Plaintext Transcript.py

import os
import re
import json
from pathlib import Path

def clean_vtt_text(text):
    # Remove VTT header
    if text.startswith('WEBVTT'):
        text = re.sub(r'^WEBVTT.*?\n\n', '', text, flags=re.DOTALL)
    
    # Remove timestamps and positioning
    text = re.sub(r'\d{2}:\d{2}:\d{2}\.\d{3} --> \d{2}:\d{2}:\d{2}\.\d{3}.*?\n', '', text)
    
    # Remove HTML-style tags
    text = re.sub(r'<[^>]+>', '', text)
    
    # Remove blank lines and clean up spacing
    lines = [line.strip() for line in text.split('\n')]
    lines = [line for line in lines if line and not line.isspace()]
    
    # Remove duplicate lines that often occur in VTT files
    cleaned_lines = []
    prev_line = None
    for line in lines:
        if line != prev_line:
            cleaned_lines.append(line)
        prev_line = line
    
    # Return the cleaned lines joined with line breaks
    return '\n'.join(cleaned_lines)

def convert_vtt_directory(directory_path):
    dir_path = Path(directory_path)

    if not dir_path.exists():
        print(f"Directory does not exist: {directory_path}")
        return

    print(f"Processing directory: {dir_path}")

    # Traverse all subdirectories recursively
    for subdir in dir_path.rglob('*'):
        if subdir.is_dir():
            print(f"Processing subdirectory: {subdir}")
            
            # Look for the JSON file in the current subdirectory
            json_file = next(subdir.glob('*.info.json'), None)
            title = "Unknown Title"
            description = ""
            if json_file:
                try:
                    print(f"Found JSON file: {json_file}")
                    with json_file.open(encoding='utf-8') as f:
                        metadata = json.load(f)
                        title = metadata.get('title', 'Unknown Title')
                        description = metadata.get('description', 'Unknown Description')
                except Exception as e:
                    print(f"Error reading JSON file {json_file}: {e}")
            else:
                print(f"No JSON file found in: {subdir}")

            # Process all .vtt files in the current subdirectory
            vtt_files = list(subdir.glob('*.en.vtt'))
            if not vtt_files:
                print(f"No .vtt files found in {subdir}")
            for vtt_file in vtt_files:
                try:
                    print(f"Processing VTT file: {vtt_file}")
                    with open(vtt_file, 'r', encoding='utf-8') as f:
                        vtt_content = f.read()

                    cleaned_text = clean_vtt_text(vtt_content)
                    txt_file = vtt_file.with_suffix('.txt')

                    with open(txt_file, 'w', encoding='utf-8') as f:
                        f.write(f"Title: {title}\n\n")
                        f.write(f"== Description ==\n{description}\n\n")
                        f.write(f"== Transcript ==\n{cleaned_text}\n")

                    print(f"Converted {vtt_file.relative_to(dir_path)} -> {txt_file.relative_to(dir_path)}")

                except Exception as e:
                    print(f"Error processing {vtt_file.relative_to(dir_path)}: {e}")

if __name__ == "__main__":
    directory = "./Transcripts"
    convert_vtt_directory(directory)