Update app.py

app.py

@@ -1,54 +1,148 @@
-import os, gradio as gr, requests
+import os
+import requests
+import pandas as pd
+import gradio as gr
+from tempfile import NamedTemporaryFile
+import shutil
 
-CID = os.getenv("SPOTIFY_CLIENT_IDS", "").split(',')[0]
-CSEC = os.getenv("SPOTIFY_CLIENT_SECRETS", "").split(',')[0]
+# —————————————
+# 1️⃣ Config de Spotify
+# —————————————
+CLIENT_ID     = os.getenv("SPOTIFY_CLIENT_IDS", "").split(',')[0]
+CLIENT_SECRET = os.getenv("SPOTIFY_CLIENT_SECRETS", "").split(',')[0]
+TOKEN_CACHE   = None
 
-def fetch_public_playlist(url):
-    # 1) Auth
-    if not (CID and CSEC):
-        return "❌ Faltan creds SPOTIFY_CLIENT_IDS o SPOTIFY_CLIENT_SECRETS"
-    tr = requests.post(
+def get_token():
+    """Pide un token Client Credentials y lo cachea."""
+    global TOKEN_CACHE
+    if TOKEN_CACHE:
+        return TOKEN_CACHE
+    resp = requests.post(
         "https://accounts.spotify.com/api/token",
         data={"grant_type":"client_credentials"},
-        auth=(CID, CSEC)
+        auth=(CLIENT_ID, CLIENT_SECRET),
     )
-    if tr.status_code != 200:
-        return f"❌ Token error {tr.status_code}"
-    token = tr.json().get("access_token")
-    
-    # 2) Extraemos ID
-    pid = url.strip().rstrip('/').split('/')[-1].split('?')[0]
-    if len(pid) != 22:
-        return f"❌ ID inválido: '{pid}' (len={len(pid)})"
-    
-    # 3) Metadata
-    meta = requests.get(
+    resp.raise_for_status()
+    TOKEN_CACHE = resp.json()["access_token"]
+    return TOKEN_CACHE
+
+def extract_pid(url):
+    """Saca el ID limpio de la URL."""
+    return url.strip().rstrip('/').split('/')[-1].split('?')[0]
+
+# —————————————
+# 2️⃣ Funciones core
+# —————————————
+def is_public_playlist(pid):
+    """Chequea metadata: devuelve (True, nombre, total) o (False, mensaje, None)."""
+    token = get_token()
+    r = requests.get(
         f"https://api.spotify.com/v1/playlists/{pid}",
         headers={"Authorization":f"Bearer {token}"}
     )
-    if meta.status_code != 200:
-        return f"❌ No pública o no existe: status {meta.status_code}"
-    data = meta.json()
-    name = data.get("name","?")
-    total = data.get("tracks",{}).get("total","?")
-    
-    # 4) Tracks (ejemplo, límite 5 para demo)
-    tracks = requests.get(
-        f"https://api.spotify.com/v1/playlists/{pid}/tracks",
-        headers={"Authorization":f"Bearer {token}"},
-        params={"limit":5}
-    ).json().get("items",[])
-    titles = [t["track"]["name"] for t in tracks if t.get("track")]
-    
-    return f"✅ “{name}”: {total} tracks\n🎵 Muestra: {titles}"
+    if r.status_code == 200:
+        j = r.json()
+        return True, j["name"], j["tracks"]["total"]
+    else:
+        return False, f"no pública / error {r.status_code}", None
+
+def fetch_all_tracks(pid, sample_limit=None):
+    """
+    Trae todos los tracks de la playlist en una lista de dicts.
+    Si sample_limit está definido, sólo jala esa cantidad (para demo).
+    """
+    token = get_token()
+    url = f"https://api.spotify.com/v1/playlists/{pid}/tracks"
+    params = {"limit":100, "market":"US"}
+    all_t = []
+    while url:
+        r = requests.get(url, headers={"Authorization":f"Bearer {token}"}, params=params)
+        r.raise_for_status()
+        data = r.json()
+        items = data.get("items", [])
+        for it in items:
+            tr = it.get("track")
+            if tr:
+                all_t.append({
+                    "Artist": tr["artists"][0]["name"],
+                    "Title":  tr["name"],
+                    "Album":  tr["album"]["name"],
+                    "Duration_ms": tr["duration_ms"],
+                    "Popularity":  tr["popularity"],
+                    "Explicit":    tr["explicit"],
+                    "Track ID":    tr["id"],
+                })
+                if sample_limit and len(all_t) >= sample_limit:
+                    return all_t
+        url = data.get("next")
+    return all_t
+
+def build_dataframe(tracks, include_all):
+    """Convierte la lista de tracks en un DataFrame y limpia duplicados."""
+    df = pd.DataFrame(tracks)
+    # Ejemplo de columnita extra si include_all
+    if include_all:
+        df["Duration_min"] = df["Duration_ms"].floordiv(60000).astype(str) + ":" + (df["Duration_ms"]%60000//1000).astype(str).str.zfill(2)
+    # Quitamos dupes por Track ID
+    return df.drop_duplicates("Track ID", ignore_index=True)
+
+# —————————————
+# 3️⃣ Función principal
+# —————————————
+def main(project_name, urls_text, include_all):
+    urls = [u for u in urls_text.replace("\n",",").split(",") if u.strip()]
+    if not urls:
+        return pd.DataFrame({"Error":["❌ Pon al menos una URL válida"]}), None
+
+    resultado = []
+    logs = []
+    for url in urls:
+        pid = extract_pid(url)
+        ok, nombre, total = is_public_playlist(pid)
+        if not ok:
+            logs.append(f"⚠️ {pid}: {nombre}")
+            continue
+        logs.append(f"✅ {pid}: “{nombre}” ({total} tracks)")
+        # Para demo sample_limit=5, quita sample_limit para todo
+        tracks = fetch_all_tracks(pid, sample_limit=None)
+        resultado.extend(tracks)
+
+    if not resultado:
+        return pd.DataFrame({"Error":logs}), None
+
+    df = build_dataframe(resultado, include_all)
+    # Generar Excel
+    with NamedTemporaryFile(delete=False, suffix=".xlsx") as tmp:
+        df.to_excel(tmp.name, index=False)
+        fname = f"{project_name or 'spotify_tracks'}.xlsx"
+        shutil.move(tmp.name, fname)
+
+    # Metemos los logs al final del DF (opcional)
+    df_logs = pd.DataFrame({"Logs": logs})
+    return df, fname
 
+# —————————————
+# 4️⃣ Interfaz Gradio
+# —————————————
 iface = gr.Interface(
-    fn=fetch_public_playlist,
-    inputs=gr.Textbox(label="URL de playlist"),
-    outputs="text",
-    title="🔎 Checa playlist pública",
-    description="Solo funciona con playlists públicas"
+    fn=main,
+    inputs=[
+        gr.Textbox(label="Nombre del proyecto"),
+        gr.Textbox(label="URLs de Spotify (coma o salto de línea)", lines=4),
+        gr.Checkbox(label="Incluir info extra", value=True),
+    ],
+    outputs=[
+        gr.Dataframe(label="Resultados"),
+        gr.File(label="Descargar Excel"),
+    ],
+    title="🎵 Spotify Track Collector PRO",
+    description="Sólo pull playlists públicas. Salta las demás.",
+    examples=[
+        ["Mi Playlist Verano", "https://open.spotify.com/playlist/13QBKWGO2VY1pc1RJz91YN", True],
+    ],
+    allow_flagging="never",
+    theme=gr.themes.Soft(),
 )
 
 if __name__=="__main__":
-    iface.launch()
+    iface.launch(server_name="0.0.0.0", server_port=7860)