Full Python Portfolio Project! Create a smart program to download & transcribe top podcasts.

Check out https://www.assemblyai.com/?utm_source=youtube&utm_medium=social&utm_campaign=keithgalli to start transcribing as many podcasts as your heart desires!

In this video we create a Python program that can automatically scrape the RSS feeds of your favorite podcasters, pulling out the episodes you’ll find most interesting, and downloading + transcribing them.

This project leverages a wide range of Python skills making it a good portfolio project. In it you’ll use the BeautifulSoup + requests libraries to first web scrape & download MP3 podcast files. You can use the regex library (re) and other NLP libraries to smart search for specific episodes that you'll enjoy. Next you'll see how you can use AssemblyAI's speech to text API to transcribe all of the episodes that you download. This code will be leveraged to create a text corpora that is going to be used in language analysis in upcoming tutorials.

To view/download source code for project: https://github.com/keithgalli/podcast-downloader

If you have any questions, let me know in the comments!

Make sure to smash like + subscribe if you enjoyed this video :)

-------------------------
Follow me on social media!
Instagram | https://www.instagram.com/keithgalli/
Twitter | https://twitter.com/keithgalli
TikTok | https://tiktok.com/@keithgalli

-------------------------
If you are curious to learn how I make my tutorials, check out this video: https://youtu.be/LEO4igyXbLs

Practice your Python Pandas data science skills with problems on StrataScratch!
https://stratascratch.com/?via=keith

Join the Python Army to get access to perks!
YouTube - https://www.youtube.com/channel/UCq6XkhO5SZ66N04IcPbqNcw/join
Patreon - https://www.patreon.com/keithgalli

*I use affiliate links on the products that I recommend. I may earn a purchase commission or a referral bonus from the usage of these links.

-------------------------
Video timeline!
0:00 - Video Introduction
1:19 - How podcasts work (RSS feeds overview)
5:11 - How can we utilize the XML webpages? (breakdown of RSS feed information & how we’ll use it to create a smart program)
7:47 - Accessing this project on GitHub
9:22 -Writing Python code to download podcasts locally (requests & beautifulsoup libraries)
18:10 - Modify our script to be able to download many podcasts
22:51 - Building in smart search capabilities to grab podcasts we’ll find most interesting!
31:00 - Using the AssemblyAI API to transcribe the podcasts we’ve downloaded
1:06:08 - Cleaning our code with functions & classes and putting everything into Python scripts.
1:18:09 - Portfolio project extension ideas! (Spotify API, NLP semantic search)
1:19:56 - Smash like & subscribe pretty please :)

Видео Full Python Portfolio Project! Create a smart program to download & transcribe top podcasts. канала Keith Galli