关于vtt 与 srt 字幕的相互转换

Posted 2020-10-30 KeepLearningEverday

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了关于vtt 与 srt 字幕的相互转换相关的知识，希望对你有一定的参考价值。

我在下载的udacity中教程时,字幕和视频是分离的,对于英文还无法完全听懂的我来说,字幕还是比较重要.不想看解释的可直接跳到最后复制代码运行即可.

查看了vtt和srt的区别,使用记事本打开vtt和srt,发现主要有两个

首行多了 WEBVTT\\n\\n 标识符
标点格式区别,vtt内部的"."在srt中为","

流程图:

基于python写了一个简单的脚本对其进行批量修改

1 引入依赖

1. os获取文件信息
2. sys获取命令行输入args
3. re对获取的文件内容进行匹配或更换

import os
import sys
import re

2 定义主函数

if __name__ == \'__main__\':
    args = sys.argv
    print(args)

    if os.path.isdir(args[1]):
        file_list = get_file_name(args[1], ".vtt")
        for file in file_list:
            vtt2srt(file)

    elif os.path.isfile(args[1]):
        vtt2srt(args[1])
    else:
        print("arg[0] should be file name or dir")

3 定义获取文件名称函数get_file_name

def get_file_name(dir, file_extension):
    f_list = os.listdir(dir)

    result_list = []

    for file_name in f_list:
        if os.path.splitext(file_name)[1] == file_extension:
            result_list.append(os.path.join(dir, file_name))
    return result_list

4 定义转换逻辑

def vtt2srt(file_name):
    content = open(file_name, "r", encoding="utf-8").read()
    # 删除WEBVTT行
    
    content = re.sub("WEBVTT\\n\\n",\'\',content)
    # 替换“.”为“,”
    content = re.sub("(\\d{2}:\\d{2}:\\d{2}).(\\d{3})", lambda m: m.group(1) + \',\' + m.group(2), content)

    output_file = os.path.splitext(file_name)[0] + \'.srt\'
    open(output_file, "w", encoding="utf-8").write(content)

def srt2vtt(file_name):
    content = open(file_name, "r", encoding="utf-8").read()
    # 添加WEBVTT行
    
    content = "WEBVTT\\n\\n" + content
    # 替换“,”为“.”
    content = re.sub("(\\d{2}:\\d{2}:\\d{2}),(\\d{3})", lambda m: m.group(1) + \'.\' + m.group(2), content)

    output_file = os.path.splitext(file_name)[0] + \'.vtt\'
    open(output_file, "w", encoding="utf-8").write(content)

5 完整代码

import os
import sys
import re


def get_file_name(dir, file_extension):
    f_list = os.listdir(dir)

    result_list = []

    for file_name in f_list:
        if os.path.splitext(file_name)[1] == file_extension:
            result_list.append(os.path.join(dir, file_name))
    return result_list


def vtt2srt(file_name):
    content = open(file_name, "r", encoding="utf-8").read()
    # 删除WEBVTT行
    
    content = re.sub("WEBVTT\\n\\n",\'\',content)
    # 替换“.”为“,”
    content = re.sub("(\\d{2}:\\d{2}:\\d{2}).(\\d{3})", lambda m: m.group(1) + \',\' + m.group(2), content)

    output_file = os.path.splitext(file_name)[0] + \'.srt\'
    open(output_file, "w", encoding="utf-8").write(content)

def srt2vtt(file_name):
    content = open(file_name, "r", encoding="utf-8").read()
    # 添加WEBVTT行
    
    content = "WEBVTT\\n\\n" + content
    # 替换“,”为“.”
    content = re.sub("(\\d{2}:\\d{2}:\\d{2}),(\\d{3})", lambda m: m.group(1) + \'.\' + m.group(2), content)

    output_file = os.path.splitext(file_name)[0] + \'.vtt\'
    open(output_file, "w", encoding="utf-8").write(content)

    
if __name__ == \'__main__\':
    args = sys.argv

    if os.path.isdir(args[1]):
        file_list = get_file_name(args[1], ".vtt")
        for file in file_list:
            vtt2srt(file)

    elif os.path.isfile(args[1]):
        vtt2srt(args[1])
        print(\'done\')
    else:
        print("arg[0] should be file name or dir")