Download Subtitles/Captions for MediaStorm Videos

mediastorm_caps.rb

#!/bin/env ruby

#### This Ruby Script extracts Captions as .srt files from 
#### MediaStorm Videos (http://mediastorm.com)

#### Download The Video, and if you want to download captions,
#### lookup the 'Network' tab in Inspector to see the video id
#### It'll be a GET request to two xml documents on the mediastorm
#### server, namely; /timecodes/<id> and /phrases/<id>

#### Sheharyar Naseer © 2015


## Requires
require 'open-uri'
require 'nokogiri'


## Methods
def nice_time(t);    t.attributes.map {|k,v| {k => v.value} } .reduce(&:merge); end
def nice_phrase(p);  p.children.first.content;                                  end
def compatible(p,t); t.count == p.count;                                        end
def srt_time(t);     "#{t}0".gsub ';', ',';                                     end

def generate_srt(id, phrases, times)
    if compatible(phrases, times)
        open("#{id}.srt", 'w') do |f|
            phrases.count.times do |i|
                phrase = phrases[i]
                time   = times[i]

                f.puts  "#{i+1}",
                        "#{srt_time(time['tIn'])} --> #{srt_time(time['tOut'])}",
                        "#{phrase}",
                        ""
            end
        end
    else
        puts "Not Compatible, can't generate srt"
    end
end


## Video ID
id = 468 #469 #512


## Open Files
t = Nokogiri::XML open("https://player.mediastorm.com/timecodes/#{id}.xml")
p = Nokogiri::XML open("https://player.mediastorm.com/phrases/#{id}.xml")


## Get children
ts = t.xpath('//time')
ps = p.xpath('//phrase')


## Make sure they are compatible
if compatible(ts, ps)
    puts "COMPATIBLE: EQUAL VALUES"
else
    puts "NOT COMPATIBLE: NOT EQUAL"
end


## Convert to simple arrays/hashes
nts = ts.map { |t| nice_time   t }
nps = ps.map { |p| nice_phrase p }


## Generate the srt file
generate_srt(id, nps, nts)