I have a need for retrieving podcast transcripts (specifically retrieving certain parts of episodes) and the website app.podscribe.com has a robots.txt file so it’s not allowing ChatGPT to access the transcripts. Is there some kind of roundabout way I can have chatGPT (or any AI service for that matter) retrieve that data? I have the websites API key, but after looking at their documentation, transcripts aren’t something it pulls.
Thanks for any thoughts or ideas.
Edit update: The transcript itself is text, the time is always in the same format, and while I could copy and paste it myself, I’m ultimately needing an automation. I guess my real question at the end of the day is is there any way around robot.txt files for retrieving website information.