A tool to fetch subtitles from edx.org

edx-sub.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
The edx.org provides video for download, but the subtitle is 
only available when watching video online. 
This script can help to convert the online subtitle to local srt file.

Usage: 
1. Open your Chrome inspector(or other debug tool)
2. Visit the video page, find the subtitle url(you can search for "subs")
3. run "python edx-sub.py [the url] > your_srt.srt
"""

import sys
import urllib2
from json import loads

def main():
    f = urllib2.urlopen(sys.argv[1])
    json_subs = loads(f.read())
    subs = zip(json_subs['start'], json_subs['end'], json_subs['text'])
    for i, s in enumerate(subs):
        print "%s\n%s --> %s\n%s\n" % (
            i, conv_time(s[0]), conv_time(s[1]), s[2])


def conv_time(num):
    seconds, ms = divmod(num, 1000)
    minutes, ss = divmod(seconds, 60)
    hh, mm = divmod(minutes, 60)
    return "%.2d:%.2d:%.2d,%.3d" % (hh, mm, ss, ms)


if __name__ == "__main__":
    if len(sys.argv) < 2:
        print "usage: 1. Use inspector to find the subtitle url, like https://courses.edx.org/123.sjson"
        print "       2. python %s [subs url] > sub.srt" % sys.argv[0]
        sys.exit()
    main()