File size: 4,194 Bytes
11fd592 1f317db 11fd592 1f317db 11fd592 1f317db 11fd592 1f317db 11fd592 1f317db 11fd592 1f317db 11fd592 1f317db 11fd592 1f317db 11fd592 1f317db 11fd592 1f317db 11fd592 1f317db 11fd592 1f317db 11fd592 1f317db |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 |
import os
import re
import sys
import subprocess
import importlib.util
import shutil
import tempfile
# === INSTALLATION AUTOMATIQUE DES DÉPENDANCES ===
def install_if_missing(package_name, import_name=None):
import_name = import_name or package_name
if importlib.util.find_spec(import_name) is None:
print(f"Installation de {package_name}...")
subprocess.check_call([sys.executable, "-m", "pip", "install", package_name])
for package in [
("requests",),
("bs4", "bs4"),
("gradio",),
]:
install_if_missing(*package)
# === IMPORTS ===
import requests
import gradio as gr
from bs4 import BeautifulSoup
# === UTILITAIRES ===
def slugify(text, max_length=50):
text = text.lower()
text = re.sub(r'[^\w\s-]', '', text)
text = re.sub(r'[-\s]+', '_', text)
return text[:max_length].strip('_')
def get_episode_links(main_url):
"""Récupère toutes les URL des pages d’épisodes depuis la page principale."""
response = requests.get(main_url)
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
links = []
for a in soup.find_all('a', href=True):
href = a['href']
if "/podcasts/" in href and href != main_url:
full_url = href if href.startswith("http") else f"https://www.radiofrance.fr{href}"
if full_url not in links:
links.append(full_url)
return list(dict.fromkeys(links)) # dédoublonner
def extract_mp3_from_episode(url):
"""Extrait le lien MP3 d’un épisode."""
try:
response = requests.get(url)
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
audio_tag = soup.find("audio")
if audio_tag and audio_tag.get("src", "").endswith(".mp3"):
return audio_tag["src"]
except Exception:
pass
return None
def get_podcast_title(url):
"""Extrait le titre général du podcast."""
try:
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
title_tag = soup.find('h1') or soup.find('title')
return slugify(title_tag.get_text()) if title_tag else "podcast"
except Exception:
return "podcast"
def download_and_zip_podcast_series(main_url):
try:
title = get_podcast_title(main_url)
episode_pages = get_episode_links(main_url)
if not episode_pages:
return "Aucune page d’épisode trouvée.", None
mp3_links = []
for ep_url in episode_pages:
mp3 = extract_mp3_from_episode(ep_url)
if mp3:
mp3_links.append(mp3)
if not mp3_links:
return "Aucun fichier MP3 trouvé dans les épisodes.", None
temp_dir = tempfile.mkdtemp()
for i, mp3_url in enumerate(mp3_links, start=1):
filename = f"{title}_{i:02}.mp3"
filepath = os.path.join(temp_dir, filename)
with requests.get(mp3_url, 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)
zip_path = os.path.join(temp_dir, f"{title}.zip")
shutil.make_archive(zip_path.replace('.zip', ''), 'zip', temp_dir)
return f"{len(mp3_links)} épisode(s) téléchargé(s).", zip_path
except Exception as e:
return f"Erreur : {str(e)}", None
# === INTERFACE GRADIO ===
with gr.Blocks() as app:
gr.Markdown("# Téléchargeur de Podcasts MP3 - France Culture")
with gr.Row():
url_input = gr.Textbox(label="URL de la série", placeholder="https://www.radiofrance.fr/...")
download_button = gr.Button("Télécharger et compresser")
output_text = gr.Textbox(label="Message")
file_output = gr.File(label="Fichier ZIP", file_types=[".zip"])
def process(url):
message, zip_file = download_and_zip_podcast_series(url)
return message, zip_file
download_button.click(fn=process, inputs=[url_input], outputs=[output_text, file_output])
# === LANCEMENT ===
if __name__ == "__main__":
app.launch(share=True) |