| #!/usr/bin/env python3 | |
| import getpodcast | |
| import re | |
| import requests | |
| def get_podcast_url_apple(podcast_url): | |
| re_pattern = re.compile(r'[^w]+/id(\d+)') | |
| matches = re_pattern.search(podcast_url) | |
| if not matches: | |
| return None | |
| id = matches.group(1) | |
| url = f"https://itunes.apple.com/lookup?id={id}&entity=podcast" | |
| response = requests.get(url) | |
| response.raise_for_status() | |
| data = response.json() | |
| results = data.get('results', []) | |
| if results: | |
| return results[0].get('feedUrl') | |
| else: | |
| return None | |
| opt = getpodcast.options( | |
| date_from='2024-01-05', | |
| root_dir='./podcast') | |
| podcasts = { | |
| # "Big Technology Podcast": "https://podcasts.apple.com/us/podcast/big-technology-podcast/id1522960417", | |
| # "Modern Wisdom": "https://feeds.megaphone.fm/SIXMSB5088139739", | |
| # "Hard Fork": "https://feeds.simplecast.com/l2i9YnTd", | |
| # "The AI Breakdown": "https://podcasts.apple.com/us/podcast/the-ai-breakdown-daily-artificial-intelligence-news/id1680633614", | |
| # "The Cognitive Revolution": "https://podcasts.apple.com/us/podcast/the-cognitive-revolution-ai-builders-researchers-and/id1669813431", | |
| "MLOps.community": "https://podcasts.apple.com/us/podcast/mlops-community/id1505372978" | |
| } | |
| for name, url in podcasts.items(): | |
| if url.startswith('https://podcasts.apple.com'): | |
| new_url = get_podcast_url_apple(url) | |
| if new_url: | |
| print(f'INFO: Found XML URL for apple podcast: {name}: {new_url}') | |
| podcasts[name] = new_url | |
| else: | |
| print(f'WARNING: could not determine URL for apple podcast: {name}, {url}') | |
| getpodcast.getpodcast(podcasts, opt) |
| from youtube_transcript_api import YouTubeTranscriptApi | |
| import sys | |
| import json | |
| if len(sys.argv) == 2: | |
| print(json.dumps(YouTubeTranscriptApi.get_transcript(sys.argv[1]))) | |
| elif len(sys.argv) == 3 and '-t' in sys.argv: | |
| sys.argv.remove('-t') | |
| transcript = YouTubeTranscriptApi.get_transcript(sys.argv[1]) | |
| for rec in transcript: | |
| print(rec['text']) |
pip install -r requirements.txt
Add your podcast URLs to download_podcasts.py
podcasts = {
"MLOps.community": "https://podcasts.apple.com/us/podcast/mlops-community/id1505372978"
}
python download_podcast.py --run
this will output a file named file.json
time whisper file.mp3 --model base --language en --output_format json
Input is a Youtube ID number.
python download_youtube_transcript.py slIVToAG98M -t > transcript.txt
| youtube-transcript-api | |
| openai-whisper | |
| getpodcast | |
| requests |
May I know is it possible to support downloading specific episode of Podcast? Thanks.