-
-
Save mbirth/26739d32dbce5ca87589 to your computer and use it in GitHub Desktop.
Timed Text Captions to SRT Subtitles converter script
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
#!/usr/bin/env python | |
# Usage: python tt2srt.py source.xml output.srt | |
# FROM: https://gist.github.com/adammw/915259 | |
from xml.dom.minidom import parse | |
import sys | |
def fixTime(time): | |
# 00:00:00.000 | |
return time.replace(".", ",") | |
i=1 | |
dom = parse(sys.argv[1]) | |
out = open(sys.argv[2], 'w') | |
styling = dom.getElementsByTagName("tt:styling")[0] | |
styles = {} | |
for style in styling.childNodes: | |
if style.nodeName == 'tt:style': | |
try: | |
if style.attributes["tts:color"]: | |
styles[style.attributes['xml:id'].value] = style.attributes['tts:color'].value | |
except: | |
pass | |
body = dom.getElementsByTagName("tt:body")[0] | |
paras = body.getElementsByTagName("tt:p") | |
for para in paras: | |
out.write(str(i) + "\n") | |
out.write(fixTime(para.attributes['begin'].value) + ' --> ' + fixTime(para.attributes['end'].value) + "\n") | |
for child in para.childNodes: | |
if child.nodeName == 'tt:span': | |
fontOpen = False | |
if child.attributes['style']: | |
styleid = child.attributes['style'].value | |
if styleid in styles: | |
out.write('<font color="' + styles[styleid] + '">') | |
fontOpen = True | |
for child2 in child.childNodes: | |
if child2.nodeName == 'tt:br': | |
out.write("\n") | |
elif child2.nodeName == '#text': | |
rawText = unicode(child2.data).encode('utf-8').strip() | |
if len(rawText) > 0: | |
out.write(rawText) | |
if fontOpen: | |
out.write('</font>') | |
elif child.nodeName == 'tt:br': | |
out.write("\n") | |
out.write("\n\n") | |
i += 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment