|
|
import gradio as gr |
|
|
import requests |
|
|
import re |
|
|
import os |
|
|
import zipfile |
|
|
import tempfile |
|
|
from urllib.parse import urljoin |
|
|
from bs4 import BeautifulSoup |
|
|
|
|
|
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/' |
|
|
} |
|
|
response = requests.get(url, headers=headers) |
|
|
response.raise_for_status() |
|
|
except Exception as e: |
|
|
return None, f"Erreur de connexion : {str(e)}" |
|
|
|
|
|
soup = BeautifulSoup(response.text, 'html.parser') |
|
|
mp3_links = [] |
|
|
|
|
|
|
|
|
scripts = soup.find_all('script', type='application/ld+json') |
|
|
for script in scripts: |
|
|
if script.string: |
|
|
matches = re.findall(r'"contentUrl"\s*:\s*"([^"]+?\.mp3)', script.string) |
|
|
for match in matches: |
|
|
full_url = urljoin(url, match.split('?')[0]) |
|
|
if full_url not in mp3_links: |
|
|
mp3_links.append(full_url) |
|
|
|
|
|
|
|
|
if not mp3_links: |
|
|
for tag in soup.find_all(attrs={"data-url": re.compile(r"\.mp3")}): |
|
|
mp3_url = urljoin(url, tag['data-url'].split('?')[0]) |
|
|
mp3_links.append(mp3_url) |
|
|
|
|
|
|
|
|
if not mp3_links: |
|
|
matches = re.findall(r'(https?://[^\s"\']+?\.mp3)', response.text) |
|
|
for match in matches: |
|
|
clean_url = urljoin(url, match.split('?')[0]) |
|
|
if clean_url not in mp3_links and 'podcast' in clean_url: |
|
|
mp3_links.append(clean_url) |
|
|
|
|
|
|
|
|
mp3_links = list(dict.fromkeys(mp3_links)) |
|
|
|
|
|
if not mp3_links: |
|
|
return None, "Aucun épisode trouvé - Structure de page inconnue" |
|
|
|
|
|
|
|
|
temp_dir = tempfile.mkdtemp() |
|
|
filenames = [] |
|
|
|
|
|
for idx, mp3_url in enumerate(mp3_links, 1): |
|
|
try: |
|
|
filename = f"{idx:02d}_{os.path.basename(mp3_url)}" |
|
|
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): |
|
|
f.write(chunk) |
|
|
filenames.append(filepath) |
|
|
except Exception: |
|
|
continue |
|
|
|
|
|
if not filenames: |
|
|
return None, "Échec du téléchargement" |
|
|
|
|
|
zip_path = os.path.join(temp_dir, 'podcast.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 |
|
|
|
|
|
with gr.Blocks() as app: |
|
|
gr.Markdown("## 🎧 Téléchargeur Radio France") |
|
|
with gr.Row(): |
|
|
url_input = gr.Textbox( |
|
|
label="URL du podcast", |
|
|
placeholder="Ex: https://www.radiofrance.fr/...", |
|
|
max_lines=1 |
|
|
) |
|
|
btn = gr.Button("Télécharger les épisodes", variant="primary") |
|
|
output = gr.File(label="Fichier ZIP") |
|
|
|
|
|
examples = gr.Examples( |
|
|
examples=[[ |
|
|
"https://www.radiofrance.fr/franceculture/podcasts/serie-le-secret-de-la-licorne-les-aventures-de-tintin" |
|
|
]], |
|
|
inputs=[url_input] |
|
|
) |
|
|
|
|
|
btn.click( |
|
|
fn=download_podcast, |
|
|
inputs=url_input, |
|
|
outputs=output, |
|
|
api_name="download" |
|
|
) |
|
|
|
|
|
app.launch() |
