如何将VTT字幕批量转换为SRT(Python脚本) 原创

一、新建一个文本文件，并重命名为main.py，然后把下面代码粘贴进去；

二、在main.py所在的文件夹下新建vtt和srt两个文件夹；

三、把所有.vtt格式文件放到vtt目录下；

四、在main.py文件所在的目录的地址栏里面输入cmd回车后输入：

python main.py

完整代码：

import os
import re
from pathlib import Path

def convert_timestamp(timestamp):
    """Convert WebVTT timestamp to SRT timestamp format"""
    # Add hour if not present (00:04.310 -> 00:00:04,310)
    if timestamp.count(':') == 1:
        timestamp = "00:" + timestamp
    # Replace '.' with ',' for milliseconds
    return timestamp.replace('.', ',')

def convert_vtt_to_srt(vtt_content):
    """Convert VTT content to SRT format"""
    # Split content into lines and remove empty lines
    lines = [line.strip() for line in vtt_content.split('\n') if line.strip()]

    # Remove WebVTT header
    if lines and lines[0].upper().startswith('WEBVTT'):
        lines = lines[1:]

    srt_lines = []
    subtitle_index = 1
    timestamp_pattern = r'(\d{2}:\d{2}\.\d{3}) --> (\d{2}:\d{2}\.\d{3})'

    i = 0
    while i < len(lines):
        line = lines[i]

        # Look for timestamp line
        match = re.match(timestamp_pattern, line)
        if match:
            # Add subtitle index
            srt_lines.append(str(subtitle_index))
            subtitle_index += 1

            # Convert and add timestamp
            start_time = convert_timestamp(match.group(1))
            end_time = convert_timestamp(match.group(2))
            srt_lines.append(f"{start_time} --> {end_time}")

            # Add subtitle text (all lines until next timestamp or end)
            i += 1
            while i < len(lines):
                next_line = lines[i]
                if re.match(timestamp_pattern, next_line):
                    break
                srt_lines.append(next_line)
                i += 1

            # Add blank line between subtitles
            srt_lines.append('')
        else:
            i += 1

    return '\n'.join(srt_lines)

def process_vtt_files():
    """Process all VTT files in the vtt directory"""
    # Get the current directory
    current_dir = Path.cwd()

    # Define input and output directories
    vtt_dir = current_dir / 'vtt'
    srt_dir = current_dir / 'srt'

    # Create srt directory if it doesn't exist
    srt_dir.mkdir(exist_ok=True)

    # Process each .vtt file
    for vtt_file in vtt_dir.glob('*.vtt'):
        try:
            # Read VTT file
            with open(vtt_file, 'r', encoding='utf-8') as f:
                vtt_content = f.read()

            # Convert content
            srt_content = convert_vtt_to_srt(vtt_content)

            # Create output file path
            srt_file = srt_dir / (vtt_file.stem + '.srt')

            # Write SRT file
            with open(srt_file, 'w', encoding='utf-8') as f:
                f.write(srt_content)

            print(f"Successfully converted: {vtt_file.name}")

        except Exception as e:
            print(f"Error converting {vtt_file.name}: {str(e)}")

if __name__ == '__main__':
    print("Starting VTT to SRT conversion...")
    process_vtt_files()
    print("Conversion completed!")