Podcast RSS Downloader

README.md

Bulk Podcast Downloader

An interactive python script that downloads all the podcasts for a given RSS feed. It also allows you to preview all the files that will be downloaded.

Requirements

This requires requests.

pip install requests

download-podcast.py

import requests
import xml.etree.ElementTree as ET
import urllib.request
import os

def download_podcast_episodes_interactive():
    # Namespace definition for parsing iTunes-specific tags
    ns = {'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd'}

    # Prompt the user for the RSS feed URL
    rss_url = input("Enter the RSS feed URL of the podcast: ")

    # Fetch the RSS feed content
    response = requests.get(rss_url)
    if response.status_code == 200:
        rss_content = response.content

        # Parse the XML content of the RSS feed
        root = ET.fromstring(rss_content)

        # Attempt to fetch podcast title
        channel = root.find('.//channel')
        podcast_title = channel.find('title').text if channel is not None else "Unknown Podcast"
        episodes = root.findall('.//item')
        total_episodes = len(episodes)

        print(f"Podcast Name: {podcast_title}")
        print(f"Total Episodes: {total_episodes}")

        # Ask the user what they wish to do next
        action = input("Enter 'yes' to download all episodes, 'preview' to see filenames, or 'no' to cancel: ").lower()

        podcast_dir = podcast_title.replace(" ", "_").replace("/", "_")  # Simplify the title for the folder name
        if not os.path.exists(podcast_dir):
            os.makedirs(podcast_dir)

        # Preview or download each episode
        for item in episodes:
            title = item.find('title').text
            episode_number = item.find('itunes:episode', ns)
            if episode_number is not None:
                episode_number = episode_number.text
            else:
                episode_number = "Unknown"
            audio_url = item.find('.//enclosure').attrib['url']

            # Format filename to include episode number and title
            filename = f"{episode_number} - {title}".replace("/", "-")  # Replace disallowed characters
            filename = "".join([c for c in filename if c.isalpha() or c.isdigit() or c==' ' or c=='-' or c=='.']).rstrip()
            filepath = os.path.join(podcast_dir, filename + '.mp3')

            if action == "preview":
                print(f"Will download: {filename}")
            elif action == "yes":
                # Download the audio file if it doesn't already exist
                if not os.path.exists(filepath):
                    print(f"Downloading: {filename}")
                    urllib.request.urlretrieve(audio_url, filepath)
                    print(f"Downloaded: {filepath}")
                else:
                    print(f"Already exists: {filepath}")

        if action == "no":
            print("Download canceled.")
    else:
        print("Failed to fetch RSS feed.")

# Start the interactive downloading process
download_podcast_episodes_interactive()