share/subtitle/youtube.lua

   1 -- libquvi-scripts
   2 -- Copyright (C) 2013  Toni Gundogdu <legatvs@gmail.com>
   3 --
   4 -- This file is part of libquvi-scripts <http://quvi.sourceforge.net/>.
   5 --
   6 -- This program is free software: you can redistribute it and/or
   7 -- modify it under the terms of the GNU Affero General Public
   8 -- License as published by the Free Software Foundation, either
   9 -- version 3 of the License, or (at your option) any later version.
  10 --
  11 -- This program is distributed in the hope that it will be useful,
  12 -- but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 -- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 -- GNU Affero General Public License for more details.
  15 --
  16 -- You should have received a copy of the GNU Affero General
  17 -- Public License along with this program.  If not, see
  18 -- <http://www.gnu.org/licenses/>.
  19 --
  20
  21 local YouTube = {} -- Utility functions unique to this script
  22
  23 -- Identify the script.
  24 function ident(qargs)
  25   local Y = require 'quvi/youtube'
  26   return Y.ident(qargs)
  27 end
  28
  29 -- Parse subtitle properties.
  30 function parse(qargs)
  31   local Y = require 'quvi/youtube'
  32   local C = require 'quvi/const'
  33
  34   local u = Y.normalize(qargs.input_url)
  35   local v = u:match('v=([%w-_]+)')
  36               or error('no match: media ID')
  37
  38   qargs.subtitles = {}
  39
  40   YouTube.tts_get(qargs, v, u, C)
  41   YouTube.cc_get(qargs, v, C)
  42
  43   return qargs
  44 end
  45
  46 --
  47 -- Utility functions
  48 --
  49
  50 -- Extract the TTS (text-to-speech, or transcript).
  51 function YouTube.tts_get(qargs, v, u, C)
  52   local u_fmt = "%s&tlang=%s&type=trackformat=1,&lang=en&kind=asr"
  53   local p = quvi.http.fetch(u).data
  54
  55   local tts_url = p:match('[\'"]TTS_URL[\'"]:%s+[\'"](.-)[\'"]')
  56   if not tts_url then return end
  57
  58   p = nil
  59
  60   tts_url = tts_url:gsub('\\u0026','&')
  61   local U = require 'quvi/util'
  62   tts_url = U.slash_unescape(tts_url)
  63   tts_url = U.unescape(tts_url)
  64
  65   local langs = tts_url:match('asr_langs=(.-)&')
  66   if not langs then return end
  67
  68   local r = {}
  69   for c in langs:gmatch('(%w+)') do
  70     table.insert(r, {
  71       url = string.format(u_fmt, tts_url, c),
  72       translated = '',
  73       id = 'tts_'..c,
  74       original = '',
  75       code = c
  76     })
  77   end
  78
  79   table.insert(qargs.subtitles, {format=C.sif_tt, type=C.st_tts, lang=r})
  80 end
  81
  82 -- Extract the CC (closed-captions) data.
  83 function YouTube.cc_get(qargs, v, C)
  84   local u_fmt =
  85     "http://youtube.com/api/timedtext?hl=en&type=track&v=%s&name=%s&lang=%s"
  86
  87   local u = 'http://video.google.com/timedtext?hl=en&type=list&v=' ..v
  88   local x = quvi.http.fetch(u).data
  89   local L = require 'lxp.lom'
  90   local t = L.parse(x)
  91   local r = {}
  92
  93   for i=1, #t do
  94     if t[i].tag == 'track' then
  95       local lang = t[i].attr['lang_code']
  96       if lang then
  97         local name = t[i].attr['name'] or ''
  98         table.insert(r, {
  99           translated = t[i].attr['lang_translated'] or '',
 100           original = t[i].attr['lang_original'] or '',
 101           url = string.format(u_fmt, v, name, lang),
 102           id = 'cc_'..lang,
 103           code = lang
 104         })
 105       end
 106     end
 107   end
 108
 109   table.insert(qargs.subtitles, {format=C.sif_tt, type=C.st_cc, lang=r})
 110 end
 111
 112 -- vim: set ts=2 sw=2 tw=72 expandtab: