Update app.py

app.py

@@ -1,21 +1,19 @@
-
+import gradio as gr
 import requests
 import pandas as pd
 import time
 import shutil
+import numpy as np
 import os
 from tempfile import NamedTemporaryFile
+from openpyxl import Workbook
 
 # Spotify API credentials from environment variables
-client_ids = os.getenv("SPOTIFY_CLIENT_IDS", "")
-client_secrets = os.getenv("SPOTIFY_CLIENT_SECRETS", "")
+client_ids = os.getenv("SPOTIFY_CLIENT_IDS")
+client_secrets = os.getenv("SPOTIFY_CLIENT_SECRETS")
 
-# For testing/demo purposes only - DO NOT use in production
 if not client_ids or not client_secrets:
-    print("WARNING: No API credentials found in environment variables. Using demo mode with limited functionality.")
-    # Provide fake credentials for demo purposes
-    client_ids = "demo_client_id"
-    client_secrets = "demo_client_secret"
+    raise ValueError("SPOTIFY_CLIENT_IDS or SPOTIFY_CLIENT_SECRETS environment variables not set.")
 
 client_ids = client_ids.split(',')
 client_secrets = client_secrets.split(',')
@@ -26,28 +24,16 @@ total_requests = 0
 
 # Spotify Functions
 def get_token(client_id, client_secret):
-    """Get Spotify API token. Returns a demo token in case of failure for testing."""
     url = 'https://accounts.spotify.com/api/token'
     headers = {'Content-Type': 'application/x-www-form-urlencoded'}
     payload = {'grant_type': 'client_credentials'}
-    
-    try:
-        response = requests.post(url, headers=headers, data=payload, auth=(client_id, client_secret))
-        global total_requests
-        total_requests += 1
-        
-        if response.status_code == 200:
-            print("Successfully obtained Spotify API token")
-            return response.json().get('access_token')
-        else:
-            print(f"Error getting token: {response.status_code} - {response.text}")
-            # For demo/testing only - simulate a token
-            if client_id == "demo_client_id":
-                print("Using demo token for testing purposes")
-                return "demo_token"
-            return None
-    except Exception as e:
-        print(f"Exception during token retrieval: {str(e)}")
+    response = requests.post(url, headers=headers, data=payload, auth=(client_id, client_secret))
+    global total_requests
+    total_requests += 1
+    if response.status_code == 200:
+        return response.json().get('access_token')
+    else:
+        print(f"Error getting token: {response.status_code} - {response.text}")
         return None
 
 def handle_rate_limit(response, attempt):
@@ -328,25 +314,99 @@ def interface(project_name, spotify_urls, include_all_info=True):
     # Get token
     token_spotify = get_token(client_ids[current_api_index], client_secrets[current_api_index])
     if not token_spotify:
-        if client_ids[0] == "demo_client_id":
-            print("Running in demo mode with sample data")
-            # In demo mode, return sample data
-            demo_data = get_demo_data()
-            df = pd.DataFrame(demo_data)
-            
-            # Save DataFrame to an Excel file
-            tmpfile = NamedTemporaryFile(delete=False, suffix='.xlsx')
-            df.to_excel(tmpfile.name, index=False)
-            
-            # Rename the file with the project name
-            project_file_name = f"{project_name}.xlsx"
-            shutil.move(tmpfile.name, project_file_name)
-            
-            return df, project_file_name
-        else:
-            error_message = "Failed to authenticate with Spotify API. Please try again later."
-            return gr.Dataframe(value=pd.DataFrame({"Error": [error_message]})), None
+        error_message = "Failed to authenticate with Spotify API. Please try again later."
+        return gr.Dataframe(value=pd.DataFrame({"Error": [error_message]})), None
     
     print(f"Successfully authenticated with Spotify API")
     
-    all_tracks = []
+    all_tracks = []
+    
+    # Process each URL
+    for url in valid_urls:
+        try:
+            print(f"Processing URL: {url}")
+            if "playlist" in url:
+                tracks = get_playlist_tracks(token_spotify, url)
+                # Add source information
+                for track in tracks:
+                    track['playlist_source'] = url
+                all_tracks.extend(tracks)
+            elif "track" in url:
+                track = get_track_info(token_spotify, url)
+                if track:
+                    track[0]['playlist_source'] = url
+                    all_tracks.extend(track)
+            elif "album" in url:
+                album_tracks = get_album_tracks(token_spotify, url)
+                all_tracks.extend(album_tracks)
+        except Exception as e:
+            print(f"Error processing URL {url}: {str(e)}")
+            continue
+    
+    if not all_tracks:
+        error_message = "Could not find any tracks in the provided URLs."
+        return gr.Dataframe(value=pd.DataFrame({"Error": [error_message]})), None
+    
+    # Extract track details including artist information
+    print("Extracting detailed track information including ISRCs...")
+    tracks_info = extract_track_details(all_tracks, token_spotify)
+    
+    # Remove duplicate tracks (based on ISRC or title+artist if ISRC not available)
+    print("Creating DataFrame and removing duplicates...")
+    df = pd.DataFrame(tracks_info)
+    
+    # Create a key for deduplication
+    df['dedup_key'] = df.apply(
+        lambda row: row['isrc'] if row['isrc'] != 'Not available' else f"{row['artist']}_{row['title']}", 
+        axis=1
+    )
+    
+    # Drop duplicates
+    df = df.drop_duplicates(subset='dedup_key')
+    df = df.drop(columns=['dedup_key'])
+    
+    print(f"Found {len(df)} unique tracks after deduplication")
+    
+    # Filter columns if not include_all_info
+    if not include_all_info:
+        columns_to_keep = ['artist', 'title', 'isrc', 'album', 'genres', 'release_date', 'track_popularity', 'explicit', 'spotify_url']
+        df = df[columns_to_keep]
+    
+    # Save DataFrame to an Excel file
+    tmpfile = NamedTemporaryFile(delete=False, suffix='.xlsx')
+    df.to_excel(tmpfile.name, index=False)
+    
+    # Rename the file with the project name
+    project_file_name = f"{project_name}.xlsx"
+    shutil.move(tmpfile.name, project_file_name)
+    
+    return df, project_file_name
+
+# Gradio Interface Configuration
+iface = gr.Interface(
+    fn=interface,
+    inputs=[
+        gr.Textbox(label="Project Name", placeholder="Enter a name for your export"),
+        gr.Textbox(
+            label="Spotify URLs (Tracks, Albums or Playlists)", 
+            placeholder="Enter one Spotify URL per line (tracks, albums or playlists)",
+            lines=5
+        ),
+        gr.Checkbox(label="Include All Track Information", value=True)
+    ],
+    outputs=[
+        gr.Dataframe(),
+        gr.File(label="Download Excel")
+    ],
+    title="Spotify Track Collector",
+    description="Extract tracks from multiple Spotify playlists, albums, and tracks into a single Excel file.",
+    examples=[
+        ["Pop Collection", "https://open.spotify.com/playlist/37i9dQZF1DXcBWIGoYBM5M\nhttps://open.spotify.com/track/4cOdK2wGLETKBW3PvgPWqT", True],
+        ["Rock Collection", "https://open.spotify.com/playlist/37i9dQZF1DWXRqgorJj26U", False],
+        ["Album Tracks", "https://open.spotify.com/album/1R5BORZZxNUg8QMgbqt0nd", True]
+    ],
+    allow_flagging="never"
+)
+
+if __name__ == "__main__":
+    iface.launch()