Last active
April 19, 2018 03:44
-
-
Save myabiku/ba6283912043a87b17f77cba5751724a to your computer and use it in GitHub Desktop.
This file contains 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
mkdir tvsenado | |
cd tvsenado | |
# faz download das legendas geradas automaticamente do youtube [não é perfeito, mas ainda vou achar os closed captions oficiais] | |
youtube-dl "https://www.youtube.com/playlist?list=PLLLnytnGoqiYTJ7yDXiq8bMtU8tKUmop6" -v --skip-download --sub-lang pt --write-auto-sub | |
# substitui os espaços por _ | |
OIFS="$IFS"; IFS=$'\n'; for file in `find . -type f -name "*.vtt"` ; do cp $file srt/$(echo $file | sed 's/ /_/g'); done | |
mkdir srt | |
# converte as legendas de vtt para srt | |
for i in $(ls *.vtt); do ffmpeg -i $i srt/$(echo $i | sed 's/vtt$/srt/'); done | |
cd srt | |
# mostra o ranking das palavras mais utilizadas em * arquivos | |
cat * | sed -e 's/[^[:alpha:]]/ /g' | tr '\n' " " | tr -s " " | tr " " '\n'| tr 'A-Z' 'a-z' | sort | uniq -c | sort -nr | nl | less |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment