Update app.py

app.py

@@ -7,10 +7,34 @@ import gradio as gr
 SIMBALS_GLOBAL_DB = 1
 SIMBALS_MAIN_DATABASE = 2
 
+from pytube import YouTube
+
+embed_html = '<iframe width="560" height="315" src="https://www.youtube.com/embed/EngW7tLk6R8" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>'
+
+embed_html1 = '<iframe width="560" height="315" src="https://www.youtube.com/embed/'
+embed_html2 = '" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>'
+
+
+def download_audio(id_video):
+    video = YouTube(id_video)
+    id = id_video.split("?v=")[-1][:11]
+    audio_streams = video.streams.filter(only_audio=True)
+    audio_stream = audio_streams[0]
+    audio_file = audio_stream.download()
+    audio_parts = audio_file.split('/')[-1]
+    audio_title = '.'.join(audio_parts.split('.')[:-1])
+    embed_html_all = embed_html1 + id +embed_html2
+    return audio_file, audio_file, embed_html_all
+
 def process(input_path):
     # setup the client
+    audio_file, audio_file, embed_html_all = download_audio(input_path)
     client = SimbalsAPIClient(os.environ['TOKEN'], debug=True)
-    parameters = client.prepare_request("31415", audio_file=input_path)
+    parameters = client.prepare_request("31415", audio_file=audio_file)
+    
+    
+    #client = SimbalsAPIClient(os.environ['TOKEN'], debug=True)
+    #parameters = client.prepare_request("31415", audio_file=input_path)
     
     # add audio features service with an available database
     #parameters = client.add_audio_features(parameters, SIMBALS_MAIN_DATABASE)
@@ -61,7 +85,7 @@ def process(input_path):
     audioquality = {}
     audioquality[res['audio_quality'][0]['name']]= res['audio_quality'][0]['probability']
     
-    return dict_moods, genres, instruments, vocalgender, timbres, themes, audioquality,str(dict_desc['Electric/Acoustic']),str(dict_desc['Danceability']),str(dict_desc['Arousal']),str(dict_desc['Vocal/Instrumental']),str(dict_desc['Studio/Live']),str(dict_desc['Music/Speech']),str(dict_desc['Valence']),str(dict_desc['Melodic']),str(dict_desc['Articulation']),str(dict_desc['RhythmicStability']),str(dict_desc['Dissonance']),str(dict_desc['BPM']),str(dict_desc['Binary']),str(dict_desc['Key']),str(dict_desc['Mode']),str(dict_desc['TexturalStability'])
+    return embed_html_all, dict_moods, genres, instruments, vocalgender, timbres, themes, audioquality,str(dict_desc['Electric/Acoustic']),str(dict_desc['Danceability']),str(dict_desc['Arousal']),str(dict_desc['Vocal/Instrumental']),str(dict_desc['Studio/Live']),str(dict_desc['Music/Speech']),str(dict_desc['Valence']),str(dict_desc['Melodic']),str(dict_desc['Articulation']),str(dict_desc['RhythmicStability']),str(dict_desc['Dissonance']),str(dict_desc['BPM']),str(dict_desc['Binary']),str(dict_desc['Key']),str(dict_desc['Mode']),str(dict_desc['TexturalStability'])
             
 
  
@@ -72,7 +96,14 @@ with gr.Blocks() as demo:
         with gr.Column():
 
             with gr.Row():
-                audio_input = gr.Audio(type="filepath", label='Audio Input')
+                #gr.HTML(embed_html)
+                html = gr.HTML()
+            
+            with gr.Row():
+                audio_input = gr.Textbox(placeholder='YouTube video URL', label='YouTube video URL')
+
+            #with gr.Row():
+            #    audio_input = gr.Audio(type="filepath", label='Audio Input')
                 
             with gr.Row():
                 analyze_btn = gr.Button('Analyze File')
@@ -136,7 +167,8 @@ with gr.Blocks() as demo:
             ''' 
     
     analyze_btn.click(process, inputs=[audio_input], 
-                      outputs=[dict_moods, 
+                      outputs=[html,
+                               dict_moods, 
                                genres, 
                                instruments,
                                vocalgender,