Last active
December 30, 2024 12:36
-
-
Save knbknb/61d56d891609bcab707d4ad641b1100a to your computer and use it in GitHub Desktop.
bash: yt-dlp subtitles only
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env bash | |
url=$1 | |
# if no url is provided, exit | |
if [ -z "$url" ]; then | |
echo "No URL provided" | |
exit 1 | |
fi | |
subtitle_url=$(yt-dlp -q --skip-download --convert-subs srt --write-sub --sub-langs "en" --write-auto-sub --print "requested_subtitles.en.url" "$url") | |
content=$(curl -s "$subtitle_url" | sed '/^$/d' | grep -v '^[0-9]*$' | grep -v '\-->' | sed 's/<[^>]*>//g' | tr '\n' ' ') | |
echo $content | |
outfile="/var/tmp/youtube-video--audiotrack-only.txt" | |
outfile_formatted="/var/tmp/youtube-video--audiotrack-only-formatted.txt" | |
# then: | |
# need to set a env var for openai api key (if you're using openai) | |
# export OPENAI_API_KEY=sk-... | |
# | |
# pipe into llm tool to format text | |
# cat $outfile \ | |
# | llm -m 4o-mini -s "format this properly with punctuation and paragraph structure" \ | |
# > $outfile_formatted | |
# pipe into fmt tool to format the text | |
# < $outfile fmt > $outfile_formatted |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment