Created
February 6, 2025 11:39
-
-
Save alessaba/15dad31023e4b593ee817c347cfa6099 to your computer and use it in GitHub Desktop.
Extract WWDC Titles from session videos
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
#!/bin/zsh | |
# Folder path containing the videos | |
folder_path="/Volumes/Alessaba/WWDC/2025" | |
timestamp_titolo='00:00:02' | |
# Extract frame from video | |
extract_frame() { | |
local video_path=$1 | |
local image_path=$2 | |
ffmpeg -ss $timestamp_titolo -i "$video_path" -frames:v 1 -q:v 2 "$image_path" > /dev/null | |
} | |
# Perform OCR and extract title | |
perform_ocr_and_extract_title() { | |
local image_path=$1 | |
local text=$(tesseract "$image_path" stdout) | |
local title=$(echo "$text" | head -4 | tail -2) # Verificare che l'OCR corrisponda. Nel 2024 era la 4a riga | |
echo "$title" | |
} | |
# Process each video in the folder | |
for video_file in "$folder_path"/*.mp4; do | |
if [[ -f "$video_file" ]]; then | |
image_path="${video_file%.*}.png" | |
extract_frame "$video_file" "$image_path" | |
title=$(perform_ocr_and_extract_title "$image_path") | |
if [[ -n "$title" ]]; then | |
new_video_path="${folder_path}/${title}.mp4" | |
mv "$video_file" "$new_video_path" | |
fi | |
rm "$image_path" | |
fi | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment