Split ASS subtilte file by style

split_ass.py

import regex as re
from pathlib import Path

TARGET_FILE = ".\YourFile.ass"

def split_ass_by_styles(file_path):
    # Convert string path to Path object if not already
    file_path = Path(file_path)
    # Read ASS content from the file
    with open(file_path, 'r', encoding='utf-8') as file:
        ass_content = file.read()

    # Splitting the content into header and events
    header, events = ass_content.split('[Events]', 1)
    header += '[Events]\n'  # Add [Events] back to the header

    # Finding all unique styles
    style_pattern = re.compile(r'^Dialogue:.*?,.*?,.*?,(.*?),', re.MULTILINE)
    styles = set(style_pattern.findall(events))

    # Splitting and writing events for each style into separate files
    for style in styles:
        # Updated regex to correctly extract dialogues by style
        filtered_events = re.findall(rf'^(Dialogue:.*?,.*?,.*?,{re.escape(style)},.*$)', events, re.MULTILINE)
        file_content = header + '\n'.join(filtered_events)
        output_file_path = file_path.with_stem(f'{file_path.stem}_{style}')

        # Warning if the file exists
        if output_file_path.exists():
            print(f"Warning: {output_file_path} will be overwritten.")

        with open(output_file_path, 'w', encoding='utf-8') as f:
            f.write(file_content)

    print("Files have been created/overwritten in the same directory as the input file.")


split_ass_by_styles(TARGET_FILE)