Update app.py

app.py

@@ -1,202 +1,105 @@
 import gradio as gr
 import requests
 from bs4 import BeautifulSoup
-import re
 import os
+import re
 import tempfile
-from urllib.parse import urlparse
+import shutil
+
+def download_soundgasm_audio(url, output_dir='downloaded_audio'):
+    if not os.path.exists(output_dir):
+        os.makedirs(output_dir)
 
-def get_audio_url(url):
-    """Extract audio URL from soundgasm.net page"""
     try:
         response = requests.get(url)
-        response.raise_for_status()
+        response.raise_for_status()  # Raise an exception for HTTP errors
+    except requests.exceptions.RequestException as e:
+        return None, f'Error fetching URL: {e}'
+
+    # Try to find the audio source directly in the HTML using regex
+    match = re.search(r'(https?://media\.soundgasm\.net/sounds/[^\"]+\.m4a)', response.text)
+    audio_url = None
+    if match:
+        audio_url = match.group(1)
+
+    if not audio_url:
+        # Fallback to BeautifulSoup if regex fails
         soup = BeautifulSoup(response.text, 'html.parser')
-        
-        # Try to find the audio source from the <audio> tag directly
-        audio_tag = soup.find('audio', {'id': 'jp_audio_0'})
+        audio_tag = soup.find('audio')
         if audio_tag and 'src' in audio_tag.attrs:
-            return audio_tag['src']
+            audio_url = audio_tag['src']
+            if not audio_url.startswith('http'):
+                audio_url = f"https://soundgasm.net{audio_url}"
 
-        # If not found, try to extract from the JavaScript part
-        script_tags = soup.find_all('script')
-        for script in script_tags:
-            if script.string:
-                match = re.search(r'm4a: "(https://media.soundgasm.net/sounds/[a-f0-9]+\.m4a)"', script.string)
-                if match:
-                    return match.group(1)
-        return None
-    except Exception as e:
-        print(f"Error extracting audio URL: {e}")
-        return None
+    if audio_url:
+        try:
+            audio_response = requests.get(audio_url, stream=True)
+            audio_response.raise_for_status()
+        except requests.exceptions.RequestException as e:
+            return None, f'Error fetching audio file: {e}'
 
-def get_audio_title(url):
-    """Extract audio title from soundgasm.net page"""
-    try:
-        response = requests.get(url)
-        response.raise_for_status()
-        soup = BeautifulSoup(response.text, 'html.parser')
-        
-        title_element = soup.find('div', class_='jp-title')
-        if title_element:
-            return title_element.get_text(strip=True)
-        return "Unknown Title"
-    except Exception as e:
-        print(f"Error extracting title: {e}")
-        return "Unknown Title"
+        file_name = os.path.join(output_dir, os.path.basename(audio_url).split('?')[0])
+        with open(file_name, 'wb') as f:
+            for chunk in audio_response.iter_content(chunk_size=8192):
+                f.write(chunk)
+        return file_name, f'Audio downloaded successfully!'
+    else:
+        return None, 'No audio source found on the page.'
 
-def download_audio(url, progress=gr.Progress()):
-    """Download audio from soundgasm.net URL"""
+def process_soundgasm_url(url):
     if not url:
-        return None, "Please enter a valid soundgasm.net URL"
+        return None, "Please enter a soundgasm.net URL"
     
     if "soundgasm.net" not in url:
         return None, "Please enter a valid soundgasm.net URL"
     
-    progress(0.1, desc="Extracting audio URL...")
-    
-    # Get audio URL
-    audio_url = get_audio_url(url)
-    if not audio_url:
-        return None, "Could not find audio URL on the page. Please check if the URL is correct."
-    
-    progress(0.3, desc="Getting audio title...")
-    
-    # Get audio title for filename
-    title = get_audio_title(url)
-    safe_title = re.sub(r'[^\w\s-]', '', title).strip()
-    safe_title = re.sub(r'[-\s]+', '-', safe_title)
-    
-    progress(0.5, desc="Downloading audio...")
-    
-    try:
-        # Download the audio file
-        response = requests.get(audio_url, stream=True)
-        response.raise_for_status()
-        
-        # Create temporary file
-        temp_dir = tempfile.gettempdir()
-        filename = f"{safe_title}.m4a"
-        filepath = os.path.join(temp_dir, filename)
-        
-        total_size = int(response.headers.get('content-length', 0))
-        downloaded = 0
-        
-        with open(filepath, 'wb') as f:
-            for chunk in response.iter_content(chunk_size=8192):
-                if chunk:
-                    f.write(chunk)
-                    downloaded += len(chunk)
-                    if total_size > 0:
-                        progress_val = 0.5 + (downloaded / total_size) * 0.4
-                        progress(progress_val, desc=f"Downloading... {downloaded}/{total_size} bytes")
-        
-        progress(1.0, desc="Download complete!")
-        
-        return filepath, f"Successfully downloaded: {title}"
-        
-    except Exception as e:
-        return None, f"Error downloading audio: {str(e)}"
-
-def validate_url(url):
-    """Validate if the URL is a valid soundgasm.net URL"""
-    if not url:
-        return "Please enter a URL"
-    
-    if "soundgasm.net" not in url:
-        return "Please enter a valid soundgasm.net URL"
-    
-    try:
-        parsed = urlparse(url)
-        if not parsed.scheme or not parsed.netloc:
-            return "Please enter a valid URL with http:// or https://"
-    except:
-        return "Invalid URL format"
+    audio_file, message = download_soundgasm_audio(url)
     
-    return ""
+    if audio_file:
+        return audio_file, message
+    else:
+        return None, message
 
-# Create Gradio interface
+# Create Gradio interface using Blocks
 with gr.Blocks(title="Soundgasm Audio Downloader", theme=gr.themes.Soft()) as demo:
-    gr.Markdown(
-        """
-        # 🎵 Soundgasm Audio Downloader
-        
-        Download audio files from soundgasm.net links using only requests and BeautifulSoup4.
-        
-        **Instructions:**
-        1. Paste a soundgasm.net audio URL in the input field
-        2. Click "Download Audio" to start the download
-        3. The audio file will be available for download once processing is complete
-        
-        **Supported URLs:** `https://soundgasm.net/u/username/audio-title`
-        """
-    )
+    gr.Markdown("# Soundgasm Audio Downloader")
+    gr.Markdown("Enter a soundgasm.net link to download and play the audio file.")
     
     with gr.Row():
-        with gr.Column(scale=3):
+        with gr.Column():
             url_input = gr.Textbox(
                 label="Soundgasm URL",
                 placeholder="https://soundgasm.net/u/username/audio-title",
                 lines=1
             )
+            download_btn = gr.Button("Download Audio", variant="primary")
             
-            url_validation = gr.Textbox(
-                label="URL Validation",
+        with gr.Column():
+            status_output = gr.Textbox(
+                label="Status",
                 interactive=False,
-                visible=False
+                lines=2
             )
-            
-        with gr.Column(scale=1):
-            download_btn = gr.Button("Download Audio", variant="primary", size="lg")
-    
-    with gr.Row():
-        status_output = gr.Textbox(
-            label="Status",
-            interactive=False,
-            lines=2
-        )
     
     with gr.Row():
-        file_output = gr.File(
-            label="Downloaded Audio File",
-            file_count="single",
-            file_types=[".m4a", ".mp3", ".wav"]
+        audio_output = gr.Audio(
+            label="Downloaded Audio",
+            type="filepath",
+            interactive=False
         )
     
     # Event handlers
-    url_input.change(
-        fn=validate_url,
-        inputs=[url_input],
-        outputs=[url_validation]
-    )
-    
     download_btn.click(
-        fn=download_audio,
+        fn=process_soundgasm_url,
         inputs=[url_input],
-        outputs=[file_output, status_output],
-        show_progress=True
+        outputs=[audio_output, status_output]
     )
     
-    # Example URLs
-    gr.Markdown(
-        """
-        ### Example URLs:
-        - `https://soundgasm.net/u/aasimaraudio/Let-Me-Help-You-Relieve-Your-Work-Related-Stress-Will-Ya`
-        - `https://soundgasm.net/u/username/audio-title`
-        
-        ### Features:
-        - ✅ Extract audio URLs using requests and BeautifulSoup4
-        - ✅ Download audio files in original quality
-        - ✅ Automatic filename generation from audio title
-        - ✅ Progress tracking during download
-        - ✅ Error handling and validation
-        
-        ### Technical Details:
-        - Uses only `requests` and `bs4` libraries as requested
-        - Extracts audio URLs from HTML and JavaScript content
-        - Supports m4a audio format (soundgasm's default format)
-        - No external dependencies beyond the specified libraries
-        """
+    # Also allow Enter key to trigger download
+    url_input.submit(
+        fn=process_soundgasm_url,
+        inputs=[url_input],
+        outputs=[audio_output, status_output]
     )
 
 if __name__ == "__main__":