#! /usr/bin/env python

# -*- coding: utf-8 -*-

u"""

TED talks subs

--------------

Download and convert the subtitles of a TED talk

Original script: http://estebanordano.com.ar/ted-talks-download-subtitles/

A few minor improvements by Aurélien Bompard <http://aurelien.bompard.org>

:License:

    MIT

"""

import optparse

import urllib

import sys

import re

import simplejson

def getFormatedTime(intvalue):

    mils = intvalue%1000

    segs = (intvalue/1000)%60

    mins = (intvalue/60000)%60

    hors = (intvalue/3600000)

    return "%02d:%02d:%02d,%03d"%(hors,mins,segs,mils)

def availableSubs(subs):

    a = subs.find("LanguageCode")

    if a == -1:

        return []

    subs = subs[a+len("LanguageCode"):]

    return [re.search("%22([^A-Z]+)%22", subs).group(1)] + availableSubs(subs)

def getVideoParameters(urldirection):

    ht = urllib.urlopen(urldirection).read()

    var = re.search('flashVars = {\n([^}]+)}', ht)

    if var:

        var = var.group(1)

    else:

        return None

    var = [a.replace('\t', '') for a in var.split('\n')]

    for a in range(len(var)):

        if var[a]:

            var[a] = var[a][:var[a].rfind(',')]

    resultado = []

    for a in var:

        l = a.find(':')

        if l != -1:

            resultado.append((a[:l], a[l+1:]))

    return dict(resultado)

def downloadSub(idtalk, lang, timeIntro):

    if options.debug:

        print("Downloading subtitles for language %s"%lang)

    c = simplejson.load(urllib.urlopen('http://www.ted.com/talks/subtitles/id/%s/lang/%s'%(idtalk, lang)))

    filename = options.output

    if not filename:

        filename = '%s_%s.srt' % (idtalk,lang)

    salida = open(filename, 'w')

    conta = 1

    c = c['captions']

    for linea in c:

        salida.write("%d\n"%conta)

        conta += 1

        salida.write("%s --> %s\n"%(getFormatedTime(timeIntro+linea['startTime']), getFormatedTime(timeIntro+linea['startTime']+linea['duration'])))

        salida.write("%s\n\n"%(linea['content'].encode('utf-8')))

    salida.close()

def main(idtalk):

    if options.debug:

        print("Loading information about TED talk number %s..."%idtalk)

    vidpar = getVideoParameters('http://www.ted.com/talks/view/id/%s'%idtalk)

    if not vidpar:

        print >>sys.stderr, "There was a problem fetching information about that TED Talk"

        sys.exit(1)

    availables = availableSubs(vidpar['languages'])

    if options.list:

        print "\n".join(availables)

        sys.exit(0)

    if options.lang and options.lang not in availables:

        print >>sys.stderr, "Sorry, this language is not available. " \

                           +"Available languages:"

        if not len(availables):

            print >>sys.stderr, "(none)"

        else:

            print >>sys.stderr, "\n".join(availables)

        sys.exit(1)

    if not options.lang:

        print("Download all subtitles (write 'all' when prompted) or only one (specify wich)?")

        lang = raw_input()

        while lang not in availables:

            print("We're sorry, the only available languages are:")

            print "\t".join(availables)

            lang = raw_input()

    else:

        lang = options.lang

    if lang == "all":

        for lang in availables:

            downloadSub(idtalk, lang, int(vidpar['introDuration']))

    else:

        downloadSub(idtalk, lang, int(vidpar['introDuration']))

def parse_opts():

    usage = "usage: %prog [-l lang] [-o output] [-t] talkid"

    parser = optparse.OptionParser(usage=usage)

    parser.add_option("-l", "--lang", dest="lang",

                      help="Use this language")

    parser.add_option("-o", "--output", dest="output",

                      help="Write the subtitle in this file")

    parser.add_option("-t", "--list-only", dest="list", action="store_true",

                      help="List available subtitles and exit")

    parser.add_option("-d", "--debug", dest="debug", action="store_true",

                      help="Print debug information")

    options, args = parser.parse_args()

    if len(args) != 1:

        parser.error("You must give a talk ID")

    try:

        int(args[0])

    except ValueError:

        parser.error("The argument must be the numeric unique talk ID")

    return options, args[0]

if __name__ == "__main__":

    global options

    options, talkid = parse_opts()

    main(talkid)