# Project - Extract podcast audio file from Xiaoyuzhou web
## Automate the web scrap process
- Cmd input: xiaoyuzhou podcast episode link + lang:

- Extract the audio file (support .mp3, .mp4a, .m4a, .wav, .aac, .ogg)
- Download and save to the ./Download folder

import requests
from bs4 import BeautifulSoup
import re
import os
import sys

def fetch_audio_url(podcast_url):
    headers = {
        'User-Agent': 'Mozilla/5.0'
    }
    response = requests.get(podcast_url, headers=headers)
    if response.status_code != 200:
        raise Exception("Failed to fetch podcast page.")

    soup = BeautifulSoup(response.text, 'html.parser')

    # Search for audio URLs with different formats using regex
    # Look for common audio formats: mp3, mp4a, m4a, wav, aac, ogg
    audio_patterns = [
        r'https://media\.xyzcdn\.net/[^"]+\.mp4a',  # Original mp4a format
        r'https://media\.xyzcdn\.net/[^"]+\.mp3',   # MP3 format
        r'https://media\.xyzcdn\.net/[^"]+\.m4a',   # M4A format
        r'https://media\.xyzcdn\.net/[^"]+\.wav',   # WAV format
        r'https://media\.xyzcdn\.net/[^"]+\.aac',   # AAC format
        r'https://media\.xyzcdn\.net/[^"]+\.ogg',   # OGG format
    ]
    
    # Try each pattern until we find a match
    for pattern in audio_patterns:
        match = re.search(pattern, response.text)
        if match:
            return match.group(0)
    
    # If no specific format found, try a more general pattern
    general_match = re.search(r'https://media\.xyzcdn\.net/[^"]+\.(mp3|mp4a|m4a|wav|aac|ogg)', response.text)
    if general_match:
        return general_match.group(0)
    
    raise Exception("Audio URL not found. No supported audio format detected.")

def download_audio(audio_url, filename=None):
    if not filename:
        filename = audio_url.split('/')[-1]
    
    # Set download directory to ~/Downloads
    download_dir = os.path.expanduser("~/Downloads")
    filepath = os.path.join(download_dir, filename)
    
    # Create Downloads directory if it doesn't exist
    os.makedirs(download_dir, exist_ok=True)

    response = requests.get(audio_url, stream=True)
    if response.status_code == 200:
        with open(filepath, 'wb') as f:
            for chunk in response.iter_content(1024):
                f.write(chunk)
        print(f"Downloaded: {filepath}")
        return filepath
    else:
        raise Exception("Failed to download audio.")

if __name__ == "__main__":
    # Check if URL argument is provided
    if len(sys.argv) != 2:
        print("Usage: python3 download_podcast.py <podcast_web_url>")
        print("Example: python3 download_podcast.py https://www.xiaoyuzhoufm.com/episode/xxxxxx")
        sys.exit(1)
    
    podcast_web_url = sys.argv[1]
    
    try:
        audio_url = fetch_audio_url(podcast_web_url)
        print("Audio URL found:", audio_url)
        filepath = download_audio(audio_url)
        print(f"File saved to: {filepath}")
    except Exception as e:
        print("Error:", e)
        sys.exit(1)