Last active
February 25, 2022 20:16
-
-
Save jaylinski/714f967ef67f5601291c0143f7c63977 to your computer and use it in GitHub Desktop.
Convert WebVTT (*.vtt) to SubRip (*.srt) with Python 2/3
This file contains 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
import re | |
import os | |
def webvtt_to_srt(webvtt): | |
srt = "" | |
counter = 1 | |
for line in webvtt.splitlines(): | |
if line.startswith("WEBVTT"): | |
continue | |
if counter == 1 and line == "": | |
continue | |
matches = re.match(r"^(?P<fh>\d{2}:)?(?P<fm>\d{2}):(?P<fs>\d{2}).(?P<fms>\d{3})\s-->\s(?P<th>\d{2}:)?(?P<tm>\d{2}):(?P<ts>\d{2}).(?P<tms>\d{3})", line) | |
if matches: | |
srt += str(counter) + os.linesep | |
srt += "{}{}:{},{} --> {}{}:{},{}{}".format( | |
matches.group('fh') or "00:", | |
matches.group('fm'), | |
matches.group('fs'), | |
matches.group('fms'), | |
matches.group('th') or "00:", | |
matches.group('tm'), | |
matches.group('ts'), | |
matches.group('tms'), | |
os.linesep | |
) | |
counter += 1 | |
else: | |
srt += line + os.linesep | |
return srt |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment