search

jdepoix / youtube-transcript-api

This is a python API which allows you to get the transcript/subtitles for a given YouTube video. It also works for automatically generated subtitles and it does not require an API key nor a headless browser, like other selenium based solutions do!
MIT License
2.54k stars 279 forks source link

Fetch chapter names [if available] for transcript segments #254

Open t0r0id opened 5 months ago

t0r0id commented 5 months ago

This can be useful to chunk transcripts into chapter level documents for RAG.

humpydonkey commented 1 month ago

Hi @jdepoix , do you know if someone is actively reviewing this PR? i think it'd be a really useful feature for a number of users of this library. would appreciate the team to review and support this feature soon! (i had to fork the repo and apply this change in the meantime.)