From 13c8e607127eb05932834521b429099e57776204 Mon Sep 17 00:00:00 2001
From: luciano <info@djluza.com>
Date: Tue, 14 Jul 2026 16:22:21 +0200
Subject: [PATCH] =?UTF-8?q?beatport:=20parse=20JSON=20=E2=86=92=20list[Bea?=
 =?UTF-8?q?tportTrack]?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 core/beatport.py       | 56 ++++++++++++++++++++++++++++++++++++++++++
 tests/test_beatport.py | 28 +++++++++++++++++++++
 2 files changed, 84 insertions(+)

diff --git a/core/beatport.py b/core/beatport.py
index 8910548..a4d5ff2 100644
--- a/core/beatport.py
+++ b/core/beatport.py
@@ -110,3 +110,59 @@ def list_genres() -> list:
     ]
     result.sort(key=lambda g: g["name"].casefold())
     return result
+
+
+def _find_tracks_results(data: dict) -> list:
+    """Cerca dentro le queries dehydrated il primo `results` che ha almeno 50 elementi
+    e la shape di una track (chiave `id` presente)."""
+    try:
+        queries = data["props"]["pageProps"]["dehydratedState"]["queries"]
+    except (KeyError, TypeError) as e:
+        raise BeatportParseError(
+            f"schema JSON inatteso, `results` non localizzabile (chiave mancante: {e})"
+        ) from e
+
+    for q in queries:
+        state_data = (q or {}).get("state", {}).get("data")
+        if not isinstance(state_data, dict):
+            continue
+        results = state_data.get("results")
+        if isinstance(results, list) and len(results) >= 50:
+            if results and isinstance(results[0], dict) and "id" in results[0]:
+                return results
+    raise BeatportParseError("nessun `results` di 50+ track trovato in __NEXT_DATA__")
+
+
+def _format_artists(artists_field: object) -> str:
+    """Beatport ritorna artists come lista di dict {name, ...}.
+    Formatta come 'A, B & C' (& prima dell'ultimo)."""
+    if not isinstance(artists_field, list) or not artists_field:
+        return ""
+    names = [a.get("name", "") for a in artists_field if isinstance(a, dict)]
+    names = [n for n in names if n]
+    if not names:
+        return ""
+    if len(names) == 1:
+        return names[0]
+    return ", ".join(names[:-1]) + " & " + names[-1]
+
+
+def _parse_tracks(data: dict) -> list:
+    """Trasforma i track dict di Beatport in BeatportTrack ordinati per posizione."""
+    raw = _find_tracks_results(data)
+    out: list = []
+    for i, item in enumerate(raw, 1):
+        try:
+            length_ms = int(item.get("length_ms") or 0)
+            track = BeatportTrack(
+                position=i,
+                title=str(item.get("name") or "").strip(),
+                mix=str(item.get("mix_name") or "").strip(),
+                artists=_format_artists(item.get("artists")),
+                duration_sec=length_ms // 1000,
+                beatport_id=int(item.get("id") or 0),
+            )
+        except (TypeError, ValueError) as e:
+            raise BeatportParseError(f"track[{i}] shape inattesa: {e}") from e
+        out.append(track)
+    return out
diff --git a/tests/test_beatport.py b/tests/test_beatport.py
index 1e533dd..4f3400c 100644
--- a/tests/test_beatport.py
+++ b/tests/test_beatport.py
@@ -83,3 +83,31 @@ class TestExtractNextData:
         broken = '<script id="__NEXT_DATA__" type="application/json">{not: valid}</script>'
         with pytest.raises(beatport.BeatportParseError, match="JSON malformato"):
             beatport._extract_next_data(broken)
+
+
+class TestParseTracks:
+    def test_extracts_100_tracks(self, fixtures_dir):
+        html = (fixtures_dir / "beatport_melodic_top100.html").read_text()
+        data = beatport._extract_next_data(html)
+        tracks = beatport._parse_tracks(data)
+        assert len(tracks) == 100
+
+    def test_positions_are_sequential_1_to_100(self, fixtures_dir):
+        html = (fixtures_dir / "beatport_melodic_top100.html").read_text()
+        tracks = beatport._parse_tracks(beatport._extract_next_data(html))
+        positions = [t.position for t in tracks]
+        assert positions == list(range(1, 101))
+
+    def test_track_shape(self, fixtures_dir):
+        html = (fixtures_dir / "beatport_melodic_top100.html").read_text()
+        tracks = beatport._parse_tracks(beatport._extract_next_data(html))
+        first = tracks[0]
+        assert isinstance(first, beatport.BeatportTrack)
+        assert first.title
+        assert first.artists
+        assert first.duration_sec > 0
+        assert first.beatport_id > 0
+
+    def test_schema_missing_results_raises(self):
+        with pytest.raises(beatport.BeatportParseError, match="results"):
+            beatport._parse_tracks({"props": {"pageProps": {}}})