Add WebVTT output support

This subset of the format is almost identical to SRT, but I think it's
cleaner to have a separate module (at the cost of a little bit of
copy-pasta).
This commit is contained in:
Will Thompson 2016-03-11 12:12:54 +00:00
parent b75a0f9bb8
commit 5355dbf821
2 changed files with 33 additions and 0 deletions

View file

@ -13,6 +13,7 @@ from . import jsonc
from . import net
from . import srt
from . import utils
from . import vtt
from .api import *
from .file import *

32
ox/vtt.py Normal file
View file

@ -0,0 +1,32 @@
# -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
import codecs
import ox
def _webvtt_timecode(t):
return ox.format_duration(t * 1000, years=False)
def encode(data, webvtt=False):
"""Encodes subtitles into WebVTT format
data: list of dicts with 'in', 'out': float and 'value': unicode
Returns: a UTF-8-encoded bytestring
>>> encode([{'in': 1.25, 'out': 60 * 60 + 1, 'value': u'touch\\u00E9'}])
'\\xef\\xbb\\xbfWEBVTT\\r\\n\\r\\n1\\r\\n00:00:01.250 --> 01:00:01.000\\r\\ntouch\\xc3\\xa9\\r\\n\\r\\n'
"""
srt = u'WEBVTT\r\n\r\n'
for i, s in enumerate(data, 1):
srt += '%d\r\n%s --> %s\r\n%s\r\n\r\n' % (
i,
_webvtt_timecode(s['in']),
_webvtt_timecode(s['out']),
s['value'].replace('\n', '\r\n').strip()
)
return codecs.BOM_UTF8 + srt.encode('utf-8')