#!/usr/bin/env python import os import re def process_caption_files(): for file in os.listdir(): if file.endswith(".caption"): # Check if the file already contains processed data with open(file, 'r') as f: lines = f.readlines() if "\n----------\n" not in "".join(lines): continue for line in lines: if "----------" in line: break # Stop processing after finding the separator content = ''.join(lines[:lines.index(line)]) # Extract text before the separator processed_content = re.sub(r'[\-]+|\n', '', content) # Remove newlines and separator with open(file, 'w') as f: # Save the condensed caption back to the same file f.write(processed_content) process_caption_files()