Update app.py

app.py

@@ -7,90 +7,76 @@ import tempfile
 from urllib.parse import urljoin
 from bs4 import BeautifulSoup
 from mutagen.mp3 import MP3
-from mutagen.id3 import ID3, TIT3
+from mutagen.id3 import ID3
 
 def get_clean_title(filepath):
     try:
         audio = MP3(filepath, ID3=ID3)
-        # Utilisation de TIT3 (Subtitle) qui contient souvent le numéro d'épisode
-        if 'TIT3' in audio:
-            title = audio['TIT3'].text[0]
-        elif 'TIT2' in audio:
-            title = audio['TIT2'].text[0]
-        else:
-            return os.path.basename(filepath)
-        
-        # Nettoyage avancé du titre
-        title = re.sub(r'\s*-\s*Radio France$', '', title, flags=re.IGNORECASE)
-        title = re.sub(r'[\\/*?:"<>|]', '', title).strip()
-        return title[:100]  # Limite la longueur du nom de fichier
-        
+        for tag in ['TIT2', 'TIT3', 'TALB']:
+            if tag in audio:
+                title = audio[tag].text[0]
+                title = re.sub(r'[\\/*?:"<>|]', '', title).strip()
+                return title[:100]
+        return os.path.basename(filepath).split('.')[0]
     except Exception:
         return os.path.basename(filepath).split('.')[0]
 
 def process_url(url):
     try:
-        headers = {
-            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
-            'Referer': 'https://www.radiofrance.fr/'
-        }
+        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'}
         response = requests.get(url, headers=headers, timeout=15)
         response.raise_for_status()
     except Exception as e:
-        return None, f"Erreur de connexion : {str(e)}"
+        return None, f"Erreur : {str(e)}"
 
-    # Détection des épisodes avec BeautifulSoup
     soup = BeautifulSoup(response.text, 'html.parser')
-    main_content = soup.find('main') or soup
-    episodes = main_content.find_all(['article', 'div'], class_=re.compile(r'episode|podcast|card', re.IGNORECASE))
-    
     mp3_links = []
-    for episode in episodes:
-        script_tag = episode.find('script', type='application/ld+json')
-        if script_tag:
-            match = re.search(r'"contentUrl"\s*:\s*"([^"]+?\.mp3)', script_tag.string)
-            if match:
-                mp3_url = urljoin(url, match.group(1).split('?')[0]
-                if mp3_url not in mp3_links:
-                    mp3_links.append(mp3_url)
+    
+    # Méthode 1 : Balises JSON-LD
+    for script in soup.find_all('script', type='application/ld+json'):
+        if script.string:
+            matches = re.findall(r'"contentUrl"\s*:\s*"([^"]+?\.mp3)', script.string)
+            for match in matches:
+                clean_url = urljoin(url, match.split('?')[0])
+                if clean_url not in mp3_links:
+                    mp3_links.append(clean_url)
 
-    # Alternative si détection échoue
+    # Méthode 2 : Fallback HTML
     if not mp3_links:
-        matches = re.findall(r'(https://media\.radiofrance-podcast\.net[^"\']+?\.mp3)', response.text)
-        mp3_links = list(dict.fromkeys(matches))
+        for a in soup.find_all('a', href=re.compile(r'\.mp3')):
+            mp3_url = urljoin(url, a['href'].split('?')[0])
+            if mp3_url not in mp3_links:
+                mp3_links.append(mp3_url)
 
     if not mp3_links:
-        return None, "Aucun épisode trouvé - Vérifiez l'URL"
+        return None, "Aucun épisode trouvé"
 
     temp_dir = tempfile.mkdtemp()
     filenames = []
     
     for idx, mp3_url in enumerate(mp3_links, 1):
         try:
-            # Téléchargement temporaire
-            temp_name = f"temp_{idx}.mp3"
-            temp_path = os.path.join(temp_dir, temp_name)
+            temp_path = os.path.join(temp_dir, f"temp_{idx}.mp3")
             
+            # Téléchargement
             with requests.get(mp3_url, headers=headers, stream=True, timeout=20) as r:
                 r.raise_for_status()
                 with open(temp_path, 'wb') as f:
                     for chunk in r.iter_content(chunk_size=8192):
                         f.write(chunk)
-
-            # Renommage final
-            clean_title = get_clean_title(temp_path)
-            final_name = f"{idx:02d} - {clean_title}.mp3"
+            
+            # Renommage
+            title = get_clean_title(temp_path)
+            final_name = f"{idx:02d} - {title}.mp3"
             final_path = os.path.join(temp_dir, final_name)
             os.rename(temp_path, final_path)
-            
             filenames.append(final_path)
-        except Exception as e:
+        except Exception:
             continue
 
     if not filenames:
-        return None, "Échec du téléchargement"
+        return None, "Échec des téléchargements"
 
-    # Création ZIP
     zip_path = os.path.join(temp_dir, 'podcast.zip')
     with zipfile.ZipFile(zip_path, 'w') as zipf:
         for file in filenames:
@@ -104,29 +90,20 @@ def download_podcast(url):
         raise gr.Error(error)
     return zip_path
 
-with gr.Blocks(title="RadioFrance Podcaster Pro") as app:
-    gr.Markdown("## 🎧 Téléchargeur Intelligent Radio France")
+with gr.Blocks() as app:
+    gr.Markdown("## 🎙️ Téléchargeur Radio France")
     with gr.Row():
-        url_input = gr.Textbox(
-            label="URL de la série podcast",
-            placeholder="Ex: https://www.radiofrance.fr/...",
-            max_lines=1
-        )
-    btn = gr.Button("Générer le ZIP", variant="primary")
-    output = gr.File(label="Épisodes téléchargés")
+        url = gr.Textbox(label="URL de la série", placeholder="Collez l'URL ici...")
+        btn = gr.Button("Télécharger", variant="primary")
+    output = gr.File(label="Épisodes")
     
     examples = gr.Examples(
         examples=[[
             "https://www.radiofrance.fr/franceculture/podcasts/serie-le-secret-de-la-licorne-les-aventures-de-tintin"
         ]],
-        inputs=[url_input]
+        inputs=[url]
     )
 
-    btn.click(
-        fn=download_podcast,
-        inputs=url_input,
-        outputs=output,
-        api_name="download"
-    )
+    btn.click(download_podcast, inputs=url, outputs=output)
 
-app.launch(show_error=True)
+app.launch()