Last active
December 7, 2024 12:17
-
-
Save ethicnology/204aded2924aa056cc3819c46534b6b3 to your computer and use it in GitHub Desktop.
Converts .vtt to .srt subtitles with python3
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# put this file in /usr/local/bin | |
# vtt2srt my_subtitle.vtt | |
import os, re, argparse | |
parser = argparse.ArgumentParser() | |
parser.add_argument("filename", help=".vtt file") | |
args = parser.parse_args() | |
input_path_filename = args.filename | |
assert input_path_filename.endswith(".vtt"), "input file should be .vtt" | |
output_path_filename = input_path_filename[:-4] + ".srt" | |
time_pattern = r"\b\d{2}:\d{2}:\d{2}\.\d{3}\b --> \b\d{2}:\d{2}:\d{2}\.\d{3}\b" | |
tag_pattern = r"<.+?>" | |
count_time = 0 | |
subtitles = False | |
print("processing… " + input_path_filename) | |
with open(output_path_filename, "w") as output: | |
with open(input_path_filename, "r") as input: | |
for line in input: | |
pattern = re.search(time_pattern, line) | |
if subtitles and not pattern: | |
subtitle_line = line.strip() | |
subtitle_line = re.sub(tag_pattern, "", subtitle_line) | |
output.write(subtitle_line + os.linesep) | |
if pattern: | |
count_time += 1 | |
time_string = pattern.group() | |
output.write(str(count_time) + os.linesep) | |
output.write(time_string.replace(".", ",") + os.linesep) | |
subtitles = True | |
print("done " + output_path_filename) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
https://github.com/yt-dlp/FFmpeg-Builds?tab=readme-ov-file#5-webvtt-decoding-fix