-BOUND + MULTI-SIGNAL)
+# =========================================================
+
+def build_scores():
+    scores = defaultdict(float)
+
+    context_vector = build_context_vector()
+
+    # -----------------------------------------------------
+    # 1. EMBY: playback events (current taste context)
+    # -----------------------------------------------------
+    events = get_emby_recent_events()
+    active_users = get_active_users(events)
+
+    user_artist_counts = defaultdict(lambda: defaultdict(int))
+
+    for e in events:
+        if e["user"] in active_users:
+            user_artist_counts[e["user"]][e["artist"]] += 1
+
+    # weighted user contribution
+    for user, artists in user_artist_counts.items():
+        weight = active_users[user]
+
+        for artist, count in artists.items():
+            scores[artist] += count * 50 * weight
+
+    # -----------------------------------------------------
+    # 2. LAST.FM: long-term identity
+    # -----------------------------------------------------
+    top = lastfm_top_artists()
+
+    for artist, plays in top:
+        scores[artist] += min(plays * 0.25, 80)
+
+    # -----------------------------------------------------
+    # 3. GRAPH EXPANSION
+    # -----------------------------------------------------
+    seeds = list(scores.keys())[:15]
+
+    for seed in seeds:
+        for s in lastfm_similar(seed):
+            scores[s["name"]] += s["match"] * 60
+
+    # -----------------------------------------------------
+    # 4. CONTEXT BLENDING (playlist influence)
+    # -----------------------------------------------------
+    for artist in list(scores.keys()):
+        for tag, weight in context_vector.items():
+            if tag.lower() in artist.lower():
+                scores[artist] += weight * 8
+
+    return scores
+
+
+# =========================================================
+# TIER CLASSIFICATION
+# =========================================================
+
+def classify_tier(score):
+    if score >= CORE_THRESHOLD:
+        return "core"
+    elif score >= CONTEXT_THRESHOLD:
+        return "context"
+    return "rotation"
+
+
+# =========================================================
+# SURVIVAL FILTER
+# =========================================================
+
+def filter_candidates(scores):
+    candidates = []
+
+    for name, score in scores.items():
+        candidates.append(ArtistCandidate(
+            name=name,
+            score=score,
+            tier=classify_tier(score)
+        ))
+
+    candidates = [c for c in candidates if c.score >= CONTEXT_THRESHOLD]
+    candidates.sort(key=lambda x: x.score, reverse=True)
+
+    return candidates
+
+
+# =========================================================
+# FINAL SELECTION (balanced survival)
+# =========================================================
+
+def select_final(candidates):
+    if not candidates:
+        return []
+
+    final = []
+
+    cores = [c for c in candidates if c.tier == "core"]
+    contexts = [c for c in candidates if c.tier == "context"]
+
+    final.extend(cores[:2])
+    final.extend(contexts[:1])
+
+    return final[:FINAL_SELECTION_LIMIT]
+
+
+# =========================================================
+# OUTPUT (LIDARR HOOK)
+# =========================================================
+
+def send_to_lidarr(artists):
+    for a in artists:
+        print(f"[{a.tier.upper()}] {a.name} ({a.score:.2f})")
+
+
+# =========================================================
+# MAIN CYCLE
+# =========================================================
+
+def run():
+    print("\n=== DISCOVERY CYCLE START ===")
+    print(f"Time: {datetime.now()}")
+
+    scores = build_scores()
+    candidates = filter_candidates(scores)
+    final = select_final(candidates)
+
+    if not final:
+        print("\nNo artists survived this cycle.")
+        return
+
+    print("\nSurvivors:")
+    for f in final:
+        print(f"- {f.name} [{f.tier}] ({f.score:.2f})")
+
+    send_to_lidarr(final)
+
+    print("\n=== CYCLE COMPLETE ===")
+
+
+if __name__ == "__main__":
+    run()