Last active
April 19, 2016 15:29
-
-
Save leonardo-fernandes/25253548ae8929ee7664 to your computer and use it in GitHub Desktop.
Convert youtube timedtext XML fromat to SRT subtitles
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 | |
# Download the .xml file from youtube by using the Network tab | |
# on the browser Developer Tools, and searching for requests to | |
# the "timedtext" endpoint | |
from xml.dom.minidom import parse | |
import sys | |
def formatSrtTime(milliseconds): | |
sec, milli = divmod(milliseconds, 1000) | |
m, s = divmod(int(sec), 60) | |
h, m = divmod(m, 60) | |
return "{:02}:{:02}:{:02},{}".format(h,m,s,milli) | |
i=1 | |
dom = parse(sys.argv[1]) | |
out = open(sys.argv[2], 'w') | |
body = dom.getElementsByTagName("body")[0] | |
paras = body.getElementsByTagName("p") | |
for para in paras: | |
out.write(str(i) + "\n") | |
out.write(formatSrtTime(int(para.attributes['t'].value)) + ' --> ' + formatSrtTime(int(para.attributes['t'].value) + int(para.attributes['d'].value)) + "\n") | |
for child in para.childNodes: | |
if child.nodeName == 'br': | |
out.write("\n") | |
elif child.nodeName == '#text': | |
out.write(unicode(child.data).encode('utf-8')) | |
out.write("\n\n") | |
i += 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment