sbv2csv.sh

#!/bin/bash
# Converts a SBV (YouTube) Subtitles to CSV format,
# so that they can be imported to Spreadsheet for editing

# Check if input file is provided
if [ "$#" -ne 1 ]; then
    echo "Usage: $0 input_file.sbv"
    exit 1
fi

input_file="$1"
output_file="${input_file%.sbv}.csv"

# Initialize variables
timestamp=""
text=""

# Start writing the CSV output
echo "Timestamp,Text" > "$output_file"

# Read the input SBV file line by line
while IFS= read -r line; do
    # If the line is a timestamp
    if [[ $line =~ ^[0-9]+:[0-9]+:[0-9]+\.[0-9]+,[0-9]+:[0-9]+:[0-9]+\.[0-9]+$ ]]; then
        # If there is previous text, write it to the CSV
        if [[ -n $timestamp && -n $text ]]; then
            # Escape any quotes in the text and replace newlines with <br/>
            text=$(echo "$text" | sed ':a;N;$!ba;s/\n/<br\/>/g' | sed 's/"/""/g')
            echo "\"$timestamp\",\"$text\"" >> "$output_file"
        fi
        # Reset for new block
        timestamp="$line"
        text=""
    # If the line is text
    elif [[ -n $line ]]; then
        # Add text to the current block
        if [[ -n $text ]]; then
            text="$text<br/>$line"
        else
            text="$line"
        fi
    fi
done < "$input_file"

# Write the last block if it exists
if [[ -n $timestamp && -n $text ]]; then
    # Escape any quotes in the text and replace newlines with <br/>
    text=$(echo "$text" | sed ':a;N;$!ba;s/\n/<br\/>/g' | sed 's/"/""/g')
    echo "\"$timestamp\",\"$text\"" >> "$output_file"
fi

echo "Conversion completed. CSV file saved as $output_file."