Skip to content

Instantly share code, notes, and snippets.

@florentroques
Forked from glasslion/vtt2text.py
Last active September 5, 2024 01:44
Show Gist options
  • Save florentroques/c08bbe54fba42ec56c9d48229ed9c49b to your computer and use it in GitHub Desktop.
Save florentroques/c08bbe54fba42ec56c9d48229ed9c49b to your computer and use it in GitHub Desktop.
This script converts youtube subtitle file(vtt) to plain text.
"""
Convert YouTube subtitles(vtt) to human readable text.
Download only subtitles from YouTube with youtube-dl:
youtube-dl --skip-download --convert-subs vtt <video_url>
Note that default subtitle format provided by YouTube is ass, which is hard
to process with simple regex. Luckily youtube-dl can convert ass to vtt, which
is easier to process.
To conver all vtt files inside a directory:
find . -name "*.vtt" -exec python vtt2text.py {} \;
"""
import sys
import re
def remove_tags(text):
"""
Remove vtt markup tags
"""
tags = [
r'</c>',
r'<c(\.color\w+)?>',
r'<\d{2}:\d{2}:\d{2}\.\d{3}>',
]
for pat in tags:
text = re.sub(pat, '', text)
# extract timestamp, only kep HH:MM
text = re.sub(
r'(\d{2}:\d{2}):\d{2}\.\d{3} --> .* align:start position:0%',
r'\g<1>',
text
)
text = re.sub(r'^\s+$', '', text, flags=re.MULTILINE)
return text
def remove_header(lines):
"""
Remove vtt file header
"""
pos = -1
for mark in ('##', 'Language: en',):
if mark in lines:
pos = lines.index(mark)
lines = lines[pos+1:]
return lines
def merge_duplicates(lines):
"""
Remove duplicated subtitles. Duplacates are always adjacent.
"""
last_timestamp = ''
last_cap = ''
for line in lines:
if line == "":
continue
if re.match('^\d{2}:\d{2}$', line):
if line != last_timestamp:
yield line
last_timestamp = line
else:
if line != last_cap:
yield line
last_cap = line
def merge_short_lines(lines):
buffer = ''
for line in lines:
if line == "" or re.match('^\d{2}:\d{2}$', line):
yield '\n' + line
continue
if len(line+buffer) < 80:
buffer += ' ' + line
else:
yield buffer.strip()
buffer = line
yield buffer
def remove_remaining_timestamp_lines(lines):
regex_remaining_timestamp_lines = re.compile('^\\n[0-9]{2}:[d0-9]{2}$')
lines = [line for line in lines if not regex_remaining_timestamp_lines.match(line)]
return lines
def remove_webvtt_header(lines):
lines[0] = re.sub('WEBVTT Kind: captions Language: [a-z]{2} ', '', lines[0])
return lines
def main():
vtt_file_name = sys.argv[1]
txt_name = re.sub(r'.vtt$', '.txt', vtt_file_name)
with open(vtt_file_name) as f:
text = f.read()
text = remove_tags(text)
lines = text.splitlines()
lines = remove_header(lines)
lines = merge_duplicates(lines)
lines = list(lines)
lines = merge_short_lines(lines)
lines = list(lines)
lines = remove_remaining_timestamp_lines(lines)
lines = remove_webvtt_header(lines)
with open(txt_name, 'w') as f:
for line in lines:
f.write(line)
f.write("\n")
if __name__ == "__main__":
main()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment