Update app.py

app.py

@@ -1,81 +1,204 @@
 import gradio as gr
 import requests
+from bs4 import BeautifulSoup
 import re
-from urllib.parse import urlparse
 import os
+import tempfile
+from urllib.parse import urlparse
 
-def validate_url(url):
-    """Validate if the URL is a valid soundgasm.net link."""
-    pattern = r'^https?://soundgasm\.net/u/[\w-]+/[\w-]+'
-    return bool(re.match(pattern, url.strip()))
-
-def extract_audio_url(page_content):
-    """Extract the direct audio URL from the Soundgasm page content."""
-    audio_pattern = r'(https?://media\.soundgasm\.net/sounds/[\w-]+\.(?:mp3|m4a))'
-    match = re.search(audio_pattern, page_content)
-    return match.group(1) if match else None
-
-def download_audio(url):
-    """Download audio from a soundgasm.net link."""
+def get_audio_url(url):
+    """Extract audio URL from soundgasm.net page"""
     try:
-        # Validate URL
-        if not validate_url(url):
-            return "Invalid Soundgasm.net URL. Please provide a valid link."
-
-        # Get the page content
-        headers = {
-            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
-        }
-        response = requests.get(url.strip(), headers=headers, timeout=10)
+        response = requests.get(url)
         response.raise_for_status()
+        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'})
+        if audio_tag and 'src' in audio_tag.attrs:
+            return audio_tag['src']
+
+        # 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
 
-        # Extract audio URL
-        audio_url = extract_audio_url(response.text)
-        if not audio_url:
-            return "Could not find audio file in the provided link."
-
-        # Download the audio
-        audio_response = requests.get(audio_url, headers=headers, stream=True, timeout=10)
-        audio_response.raise_for_status()
-
-        # Extract filename from URL
-        parsed_url = urlparse(audio_url)
-        filename = os.path.basename(parsed_url.path)
-
-        # Save the audio file temporarily
-        temp_dir = "downloads"
-        os.makedirs(temp_dir, exist_ok=True)
-        file_path = os.path.join(temp_dir, filename)
-
-        with open(file_path, 'wb') as f:
-            for chunk in audio_response.iter_content(chunk_size=8192):
+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"
+
+def download_audio(url, progress=gr.Progress()):
+    """Download audio from soundgasm.net URL"""
+    if not url:
+        return None, "Please enter a valid 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)
-
-        return file_path
-
-    except requests.exceptions.RequestException as e:
-        return f"Error downloading audio: {str(e)}"
+                    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 f"An unexpected error occurred: {str(e)}"
-
-# Gradio Blocks UI
-with gr.Blocks(title="Soundgasm Audio Downloader") as demo:
-    gr.Markdown("# Soundgasm Audio Downloader")
-    gr.Markdown("Enter a Soundgasm.net link to download the audio file.")
+        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"
+    
+    return ""
+
+# Create Gradio interface
+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`
+        """
+    )
+    
     with gr.Row():
-        url_input = gr.Textbox(label="Soundgasm URL", placeholder="https://soundgasm.net/u/username/audio-title")
-        download_button = gr.Button("Download Audio")
-
-    output = gr.File(label="Downloaded Audio")
-    error_message = gr.Textbox(label="Status", interactive=False)
-
-    download_button.click(
+        with gr.Column(scale=3):
+            url_input = gr.Textbox(
+                label="Soundgasm URL",
+                placeholder="https://soundgasm.net/u/username/audio-title",
+                lines=1
+            )
+            
+            url_validation = gr.Textbox(
+                label="URL Validation",
+                interactive=False,
+                visible=False
+            )
+            
+        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"]
+        )
+    
+    # Event handlers
+    url_input.change(
+        fn=validate_url,
+        inputs=[url_input],
+        outputs=[url_validation]
+    )
+    
+    download_btn.click(
         fn=download_audio,
-        inputs=url_input,
-        outputs=[output, error_message]
+        inputs=[url_input],
+        outputs=[file_output, status_output],
+        show_progress=True
+    )
+    
+    # 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
+        """
     )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(server_name="0.0.0.0", server_port=7860, share=False)
+