feat(pipeline): finalize audited multi-platform dataset with clean provenance and entity resolution

collectors/test_spotify_endpoints.py

@@ -0,0 +1,69 @@
+"""
+collectors/test_spotify_endpoints.py
+Direct diagnostic to test Spotify OAuth2 Client Credentials flow
+and probe endpoint permissions for Artist data, Top Tracks, and Search.
+"""
+
+import os
+import requests
+import base64
+
+CLIENT_ID = os.getenv("SPOTIFY_CLIENT_ID", "a4a008ec790d45fba6a37315a1a3d847")
+CLIENT_SECRET = os.getenv("SPOTIFY_CLIENT_SECRET", "a5c67d9a63d340b6ae4a5bec83bca241")
+
+
+def get_token(client_id: str, client_secret: str):
+    """Requests a bearer token via standard OAuth2 Client Credentials."""
+    auth_header = base64.b64encode(f"{client_id}:{client_secret}".encode()).decode()
+    url = "https://accounts.spotify.com/api/token"
+    res = requests.post(
+        url,
+        data={"grant_type": "client_credentials"},
+        headers={"Authorization": f"Basic {auth_header}"},
+        timeout=10,
+    )
+    return res.status_code, res.json()
+
+
+def test_endpoints(token: str):
+    headers = {"Authorization": f"Bearer {token}"}
+    pilot_artist_id = "3TVXtAsR1Inumwj472S9r4"  # Drake
+
+    endpoints = {
+        "Artist Metadata (GET /v1/artists/{id})": f"https://api.spotify.com/v1/artists/{pilot_artist_id}",
+        "Artist Top Tracks (GET /v1/artists/{id}/top-tracks)": f"https://api.spotify.com/v1/artists/{pilot_artist_id}/top-tracks?market=US",
+        "Search Endpoint (GET /v1/search)": "https://api.spotify.com/v1/search?q=Drake&type=artist&limit=1",
+    }
+
+    results = {}
+    for name, url in endpoints.items():
+        res = requests.get(url, headers=headers, timeout=10)
+        results[name] = {
+            "status_code": res.status_code,
+            "response_preview": res.text[:300],
+        }
+    return results
+
+
+if __name__ == "__main__":
+    print("=" * 80)
+    print("SPOTIFY API AUTHENTICATION & ENDPOINT PERMISSION DIAGNOSTIC")
+    print("=" * 80)
+
+    status, token_resp = get_token(CLIENT_ID, CLIENT_SECRET)
+    print(f"Token Endpoint Status: {status}")
+
+    if status == 200:
+        token = token_resp.get("access_token")
+        print(f"Bearer Token Acquired: {token[:15]}... [expires_in: {token_resp.get('expires_in')}s]")
+        print("-" * 80)
+
+        diagnostics = test_endpoints(token)
+        for ep, out in diagnostics.items():
+            print(f"\nEndpoint: {ep}")
+            print(f"Status:   {out['status_code']}")
+            print(f"Payload:  {out['response_preview']}")
+    else:
+        print(f"Failed to obtain token: {token_resp}")
+
+    print("\n" + "=" * 80)