app.py

import gradio as gr
import requests
import re
import os
import zipfile
import tempfile
from urllib.parse import urljoin

def process_url(url):
    try:
        headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'}
        response = requests.get(url, headers=headers)
        response.raise_for_status()
    except Exception as e:
        return None, f"Erreur de connexion : {str(e)}"

    # Recherche approfondie dans les scripts
    mp3_links = []
    pattern = r'(?:contentUrl|url)"\s*:\s*"([^"]+?\.mp3)(?:[^"]*)"'  # Capture les URLs .mp3 dans les objets JS
    matches = re.findall(pattern, response.text)
    
    for match in matches:
        # Nettoyage de l'URL
        clean_url = match.split('";')[0] if '";' in match else match
        absolute_url = urljoin(response.url, clean_url)
        mp3_links.append(absolute_url)

    # Dédoublonnage tout en conservant l'ordre
    seen = set()
    mp3_links = [x for x in mp3_links if not (x in seen or seen.add(x))]

    if not mp3_links:
        return None, "Aucun lien MP3 détecté dans le code source"

    # Téléchargement des fichiers
    temp_dir = tempfile.mkdtemp()
    filenames = []
    
    for idx, mp3_url in enumerate(mp3_links, 1):
        try:
            filename = f"{idx:02d}_{os.path.basename(mp3_url).split('?')[0]}"
            filepath = os.path.join(temp_dir, filename)
            
            with requests.get(mp3_url, headers=headers, stream=True) as r:
                r.raise_for_status()
                with open(filepath, 'wb') as f:
                    for chunk in r.iter_content(chunk_size=8192):
                        if chunk:
                            f.write(chunk)
            filenames.append(filepath)
        except Exception as e:
            print(f"Échec du téléchargement {mp3_url} : {str(e)}")
            continue

    if not filenames:
        return None, "Échec de tous les téléchargements"

    # Création du ZIP
    zip_path = os.path.join(temp_dir, 'episodes.zip')
    with zipfile.ZipFile(zip_path, 'w') as zipf:
        for file in filenames:
            zipf.write(file, arcname=os.path.basename(file))

    return zip_path, None

def download_podcast(url):
    zip_path, error = process_url(url)
    if error:
        raise gr.Error(error)
    return zip_path

iface = gr.Interface(
    fn=download_podcast,
    inputs=gr.Textbox(label="URL Radio France", placeholder="Collez l'URL ici..."),
    outputs=gr.File(label="Épisodes téléchargés"),
    examples=[[
        "https://www.radiofrance.fr/franceculture/podcasts/serie-le-secret-de-la-licorne-les-aventures-de-tintin"
    ]],
    title="Extracteur MP3 Radio France",
    description="Téléchargez les épisodes MP3 des podcasts Radio France directement depuis l'URL de la série"
)

iface.launch()